Author: "MedisysResearch Lab ( Medisys )" / Topic: business.industry - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"MedisysResearch Lab ( Medisys )"' showing total 71 results

Start Over Author "MedisysResearch Lab ( Medisys )" Topic business.industry

71 results on '"MedisysResearch Lab ( Medisys )"'

1. The role of the image phase in cardiac strain imaging

Author: Adrian Basarab, M. De Craene, Maxime Sermesant, Jan D'hooge, Herve Liebgott, Martino Alessandrini, Olivier Bernard, Laboratory of Cardiovascular Imaging and Dynamics, Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Traitement et Compréhension d’Images (IRIT-TCI), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), MedisysResearch Lab (Medisys), Philips Research, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Imagerie Ultrasonore, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Images et Modèles, Katholieke Universiteit Leuven ( KU Leuven ), Institut de recherche en informatique de Toulouse ( IRIT ), Institut National Polytechnique [Toulouse] ( INP ) -Université Toulouse 1 Capitole ( UT1 ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -Centre National de la Recherche Scientifique ( CNRS ), MedisysResearch Lab ( Medisys ), Analysis and Simulation of Biomedical Images ( ASCLEPIOS ), Inria Sophia Antipolis - Méditerranée ( CRISAM ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), 3 - Imagerie Ultrasonore, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé ( CREATIS ), Université Claude Bernard Lyon 1 ( UCBL ), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon ( INSA Lyon ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ) -Hospices Civils de Lyon ( HCL ) -Université Jean Monnet [Saint-Étienne] ( UJM ) -Institut National de la Santé et de la Recherche Médicale ( INSERM ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Claude Bernard Lyon 1 ( UCBL ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ) -Hospices Civils de Lyon ( HCL ) -Université Jean Monnet [Saint-Étienne] ( UJM ) -Institut National de la Santé et de la Recherche Médicale ( INSERM ) -Centre National de la Recherche Scientifique ( CNRS ), 2 - Images et Modèles, (OATAO), Open Archive Toulouse Archive Ouverte, Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse Capitole (UT Capitole), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut National de la Recherche en Informatique et en Automatique - INRIA (FRANCE), Institut National des Sciences Appliquées de Lyon - INSA (FRANCE), Institut National de la Santé et de la Recherche Médicale - INSERM (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Philips (NETHERLANDS), Katholieke Universiteit Leuven - KU LEUVEN (BELGIUM), Centre de Recherche en Acquisition et Traitement d'Images pour la Santé - CREATIS (Villeurbanne, France), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), and Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Simulations, [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, Computer science, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Pipeline (computing), Phase (waves), [INFO.INFO-GR] Computer Science [cs]/Graphics [cs.GR], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, [ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Field (computer science), 030218 nuclear medicine & medical imaging, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 03 medical and health sciences, Traitement des images, 0302 clinical medicine, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Motion estimation, [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, 0202 electrical engineering, electronic engineering, information engineering, medicine, Medical imaging, Traitement du signal et de l'image, 3D ultrasound, Computer vision, [ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI], Synthèse d'image et réalité virtuelle, medicine.diagnostic_test, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Magnetic resonance imaging, Heart, Vision par ordinateur et reconnaissance de formes, [ INFO.INFO-GR ] Computer Science [cs]/Graphics [cs.GR], Intelligence artificielle, Quality assurance, [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], Deformation imaging, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], Echocardiography, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Benchmark (computing), 020201 artificial intelligence & image processing, Artificial intelligence, business, MRI
Abstract: International audience; This paper reviews our most recent contributions in the field of cardiac deformation imaging, which includes a motion estimation framework based on the conservation of the image phase over time and an open pipeline to benchmark algorithms for cardiac strain imaging in 2D and 3D ultrasound. The paper also shows an original evaluation of the proposed motion estimation technique based on the new benchmarking pipeline.
Published: 2015

2. 3D strain assessment in ultrasound (straus): A synthetic comparison of five tracking methodologies

Author: Maxime Sermesant, Anja Hennemuth, Jan D'hooge, Olivier Bernard, Hang Gao, Oudom Somphone, Gemma Piella, Eric Saloux, Herve Liebgott, Lennart Tautz, M. De Craene, Pascal Allain, Martino Alessandrini, Hervé Delingette, Brecht Heyde, Stephanie Marchesseau, S. Makram Ebeid, Adityo Prakosa, Antonio R. Porras, MedisysResearch Lab (Medisys), Philips Research, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Laboratory of Cardiovascular Imaging and Dynamics, Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Imagerie Ultrasonore, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), Physicochimie des Electrolytes, Colloïdes et Sciences Analytiques (PECSA), Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Ecole Superieure de Physique et de Chimie Industrielles de la Ville de Paris (ESPCI Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Université Pierre et Marie Curie - Paris 6 (UPMC), Center for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), Universitat Pompeu Fabra [Barcelona] (UPF), Fraunhofer Institute for Digital Medicine (Fraunhofer MEVIS), Fraunhofer (Fraunhofer-Gesellschaft), Service de Radiologie [CHU Caen], Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-CHU Caen, Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN)-Tumorothèque de Caen Basse-Normandie (TCBN), MedisysResearch Lab ( Medisys ), Analysis and Simulation of Biomedical Images ( ASCLEPIOS ), Inria Sophia Antipolis - Méditerranée ( CRISAM ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), Katholieke Universiteit Leuven ( KU Leuven ), 3 - Imagerie Ultrasonore, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé ( CREATIS ), Université Claude Bernard Lyon 1 ( UCBL ), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon ( INSA Lyon ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ) -Hospices Civils de Lyon ( HCL ) -Université Jean Monnet [Saint-Étienne] ( UJM ) -Institut National de la Santé et de la Recherche Médicale ( INSERM ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Claude Bernard Lyon 1 ( UCBL ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ) -Hospices Civils de Lyon ( HCL ) -Université Jean Monnet [Saint-Étienne] ( UJM ) -Institut National de la Santé et de la Recherche Médicale ( INSERM ) -Centre National de la Recherche Scientifique ( CNRS ), Physicochimie des Electrolytes, Colloïdes et Sciences Analytiques ( PECSA ), Université Pierre et Marie Curie - Paris 6 ( UPMC ) -ESPCI ParisTech-Centre National de la Recherche Scientifique ( CNRS ), Center for Computational Imaging and Simulation Technologies in Biomedicine ( CISTIB ), Universitat Pompeu Fabra [Barcelona], Fraunhofer Institute for Medical Image Computing MEVIS [Bremen] ( Fraunhofer MEVIS ), Département de Radiologie [Caen], Université de Caen Normandie ( UNICAEN ), Normandie Université ( NU ) -Normandie Université ( NU ) -CHU Caen, Publica, Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Ecole Superieure de Physique et de Chimie Industrielles de la Ville de Paris (ESPCI Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), and Asclepios, Project-Team
Subjects: [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, 3d strain, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Computer science, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Echocardiography, Three-Dimensional, Myocardial Ischemia, [ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processing, 030204 cardiovascular system & hematology, Tracking (particle physics), 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Computer Simulation, 3D ultrasound, Computer vision, Electrical and Electronic Engineering, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Radiological and Ultrasound Technology, medicine.diagnostic_test, [ INFO.INFO-IM ] Computer Science [cs]/Medical Imaging, business.industry, Myocardium, Ultrasound, Models, Cardiovascular, Biomechanics, Reproducibility of Results, Heart, Pattern recognition, Biomechanical Phenomena, Computer Science Applications, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Artificial intelligence, Deformation (engineering), business, Radial stress, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms, Software
Abstract: International audience; This paper evaluates five 3D ultrasound tracking algorithms regarding their ability to quantify abnormal deformation in timing or amplitude. A synthetic database of B-mode image sequences modeling healthy, ischemic and dyssynchrony cases was generated for that purpose. This database is made publicly available to the community. It combines recent advances in electromechanical and ultrasound modeling. For modeling heart mechanics, the Bestel-Clement-Sorine electromechanical model was applied to a realistic geometry. For ultrasound modeling, we applied a fast simulation technique to produce realistic images on a set of scatterers moving according to the electromechanical simulation result. Tracking and strain accuracies were computed and compared for all evaluated algorithms. For tracking, all methods were estimating myocardial displacements with an error below one milimeter on the ischemic sequences. The introduction of a dilated geometry was found to have a significant impact on accuracy. Regarding strain, all methods were able to recover timing differences between segments, as well as low strain values. On all cases, radial strain was found to have a low accuracy in comparison to longitudinal and circumferential components.
Published: 2013

3. Incorporating patient-specific variability in the oncoPET_DB database

Author: Rémy Prost, J.-M. Rouet, S. Marache-Francisco, Carole Lartizien, MedisysResearch Lab (Medisys), Philips Research, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Images et Modèles, Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), MedisysResearch Lab ( Medisys ), Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé ( CREATIS ), Hospices Civils de Lyon ( HCL ) -Université Jean Monnet [Saint-Étienne] ( UJM ) -Institut National de la Santé et de la Recherche Médicale ( INSERM ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Claude Bernard Lyon 1 ( UCBL ), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon ( INSA Lyon ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ), 2 - Images et Modèles, and Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ) -Hospices Civils de Lyon ( HCL ) -Université Jean Monnet [Saint-Étienne] ( UJM ) -Institut National de la Santé et de la Recherche Médicale ( INSERM ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Claude Bernard Lyon 1 ( UCBL )
Subjects: Database, medicine.diagnostic_test, [ INFO.INFO-IM ] Computer Science [cs]/Medical Imaging, business.industry, Philips healthcare, Respiratory motion, Patient specific, computer.software_genre, Homogeneous, Positron emission tomography, medicine, Calibration, Breathing, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Whole body pet, business, computer
Abstract: International audience; The purpose of this study was to generate a series of simulated 8F-FDG PET oncology images incorporating variability of patient anatomy and 18F-FDG uptake in the main organs as well as realistic respiratory motion. These data are based on the XCAT model adapted to a series of clinical CT data and on patient respiratory cycles derived from spirometry records. Spherical 8 and 12 mm diameter lesions of homogeneous uptake were randomly distributed in the lungs and the liver, which are both significantly impacted by respiratory motion. Five different lesion contrasts per diameter and per organ were sampled based on a human observer detection study so as to cover the entire range of detectability. The simulated database was generated with the PET-SORTEO Monte-Carlo simulation tool that was fully validated against the geometry of the GEMINI system (Philips Healthcare, Cleveland, OH). The simulated database is actually composed of 15 whole body PET simulated images with a total of 107 tumors in the liver and 173 tumors in the lungs. These data will complete the first series of images of the oncoPET_DB database (www.creatis.insa-lyon.fr/oncoPET_DB) by providing the raw list-mode files of the 15 models as well as four sets of reconstruction per model. These four series include the extreme cases of respiration-free (non breathing) and free-respiration (no correction) images and two respiratory motion corrected images based on the estimation of elastic transformation fields applied either on the reconstruction system matrix, during reconstruction, or a posteriori, on the reconstructed PET gated images. Perspectives include performing a human FROC study on the 15 images to validate the lesion contrast calibration.
Published: 2011

4. Realistic X-ray CT simulation of the XCAT phantom with SINDBAD

Author: W. Paul Segars, Joachim Tabary, Carole Lartizien, Sébastien Valette, S. Marache-Francisco, Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information (CEA-LETI), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Centre de Recherche et d'Application en Traitement de l'Image et du Signal (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-École Supérieure de Chimie Physique Électronique de Lyon (CPE)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), MedisysResearch Lab (Medisys), Philips Research, Department of Radiology, Duke University [Durham], Laboratoire d'Electronique et des Technologies de l'Information ( CEA-LETI ), Commissariat à l'énergie atomique et aux énergies alternatives ( CEA ) -Université Grenoble Alpes [Saint Martin d'Hères], Centre de Recherche et d'Application en Traitement de l'Image et du Signal ( CREATIS ), Université Claude Bernard Lyon 1 ( UCBL ), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon ( INSA Lyon ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ) -École Supérieure Chimie Physique Électronique de Lyon-Institut National de la Santé et de la Recherche Médicale ( INSERM ) -Centre National de la Recherche Scientifique ( CNRS ), MedisysResearch Lab ( Medisys ), Duke university [Durham], Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-École Supérieure Chimie Physique Électronique de Lyon-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Physics, Scanner, [ INFO.INFO-IM ] Computer Science [cs]/Medical Imaging, business.industry, Computation, Monte Carlo method, Detector, Physics::Medical Physics, Solid modeling, computer.software_genre, Imaging phantom, 030218 nuclear medicine & medical imaging, Simulation software, 03 medical and health sciences, 0302 clinical medicine, 030220 oncology & carcinogenesis, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Computer vision, Artificial intelligence, business, Projection (set theory), computer
Abstract: International audience; An efficient simulation tool is developed to generate realistic X-ray CT images, including a good modeling of physics and a very detailed anthropomorphic model in a reasonable computing time. This simulation tool consists in a coupling of the existing X-ray radiographic simulation software SINDBAD with the extended NURBS-Based Cardiac-Torso (XCAT) phantom. Both primary and scatter contributions in X-ray CT projections are calculated thanks to a combination of analytical and Monte Carlo approaches. The representation of the XCAT phantom is adapted to the level of resolution required by the primary and scatter images. We present in this paper first X-ray CT projection data which are simulated under an angiography configuration. Although the XCAT phantom is complex, the computation time is reasonable, even with the estimation of the scatter radiation. In future studies, similar simulations will be performed in real clinical CT scanner conditions, with an accurate modelling of detectors and a finer representation of the XCAT phantom, and will be compared with real X-rays CT images for validation.
Published: 2009

5. Multi-Scale Diffeomorphic Cortical Registration Under Manifold Sulcal Constraints

Author: Guillaume Auzias, Joan Alexis Glaunès, Olivier Colliot, Sylvain Baillet, Alain Trouvé, J.-F. Mangin, Arnaud Cachia, P. Cathier, Eric Bardinet, Glaunès, Joan Alexis, Mathématiques Appliquées à Paris 5 ( MAP5 - UMR 8145 ), Université Paris Descartes - Paris 5 ( UPD5 ) -Institut National des Sciences Mathématiques et de leurs Interactions-Centre National de la Recherche Scientifique ( CNRS ), MedisysResearch Lab ( Medisys ), Philips Research, Centre de Recherche de l'Institut du Cerveau et de la Moelle épinière ( CRICM ), Centre National de la Recherche Scientifique ( CNRS ) -Institut National de la Santé et de la Recherche Médicale ( INSERM ) -Université Pierre et Marie Curie - Paris 6 ( UPMC ), Neurosciences cognitives et imagerie cérébrale ( NCIC ), Centre National de la Recherche Scientifique ( CNRS ), CHU Pitié-Salpêtrière [APHP], Centre de Mathématiques et de Leurs Applications ( CMLA ), École normale supérieure - Cachan ( ENS Cachan ) -Centre National de la Recherche Scientifique ( CNRS ), Laboratoire de neurosciences cognitives et d'imagerie cérébrale ( LENA ), Université Pierre et Marie Curie - Paris 6 ( UPMC ) -Centre National de la Recherche Scientifique ( CNRS ), Mathématiques Appliquées Paris 5 (MAP5 - UMR 8145), Université Paris Descartes - Paris 5 (UPD5)-Institut National des Sciences Mathématiques et de leurs Interactions (INSMI)-Centre National de la Recherche Scientifique (CNRS), MedisysResearch Lab (Medisys), Centre de Recherche de l'Institut du Cerveau et de la Moelle épinière (CRICM), Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC), Neurosciences cognitives et imagerie cérébrale (NCIC), Centre National de la Recherche Scientifique (CNRS), Centre de Mathématiques et de Leurs Applications (CMLA), École normale supérieure - Cachan (ENS Cachan)-Centre National de la Recherche Scientifique (CNRS), Laboratoire de neurosciences cognitives et d'imagerie cérébrale (LENA), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), and Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)
Subjects: Surface (mathematics), Matching (graph theory), business.industry, Image registration, Sulcus, Manifold, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, medicine.anatomical_structure, Neuroimaging, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Spatial normalization, [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, medicine, Computer vision, Artificial intelligence, Scale (map), business, 030217 neurology & neurosurgery, ComputingMilieux_MISCELLANEOUS, Mathematics
Abstract: Neuroimaging at the group level requires spatial normalization across individuals. This issue has been receiving considerable attention from multiple research groups. Here we suggest a surface-based geometric approach that consists in matching a set of cortical surfaces through their sulcal imprints. We provide the proof-of-concept of this approach by showing 1) how sulci may be automatically identified and simplified from Tl-weighted MRI data series, and 2) how this sulcal information may be considered as landmarks for recent measure-based diffeomorphic deformation approaches. In our framework, the resulting 3D transforms are naturally applied to the entire cortical surface and MRI volumes.
Published: 2008

6. Cooperating Networks To Enforce A Similarity Constraint In Paired But Unregistered Multimodal Liver Segmentation

Author: Guillaume Julien Joseph Pizaine, Olivier Pierre Nempont, Vincent Couteaux, Pierre-Jean Valette, Mathilde Trintignac, Laurent Milot, Isabelle Bloch, Anna Sesilia Vlachomitrou, Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, MedisysResearch Lab (Medisys), Philips Research, Hospices Civils de Lyon (HCL), Centre Hospitalier Lyon Sud [CHU - HCL] (CHLS), Centre de Recherche et d'Application en Traitement de l'Image et du Signal (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-École Supérieure Chimie Physique Électronique de Lyon-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Learning, Fuzzy and Intelligent systems (LFI), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Image, Modélisation, Analyse, GEométrie, Synthèse (IMAGES), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Département Images, Données, Signal (IDS), and Télécom ParisTech
Subjects: Forcing (recursion theory), Modalities, Computer science, business.industry, [SDV]Life Sciences [q-bio], Pattern recognition, Dice, 02 engineering and technology, Image segmentation, 030218 nuclear medicine & medical imaging, Constraint (information theory), 03 medical and health sciences, 0302 clinical medicine, Market segmentation, Similarity (network science), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, [INFO]Computer Science [cs], Artificial intelligence, business
Abstract: International audience; We propose a method for segmenting two unregistered images from different modalities of the same patient and study at once, while enforcing a similarity constraint between the two segmentation masks. Our method relies on a segmentation network and a registration network, cooperating to get accurate and consistent segmentation masks across modalities, while forcing the segmentor to use all information available. Experiments on a dataset of T1 and T2-weighted liver MRI show that our method enables to get more similar segmentation masks across modalities than manual annotations, without deteriorating the performance (Dice =0.95 for T1, 0.92 for T2).
Published: 2021

7. A Pilot Study on Convolutional Neural Networks for Motion Estimation From Ultrasound Images

Author: Khuram Faraz, Olivier Bernard, Thomas Grenier, Mathieu De Craene, Ewan Evain, Damien Garcia, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), MedisysResearch Lab (Medisys), Philips Research, Modeling & analysis for medical imaging and Diagnosis (MYRIAD), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Philips Research-Philips Research, Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), and Bernard, Olivier
Subjects: [PHYS.PHYS.PHYS-FLU-DYN]Physics [physics]/Physics [physics]/Fluid Dynamics [physics.flu-dyn], Acoustics and Ultrasonics, Computer science, Movement, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pilot Projects, Iterative reconstruction, Motion estimation, 01 natural sciences, Convolutional neural network, Speckle pattern, [SDV.MHEP.CSC]Life Sciences [q-bio]/Human health and pathology/Cardiology and cardiovascular system, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Segmentation, Computer vision, Electrical and Electronic Engineering, 010301 acoustics, Instrumentation, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Ultrasonography, Pixel, Phantoms, Imaging, business.industry, ultrasound, Deep learning, deep learning, Motion field, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract: International audience; In recent years, deep learning (DL) has been successfully applied to the analysis and processing of ultrasound images. To date, most of this research has focused on segmentation and view recognition. This article benchmarks different convolutional neural network algorithms for motion estimation in ultrasound imaging. We evaluated and compared several networks derived from FlowNet2, one of the most efficient architectures in computer vision. The networks were tested with and without transfer learning, and the best configuration was compared against the particle imaging velocimetry method, a popular state-of-the-art block-matching algorithm. Rotations are known to be difficult to track from ultrasound images due to a significant speckle decorrelation. We thus focused on the images of rotating disks, which could be tracked through speckle features only. Our database consisted of synthetic and in vitro B-mode images after log compression and covered a large range of rotational speeds. One of the FlowNet2 subnetworks, FlowNet2SD, produced competitive results with a motion field error smaller than 1 pixel on real data after transfer learning based on the simulated data. These errors remain small for a large velocity range without the need for hyperparameter tuning, which indicates the high potential and adaptability of DL solutions to motion estimation in ultrasound imaging.
Published: 2020

8. Machine learning approaches for myocardial motion and deformation analysis

Author: Nicolas Duchateau, Mathieu De Craene, Andrew P. King, Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales (MOTIVATE), Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), Modeling & analysis for medical imaging and Diagnosis (MYRIAD), MedisysResearch Lab (Medisys), Philips Research, and ANR-19-CE45-0005,MIC-MAC,Modélisation de la hiérarchie entre descripteurs cardiaques par apprentissage automatique(2019)
Subjects: 0301 basic medicine, lcsh:Diseases of the circulatory (Cardiovascular) system, Computer science, Mini Review, Cardiovascular Medicine, 030204 cardiovascular system & hematology, Deformation (meteorology), Machine learning, computer.software_genre, Motion (physics), cardiac imaging, 03 medical and health sciences, 0302 clinical medicine, Robustness (computer science), [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, ComputingMilieux_MISCELLANEOUS, business.industry, 030104 developmental biology, machine learning, Computer-aided diagnosis, lcsh:RC666-701, Myocardial strain, myocardial motion, Key (cryptography), Myocardial motion, myocardial strain, computer-aided diagnosis, Artificial intelligence, Cardiology and Cardiovascular Medicine, business, computer
Abstract: Information about myocardial motion and deformation is key to differentiate normal and abnormal conditions. With the advent of approaches relying on data rather than pre-conceived models, machine learning could either improve the robustness of motion quantification or reveal patterns of motion and deformation (rather than single parameters) that differentiate pathologies. We review machine learning strategies for extracting motion-related descriptors and analyzing such features among populations, keeping in mind constraints specific to the cardiac application.
Published: 2020

9. Optimization of Fetal Biometry With 3D Ultrasound and Image Recognition (EPICEA): protocol for a prospective cross-sectional study

Author: Gabriela Hossu, Marine Beaumont, Claire Banasiak, Laurence Rouet, Gaëlle Ambroise Grandjean, Olivier Morel, Cybèle Ciofolo-Veit, Caroline Raynaud, Imagerie Adaptative Diagnostique et Interventionnelle (IADI), Université de Lorraine (UL)-Institut National de la Santé et de la Recherche Médicale (INSERM), Service d'Obstétrique et de Médecine fœtale [CHRU Nancy], Pôle de Gynécologie-Obstétrique et Reproduction, Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Université de Lorraine (UL), Centre d'Investigation Clinique - Innovation Technologique [Nancy] (CIC-IT), Centre d'investigation clinique [Nancy] (CIC), Université de Lorraine (UL)-Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Lorraine (UL)-Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Institut National de la Santé et de la Recherche Médicale (INSERM), Philips Research, MedisysResearch Lab (Medisys), Philips Research-Philips Research, BIRKER, Juliette, Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Lorraine (UL), Université de Lorraine (UL)-Service d'Obstétrique et de Gynécologie [CHRU Nancy], and Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)
Subjects: [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, fetal biometry, 030218 nuclear medicine & medical imaging, Fetal Development, 0302 clinical medicine, Pregnancy, Abdomen, Obstetrics and Gynaecology, Protocol, Fetal head, 3D ultrasound, Femur, Prospective Studies, Clinical Trials as Topic, 030219 obstetrics & reproductive medicine, [SDV.MHEP] Life Sciences [q-bio]/Human health and pathology, medicine.diagnostic_test, ultrasound, General Medicine, Institutional review board, artificial intelligence, Female, medicine.medical_specialty, Biometry, Cephalometry, Interclass correlation, Context (language use), Gestational Age, [SDV.IB.MN]Life Sciences [q-bio]/Bioengineering/Nuclear medicine, Ultrasonography, Prenatal, [SDV.IB.MN] Life Sciences [q-bio]/Bioengineering/Nuclear medicine, 03 medical and health sciences, Fetus, Imaging, Three-Dimensional, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Medical physics, reproducibility, Protocol (science), Reproducibility, business.industry, Reproducibility of Results, Cross-Sectional Studies, Calipers, business, Head, Software, [SDV.MHEP]Life Sciences [q-bio]/Human health and pathology
Abstract: ContextVariability in 2D ultrasound (US) is related to the acquisition of planes of reference and the positioning of callipers and could be reduced in combining US volume acquisitions and anatomical structures recognition.ObjectivesThe primary objective is to assess the consistency between 3D measurements (automated and manual) extracted from a fetal US volume with standard 2D US measurements (I). Secondary objectives are to evaluate the feasibility of the use of software to obtain automated measurements of the fetal head, abdomen and femur from US acquisitions (II) and to assess the impact of automation on intraobserver and interobserver reproducibility (III).Methods and analysis225 fetuses will be measured at 16–30 weeks of gestation. For each fetus, six volumes (two for head, abdomen and thigh, respectively) will be prospectively acquired after performing standard 2D biometry measurements (head and abdominal circumference, femoral length). Each volume will be processed later by both a software and an operator to extract the reference planes and to perform the corresponding measurements. The different sets of measurements will be compared using Bland-Altman plots to assess the agreement between the different processes (I). The feasibility of using the software in clinical practice will be assessed through the failure rate of processing and the score of quality of measurements (II). Interclass correlation coefficients will be used to evaluate the intraobserver and interobserver reproducibility (III).Ethics and disseminationThe study and related consent forms were approved by an institutional review board (CPP SUD-EST 3) on 2 October 2018, under reference number 2018–033 B. The study has been registered inhttps://clinicaltrials.govregistry on 23 January 2019, under the numberNCT03812471. This study will enable an improved understanding and dissemination of the potential benefits of 3D automated measurements and is a prerequisite for the design of intention to treat randomised studies assessing their impact.Trial registration numberNCT03812471; Pre-results.
Published: 2019

10. Left Ventricular Shape and Motion Reconstruction through a Healthy Model for Characterizing Remodeling after Infarction

Author: Mathieu De Craene, Eric Saloux, Nicolas Duchateau, Pascal Allain, Paolo Piro, Philips Research, MedisysResearch Lab (Medisys), Philips Research-Philips Research, Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales (MOTIVATE), Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Modeling & analysis for medical imaging and Diagnosis (MYRIAD), CHU Caen, Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN), Yves Coudière, Valéry Ozenne, Edward Vigmond, and Nejib Zemzemi
Subjects: Computer science, Quantitative Biology::Tissues and Organs, Physics::Medical Physics, Population, Motion (geometry), Infarction, 030218 nuclear medicine & medical imaging, Anatomical space, 03 medical and health sciences, Motion, 0302 clinical medicine, [SDV.MHEP.CSC]Life Sciences [q-bio]/Human health and pathology/Cardiology and cardiovascular system, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Computer vision, education, education.field_of_study, Abnormality, Atlas (topology), business.industry, Dynamics (mechanics), Shape, medicine.disease, 3. Good health, medicine.anatomical_structure, Ventricle, Artificial intelligence, Affine transformation, business, Cardiac, 030217 neurology & neurosurgery
Abstract: International audience; We introduce a framework for the statistical characterization of heart remodeling from both shape and dynamics of the left ventricle. Shape was characterized by thickness and radius maps, unfolded in a two-dimensional dense Bull's eye. Motion was represented as a mixture of affine transformations in an anatomical space of coordinates. Using this representation, a population can be projected (after defining spa-tiotemporal correspondences) to an atlas space built for a given reference population-here, healthy subjects using a classic PCA approach-yielding a joint model of healthy shape and motion statistics. The reconstruction error on shape and motion can then be exploited to quantify remodeling abnormalities. We demonstrate these concepts on 48 healthy subjects and 62 patients with infarct (29 with one year follow-up) imaged with 3D echocardiography, analyzing a total of 139 sequences.
Published: 2019

11. A pipeline for image based intracardiac CFD modeling and application to the evaluation of the PISA method

Author: Hernán G. Morales, Alexandre This, Miguel Angel Fernández, Odile Bonnefous, Jean-Frédéric Gerbeau, MedisysResearch Lab (Medisys), Philips Research, COmputational Mathematics for bio-MEDIcal Applications (COMMEDIA), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jacques-Louis Lions (LJLL (UMR_7598)), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), Inria Siège, Institut National de Recherche en Informatique et en Automatique (Inria), Funds were supported by a CIFRE Ph.D convention established between INRIA Paris and Philips Research, France, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP), Université Paris Diderot - Paris 7 (UPD7)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Diderot - Paris 7 (UPD7)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Numerical simulation of biological flows (REO), Sorbonne Université (SU)-Inria de Paris, and Université Paris Diderot - Paris 7 (UPD7)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Computer science, Computational Mechanics, General Physics and Astronomy, Numerical simulation, 010103 numerical & computational mathematics, Computational fluid dynamics, 01 natural sciences, Intracardiac injection, Mitral valve, medicine, 0101 mathematics, Image resolution, Mitral regurgitation, Computer simulation, business.industry, Mechanical Engineering, valvular heart disease, [INFO.INFO-NA]Computer Science [cs]/Numerical Analysis [cs.NA], medicine.disease, Computer Science Applications, 010101 applied mathematics, medicine.anatomical_structure, Mechanics of Materials, Patient-specific, business, Algorithm, Image based
Abstract: International audience; Mitral regurgitation is one of the most prevalent valvular heart disease. Proper evaluation of its severity is necessary to choose appropriate treatment. The PISA method, based on Color Doppler echocardiography, is widely used in the clinical setting to estimate various relevant quantities related to the severity of the disease. In this paper, the use of a pipeline to quickly generate image-based numerical simulation of intracardiac hemodynamics is investigated. The pipeline capabilities are evaluated on a database of twelve volunteers. Full pre-processing is achieved completely automatically in 55 minutes, on average, with small registration errors compared to the image spatial resolution. This pipeline is then used to study the intracardiac hemodynamics in the presence of diseased mitral valve. A strong variability among the simulated cases, mainly due to the valve geometry and regurgitation specifics, is found. The results from those numerical simulations is used to assess the potential limitations of the PISA method with respect to different MR types. While the PISA method provides reasonable estimates in the case of a simple circular regurgitation, it is shown that unsatisfying estimates are obtained in the case of non-circular leakage. Moreover, it is shown that the choice of high aliasing velocities can lead to difficulties in quantifying MR.
Published: 2020

12. Realistic Vendor-Specific Synthetic Ultrasound Data for Quality Assurance of 2-D Speckle Tracking Echocardiography: Simulation Pipeline and Open Access Database

Author: Mathieu De Craene, Olivier Bernard, Martino Alessandrini, Brecht Heyde, Maxime Sermesant, Jan D'hooge, Bidisha Chakraborty, Imagerie Ultrasonore, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Laboratory of Cardiovascular Imaging and Dynamics, Images et Modèles, MedisysResearch Lab (Medisys), Philips Research, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Acoustics and Ultrasonics, Databases, Factual, Image quality, Computer science, Speckle tracking echocardiography, 030204 cardiovascular system & hematology, computer.software_genre, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Speckle pattern, 0302 clinical medicine, Image Interpretation, Computer-Assisted, Humans, Computer Simulation, Electrical and Electronic Engineering, Instrumentation, ComputingMilieux_MISCELLANEOUS, Ground truth, business.industry, Heart, Pipeline (software), Data set, Echocardiography, Benchmark (computing), Data mining, business, computer, Quality assurance, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms
Abstract: Two-dimensional (2-D) echocardiography is the modality of choice in the clinic for the diagnosis of cardiac disease. Hereto, speckle tracking (ST) packages complement visual assessment by the cardiologist by providing quantitative diagnostic markers of global and regional cardiac function (e.g., displacement, strain, and strain-rate). Yet, the reported high vendor-dependence between the outputs of different ST packages raises clinical concern and hampers the widespread dissemination of the ST technology. In part, this is due to the lack of a solid commonly accepted quality assurance pipeline for ST packages. Recently, we have developed a framework to benchmark ST algorithms for 3-D echocardiography by using realistic simulated volumetric echocardiographic recordings. Yet, 3-D echocardiography remains an emerging technology, whereas the compelling clinical concern is, so far, directed to the standardization of 2-D ST only. Therefore, by building upon our previous work, we present in this paper a pipeline to generate realistic synthetic sequences for 2-D ST algorithms. Hereto, the synthetic cardiac motion is obtained from a complex electromechanical heart model, whereas realistic vendor-specific texture is obtained by sampling a real clinical ultrasound recording. By modifying the parameters in our pipeline, we generated an open-access library of 105 synthetic sequences encompassing: 1) healthy and ischemic motion patterns; 2) the most common apical probe orientations; and 3) vendor-specific image quality from seven different systems. Ground truth deformation is also provided to allow performance analysis. The application of the provided data set is also demonstrated in the benchmarking of a recent academic ST algorithm.
Published: 2018

13. The role of telemedicine in the management of maxillofacial trauma in emergency departments - preliminary results

Author: R. Prevost, Béatrice Ambroise, Rachid Garmi, Hervé Benateau, Alexis Veyssière, K. Hauchard, Biotechnologie des tissus conjonctifs et cutanés / Biology of Connective and Cutaneous Tissues (BioConnecT), Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU), MedisysResearch Lab (Medisys), Philips Research, Hôpital Côte de Nacre [CHU Caen], CHU Caen, and Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN)-Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN)
Subjects: Telemedicine, [SDV]Life Sciences [q-bio], Mobile application, Context (language use), Telehealth, Emergency treatment, 03 medical and health sciences, 0302 clinical medicine, Phone, Medicine, Humans, Applied research, 030223 otorhinolaryngology, business.industry, Medical record, 030206 dentistry, medicine.disease, Mobile Applications, 3. Good health, Otorhinolaryngology, Information and Communications Technology, Surgery, The Internet, Maxillofacial Injuries, Medical emergency, Smartphone, Oral Surgery, business, Emergency Service, Hospital
Abstract: International audience; New technologies have over the past forty years become widespread across all domains of basic and applied research particularly in health-related fields. Telemedicine is a form of remote medical practice using information and communication technologies. It connects one or more health professionals with other health professionals or with patients. Within the framework of emergencies in maxillofacial surgery, requests received for specialist advice often pertain to procedures to be followed for facial wounds, bites, burns, maxillofacial bone trauma or facial cellulitis. These requests for specialist advice were previously made by phone between emergency physicians and maxillofacial specialists, with exchange of patient photos by text messaging, which raised security issues. We collaborated with the Telehealth Normandy Health Cooperation Group (GCS TSBN) for the implementation of a mobile application using the “Therap-e” telemedicine platform. This platform links together websites and remote health professionals via the Internet. Physicians communicate over a mobile network or from a health institution, in online or offline mode, synchronously or asynchronously, using any medium (tablet, PC, Mac, smartphone). This scheme both ensures secure transmission of personal and clinical data (especially facial photographs) and records specialist advice in patient medical records. The purpose of tele-expertise applications in an emergency context is to provide a solution to the demographic problems facing healthcare professionals and to rise to the growing challenges surrounding quality and security issues.
Published: 2018

14. Multi-organ localization with cascaded global-to-local regression and shape prior

Author: Romane Gauriau, David Lesage, Rémi Cuingnet, Isabelle Bloch, MedisysResearch Lab (Medisys), Philips Research, Image, Modélisation, Analyse, GEométrie, Synthèse (IMAGES), Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Département Traitement du Signal et des Images (TSI), and Centre National de la Recherche Scientifique (CNRS)-Télécom ParisTech
Subjects: Radiography, Abdominal, multi-organ localization, Health Informatics, 3D CT, Kidney, computer.software_genre, Machine learning, Set (abstract data type), Imaging, Three-Dimensional, Robustness (computer science), Voxel, Bounding overwatch, Humans, Radiology, Nuclear Medicine and imaging, abdominal organs, Mathematics, Radiological and Ultrasound Technology, business.industry, Decision Trees, Stomach, Probabilistic logic, Local regression, Pattern recognition, Computer Graphics and Computer-Aided Design, Regression, Cholecystography, Random forest, Liver, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Radiographic Image Interpretation, Computer-Assisted, regression, Computer Vision and Pattern Recognition, Artificial intelligence, Tomography, X-Ray Computed, business, computer, random forest, Spleen
Abstract: We propose a method for fast, accurate and robust localization of several organs in medical images. We generalize the global-to-local cascade of regression random forest to multiple organs. A first regressor encodes the global relationships between organs, learning simultaneously all organs parameters. Then subsequent regressors refine the localization of each organ locally and independently for improved accuracy. By combining the regression vote distribution and the organ shape prior (through probabilistic atlas representation) we compute confidence maps that are organ-dedicated probability maps. They are used within the cascade itself, to better select the test voxels for the second set of regressors, and to provide richer information than the classical bounding boxes result thanks to the shape prior. We propose an extensive study of the different learning and testing parameters, showing both their robustness to reasonable perturbations and their influence on the final algorithm accuracy. Finally we demonstrate the robustness and accuracy of our approach by evaluating the localization of six abdominal organs (liver, two kidneys, spleen, gallbladder and stomach) on a large and diverse database of 130 CT volumes. Moreover, the comparison of our results with two existing methods shows significant improvements brought by our approach and our deep understanding and optimization of the parameters.
Published: 2015

15. Cardiac Electrophysiological Activation Pattern Estimation From Images Using a Patient-Specific Database of Synthetic Image Sequences

Author: Hervé Delingette, Adityo Prakosa, Pascal Allain, Nicholas Ayache, Maxime Sermesant, Reza Razavi, Kawal Rhode, Nicolas Villain, C. Aldo Rinaldi, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), MedisysResearch Lab (Medisys), Philips Research, Department of cardiology [Guy's and St. Thomas ' hospitals] [London], Guy's and St Thomas' Hospital [London]-Guy's Hospital [London], Division of Imaging Sciences, King‘s College London, and European Project: 291080,EC:FP7:ERC,ERC-2011-ADG_20110209,MEDYMA(2012)
Subjects: Male, Databases, Factual, Computer science, Biomedical Engineering, computer.software_genre, Activation pattern, Intracardiac injection, Electrocardiography, Motion, Artificial Intelligence, Motion estimation, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, medicine, Humans, Computer Simulation, Computer vision, Aged, Database, medicine.diagnostic_test, business.industry, Models, Cardiovascular, Heart, Middle Aged, Patient specific, 3. Good health, Electrophysiology, Female, Artificial intelligence, business, computer
Abstract: International audience; While abnormal patterns of cardiac electrophysiological activation are at the origin of important cardiovascular diseases (e.g. arrhythmia, asynchrony), the only clinically available method to observe detailed left ventricular endocardial surface activation pattern is through invasive catheter mapping. However this electrophysiological activation controls the onset of the mechanical contraction, therefore important information about the electrophysiology could be deduced from the detailed observation of the resulting motion patterns. In this article, we present the study of this inverse cardiac electro-kinematic relationship. The objective is to predict the activation pattern knowing the cardiac motion from the analysis of cardiac image sequences. To achieve this, we propose to create a rich patientspecific database of synthetic time series of cardiac images using simulations of a personalized cardiac electromechanical model, in order to study this complex relationship between electrical activity and kinematic patterns in the context of this specific patient. We use this database to train a machine learning algorithm which estimates the depolarization times of each cardiac segment from global and regional kinematic descriptors based on displacements or strains and their derivatives. Finally, we use this learning to estimate the patient's electrical activation times using the acquired clinical images. Experiments on the inverse electro-kinematic learning are demonstrated on synthetic sequences and are evaluated on clinical data with promising results. The error calculated between our prediction and the invasive intracardiac mapping ground truth is relatively small (around 10 ms for ischemic patients and 20 ms for non-ischemic patient). This approach suggests the possibility of non-invasive electrophysiological pattern estimation using cardiac motion imaging.
Published: 2014

16. Understanding the mechanisms amenable to CRT response: from pre-operative multimodal image data to patient-specific computational models

Author: Reza Razavi, Oscar Camara, M. Steghofer, Jatin Relan, Stephanie Marchesseau, Ali Pashaei, Pablo Lamata, Mireille Garreau, Catalina Tobon-Gomez, Alfredo Hernandez, Maxime Sermesant, Hervé Delingette, Simon G. Duckett, Erwan Donal, K. S. Rhode, Christophe Leclercq, Nicholas Ayache, Alejandro F. Frangi, Rafael Sebastian, M. De Craene, Nicolas P. Smith, Nicolas Duchateau, Center for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), Universitat Pompeu Fabra [Barcelona] (UPF), Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), Instituto de Salud Carlos III [Madrid] (ISC)-ministerio de ciencia e innovacion, Computational Multi-Scale Physiology Lab [Valencia], Universitat de València (UV), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire Traitement du Signal et de l'Image (LTSI), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de la Santé et de la Recherche Médicale (INSERM), MedisysResearch Lab (Medisys), Philips Research, School of Biomedical Engineering & Imaging Sciences [London], Guy's and St Thomas' Hospital [London]-King‘s College London, Department of Computer Science [Oxford], University of Oxford [Oxford], Division of Imaging Sciences, King‘s College London, Université de Rennes (UR)-Institut National de la Santé et de la Recherche Médicale (INSERM), and University of Oxford
Subjects: Adult, Computer science, medicine.medical_treatment, 0206 medical engineering, Biomedical Engineering, Cardiac resynchronization therapy, 02 engineering and technology, 030204 cardiovascular system & hematology, Machine learning, computer.software_genre, Cardiac Resynchronization Therapy, Electrocardiography, 03 medical and health sciences, Imaging, Three-Dimensional, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, medicine, Humans, Computer Simulation, Computer vision, Precision Medicine, Aged, Computational model, business.industry, Patient Selection, Models, Cardiovascular, Middle Aged, Patient specific, Precision medicine, Magnetic Resonance Imaging, 020601 biomedical engineering, Pipeline (software), Pre operative, 3. Good health, Computer Science Applications, Multimodal image, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Fully automatic, [SDV.IB]Life Sciences [q-bio]/Bioengineering, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, computer
Abstract: International audience; This manuscript describes our recent developments towards better understanding of the mechanisms amenable to cardiac resynchronization therapy response. We report the results from a full multimodal dataset corresponding to eight patients from the euHeart project. The datasets include echocardiography, MRI and electrophysiological studies. We investigate two aspects. The first one focuses on pre-operative multimodal image data. From 2D echocardiography and 3D tagged MRI images, we compute atlas based dyssynchrony indices. We complement these indices with presence and extent of scar tissue and correlate them with CRT response. The second one focuses on computational models. We use pre-operative imaging to generate a patient-specific computational model. We show results of a fully automatic personalized electromechanical simulation. By case-per-case discussion of the results, we highlight the potential and key issues of this multimodal pipeline for the understanding of the mechanisms of CRT response and a better patient selection.
Published: 2013

17. A High-Resolution Atlas and Statistical Model of the Human Heart From Multislice CT

Author: Corné Hoogendoorn, Mathieu De Craene, Karim Lekadir, Nicolas Duchateau, Federico M. Sukno, Alejandro F. Frangi, Damián Sánchez-Quintana, Tristan Whitmarsh, Center for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), Universitat Pompeu Fabra [Barcelona] (UPF), Cardiology Department, Thorax Clinic Institute, Hospital Cliınic, Institut d'Investigacions Biomèdiques [Barcelona], Universitat de Barcelona (UB), MedisysResearch Lab (Medisys), Philips Research, Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), and Instituto de Salud Carlos III [Madrid] (ISC)-ministerio de ciencia e innovacion
Subjects: Computer science, Image registration, Computed tomography, Image processing, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Atlases as Topic, 0302 clinical medicine, Atlas (anatomy), Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, medicine, Humans, Computer vision, Electrical and Electronic Engineering, Retrospective Studies, Models, Statistical, Radiological and Ultrasound Technology, medicine.diagnostic_test, business.industry, Atlas (topology), Models, Cardiovascular, Reproducibility of Results, Heart, Pattern recognition, Statistical model, Computer Science Applications, medicine.anatomical_structure, Spatial normalization, Artificial intelligence, Tomography, X-Ray Computed, business, 030217 neurology & neurosurgery, Software, Level of detail
Abstract: Atlases and statistical models play important roles in the personalization and simulation of cardiac physiology. For the study of the heart, however, the construction of comprehensive atlases and spatio-temporal models is faced with a number of challenges, in particular the need to handle large and highly variable image datasets, the multi-region nature of the heart, and the presence of complex as well as small cardiovascular structures. In this paper, we present a detailed atlas and spatio-temporal statistical model of the human heart based on a large population of 3D+time multi-slice computed tomography sequences, and the framework for its construction. It uses spatial normalization based on nonrigid image registration to synthesize a population mean image and establish the spatial relationships between the mean and the subjects in the population. Temporal image registration is then applied to resolve each subject-specific cardiac motion and the resulting transformations are used to warp a surface mesh representation of the atlas to fit the images of the remaining cardiac phases in each subject. Subsequently, we demonstrate the construction of a spatio-temporal statistical model of shape such that the inter-subject and dynamic sources of variation are suitably separated. The framework is applied to a 3D+time data set of 138 subjects. The data is drawn from a variety of pathologies, which benefits its generalization to new subjects and physiological studies. The obtained level of detail and the extendability of the atlas present an advantage over most cardiac models published previously.
Published: 2013

18. Generation of Realistic 4D Synthetic CSPAMM Tagged MR Sequences for Benchmarking Cardiac Motion Tracking Algorithms

Author: Maxime Sermesant, Oudom Somphone, Yitian Zhou, Mathieu De Craene, Olivier Bernard, Harvard Medical School [Boston] (HMS), MedisysResearch Lab (Medisys), Philips Research, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Images et Modèles, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: business.industry, Computer science, Pipeline (computing), Benchmarking, 030204 cardiovascular system & hematology, Tracking (particle physics), computer.software_genre, Synthetic data, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, ComputingMethodologies_PATTERNRECOGNITION, 0302 clinical medicine, Voxel, Cardiac motion, Cardiac deformation, Computer vision, Artificial intelligence, business, computer, Algorithm, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Normal heart, ComputingMilieux_MISCELLANEOUS
Abstract: This paper introduces a novel pipeline for synthesizing realistic 3D+t CSPAMM cardiac tagged magnetic resonance (MR) images. The proposed framework is based on the combination of an electro-mechanical model for generating cardiac deformation fields and a template tagging recording for assigning realistic voxel intensities. We developed a spatio-temporal alignment strategy for mapping voxel positions in the simulation space to the template recording space. As a preliminary result, we generated a synthetic dataset of a normal heart, and further compared the performance of two state-of-the-art cardiac motion tracking algorithms using this synthetic data. In this study, we aim at showing the capability of the proposed pipeline to simulate realistic cardiac tagged MR images, and its extension to more synthetic cases especially pathological ones are currently left to future work.
Published: 2016

19. Phase-Based Registration of Cardiac Tagged MR Images by Incorporating Anatomical Constraints

Author: Yitian Zhou, Olivier Bernard, Mathieu De Craene, Maxime Sermesant, Harvard Medical School [Boston] (HMS), Philips Research, MedisysResearch Lab (Medisys), Philips Research-Philips Research, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Images et Modèles, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: business.industry, Computer science, Phase (waves), Pattern recognition, Tracking (particle physics), Synthetic data, Cardiac tagged MR, Strain, Healthy volunteers, Artificial intelligence, Mr images, Tag number constant constraint, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Normal heart
Abstract: International audience; This paper presents a novel method that combines respective benefits of the tracking-based methods and the Gabor-based non-tracking approaches for improving the motion/strain quantification from tagged MR images. The “tag number constant” concept used in Gabor-based non-tracking methods is integrated into a recent phase-based registration framework. We evaluated our method on both synthetic and real data: (1) on a synthetic data of a normal heart, we found that the constraint improved both longitudinal and circumferential strains accuracies; (2) on 15 healthy volunteers, the proposed method achieved better tracking accuracy compared to three state-of-the-art methods; (3) on one patient dataset, we show that our method is able to distinguish the infarcted segments from the normal ones.
Published: 2016

20. Phase-based registration of cardiac tagged MR images using anatomical deformation model

Author: Mathieu De Craene, Yitian Zhou, Olivier Bernard, Harvard Medical School [Boston] (HMS), MedisysResearch Lab (Medisys), Philips Research, Images et Modèles, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Similarity (geometry), business.industry, Computer science, Phase (waves), Deformation (meteorology), Tracking (particle physics), 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Computer vision, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS, 030217 neurology & neurosurgery, Parametric statistics
Abstract: We developed a phase-based registration method applied to cardiac motion and strain quantification from tagged MR images. A parametric deformation model defined in an anatomical space of the heart was incorporated into the registration framework. The model parameters were optimized by minimizing phase-based similarity criteria. The proposed method was compared to a previously developed algorithm where point-wise HARP tracking results were regularized a posteriori by the same parametric deformation model. On synthetic data, the two methods achieved similar results on motion and circumferential strain accuracies. However, our method achieved better accuracy on longitudinal strain. On volunteer data, our method gave smaller median and variance values on tracking errors with statistical significance.
Published: 2016

21. Detailed Evaluation of Five 3D Speckle Tracking Algorithms Using Synthetic Echocardiographic Recordings

Author: Brecht Heyde, Olivier Bernard, Szymon Cygan, Martino Alessandrini, Sandro Queirós, Oudom Somphone, Matthew O'Donnell, Mathieu De Craene, Daniel Barbosa, Hervé Delingette, Maria Zontak, Jan D'hooge, Maxime Sermesant, Rayet, Béatrice, Laboratory of Cardiovascular Imaging and Dynamics, Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Life and Health Sciences Research Institute [Braga] (ICVS), University of Minho [Braga], Warsaw University of Technology [Warsaw], Department of Bioengineering [Seattle], University of Washington [Seattle], MedisysResearch Lab (Medisys), Philips Research, Images et Modèles, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ICVS/3B's, PT Government Associate Laboratory, Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Computer science, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Optical flow, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Echocardiography, Three-Dimensional, 030204 cardiovascular system & hematology, Tracking (particle physics), Field (computer science), 030218 nuclear medicine & medical imaging, Set (abstract data type), 03 medical and health sciences, Speckle pattern, 0302 clinical medicine, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, 3D ultrasound, Computer vision, Electrical and Electronic Engineering, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Radiological and Ultrasound Technology, medicine.diagnostic_test, business.industry, Contrast (statistics), Heart, Computer Science Applications, [SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, Artificial intelligence, business, Algorithm, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Software, Algorithms
Abstract: A plethora of techniques for cardiac deformation imaging with 3D ultrasound, typically referred to as 3D speckle tracking techniques, are available from academia and industry. Although the benefits of single methods over alternative ones have been reported in separate publications, the intrinsic differences in the data and definitions used makes it hard to compare the relative performance of different solutions. To address this issue, we have recently proposed a framework to simulate realistic 3D echocardiographic recordings and used it to generate a common set of ground-truth data for 3D speckle tracking algorithms, which was made available online. The aim of this study was therefore to use the newly developed database to contrast non-commercial speckle tracking solutions from research groups with leading expertise in the field. The five techniques involved cover the most representative families of existing approaches, namely block-matching, radio-frequency tracking, optical flow and elastic image registration. The techniques were contrasted in terms of tracking and strain accuracy. The feasibility of the obtained strain measurements to diagnose pathology was also tested for ischemia and dyssynchrony. ispartof: IEEE Transactions on Medical Imaging vol:35 issue:8 pages:1915-1926 ispartof: location:United States status: published
Published: 2016

22. Adaptive Particle Filtering for Coronary Artery Segmentation from 3D CT Angiograms

Author: Gareth Funka-Lea, David Lesage, Elsa D. Angelini, Isabelle Bloch, HAL, TelecomParis, MedisysResearch Lab (Medisys), Philips Research, Laboratoire Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Image, Modélisation, Analyse, GEométrie, Synthèse (IMAGES), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Département Traitement du Signal et des Images (TSI), and Télécom ParisTech-Centre National de la Recherche Scientifique (CNRS)
Subjects: Quantitative Biology::Tissues and Organs, Kernel density estimation, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, 02 engineering and technology, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Sørensen–Dice coefficient, Robustness (computer science), [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0202 electrical engineering, electronic engineering, information engineering, Segmentation, Computer vision, Mean-shift, Cluster analysis, ComputingMilieux_MISCELLANEOUS, Mathematics, business.industry, Pattern recognition, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Signal Processing, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, Geometric modeling, business, Particle filter, Software
Abstract: Design of a geometric vascular model.Non-parametric Bayesian model, learned by kernel density estimation from manually segmented datasets.Design of a new sampling scheme, Adaptive Auxiliary Particle Filtering (AAPF).Mean-Shift clustering for bifurcation detection and coronary tree extraction, and high computational efficiency.Experiments demonstrate the robustness of the proposed approach for complete vessel tree segmentation. Considering vessel segmentation as an iterative tracking process, we propose a new Bayesian tracking algorithm based on particle filters for the delineation of coronary arteries from 3D computed tomography angiograms. It relies on a medial-based geometric model, learned by kernel density estimation, and on a simple, fast and discriminative flux-based image feature. Combining a new sampling scheme and a mean-shift clustering for bifurcation detection and result extraction leads to an efficient and robust method. Results on a database of 61 volumes demonstrate the effectiveness of the proposed approach, with an overall Dice coefficient of 86.2% (and 92.5% on clinically relevant vessels), and a good accuracy of centerline position and radius estimation (errors below the image resolution).
Published: 2016

23. Infarct localization from myocardial deformation: Prediction and uncertainty quantification by regression from a low-dimensional space

Author: Pascal Allain, Mathieu De Craene, Eric Saloux, Nicolas Duchateau, Maxime Sermesant, Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales (MOTIVATE), Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), MedisysResearch Lab (Medisys), Philips Research, Service de cardiologie et de pathologie vasculaire [CHU Caen], Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-CHU Caen, Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN)-Tumorothèque de Caen Basse-Normandie (TCBN), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), CHU Caen, Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN), Signalisation, électrophysiologie et imagerie des lésions d’ischémie-reperfusion myocardique (SEILIRM), and Normandie Université (NU)-Normandie Université (NU)
Subjects: Databases, Factual, biomechanical modeling, Myocardial Infarction, pattern recognition & classification, 030204 cardiovascular system & hematology, Deformation (meteorology), 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Image Interpretation, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Computer vision, Electrical and Electronic Engineering, Uncertainty quantification, ComputingMilieux_MISCELLANEOUS, Mathematics, dimensionality reduction, Radiological and Ultrasound Technology, business.industry, ultrasound, Dimensionality reduction, Pattern recognition, Heart, delayed-enhancement, Thresholding, Magnetic Resonance Imaging, Regression, 3. Good health, Computer Science Applications, ROC Curve, Index Terms—Myocardial infarct, Computer-aided diagnosis, Kernel (statistics), Regression Analysis, computer-aided diagnosis, Artificial intelligence, business, Software, Algorithms, Curse of dimensionality
Abstract: International audience; Diagnosing and localizing myocardial infarct is crucial for early patient management and therapy planning. We propose a new method for predicting the location of myocardial infarct from local wall deformation, which has value for risk stratification from routine examinations such as (3D) echocardiography. The pipeline combines non-linear dimensionality reduction of deformation patterns and two multi-scale kernel regressions. Confidence in the diagnosis is assessed by a map of local uncertainties, which integrates plausible infarct locations generated from the space of reduced dimensionality. These concepts were tested on 500 synthetic cases generated from a realistic cardiac electromechanical model, and 108 pairs of 3D echocardiographic sequences and delayed-enhancement magnetic resonance images from real cases. Infarct prediction is made at a spatial resolution around 4 mm, more than 10 times smaller than the current diagnosis, made regionally. Our method is accurate, and significantly outperforms the clinically-used thresholding of the deformation patterns (on real data: sensitivity / specificity of 0.828/0.804, area under the curve: 0.909 vs. 0.742 for the most predictive strain component). Uncertainty adds value to refine the diagnosis and eventually re-examine suspicious cases.
Published: 2016

24. Evaluation framework for carotid bifurcation lumen segmentation and stenosis grading

Author: Leo Joskowicz, Moti Freiman, Karl Krissian, Jacob Sosna, Coert Metz, Noy Cohen, Ingrid Sanchez, Julien Mille, T. van Walsum, Wiro J. Niessen, Maciej Orkisz, Wilbur C.K. Wong, M. P M Q van Gils, K. Hameeteman, M. Hernández Hoyos, Gabriel P. Krestin, L. Florez Valencia, L. van den Borne, Olivier Cuisenaire, Michiel Schaap, Mehmet Akif Gulsun, P. Berman, A. van der Lugt, Philippe Douek, Maria A. Zuluaga, Huseyin Tek, M. Aissat, Fethallah Benmansour, S. Rozie, Albert C. S. Chung, Biomedical Imaging Group [Rotterdam] (BIG), Erasmus University Medical Center [Rotterdam] (Erasmus MC), Imagerie Tomographique et Radiothérapie, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), Grupo IMAGINE, Universidad de los Andes [Bogota] (UNIANDES), Computer-Aided Surgery and Medical Image Processing Laboratory, The Hebrew University of Jerusalem (HUJ), MedisysResearch Lab (Medisys), Philips Research, Departamento de Ingeniería de Sistemas, Facultad de Ingeniería, Pontificia Universidad Javeriana (PUJ), Imaging and Visualization Department, Siemens Corporate Research, GIMET, Dept. de Informática y Sistemas (GIMET), University of Las Palmas de Gran Canaria (ULPGC), Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), Lo Kwee-Seong Medical Image Analysis Laboratory, Hong Kong University of Science and Technology (HKUST), Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales (MOTIVATE), CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Department of Radiology, Hadassah Hebrew University Medical Centre, Hadassah Hebrew University, Service de Radiologie, Hôpital Louis Pradel [CHU - HCL], Hospices Civils de Lyon (HCL)-Hospices Civils de Lyon (HCL), Imaging Science and Technology, Delft University of Technology (TU Delft), and Radiology & Nuclear Medicine
Subjects: medicine.medical_specialty, medicine.medical_treatment, Carotid arteries, Evaluation framework, Health Informatics, Information repository, computer.software_genre, Sensitivity and Specificity, Pattern Recognition, Automated, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Imaging, Three-Dimensional, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 3d segmentation, medicine, Carotid bifurcation, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Carotid Stenosis, Radiology, Nuclear Medicine and imaging, Endarterectomy, Lumen segmentation, Carotid, Radiological and Ultrasound Technology, medicine.diagnostic_test, CTA, business.industry, Stenosis grading, Angiography, Reproducibility of Results, medicine.disease, Computer Graphics and Computer-Aided Design, Radiographic Image Enhancement, Stenosis, Carotid Arteries, Radiographic Image Interpretation, Computer-Assisted, Computer Vision and Pattern Recognition, Radiology, Data mining, Tomography, X-Ray Computed, business, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms, 030217 neurology & neurosurgery
Abstract: International audience; This paper describes an evaluation framework that allows a standardized and objective quantitative comparison of carotid artery lumen segmentation and stenosis grading algorithms. We describe the data repository comprising 56 multi-center, multi-vendor CTA datasets, their acquisition, the creation of the reference standard and the evaluation measures. This framework has been introduced at the MICCAI 2009 workshop 3D Segmentation in the Clinic: A Grand Challenge III, and we compare the results of eight teams that participated. These results show that automated segmentation of the vessel lumen is possible with a precision that is comparable to manual annotation. The framework is open for new submissions through the website http://cls2009.bigr.nl. The final accepted version of this paper is published in Medical Image Analysis, vol 15(4) ,doi:10.1016/j.media.2011.02.004
Published: 2011

25. Multidimensional classification of hippocampal shape features discriminates Alzheimer's disease and mild cognitive impairment from normal aging

Author: Francis Eustache, Hosung Kim, Marie Chupin, Bruno Dubois, Béatrice Desgranges, Line Garnero, Rémi Cuingnet, Marc Niethammer, Stéphane Lehéricy, Emilie Gerardin, Olivier Colliot, Gaël Chételat, Institut Européen des membranes (IEM), Université Montpellier 2 - Sciences et Techniques (UM2)-Ecole Nationale Supérieure de Chimie de Montpellier (ENSCM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS), Equipe NEMESIS - Centre de Recherches de l'Institut du Cerveau et de la Moelle épinière (NEMESIS-CRICM), Centre de Recherche de l'Institut du Cerveau et de la Moelle épinière (CRICM), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Neuropsychologie cognitive et neuroanatomie fonctionnelles de la mémoire humaine, Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-École Pratique des Hautes Études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM), MedisysResearch Lab (Medisys), Philips Research, McConnell Brain Imaging Center (BIC), McGill University = Université McGill [Montréal, Canada], Department of Computer Science [Chapel Hill], University of North Carolina [Chapel Hill] (UNC), University of North Carolina System (UNC)-University of North Carolina System (UNC), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Institut d'imagerie neurofonctionnelle (IIN), Université Paris-Sud - Paris 11 (UP11)-Université Pierre et Marie Curie - Paris 6 (UPMC)-École des hautes études en sciences sociales (EHESS)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Ecole Nationale Supérieure des Télécommunications (ENST)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Laboratoire de neurosciences cognitives et d'imagerie cérébrale (LENA), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de Chimie de Montpellier (ENSCM)-Université Montpellier 2 - Sciences et Techniques (UM2)-Institut de Chimie du CNRS (INC)-Université de Montpellier (UM), Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC), École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-Institut National de la Santé et de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC), and Institut National de la Santé et de la Recherche Médicale (INSERM)-Ecole Nationale Supérieure des Télécommunications (ENST)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-École des hautes études en sciences sociales (EHESS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)
Subjects: FOS: Computer and information sciences, Male, Aging, Pathology, hippocampus, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Disease, Audiology, Hippocampal formation, support vector machines, Pattern Recognition, Automated, 0302 clinical medicine, Statistics - Machine Learning, Cluster Analysis, magnetic resonance imaging, Aged, 80 and over, 0303 health sciences, medicine.diagnostic_test, Middle Aged, Alzheimer's disease, Neurology, Neurons and Cognition (q-bio.NC), Female, Psychology, Algorithms, Alzheimer's Disease Neuroimaging Initiative, medicine.medical_specialty, Cognitive Neuroscience, Machine Learning (stat.ML), Sensitivity and Specificity, Article, Diagnosis, Differential, 03 medical and health sciences, Text mining, Alzheimer Disease, Image Interpretation, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, medicine, Humans, Aged, 030304 developmental biology, business.industry, Reproducibility of Results, Magnetic resonance imaging, Image Enhancement, medicine.disease, MCI, Support vector machine, Quantitative Biology - Neurons and Cognition, FOS: Biological sciences, Differential diagnosis, Cognition Disorders, business, 030217 neurology & neurosurgery
Abstract: We describe a new method to automatically discriminate between patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and elderly controls, based on multidimensional classification of hippocampal shape features. This approach uses spherical harmonics (SPHARM) coefficients to model the shape of the hippocampi, which are segmented from magnetic resonance images (MRI) using a fully automatic method that we previously developed. SPHARM coefficients are used as features in a classification procedure based on support vector machines (SVM). The most relevant features for classification are selected using a bagging strategy. We evaluate the accuracy of our method in a group of 23 patients with AD (10 males, 13 females, age $\pm$ standard-deviation (SD) = 73 $\pm$ 6 years, mini-mental score (MMS) = 24.4 $\pm$ 2.8), 23 patients with amnestic MCI (10 males, 13 females, age $\pm$ SD = 74 $\pm$ 8 years, MMS = 27.3 $\pm$ 1.4) and 25 elderly healthy controls (13 males, 12 females, age $\pm$ SD = 64 $\pm$ 8 years), using leave-one-out cross-validation. For AD vs controls, we obtain a correct classification rate of 94%, a sensitivity of 96%, and a specificity of 92%. For MCI vs controls, we obtain a classification rate of 83%, a sensitivity of 83%, and a specificity of 84%. This accuracy is superior to that of hippocampal volumetry and is comparable to recently published SVM-based whole-brain classification methods, which relied on a different strategy. This new method may become a useful tool to assist in the diagnosis of Alzheimer's disease., Comment: Data used in the preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database
Published: 2009

26. Performance analysis of a dedicated breast MR-HIFU system for tumor ablation in breast cancer patients

Author: Roel Deckers, B Denis de Senneville, Gerald Schubert, W.P.Th.M. Mali, Chrit T. W. Moonen, Floortje M. Knuttel, Laura G. Merckel, Max O. Köhler, Lambertus W. Bartels, M. A. A. J. van den Bosch, University Medical Center [Utrecht], Institut de Mathématiques de Bordeaux (IMB), Université Bordeaux Segalen - Bordeaux 2-Université Sciences et Technologies - Bordeaux 1-Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS), MedisysResearch Lab (Medisys), Philips Research, and Image sciences institute - University of Utrecht (ISI)
Subjects: Radiofrequency ablation, medicine.medical_treatment, Contrast Media, Magnetic Resonance Imaging, Interventional, THERAPY, Tumor ablation, 030218 nuclear medicine & medical imaging, law.invention, CONTRAST-ENHANCED MRI, 0302 clinical medicine, law, Image Processing, Computer-Assisted, Medicine, Breast, Non-U.S. Gov't, ComputingMilieux_MISCELLANEOUS, Radiological and Ultrasound Technology, medicine.diagnostic_test, Research Support, Non-U.S. Gov't, FOCUSED ULTRASOUND SURGERY, Temperature, Ablation, Healthy Volunteers, 3. Good health, 030220 oncology & carcinogenesis, Female, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, MRI, medicine.medical_specialty, Accuracy and precision, FEASIBILITY, thermometry, Breast Neoplasms, Research Support, 03 medical and health sciences, MAMMOGRAPHY, Breast cancer, breast cancer, Journal Article, Mammography, Humans, Radiology, Nuclear Medicine and imaging, Neoplasm Invasiveness, Comparative Study, RADIOFREQUENCY ABLATION, US, business.industry, 20-YEAR FOLLOW-UP, Magnetic resonance imaging, medicine.disease, High-intensity focused ultrasound, Surgery, TISSUE, Case-Control Studies, high intensity focused ultrasound, High-Intensity Focused Ultrasound Ablation, business, Nuclear medicine
Abstract: MR-guided HIFU ablation is a promising technique for the non-invasive treatment of breast cancer. A phase I study was performed to assess the safety and treatment accuracy and precision of MR-HIFU ablation in breast cancer patients (n=10) using a newly developed MR-HIFU platform dedicated to applications in the breast. In this paper a technical analysis of the performance of the dedicated breast MR-HIFU system during breast tumors ablation is described. The main points of investigation were the spatial targeting accuracy and precision of the system and the performance of real-time respiration-corrected MR thermometry.The mean targeting accuracy was in the range of 2.4-2.6 mm, whereas the mean targeting precision was in the range of 1.5-1.8 mm. To correct for respiration-induced magnetic field fluctuations during MR temperature mapping a look-up-table (LUT)-based correction method was used. An optimized procedural sedation protocol in combination with the LUT-based correction method allowed for precise MR thermometry during the ablation procedure (temperature standard deviation3 °C). No unwanted heating in the near field (i.e. skin) nor in the far field (pectoral muscle) was detected.The newly developed dedicated breast MR-HIFU system allows for safe, accurate and precise ablation of breast tumors.
Published: 2015

27. Multiple template deformation. Application to abdominal organ segmentation

Author: Roberto Ardori, David Lesage, Romane Gauriau, Isabelle Bloch, Laboratoire Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), MedisysResearch Lab (Medisys), Philips Research, and Télécom Paristech, Admin
Subjects: business.industry, Computer science, template deformation, Scale-space segmentation, Image segmentation, Deformation (meteorology), automatic segmentation, Transformation (function), [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Segmentation, Computer vision, Multi-organ segmentation, Artificial intelligence, business
Abstract: We propose a fast, automatic and versatile framework for the segmentation of multiple anatomical structures from 2D and 3D images. We extend the work of [1] on implicit template deformation to multiple targets. Our variational formulation optimizes the non-rigid transformation of a set of templates according to image-driven forces. It embeds non-overlapping constraints ensuring a consistent segmentation result. We demonstrate the potential of our approach on the segmentation of abdominal organs (liver, kidneys, spleen and gallbladder) with an evaluation on CT volumes (50 for training and 50 for testing). Our method reaches state-of-the-art accuracy, ranging from 2mm (liver and kidneys) to 8mm (gallbladder).
Published: 2015

28. A Pipeline for the Generation of Realistic 3D Synthetic Echocardiographic Sequences: Methodology and Open-access Database

Author: Pascal Allain, Hervé Delingette, Eric Saloux, Martino Alessandrini, Olivier Bernard, M. De Craene, I. Waechter-Stehle, Jürgen Weese, Sophie Giffard-Roisin, Maxime Sermesant, Jan D'hooge, Laboratory of Cardiovascular Imaging and Dynamics, Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), MedisysResearch Lab (Medisys), Philips Research, Images et Modèles, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Philips Research Europe - Hamburg, Sector Medical Imaging Systems, Service de cardiologie et de pathologie vasculaire [CHU Caen], Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-CHU Caen, Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN)-Tumorothèque de Caen Basse-Normandie (TCBN), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), and Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)
Subjects: Computer science, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Context (language use), computer.software_genre, Speckle pattern, Match moving, medicine, 3D ultrasound, Computer vision, Sensitivity (control systems), Electrical and Electronic Engineering, Radiological and Ultrasound Technology, medicine.diagnostic_test, business.industry, Ultrasound, Process (computing), Pipeline (software), Computer Science Applications, Ultrasonic imaging, Displacement field, Artificial intelligence, Data mining, business, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Software
Abstract: Quantification of cardiac deformation and strain with 3D ultrasound takes considerable research efforts. Nevertheless, a widespread use of these techniques in clinical practice is still held back due to the lack of a solid verification process to quantify and compare performance. In this context, the use of fully synthetic sequences has become an established tool for initial in silico evaluation. Nevertheless, the realism of existing simulation techniques is still too limited to represent reliable benchmarking data. Moreover, the fact that different centers typically make use of in-house developed simulation pipelines makes a fair comparison difficult. In this context, this paper introduces a novel pipeline for the generation of synthetic 3D cardiac ultrasound image sequences. State-of-the art solutions in the fields of electromechanical modeling and ultrasound simulation are combined within an original framework that exploits a real ultrasound recording to learn and simulate realistic speckle textures. The simulated images show typical artifacts that make motion tracking in ultrasound challenging. The ground-truth displacement field is available voxelwise and is fully controlled by the electromechanical model. By progressively modifying mechanical and ultrasound parameters, the sensitivity of 3D strain algorithms to pathology and image properties can be evaluated. The proposed pipeline is used to generate an initial library of 8 sequences including healthy and pathological cases, which is made freely accessible to the research community via our project web-page.. ispartof: IEEE Transactions on Medical Imaging vol:34 issue:7 pages:1436-1451 ispartof: location:United States status: published
Published: 2015

29. Tagged template deformation

Author: Rémi Cuingnet, Laurent D. Cohen, Benoit Mory, Raphael Prevost, Roberto Ardon, MedisysResearch Lab (Medisys), Philips Research, CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)
Subjects: Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Documentation, Sensitivity and Specificity, 030218 nuclear medicine & medical imaging, Pattern Recognition, Automated, 03 medical and health sciences, 0302 clinical medicine, Image Interpretation, Computer-Assisted, 0202 electrical engineering, electronic engineering, information engineering, Humans, Segmentation, Computer vision, ComputingMilieux_MISCELLANEOUS, business.industry, Atlas (topology), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Reproducibility of Results, Image segmentation, Image Enhancement, Active appearance model, Feature (computer vision), Echocardiography, Subtraction Technique, 020201 artificial intelligence & image processing, Artificial intelligence, business, Algorithms
Abstract: Model-based approaches are very popular for medical image segmentation as they carry useful prior information on the target structure. Among them, the implicit template deformation framework recently bridged the gap between the efficiency and flexibility of level-set region competition and the robustness of atlas deformation approaches. This paper generalizes this method by introducing the notion of tagged templates. A tagged template is an implicit model in which different subregions are defined. In each of these subregions, specific image features can be used with various confidence levels. The tags can be either set manually or automatically learnt via a process also hereby described. This generalization therefore greatly widens the scope of potential clinical application of implicit template deformation while maintaining its appealing algorithmic efficiency. We show the great potential of our approach in myocardium segmentation of ultrasound images.
Published: 2014

30. Elastic registration vs. block matching for quantification of cardiac function with 3D ultrasound: Initial results of a direct comparison in silico based on a new evaluation pipeline

Author: Mathieu De Craene, Olivier Bernard, Szymon Cygan, Brecht Heyde, Jan D'hooge, Martino Alessandrini, Maxime Sermesant, Hervé Delingette, Laboratory of Cardiovascular Imaging and Dynamics, Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Warsaw University of Technology [Warsaw], Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Images et Modèles, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Philips Research, MedisysResearch Lab (Medisys), Philips Research-Philips Research, Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Sermesant, Maxime, Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Cardiac function curve, Matching (statistics), medicine.diagnostic_test, Computer science, business.industry, Pipeline (computing), Ultrasound, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Pattern recognition, Ultrasonic imaging, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 3D ultrasound, Artificial intelligence, business, Block (data storage)
Abstract: This paper presents a comparison between block matching and elastic registration for the estimation of cardiac deformation and strain from 3D ultrasound. The comparison study exploits a new evaluation pipeline recently developed by the authors. The pipeline generates synthetic sequences that are extremely similar to real ultrasound recording while the synthetic cardiac motion is fully controlled by an electro-mechanical model of the heart. Hereto, five synthetic sequences were generated corresponding to one healthy heart and four ischemic ones. Elastic registration returned both the smaller tracking errors and the most robust strain estimates. Although with limitations, this study brings further evidence that the new technique might be ready for extensive clinical testing ispartof: pages:608-611 ispartof: IEEE International Ultrasonic Symposium pages:608-611 ispartof: IEEE International Ultrasonics Symposium location:IL, Chicago date:3 Sep - 6 Sep 2014 status: published
Published: 2014

31. Improved Myocardial Motion Estimation Combining Tissue Doppler and B-Mode Echocardiographic Images

Author: Nicolas Duchateau, Maxime Sermesant, Jan D'hooge, M. De Craene, Martino Alessandrini, Gemma Piella, Alejandro F. Frangi, Hervé Delingette, Antonio R. Porras, Bart Bijnens, Marta Sitges, Center for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), Universitat Pompeu Fabra [Barcelona] (UPF), Laboratory of Cardiovascular Imaging and Dynamics, Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), MedisysResearch Lab (Medisys), Philips Research, Cardiology Department, Thorax Clinic Institute, Hospital Cliınic, Institut d'Investigacions Biomèdiques [Barcelona], Universitat de Barcelona (UB), Institució Catalana de Recerca i Estudis Avançats (ICREA), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Department of Mechanical Engineering [Sheffield], and University of Sheffield [Sheffield]
Subjects: Male, Image quality, Physics::Medical Physics, 02 engineering and technology, Doppler echocardiography, Motion estimation, Displacement (vector), 030218 nuclear medicine & medical imaging, Multi-modal integration, Imaging, motion estimation, 0302 clinical medicine, Free form deformation (FFD), 0202 electrical engineering, electronic engineering, information engineering, Image Processing, Computer-Assisted, Ventricular Function, Computer vision, Image registration, Mathematics, Radiological and Ultrasound Technology, medicine.diagnostic_test, Heart, Transforms, free form deformation (FFD), Echocardiography, Doppler, Computer Science Applications, Splines (mathematics), Echocardiography, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], symbols, 020201 artificial intelligence & image processing, Female, Doppler effect, Adult, Velocity measurement, Heart Ventricles, Movement, Transducers, Ultrasound (US), 03 medical and health sciences, Speckle pattern, symbols.namesake, Young Adult, Temporal diffeomorphic free form deformation (TDFFD), medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Electrical and Electronic Engineering, Scan conversion, business.industry, Myocardium, Reproducibility of Results, image registration, Artificial intelligence, Tissue Doppler, business, Software
Abstract: International audience; We propose a technique for myocardial motion estimation based on image registration using both B-mode echocardiographic images and tissue Doppler sequences acquired interleaved. The velocity field is modeled continuously using B-splines and the spatiotemporal transform is constrained to be diffeomorphic. Images before scan conversion are used to improve the accuracy of the estimation. The similarity measure includes a model of the speckle pattern distribution of B-mode images. It also penalizes the disagreement between tissue Doppler velocities and the estimated velocity field. Registration accuracy is evaluated and compared to other alternatives using a realistic synthetic dataset, obtaining mean displacement errors of about 1 mm. Finally, the method is demonstrated on data acquired from six volunteers, both at rest and during exercise. Robustness is tested against low image quality and fast heart rates during exercise. Results show that our method provides a robust motion estimate in these situations.
Published: 2014

32. Complex question answering: homogeneous or heterogeneous, which ensemble is better?

Author: Yllias Chali, Sadid A. Hasan, Mustapha Mojahid, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Philips Research (USA), University of Lethbridge (CANADA), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), University of Lethbridge, Philips Research, MedisysResearch Lab (Medisys), Philips Research-Philips Research, Etude de L’Interaction Personne SystèmE (IRIT-ELIPSE), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, and Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: Conditional random field, Homogeneous ensemble, Computer science, business.industry, Principle of maximum entropy, Complex question, Complex question answering, Base (topology), Machine learning, computer.software_genre, Ensemble learning, Interface homme-machine, Support vector machine, Task (computing), ComputingMethodologies_PATTERNRECOGNITION, Heterogeneous ensemble, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Artificial intelligence, Hidden Markov model, business, computer
Abstract: International audience; This paper applies homogeneous and heterogeneous ensembles to perform the complex question answering task. For the homogeneous ensemble, we employ Support Vector Machines (SVM) as the learning algorithm and use a Cross-Validation Committees (CVC) approach to form several base models. We use SVM, Hidden Markov Models (HMM), Conditional Random Fields (CRF), and Maximum Entropy (MaxEnt) techniques to build different base models for the heterogeneous ensemble. Experimental analyses demonstrate that both ensemble methods outperform conventional systems and heterogeneous ensemble is better.
Published: 2014

33. Registration of Free-Breathing 3D+t Abdominal Perfusion CT Images via Co-Segmentation

Author: Laurent D. Cohen, Laurence Rouet, Roberto Ardon, Rémi Cuingnet, Benoit Mory, Olivier Lucidarme, Blandine Romain, Raphael Prevost, CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), MedisysResearch Lab (Medisys), Philips Research, Informatique, Biologie Intégrative et Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE), Mathématiques Appliquées aux Systèmes - EA 4037 (MAS), Ecole Centrale Paris, CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Université Paris Dauphine-PSL, and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Radiography, Abdominal, Computer science, Perfusion Imaging, Image registration, Perfusion scanning, Sensitivity and Specificity, 030218 nuclear medicine & medical imaging, Pattern Recognition, Automated, 03 medical and health sciences, 0302 clinical medicine, Imaging, Three-Dimensional, Humans, Computer vision, Segmentation, Rigid transformation, ComputingMilieux_MISCELLANEOUS, Active contour model, Modality (human–computer interaction), Pixel, business.industry, Reproducibility of Results, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Kidney Neoplasms, Radiographic Image Enhancement, Subtraction Technique, Pattern recognition (psychology), Respiratory Mechanics, Radiographic Image Interpretation, Computer-Assisted, Artificial intelligence, business, Tomography, X-Ray Computed, Perfusion, 030217 neurology & neurosurgery, Algorithms
Abstract: Dynamic contrast-enhanced computed tomography (DCE-CT) is a valuable imaging modality to assess tissues properties, particularly in tumours, by estimating pharmacokinetic parameters from the evolution of pixels intensities in 3D+t acquisitions. However, this requires a registration of the whole sequence of volumes, which is challenging especially when the patient breathes freely. In this paper, we propose a generic, fast and automatic method to address this problem. As standard iconic registration methods are not robust to contrast intake, we rather rely on the segmentation of the organ of interest. This segmentation is performed jointly with the registration of the sequence within a novel co-segmentation framework. Our approach is based on implicit template deformation, that we extend to a co-segmentation algorithm which provides as outputs both a segmentation of the organ of interest in every image and stabilising transformations for the whole sequence. The proposed method is validated on 15 datasets acquired from patients with renal lesions and shows improvement in terms of registration and estimation of pharmacokinetic parameters over the state-of-the-art method.
Published: 2013

34. A multi-task learning approach for compartmental model parameter estimation in DCE-CT sequences

Author: Véronique Letort, Laurence Rouet, Florence d'Alché-Buc, Blandine Romain, Olivier Lucidarme, Informatique, Biologie Intégrative et Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE), MedisysResearch Lab (Medisys), Philips Research, Mathématiques Appliquées aux Systèmes - EA 4037 (MAS), Ecole Centrale Paris, CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Machine Learning and Optimisation (TAO), Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Paris-Sud - Paris 11 (UP11)-Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec, and Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)
Subjects: 0303 health sciences, Estimation theory, Computer science, business.industry, Contrast (statistics), Multi-task learning, Pattern recognition, Machine learning, computer.software_genre, behavioral disciplines and activities, 030218 nuclear medicine & medical imaging, Task (project management), 03 medical and health sciences, 0302 clinical medicine, Similarity (network science), Voxel, Relevance (information retrieval), [INFO]Computer Science [cs], Artificial intelligence, Noise (video), business, computer, 030304 developmental biology
Abstract: International audience; Today's follow-up of patients presenting abdominal tumors is generally performed through acquisition of dynamic sequences of contrast-enhanced CT. Estimating parameters of appropriate models of contrast intake diffusion through tissues should help characterizing the tumor physiology, but is impeded by the high level of noise inherent to the acquisition conditions. To improve the quality of estimation, we consider parameter estimation in voxels as a multi-task learning problem (one task per voxel) that takes advantage from the similarity between two tasks. We introduce a temporal similarity between tasks based on a robust distance between observed contrast-intake profiles of intensity. Using synthetic images, we compare multi-task learning using this temporal similarity, a spatial similarity and a single-task learning. The similarities based on temporal profiles are shown to bring significant improvements compared to the spatial one. Results on real CT sequences also confirm the relevance of the approach.
Published: 2013

35. Abdominal aortic aneurysm imaging with 3-D ultrasound: 3-D-based maximum diameter measurement and volume quantification

Author: Laurence Rouet, C. Barbe, A. Debreuve, Anne Long, Jean-Pierre Becquemin, Eric Allaire, Roberto Ardon, Vascular Medicine, Centre Hospitalier Universitaire de Reims, Centre Hospitalier Universitaire de Reims (CHU Reims), MedisysResearch Lab (Medisys), Philips Research, Science et Ingénierie des Matériaux et Procédés (SIMaP), Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS), Vascular Surgery, CHI Créteil, Centre de Recherches Chirurgicales, CNRS EAC 7054, and Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12)
Subjects: Male, medicine.medical_specialty, Acoustics and Ultrasonics, Partial volume, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Biophysics, 030204 cardiovascular system & hematology, 3 d ultrasound, Sensitivity and Specificity, 030218 nuclear medicine & medical imaging, Pattern Recognition, Automated, Imaging, 03 medical and health sciences, Aortic aneurysm, 0302 clinical medicine, Imaging, Three-Dimensional, Maximum diameter, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Image Interpretation, Computer-Assisted, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Radiology, Nuclear Medicine and imaging, Abdominal, Aged, Ultrasonography, Reproducibility, Radiological and Ultrasound Technology, business.industry, Reproducibility of Results, Repeatability, medicine.disease, Image Enhancement, Abdominal aortic aneurysm, Radiology Nuclear Medicine and imaging, Female, Radiology, Nuclear medicine, business, Three-dimensional, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms, Volume (compression), Aortic Aneurysm, Abdominal
Abstract: International audience; The clinical reliability of 3-D ultrasound imaging (3-DUS) in quantification of abdominal aortic aneurysm (AAA) was evaluated. B-mode and 3-DUS images of AAAs were acquired for 42 patients. AAAs were segmented. A 3-D-based maximum diameter (Max3-D) and partial volume (Vol30) were defined and quantified. Comparisons between 2-D (Max2-D) and 3-D diameters and between orthogonal acquisitions were performed. Intra- and inter-observer reproducibility was evaluated. Intra- and inter-observer coefficients of repeatability (CRs) were less than 5.18 mm for Max3-D. Intra-observer and inter-observer CRs were respectively less than 6.16 and 8.71 mL for Vol30. The mean of normalized errors of Vol30 was around 7%. Correlation between Max2-D and Max3-D was 0.988 (p < 0.0001). Max3-D and Vol30 were not influenced by a probe rotation of 90°. Use of 3-DUS to quantify AAA is a new approach in clinical practice. The present study proposed and evaluated dedicated parameters. Their reproducibility makes the technique clinically reliable.
Published: 2013

36. Extended-field-of-view three-dimensional transesophageal echocardiography using image-based X-ray probe tracking

Author: Victoria Parish, Pascal Yves François Cathier, C. Aldo Rinaldi, Aruna Arujuna, YingLiang Ma, Niels Nijhof, Geert Gijsbers, Roland W. M. Bullens, Jaswinder Gill, R. James Housden, Kawal Rhode, Division of Imaging Sciences, King‘s College London, Cardiothoracic Centre, Guy's and St Thomas' Hospital [London], Business Unit iXR / Business Program EP, Philips Healthcare, MedisysResearch Lab (Medisys), and Philips Research
Subjects: Acoustics and Ultrasonics, Registration, MESH: Subtraction Technique, Echocardiography, Three-Dimensional, MESH: Ultrasonography, Interventional, 030204 cardiovascular system & hematology, Transesophageal ultrasound, Tracking (particle physics), Radiography, Interventional, Multimodal Imaging, 030218 nuclear medicine & medical imaging, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Extended field of view, Computer vision, Cardiac imaging, Probe tracking, Radiological and Ultrasound Technology, Phantoms, Imaging, Ultrasound, MESH: Multimodal Imaging, MESH: Echocardiography, Three-Dimensional, MESH: Reproducibility of Results, MESH: Radiography, Interventional, Radiology, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, medicine.medical_specialty, Biophysics, MESH: Echocardiography, Transesophageal, Compounding, Sensitivity and Specificity, Interventional guidance, Imaging phantom, 03 medical and health sciences, [SDV.MHEP.CSC]Life Sciences [q-bio]/Human health and pathology/Cardiology and cardiovascular system, Robustness (computer science), Position (vector), medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Radiology, Nuclear Medicine and imaging, Ultrasonography, Interventional, MESH: Humans, business.industry, Reproducibility of Results, MESH: Sensitivity and Specificity, MESH: Phantoms, Imaging, Subtraction Technique, Artificial intelligence, business, Echocardiography, Transesophageal, Volume (compression)
Abstract: International audience; The use of ultrasound imaging for guidance of cardiac interventional procedures is limited by the small field of view of the ultrasound volume. A larger view can be created by image-based registration of several partially overlapping volumes, but automatic registration is likely to fail unless the registration is initialized close to the volumes' correct alignment. In this article, we use X-ray images to track a transesophageal ultrasound probe and thereby provide initial position information for the registration of the ultrasound volumes. The tracking is possible using multiple X-rays or just a single X-ray for each probe position. We test the method in a phantom experiment and find that with at least 50% overlap, 88% of volume pairs are correctly registered when tracked using three X-rays and 86% when using single X-rays. Excluding failed registrations with errors greater than 10 mm, the average registration accuracy is 2.92 mm between ultrasound volumes and 4.75 mm for locating an ultrasound volume in X-ray space. We conclude that the accuracy and robustness of the registrations are sufficient to provide useful images for interventional guidance.
Published: 2013

37. Where is my baby? A fast fetal head auto-alignment in 3D-ultrasound

Author: J.A. Noble, Benoit Mory, David N. Roundhill, Oudom Somphone, Raphael Prevost, Rémi Cuingnet, Mohammad Yaqub, Roberto Ardon, Raffaele Napolitano, Aris T. Papageorghiou, MedisysResearch Lab (Medisys), Philips Research, CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Institute of Biomedical Engineering [Oxford] (IBME), University of Oxford [Oxford], Nuffield Department of Obstetrics and Gynaecology, Philips Ultrasound Bothell, and Philips Healthcare
Subjects: Fetus, Modality (human–computer interaction), medicine.diagnostic_test, business.industry, Computer science, Ultrasound, Transventricular, Neurophysiology, 030218 nuclear medicine & medical imaging, Fetal brain, 03 medical and health sciences, Skull, 0302 clinical medicine, medicine.anatomical_structure, Prenatal screening, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 3D ultrasound, Fetal head, Computer vision, Artificial intelligence, Ultrasonography, business, 030217 neurology & neurosurgery
Abstract: International audience; Ultrasonography is the main modality for prenatal screening examination of the fetal central nervous system. Due to the variability of the position of the fetal brain relatively to the probe, getting through structures of interest requires both time and a high level of expertise. The method presented in this paper aims at helping the clinician navigate through the brain by automatically aligning the head in near real time (
Published: 2013

38. Fast Myocardial Motion and Strain Estimation in 3D Cardiac Ultrasound with Sparse Demons

Author: M. De Craene, Eric Saloux, Roberto Ardon, Benoit Mory, Pascal Allain, Oudom Somphone, Stephanie Marchesseau, Hang Gao, Hervé Delingette, Jan D'hooge, Maxime Sermesant, MedisysResearch Lab (Medisys), Philips Research, Center for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), Universitat Pompeu Fabra [Barcelona] (UPF), Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Service de cardiologie et de pathologie vasculaire [CHU Caen], Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-CHU Caen, and Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN)-Tumorothèque de Caen Basse-Normandie (TCBN)
Subjects: medicine.diagnostic_test, business.industry, Ultrasound, 01 natural sciences, Cardiac Ultrasound, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Motion estimation, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0103 physical sciences, Myocardial motion, medicine, Strain estimation, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Biomechanical model, Computer vision, 3D ultrasound, Artificial intelligence, business, 010301 acoustics, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 3d echocardiography
Abstract: International audience; This article presents a new method for motion and strain estimation in 3D echocardiography, called Sparse Demons, along with quantitative and qualitative evaluations from a dataset of synthetic ultrasound sequences. Motion estimation is based on a fast demons-like algorithm focusing on myocardial tissue. Synthetic 3D ultrasound images were generated by combining a biomechanical model of the heart with a realistic ultrasound imaging model. Ischemic areas were defined in the mechanical model to investigate whether our algorithm can discriminate healthy from diseased segments.
Published: 2013

39. Benchmarking framework for myocardial tracking and deformation algorithms: an open access database

Author: Kawal Rhode, Adityo Prakosa, Wenzhe Shi, Daniel Rueckert, Reza Razavi, Alejandro F. Frangi, Anja Hennemuth, H-O. Peitgen, Catalina Tobon-Gomez, Sebastien Ourselin, Lennart Tautz, Gerald Carr-White, Tobias Schaeffter, Xavier Pennec, Kristin McLeod, Volker Rasche, Maxime Sermesant, Tommaso Mansi, Ola Friman, Anja Lutz, Haiyan Wang, M. De Craene, Stamatis Kapetanakis, Constantine Butakoff, Xiahai Zhuang, Division of Imaging Sciences, King‘s College London, MedisysResearch Lab (Medisys), Philips Research, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Department of Medical Engineering and Neuroprosthetics, Fraunhofer Institute for Biomedical Engineering [Sulzbach] (Fraunhofer IBMT), Fraunhofer (Fraunhofer-Gesellschaft)-Fraunhofer (Fraunhofer-Gesellschaft), Department of Computing [London], Biomedical Image Analysis Group [London] (BioMedIA), Imperial College London-Imperial College London, Universität Ulm - Ulm University [Ulm, Allemagne], Center for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), Universitat Pompeu Fabra [Barcelona] (UPF), SICS, Swedish Institute of Computer Science [Stockholm] (SICS), Siemens Corporate Research, Siemens AG [Munich], Computer science department [University College London] (UCL-CS), University College of London [London] (UCL), Department of Computer science [University College of London] (UCL-CS), and Publica
Subjects: Adult, Databases, Factual, Computer science, Image quality, Movement, Cardiac-Gated Imaging Techniques, Health Informatics, computer.software_genre, Sensitivity and Specificity, Imaging phantom, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Imaging, Three-Dimensional, Match moving, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Medical imaging, medicine, Humans, Radiology, Nuclear Medicine and imaging, Computer vision, 3D ultrasound, Radiological and Ultrasound Technology, Database, medicine.diagnostic_test, business.industry, Reproducibility of Results, Heart, Steady-state free precession imaging, Benchmarking, Computer Graphics and Computer-Aided Design, Magnetic Resonance Imaging, Healthy Volunteers, Visualization, Europe, Echocardiography, Computer Vision and Pattern Recognition, Artificial intelligence, business, computer, Algorithm, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 030217 neurology & neurosurgery, Algorithms
Abstract: In this paper we present a benchmarking framework for the validation of cardiac motion analysis algorithms. The reported methods are the response to an open challenge that was issued to the medical imaging community through a MICCAI workshop. The database included magnetic resonance (MR) and 3D ultrasound (3DUS) datasets from a dynamic phantom and 15 healthy volunteers. Participants processed 3D tagged MR datasets (3DTAG), cine steady state free precession MR datasets (SSFP) and 3DUS datasets, amounting to 1158 image volumes. Ground-truth for motion tracking was based on 12 landmarks (4 walls at 3 ventricular levels). They were manually tracked by two observers in the 3DTAG data over the whole cardiac cycle, using an in-house application with 4D visualization capabilities. The median of the inter-observer variability was computed for the phantom dataset (0.77 mm) and for the volunteer datasets (0.84 mm). The ground-truth was registered to 3DUS coordinates using a point based similarity transform. Four institutions responded to the challenge by providing motion estimates for the data: Fraunhofer MEVIS (MEVIS), Bremen, Germany; Imperial College London - University College London (IUCL), UK; Universitat Pompeu Fabra (UPF), Barcelona, Spain; Inria-Asclepios project (INRIA), France. Details on the implementation and evaluation of the four methodologies are presented in this manuscript. The manually tracked landmarks were used to evaluate tracking accuracy of all methodologies. For 3DTAG, median values were computed over all time frames for the phantom dataset (MEVIS = 1.20 mm, IUCL = 0.73 mm, UPF = 1.10 mm, INRIA = 1.09 mm) and for the volunteer datasets (MEVIS = 1.33 mm, IUCL = 1.52 mm, UPF = 1.09 mm, INRIA = 1.32 mm). For 3DUS, median values were computed at end diastole and end systole for the phantom dataset (MEVIS = 4.40 mm, UPF = 3.48 mm, INRIA = 4.78 mm) and for the volunteer datasets (MEVIS = 3.51 mm, UPF = 3.71 mm, INRIA = 4.07 mm). For SSFP, median values were computed at end diastole and end systole for the phantom dataset(UPF = 6.18 mm, INRIA = 3.93 mm) and for the volunteer datasets (UPF = 3.09 mm, INRIA = 4.78 mm). Finally, strain curves were generated and qualitatively compared. Good agreement was found between the different modalities and methodologies, except for radial strain that showed a high variability in cases of lower image quality.
Published: 2013

40. Generation of Synthetic but Visually Realistic Time Series of Cardiac Images Combining a Biophysical Model and Clinical Images

Author: Eric Saloux, Nicolas Villain, Nicholas Ayache, Stephanie Marchesseau, Hervé Delingette, Pascal Allain, Maxime Sermesant, Adityo Prakosa, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), MedisysResearch Lab (Medisys), Philips Research, GIP Cyceron (Cyceron), Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-CHU Caen, Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN)-Tumorothèque de Caen Basse-Normandie (TCBN)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Neuropsychologie cognitive et neuroanatomie fonctionnelles de la mémoire humaine, Normandie Université (NU)-Normandie Université (NU)-École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM), European Project: 291080,EC:FP7:ERC,ERC-2011-ADG_20110209,MEDYMA(2012), and Normandie Université (NU)-Normandie Université (NU)-École Pratique des Hautes Études (EPHE)
Subjects: Adult, Diagnostic Imaging, Male, Databases, Factual, Computer science, 0206 medical engineering, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image registration, Image processing, 02 engineering and technology, Motion (physics), 030218 nuclear medicine & medical imaging, Motion, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Motion estimation, Digital image processing, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Computer Simulation, Computer vision, Segmentation, Electrical and Electronic Engineering, Aged, 80 and over, Sequence, Radiological and Ultrasound Technology, business.industry, Models, Cardiovascular, Heart, Image segmentation, 020601 biomedical engineering, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Computer Science Applications, ComputingMethodologies_PATTERNRECOGNITION, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms, Software
Abstract: International audience; We propose a new approach for the generation of synthetic but visually realistic time series of cardiac images based on an electromechanical model of the heart and real clinical 4D image sequences. This is achieved by combining three steps. The first step is the simulation of a cardiac motion using an electromechanical model of the heart and the segmentation of the end diastolic image of a cardiac sequence. We use biophysical parameters related to the desired condition of the simulated subject. The second step extracts the cardiac motion from the real sequence using non-rigid image registration. Finally, a synthetic time series of cardiac images corresponding to the simulated motion is generated in the third step by combining the motion estimated by image registration and the simulated one. With this approach, image processing algorithms can be evaluated as we know the ground-truth motion underlying the image sequence. Moreover, databases of visually realistic images of controls and patients can be generated for which the underlying cardiac motion and some biophysical parameters are known. Such databases can open new avenues for machine learning approaches.
Published: 2013

41. Manifold learning characterization of abnormal myocardial motion patterns: application to CRT-induced changes

Author: Bart Bijnens, Lluís Mont, Josep Brugada, Gemma Piella, Mathieu De Craene, Nicolas Duchateau, Adelina Doltra, Marta Sitges, Cardiology Department, Thorax Clinic Institute, Hospital Cliınic, Institut d'Investigacions Biomèdiques [Barcelona], Universitat de Barcelona (UB), Universitat Pompeu Fabra [Barcelona] (UPF), Institució Catalana de Recerca i Estudis Avançats (ICREA), MedisysResearch Lab (Medisys), and Philips Research
Subjects: medicine.medical_specialty, education.field_of_study, business.industry, medicine.medical_treatment, Population, Nonlinear dimensionality reduction, Cardiac resynchronization therapy, 030204 cardiovascular system & hematology, Motion (physics), 03 medical and health sciences, 0302 clinical medicine, Cardiac motion, Internal medicine, Healthy volunteers, medicine, Myocardial motion, Cardiology, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Computer vision, Artificial intelligence, education, business, 030217 neurology & neurosurgery, Mathematics
Abstract: International audience; The present paper aims at quantifying the evolution of a given motion pattern under cardiac resynchronization therapy (CRT). It builds upon techniques for population-based cardiac motion quantifica-tion (statistical atlases, for inter-sequence spatiotemporal alignment and the definition of normal/abnormal motion). Manifold learning is used on spatiotemporal maps of myocardial motion abnormalities to represent a given abnormal pattern and to compare any individual to that pattern. The methodology was applied to 2D echocardiographic sequences in a 4-chamber view from 108 subjects (21 healthy volunteers and 87 CRT candidates) at baseline, with pacing ON, and at 12 months follow-up. Experiments confirmed that recovery of a normal motion pattern is a necessary but not su cient condition for CRT response.
Published: 2013

42. Motion Estimation in 3D Echocardiography Using Smooth Field Registration

Author: Pascal Allain, Cecile Dufour, Sherif Makram-Ebeid, Mathieu De Craene, Eric Saloux, Benoit Mory, Nicolas Villain, Oudom Somphone, Loic Hilpert, MedisysResearch Lab (Medisys), Philips Research, Service de cardiologie et de pathologie vasculaire [CHU Caen], Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-CHU Caen, Normandie Université (NU)-Tumorothèque de Caen Basse-Normandie (TCBN)-Tumorothèque de Caen Basse-Normandie (TCBN), O. Camara, T. Mansi, M. Pop, K. Rhode, M. Sermesant, and A. Young
Subjects: Phantom, Field (physics), Microsonometry, Physics::Medical Physics, 030204 cardiovascular system & hematology, Deformation (meteorology), Imaging phantom, 030218 nuclear medicine & medical imaging, Convolution, 03 medical and health sciences, symbols.namesake, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Motion estimation, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Gaussian function, Computer vision, Mathematics, Ground truth, business.industry, Myocardial Motion, 3D Cardiac Ultra- sound, Demons, Displacement field, symbols, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Motion Estimation
Abstract: International audience; This paper describes an algorithm for motion and deforma- tion quanti cation of 3D cardiac ultrasound sequences. The algorithm is based on the assumption that the deformation eld is smooth inside the myocardium. Thus, we assume that the displacement eld can be represented as the convolution of an unknown eld with a Gaussian kernel. We apply our algorithm to datasets with reliable ground truth: a set of synthetic sequences with known trajectories and a set of sequences of a mechanical phantom implanted with microsonometry crystals. The final publication is available at link.springer.com
Published: 2013

43. Adaptation of multiscale function extension to inexact matching. Application to the mapping of individuals to a learnt manifold

Author: Marta Sitges, Vicent Caselles, Nicolas Duchateau, Mathieu De Craene, Cardiology Department, Thorax Clinic Institute, Hospital Cliınic, Institut d'Investigacions Biomèdiques [Barcelona], Universitat de Barcelona (UB), MedisysResearch Lab (Medisys), Philips Research, Departament de Tecnologies de la Informació i les Comunicacions, and Universitat Pompeu Fabra [Barcelona] (UPF)
Subjects: Matching (graph theory), business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, 02 engineering and technology, Function (mathematics), 030204 cardiovascular system & hematology, Synthetic data, law.invention, Ambient space, 03 medical and health sciences, 0302 clinical medicine, law, Kernel (statistics), 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 020201 artificial intelligence & image processing, Artificial intelligence, Representation (mathematics), business, Manifold (fluid mechanics), Mathematics, Interpolation, ComputingMethodologies_COMPUTERGRAPHICS
Abstract: International audience; This paper targets the specific issue of out-of-sample interpolation when mapping individuals to a learnt manifold. This process involves two successive interpolations, which we formulate by means of kernel functions: from the ambient space to the coordinates space parametrizing the manifold and reciprocally. We combine two existing interpolation schemes: (i) inexact matching, to take into account the data dispersion around the manifold, and (ii) a multiscale strategy, to overcome single kernel scale limitations. Experiments involve synthetic data, and real data from 108 subjects, representing myocardial motion patterns used for the comparison of individuals to both normality and to a given abnormal pattern, whose manifold representation has been learnt previously.
Published: 2013

44. Real-Time 3D Image Segmentation by User-Constrained Template Deformation

Author: Benoit Mory, Raphael Prevost, Oudom Somphone, Roberto Ardon, MedisysResearch Lab (Medisys), Philips Research, CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), N. Ayache, H. Delingette, P. Golland, and K. Mori
Subjects: Computer science, Segmentation-based object categorization, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-space segmentation, Image processing, 02 engineering and technology, Image segmentation, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Robustness (computer science), Computer Science::Computer Vision and Pattern Recognition, Active shape model, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 020201 artificial intelligence & image processing, Computer vision, Segmentation, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract: International audience; We describe an algorithm for 3D interactive image segmenta- tion by non-rigid implicit template deformation, with two main original features. First, our formulation incorporates user input as inside/outside labeled points to drive the deformation and improve both robustness and accuracy. This yields inequality constraints, solved using an Augmented Lagrangian approach. Secondly, a fast implementation of non-rigid template-to-image registration enables interactions with a real-time visual feedback. We validated this generic technique on 21 Contrast-Enhanced Ultrasound images of kidneys and obtained accurate segmentation results (Dice> 0:93) in less than 3 clicks in average. Copyright Springer-Verlag Berlin Heidelberg 2012. The original publication is available at www.springerlink.com: http://link.springer.com/chapter/10.1007%2F978-3-642-33415-3_69.
Published: 2012

45. Deconvolution for limited-view streak artifacts removal: improvements upon an existing approach

Author: Michael Grass, Françoise Peyrin, Vincent Auvray, Loic Boussel, Bo Zhang, Cyril Mory, Philippe Douek, Simon Rit, Dirk Schäfer, Imagerie Tomographique et Radiothérapie, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), MedisysResearch Lab (Medisys), Philips Research, Philips Research [Germany], Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales (MOTIVATE), Service de Radiologie [Hôpital de la Croix-Rousse - HCL], Hôpital de la Croix-Rousse [CHU - HCL], Hospices Civils de Lyon (HCL)-Hospices Civils de Lyon (HCL), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), and Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)
Subjects: Artifact (error), Radon transform, business.industry, Iterative method, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Streak, Inverse, Iterative reconstruction, Inverse problem, 01 natural sciences, 030218 nuclear medicine & medical imaging, 010309 optics, 03 medical and health sciences, 0302 clinical medicine, 0103 physical sciences, Computer vision, Artificial intelligence, Deconvolution, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Mathematics
Abstract: International audience; Cardiac C-Arm computed tomography leads to a view-starved reconstruction problem because of electrocardiogram gating. Reconstruction with the Feldkamp, Davis and Kress method (FDK) generates large streak artifacts in the reconstructed volumes, hampering the medical interpretation. In order to remove these artifacts, deconvolution techniques have been proposed. In this paper, we start from a recent inverse filtering method developed for streak artifact removal. Two ways to improve upon this method are described. It is then proposed to replace inverse filtering with an iterative deconvolution scheme. Finally, we show that the iterative deconvolution method can itself be replaced by iterative filtered back projection (IFBP). The IFBP approach is flexible and could be used in a broad range of applications, while the improved inverse filtering approaches are computationally less demanding and better suited for time-critical applications.
Published: 2012

46. Registration of free-breathing abdominal 3D contrast-enhanced CT

Author: Blandine Romain, Olivier Lucidarme, Véronique Letort, Laurence Rouet, Florence d'Alché-Buc, MedisysResearch Lab (Medisys), Philips Research, Mathématiques Appliquées aux Systèmes - EA 4037 (MAS), Ecole Centrale Paris, Informatique, Biologie Intégrative et Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE), CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Machine Learning and Optimisation (TAO), Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), H. Yoshida, D. Hawkes, M. W. Vannier, Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Paris-Sud - Paris 11 (UP11)-Laboratoire de Recherche en Informatique (LRI), and Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec
Subjects: free-breathing, medicine.medical_specialty, Enhanced ct, spatio-temporal registration, Image registration, Perfusion scanning, 02 engineering and technology, Similarity measure, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Image acquisition, Computer vision, business.industry, Respiratory motion, DCE-CT, evaluation criteria, 3d image, 020201 artificial intelligence & image processing, Artificial intelligence, Radiology, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Free breathing
Abstract: International audience; CT perfusion imaging is used for the follow-up of abdominal tumors. A speci city of our work is that patients are breathing freely during image acquisition (5 minutes). We propose an automatic 3D image registration to compensate respiratory motion. The registration is computed in two main steps: global translation in the z-direction and 3D multiresolution blockmatching. Within this algorithm, the choice of similarity measure largely determines the algorithm robustness in presence of intensity shifts due to contrast di usion. We exploit a modi ed entropy-based similarity measure to improve the quality of registration. We also propose two relevant criteria allowing to quantify the registration quality: one based on the gradients of image volumes of di erences and one based on the smoothness of enhanced-intensity curves. Copyright Springer-Verlag Berlin Heidelberg. The original publication can be found at http://link.springer.com/chapter/10.1007/978-3-642-33612-6_29
Published: 2012

47. Kidney detection and real-time segmentation in 3D contrast-enhanced ultrasound images

Author: Benoit Mory, Roberto Ardon, Jean-Michel Correas, Laurent D. Cohen, Raphael Prevost, CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), MedisysResearch Lab (Medisys), Philips Research, Department of Adult Radiology, CHU Necker - Enfants Malades [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), and Alejandro Frangi, Andrés Santos
Subjects: Image quality, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Kidney, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Segmentation, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, medicine, 3D Ultrasound, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Computer vision, 3D ultrasound, ComputingMilieux_MISCELLANEOUS, medicine.diagnostic_test, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Image segmentation, Contrast, Ellipsoid, Visualization, Detection, CEUS, 020201 artificial intelligence & image processing, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Contrast-enhanced ultrasound
Abstract: International audience; In this paper, we present an automatic method to segment the kidney in 3D contrast-enhanced ultrasound (CEUS) images. This modality has lately benefited of an increasing interest for diagnosis and intervention planning, as it allows to visualize blood flow in real-time harmlessly for the patient. Our method is composed of two steps: first, the kidney is automatically localized by a novel robust ellipsoid detector; then, segmentation is obtained through the deformation of this ellipsoid with a model-based approach. To cope with low image quality and strong organ variability induced by pathologies, the algorithm allows the user to refine the result by real-time interactions. Our method has been validated on a representative clinical database. (c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Published: 2012

48. Measuring the maximum diameter of native abdominal aortic aneurysms: review and critical analysis

Author: A Long, Laurence Rouet, Eric Allaire, Jes S. Lindholt, Vascular Medicine, Centre Hospitalier Universitaire de Reims, Centre Hospitalier Universitaire de Reims (CHU Reims), MedisysResearch Lab (Medisys), Philips Research, Vascular Research Unit, Viborg Hospital, Centre de Recherches Chirurgicales, CNRS EAC 7054, Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), Vascular Surgery Department, and Hôpital Henri Mondor
Subjects: medicine.medical_specialty, Diameter measurement, MESH: Aorta, Abdominal, Computed tomography, 030230 surgery, 030204 cardiovascular system & hematology, Severity of Illness Index, 03 medical and health sciences, 0302 clinical medicine, Maximum diameter, [SDV.MHEP.CSC]Life Sciences [q-bio]/Human health and pathology/Cardiology and cardiovascular system, MESH: Severity of Illness Index, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Medicine, Body Weights and Measures, cardiovascular diseases, Aorta, Abdominal, 030212 general & internal medicine, MESH: Body Weights and Measures, Ultrasonography, Medicine(all), Measurement method, MESH: Humans, medicine.diagnostic_test, business.industry, Ultrasound, medicine.disease, Abdominal aortic aneurysm, 3. Good health, Quality Score, Calipers, Surgery, Radiology, Tomography, X-Ray Computed, Cardiology and Cardiovascular Medicine, business, MESH: Tomography, X-Ray Computed, MESH: Aortic Aneurysm, Abdominal, Aortic Aneurysm, Abdominal
Abstract: International audience; OBJECTIVES: Maximum diameter is a determinant parameter for the clinical management of asymptomatic abdominal aortic aneurysm (AAA). However, its measurement is not standardised. We review the different methods used to measure AAA maximum diameter, with ultrasound (US) or computed tomography (CT). METHODS: A review of maximum diameter measurement methods with US and CT was performed, focussing on screening, surveillance before repair and decision for intervention. Diameter measurement methodology was described according to four parameters: plane of acquisition, axis of measurement, position of callipers and selected diameter. A quality score to evaluate methodology descriptions was defined (plane, axis, callipers placement and selected diameter), ranging from 0 (worst) to 4 (best). RESULTS: Review showed a wide range of definitions and practices. The mean value of the quality score was 2.52 in screening studies, 1.66 in guidelines for screening, 2.81 in follow-up studies and 1.63 in studies describing decision for intervention. CONCLUSION: To improve the efficiency of AAA management (in screening programmes, follow-up and decision for intervention), and enable comparison between future studies, a standardised methodology for AAA maximum diameter measurement is necessary. Until such a consensus is reached, publications should at least clearly report the method of measurement.
Published: 2012

49. Automatic detection and segmentation of renal lesions in 3D contrast-enhanced ultrasound images

Author: Roberto Ardon, Jean-Michel Correas, Raphael Prevost, Laurent D. Cohen, MedisysResearch Lab (Medisys), Philips Research, CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Department of Adult Radiology, CHU Necker - Enfants Malades [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), and David R. Haynor, Sébastien Ourselin
Subjects: kidney, Computer science, detection, fast marching, cysts, 02 engineering and technology, lesions, 030218 nuclear medicine & medical imaging, Lesion, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0202 electrical engineering, electronic engineering, information engineering, medicine, contrast-enhanced, Segmentation, Computer vision, Kidney, Pixel, ultrasound, business.industry, segmentation, Ultrasound, Visibility (geometry), Visualization, medicine.anatomical_structure, fi ltering, front propagation, 020201 artificial intelligence & image processing, Artificial intelligence, medicine.symptom, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 3D, Contrast-enhanced ultrasound
Abstract: International audience; Contrast-enhanced ultrasound (CEUS) is a valuable imaging modality in the detection and evaluation of different kinds of lesions. Three-dimensional CEUS acquisitions allow quantitative volumetric assessments and better visualization of lesions, but automatic and robust analysis of such images is very challenging because of their poor quality. In this paper, we propose a method to automatically segment lesions such as cysts in 3D CEUS data. First we use a pre-processing step, based on the guided filtering framework, to improve the visibility of the lesions. The lesion detection is then performed through a multi-scale radial symmetry transform. We compute the likelihood of a pixel to be the center of a dark rounded shape. The local maxima of this likelihood are considered as lesions centers. Finally, we recover the whole lesions volume with multiple front propagation based on image intensity, using a fast marching method. For each lesion, the final segmentation is chosen as the one which maximizes the gradient flux through its boundary. Our method has been tested on several clinical 3D CEUS images of the kidney and provides promising results. Copyright 2012 Society of Photo Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. The original version of this work can be found by using the doi:10.1117/12.911103
Published: 2012

50. Optimisation of reconstruction for the registration of CT liver perfusion sequences

Author: Véronique Letort, Laurence Rouet, Olivier Lucidarme, Blandine Romain, Florence d'Alché-Buc, Informatique, Biologie Intégrative et Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE), Mathématiques Appliquées aux Systèmes - EA 4037 (MAS), Ecole Centrale Paris, MedisysResearch Lab (Medisys), Philips Research, CHU Pitié-Salpêtrière [AP-HP], Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Machine Learning and Optimisation (TAO), Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Paris-Sud - Paris 11 (UP11)-Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec, Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)
Subjects: Spatio-temporal registration, business.industry, Computer science, Validation criteria, Image registration, 030218 nuclear medicine & medical imaging, Liver ct, Visual inspection, Perfusion, 03 medical and health sciences, Contrast medium, 0302 clinical medicine, Blockmatching, 030220 oncology & carcinogenesis, Computer vision, [INFO]Computer Science [cs], Artificial intelligence, Image warping, Free-breathing, business, Multiresolution, Ct reconstruction
Abstract: International audience; Objective. CT abdominal perfusion is frequently used to evaluate tumor evolution when patients are undergoing an-tiangiogenic therapy. Parameters depending on longer-term dynamics of the diffusion of the contrast medium (e. g. permeability) could help assessing the treatment efficacy. To this end, dynamic image sequences are obtained while patients breath freely. Prior to any analysis, one needs to compensate the respiratory motion. The goal of our study is to optimize the CT reconstruction parameters (filter of reconstruction, thickness of image volumes) for our registration method. We also aim at proposing relevant criteria allowing to quantify the registration quality. Methods. Registration is computed in 4 steps: z-global rigid registration, local refinements with multiresolution blockmatching, regularization and warping. Two new criteria are defined to evaluate the quality of registration: one for spatial evaluation and the other for temporal evaluation. Results. The two measures decrease after registration (58% and 10% average decrease for the best reconstruction parameters for the spatial and temporal criteria respectively) which is consistent with visual inspection of the images. They are therefore used to determine the best combination of reconstruction parameters.
Published: 2012

Catalog

Books, media, physical & digital resources

See catalog results

Searchworks

Select search scope, currently: Articles Catalog books, media & more in Jio Institute collections Articles journal articles & other e-resources

Search

Search Constraints

Refine your results

Search Limiters

Topic

Publication Year Range

Language

Journal

Database

Publisher

71 results on '"MedisysResearch Lab ( Medisys )"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources