Search

Your search keyword '"Laurent Launay"' showing total 23 results
Start Over Author "Laurent Launay"
23 results on '"Laurent Launay"'

12. Assisted phase and step annotation for surgical videos

Author

Nicolas Martin, Martin Ragot, Gurvan Lecuyer, Laurent Launay, Pierre Jannin, Institut de Recherche Technologique b-com (IRT b-com), 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), and Université de Rennes (UR)-Institut National de la Santé et de la Recherche Médicale (INSERM)

Subjects
Computer science, 0206 medical engineering, Biomedical Engineering, Health Informatics, Cataract Extraction, 02 engineering and technology, computer.software_genre, Convolutional neural network, Health informatics, Workflow, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Annotation, 0302 clinical medicine, Software, Humans, Step recognition, Cholecystectomy, Radiology, Nuclear Medicine and imaging, Surgical workflow, Artificial neural network, business.industry, Assisted annotation, Deep learning, General Medicine, 020601 biomedical engineering, Computer Graphics and Computer-Aided Design, Computer Science Applications, User assistance, Phase recognition, Surgery, [SDV.IB]Life Sciences [q-bio]/Bioengineering, Neural Networks, Computer, Computer Vision and Pattern Recognition, Artificial intelligence, business, computer, Algorithms, Natural language processing
Abstract

International audience; Purpose - Annotation of surgical videos is a time-consuming task which requires specific knowledge. In this paper, we present and evaluate a deep learning-based method that includes pre-annotation of the phases and steps in surgical videos and user assistance in the annotation process. Methods - We propose a classification function that automatically detects errors and infers temporal coherence in predictions made by a convolutional neural network. First, we trained three different architectures of neural networks to assess the method on two surgical procedures: cholecystectomy and cataract surgery. The proposed method was then implemented in an annotation software to test its ability to assist surgical video annotation. A user study was conducted to validate our approach, in which participants had to annotate the phases and the steps of a cataract surgery video. The annotation and the completion time were recorded. Results - The participants who used the assistance system were 7% more accurate on the step annotation and 10 min faster than the participants who used the manual system. The results of the questionnaire showed that the assistance system did not disturb the participants and did not complicate the task. Conclusion - The annotation process is a difficult and time-consuming task essential to train deep learning algorithms. In this publication, we propose a method to assist the annotation of surgical workflows which was validated through a user study. The proposed assistance system significantly improved annotation duration and accuracy.

Published
2020
Full Text
View/download PDF

13. X-Ray Angiography in Stereotactic Conditions: Techniques and Interest for Interventional Neuroradiology

Author

Eric Maurincomme, Laurent Launay, Michael Söderman, Jacques Feldmar, Serge Bracard, Nicholas Ayache, Erwan Kerrien, René Anxionnat, Luc Picard, K. Ericson, Olof Flodmark, Grégoire Malandain, Medical imaging and robotics (EPIDAURE), 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), Models, algorithms and geometry for computer graphics and vision (ISA), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
medicine.medical_specialty, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, anatomy & histology, Radiology, Interventional, Magnetic resonance angiography, methods, 030218 nuclear medicine & medical imaging, Stereotaxic Techniques, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Angiography Digital Subtraction, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, medicine, Humans, Interventional neuroradiology, medicine.diagnostic_test, business.industry, Angiography, Digital Subtraction, Interventional radiology, Digital subtraction angiography, Image Enhancement, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Cerebral Angiography, Carotid Arteries, Anatomy & histology, Stereotaxic technique, Angiography, Surgery, Neurology (clinical), Radiology, business, Nuclear medicine, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Magnetic Resonance Angiography, 030217 neurology & neurosurgery, Human, Radiology Interventional, Cerebral angiography
Abstract

International audience; This paper reports work in progress on X-ray angiography acquired under stereotactic conditions. The objective is to be able to match multimodality images (typically MRI and X-ray) without a stereotactic frame but with stereotactic precision. We have identified potential problems and have studied them in detail. We conclude that, although the overall application is feasible, much work remains to be done on the estimation of the X-ray system conic projection and on automatic matching based on vascular structures.

Published
1997
Full Text
View/download PDF

14. Stereotactic and Image-Guided Surgery: Abstracts

Author

Stefan Kunze, J.H. Song, Catherine Fischer, D. Hellwig, Andrey V. Oblyapin, H. Bertalanffy, Juriy Z. Polonskiy, M. Wallace, Dennis E. Bullard, In Ki Mun, Volker M. Tronnier, Grégoire Malandain, W.R. Niendorf, C. Vial, Matthew A. Howard, Mario M. Bonsanto, Franck Sturtz, Andrey D. Anichkov, François Mauguière, Friedrich K. Albert, Jacques Favre, J. Mukawa, Y. Muragaki, Igor O. Volkov, D.S. Casolino, R.R. Tasker, D. Heyman, E. Emery, Bernard Laurent, Jin Woo Chang, K. Yamashiro, Joseph A. Maldjian, B. Abdennebi, Peter McL. Black, R. Andrews, Audun Stubhaug, Michael L. Levy, E. Franchin, A. Perneczky, Jacques Feldmar, Thomas M. Moriarty, Luis Garcia-Larrea, K. Roessler, Roman Mirsky, A. Cavaggioni, C.W. Dempsey, Joon Hyong Cho, A. Ishida, J.R. Schvarcz, T. Taira, L. Benes, M. Iwahara, Wen-Ching Liu, Y. Yoshii, Frédéric Bonnefoi, T. Nedjahi, H.W.S. Schroeder, William T. O'Connor, M. Daniel Noh, Andreas Staubert, J.C. Acevedo, G. Antoniadis, Yong Gou Park, L. Mahfouf, Eben Alexander, M.R. Gaab, F. Lavenne, Märta Segerdahl, Arcady V. Korzenev, R. Papasin, Luc Picard, Vadim Yakhnitsa, Per Kristian Eide, Serge Bracard, Y. Masutani, Björn A. Meyerson, K. Ericson, N.L. Dorward, Y. Terada, Peter W. Carmel, C. Manelfe, Jeffrey Labuz, Ch. Matula, Nicholas Ayache, P. Shamsgovara, I. Berry, Ron Kikinis, D. Albe-Fessard, Kazuhiro Katada, T. Dohi, P. Charles Garell, N.D. Kitchen, A.T. Bergenheim, Kim J. Burchiel, Xiaozhuo Chen, Olof Flodmark, D.E. Richardson, Marshall Devor, Th. Czech, M. Aichholzer, N. Hopf, Vladimir B. Nizkovolos, Janine Shulok, Chul-Won Park, L. Casentini, Laurent Launay, J. Sabatier, Marc Sindou, G. Palù, Ruth Govrin-Lippmann, W. Wagner, Sang Sup Chung, Karen Waddell, P. Calvi, P. Grunert, Y. Lajat, Kirk Moffitt, Vladimir A. Shoustin, A. Galvagni, Ferenc M. Jolesz, Patrick Mertens, C.R. Wirtz, W.Th. Koos, H.-P. Richter, W. Dietrich, Michael Knauth, Yong Ko, Margareta B. Møller, P.-Å. Ridderheim, H. Ralph Snodgrass, Mark A. Granner, Bengt Linderoth, R. Deinsberger, J.F. Kahamba, Carl-Olav Stiller, Jamal M. Taha, N. Tomiyama, Joseph C.T. Chen, Kazuhiko Nonomura, Philip L. Gildenberg, K. Boulanouar, K. Ungersboeck, M. Tremoulet, S.A. Rath, G. Lanner, H. Goerzer, Blaine S. Nashold, R. Mah, Marie-Claude Gregoire, Krupa Shanker, Eric Maurincomme, Kyung Hoe Lee, J. Winters, Z. Harry Rappaport, F.E. Roux, E. Blondet, Michael Söderman, Doros Platika, M.C. Spendel, C. Giorgi, Michael Schulder, B.L. Bauer, T. Tanikawa, René Anxionnat, D.G.T. Thomas, M. Guerrero, M. Zanusso, K. Seitz, W. Tschiltschke, O. Alberti, Alf Sollevi, H. Iseki, F. Colombo, Erwan Kerrien, N. Soliman, K. Takakura, Jian-Guo Cui, Tetsuo Kanno, J.P. Ranjeva, Roland Peyron, and D. Menegalli-Boggelli

Subjects
medicine.medical_specialty, Image-guided surgery, business.industry, medicine, Surgery, Medical physics, Neurology (clinical), business
Published
1997
Full Text
View/download PDF

15. 3D Angiography

Author

Regis Vaillant, Serge Bracard, Yves Trousset, J. Macho, Luc Picard, Laurent Launay, and R. Anxionnat

Subjects
Algebraic Reconstruction Technique, Radiological and Ultrasound Technology, medicine.diagnostic_test, business.industry, 3D reconstruction, Angioscopy, Computed tomography, Angiography, medicine, Radiology, Nuclear Medicine and imaging, Surface rendering, Neurology (clinical), Nuclear medicine, business, 3d angiography
Abstract

To evaluate the interest of 3D angiography in the diagnosis, treatment and follow-up of aneurysms with special regard with endovascular GDC treatment. Spin angiography with 44 subtracted views (512×512 image matrix) is first acquired with a rotation of a C-arm through 200 degrees at 40° per second in an angiographic room prototype LCV+ single plane (GEMS). 3D reconstruction ART (Algebraic Reconstruction Technique) is automatically applied and interactive visualisation of the 3D angiography is available on a workstation (UltraSparc 2, Sun microsystems) 10 minutes after the spin angiography acquisition. 3D angiography is displayed in MIP, surface rendering and endovascular views (virtual angioscopy). 52 2D and 3D angiographies were performed in 40 patients with 49 intracranial aneurysms whith the same protocol of acquisition (AP, lateral and spin angiography). Each 3D angiography (MIP and surface rendering) was analysed by 2 senior radiologists and compared with the corresponding 2D angiographies (AP, lateral and spin views). Artefacts due to GDC were present in 24 cases, but bothering in only 12 cases. Analysis of the aneurysm was better in MIP than in 2D in 32 cases, equivalent in 18 and worse in 2 due to patient movements during acquisition. Surface rendering gave additional information in 29 cases. The impact was judged important for decision making or choice of treatment in 25 cases. 3D angiography improves the analysis of the aneurysms, gives crucial information to make the decision for treatment and is now routinely used in our institution for the diagnosis of intracranial aneurysms and follow-up after GDC treatment.

Published
1999
Full Text
View/download PDF

16. Intracranial Aneurysms: Clinical Value of 3D Digital Subtraction Angiography in the Therapeutic Decision and Endovascular Treatment

Author

Serge Bracard, Ariel Lebedinsky, Luc Picard, Marc Braun, Laurent Launay, Erwan Kerrien, R. Anxionnat, Francesco Scomazzoni, Regis Vaillant, Yves Trousset, Xavier Ducrocq, Models, algorithms and geometry for computer graphics and vision (ISA), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Adult, Male, medicine.medical_specialty, angiographie 3d, clinical evaluation, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], Image subtraction, évaluation clinique, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Imaging, Three-Dimensional, 0302 clinical medicine, Aneurysm, medicine, neuroradiologie interventionnelle, Humans, Minimally Invasive Surgical Procedures, Radiology, Nuclear Medicine and imaging, cardiovascular diseases, Endovascular treatment, Interventional neuroradiology, Aged, medicine.diagnostic_test, business.industry, Angiography, Digital Subtraction, anévrysme, Intracranial Aneurysm, Interventional radiology, Digital subtraction angiography, Middle Aged, medicine.disease, body regions, Maximum intensity projection, 3d x-ray angiography, Angiography, cardiovascular system, aneurysm, interventional neuroradiology, Feasibility Studies, Female, Radiology, business, Vascular Surgical Procedures, 030217 neurology & neurosurgery
Abstract

Article dans revue scientifique avec comité de lecture.; PURPOSE: To evaluate three-dimensional (3D) digital subtraction angiography (DSA) as a supplement to two-dimensional (2D) DSA in the endovascular treatment (EVT) of intracranial aneurysms. MATERIALS AND METHODS: In 22 ruptured aneurysms, neck visualization, aneurysm shape, and EVT feasibility were analyzed at 2D DSA (anteroposterior, lateral, rotational views) and at maximum intensity projection (MIP) and surface shaded display (SSD) 3D DSA. The possibility of obtaining a working view for EVT at 3D DSA and the relevance of measurements in choosing the first coil also were assessed. RESULTS: Two-dimensional DSA images clearly depicted the aneurysm neck in four of 22 aneurysms; MIP images, in 10; and SSD images, in 21, but SSD led to overestimation of the neck size in one aneurysm. Aneurysm shape was precisely demonstrated in five of 22 aneurysms, EVT seemed to be nonfeasible at 2D DSA; however, SSD demonstrated feasibility and EVT was successfully performed. In one aneurysm, only SSD demonstrated the extension of the neck to a parent vessel, which was proved at surgery. Working views for EVT were deduced from 3D DSA findings in 20 of 21 aneurysms. The choice of the first coil was correct in 19 of 21 aneurysms. CONCLUSION: Three-dimensional DSA is valuable for evaluating the potential for EVT, finding a working view, and performing accurate measurements.

Published
2001

17. Fully automatic 3D/2D subtracted angiography registration

Author

Regis Vaillant, Eric Maurincomme, Luc Picard, Erwan Kerrien, Laurent Launay, Marie-Odile Berger, Models, algorithms and geometry for computer graphics and vision (ISA), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), and Chris Taylor, Alan Colchester

Subjects
medicine.diagnostic_test, business.industry, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], recalage, 02 engineering and technology, Translation (geometry), angiographie, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, registration, Rotational angiography, Maximum intensity projection, Fully automatic, Angiography, 0202 electrical engineering, electronic engineering, information engineering, medicine, 020201 artificial intelligence & image processing, Computer vision, Rigid motion, angiography, Artificial intelligence, business, Rotation (mathematics), Mathematics
Abstract

Colloque avec actes et comité de lecture.; Today, 3-D angiography volumes are routinely generated from rotational angiography sequences. In previous work \cite{Kerrien98}, we have studied the precision reached by registering such volumes with classical 2-D angiography images, inferring this matching only from the sensors of the angiography machine. The error led by such a registration can be described as a 3-D rigid motion composed of a large translation and a small rotation. This paper describes the strategy we followed to correct this error. The angiography image is compared in a two-step process to the Maximum Intensity Projection (MIP) of the angiography volume. The first step provides most of the translation by maximizing the cross-correlation. The second step recovers the residual rigid-body motion, thanks to a modified optical flow technique. A fine analysis of the equations encountered in both steps allows for a speed-up of the calculations. This algorithm was validated on 17 images of a phantom, and 5 patients. The residual error was determined by manually indicating points of interest and was found to be around 1 mm.

Published
1999

18. A flexible iterative method for 3D reconstruction from X-ray projections

Author

Marie-Odile Berger, Laurent Launay, J.-L. Mallet, P. Bouchet, and E. Maurincomme

Subjects
Mathematical optimization, Underdetermined system, business.industry, Iterative method, 3D reconstruction, Inverse, Iterative reconstruction, Regularization (mathematics), Minification, Artificial intelligence, Algebraic number, business, Algorithm, Mathematics
Abstract

The problem of reconstructing a 3D image of an object from a few number of X-ray projections is highly underdetermined. We propose a flexible method based on the regularization of the inverse linear problem with a general quadratic criterion. The minimization is performed by an iterative algorithm with a Gauss-Seidel behaviour. Due to the discrete smooth interpolation formulation, additional linear constraints are inserted, and the method is ensured to converge to the unique minimum. The application of this method is shown for 3D reconstruction of cerebral blood vessels from six projections, and the effect of various criteria is compared to the result of other algebraic methods.

Published
1996
Full Text
View/download PDF

19. 3D reconstruction of cerebral vessels and pathologies from a few biplane digital angiographies

Author

Pierre Bouchet, Jean-Laurent Mallet, Luc Picard, Eric Maurincomme, and Laurent Launay

Subjects
Algebraic Reconstruction Technique, medicine.medical_specialty, medicine.diagnostic_test, Computer science, 3D reconstruction, medicine, Arteriovenous malformation, Digital subtraction angiography, Radiology, Cerebral vessel, medicine.disease, Digital angiography, Biplane
Abstract

3D reconstructions of cerebral vessels and Arteriovenous Malformations from six digital angiography sequences are compared for three iterative methods, one of them being new. The interest of Multiplicative ART is underlined, and the effects of a criterion minimizing the total density are discussed.

Published
1996
Full Text
View/download PDF

20. Quantitative evaluation of an algorithm for correcting geometrical distortions in DSA images: applications to stereotaxy

Author

Catherine Picard, Luc Picard, Eric Maurincomme, Laurent Launay, Pierre Bouchet, and René Anxionnat

Subjects
Image fusion, medicine.diagnostic_test, business.industry, Subtraction, Image intensifier, Digital subtraction angiography, 3D modeling, Imaging phantom, law.invention, law, Distortion, Stereotaxy, medicine, Computer vision, Artificial intelligence, business, Mathematics
Abstract

In Digital Subtraction Angiography, the use of an Image Intensifier as a detector introduces geometrical distortions in theimages. For stereotactic applications, such as the irradiation of cerebral arteriovenous malformations, these distortions have nec-essarily to be corrected, and the accuracy of this correction has to be examined. As the distortions depend on many parametersthat vary during an examination (such as magnetic field and spatial position of the acquisition chain), the correction accuracymust be defined as a function of the acquisition protocol. We have developed a correction method based on the calibration of geo-metrical distortions using an image of a grid phantom. An experimental study of the influence of acquisition parameters over thedistortion has been performed. A protocol has been defined which ensures a correction accuracy of 0. 1 millimeter. Finally, wehave studied the accuracy obtained in the 3D location of a target as a function of the accuracy of the distortion correction. Thefinal precision allows the use of our method for digital X-Ray stereotactic applications.Keywords: geometrical distortions, Digital Subtraction Angiography, stereotaxy, correction, accuracy, 3-D localization1. INTRODUCTIONX-Ray angiography in stereotactic conditions is mainly used for planning radiotherapic treatments of cerebral ArteriovenousMalformations (AVMs): angiographic images are used to localize one point in the nidus which will become the target. Otherapplications include biopsies: the target and the entry point are determined in another modality (CT or MR) and angiographicimages are used to check that the trajectory of the needle will not encounter any important vessel. Radiologists widely accept thatthe accuracy which is needed for the 3-D location of a point in stereotactic applications is one millimeter.Digital Subtraction Angiography (DSA) provides high quality images; however the limitation for stereotaxy is the geometri-cal distortion induced by the Image Intensifier (II). This is the reason why most radiologists are still using plain films for makingmeasurements. On the other hand, DSA images have the advantage of being easy to transfer to a computer. It enables switchingbetween original images and subtracted images, easy travelling inside the injection sequence and also postprocessing such asimage fusion with another modality. Our aim was to be able to use the numerical images coming directly from a digital angiogra-phic system for stereotactic applications, hence to correct distorted images with a good accuracy.Geometrical distortions are generally described as the combination of two effects which have a different origin. The pincush-ion distortion is purely geometric: it is induced by the curvature of the input surface of the II. The S distortion is caused by theinfluence of the ambient magnetic field on the electronic optics of the II. Therefore, it is sensitive to its relative geometric orienta-tion. All the methods developed to correct images are based on the evaluation of the global distortion and the application of itsinverse to the image to be corrected. Most of the time, a model is used to describe the distortion field and the current parametersof this model are estimated with the image of a phantom containing known marker positions. Our approach is based on the eval-uation of the global distortion of the image of a regular grid. We call this step the distortion calibration.After a description of the distortion calibration algorithm, this paper addresses the issue of accuracy, which is critical in ste-reotaxy. The main source of possible loss of accuracy is the variability of the distortion. Many parameters, such as the magneticfield or the spatial position of the acquisition chain, have an impact on the distortion, which may then be different for the gridimage and for the patient image. The third section of this paper presents an experimental study, where the influence of these520

Published
1995
Full Text
View/download PDF

21. Transplantation and Gene Therapy: Abstract

Author

Jacques Favre, D. Albe-Fessard, Frédéric Bonnefoi, T. Nedjahi, D.S. Casolino, Märta Segerdahl, Michael Schulder, Arcady V. Korzenev, R. Papasin, Dennis E. Bullard, E. Emery, William T. O'Connor, A. Galvagni, H. Goerzer, Th. Czech, Janine Shulok, K. Boulanouar, L. Mahfouf, Chul-Won Park, P. Grunert, Nicholas Ayache, P. Charles Garell, Ferenc M. Jolesz, F. Lavenne, F. Colombo, Erwan Kerrien, N. Hopf, J. Winters, Bernard Laurent, C.R. Wirtz, F.E. Roux, Yong Ko, Margareta B. Møller, Xiaozhuo Chen, Bengt Linderoth, N.D. Kitchen, A.T. Bergenheim, T. Dohi, D.E. Richardson, M. Aichholzer, H. Iseki, H. Ralph Snodgrass, Marshall Devor, W.R. Niendorf, M.C. Spendel, Marc Sindou, Y. Muragaki, N.L. Dorward, Y. Terada, N. Soliman, K. Takakura, Kyung Hoe Lee, Thomas M. Moriarty, Andrey D. Anichkov, Blaine S. Nashold, Roman Mirsky, Jeffrey Labuz, François Mauguière, H.-P. Richter, R.R. Tasker, D. Heyman, B.L. Bauer, T. Tanikawa, R. Mah, Z. Harry Rappaport, D.G.T. Thomas, Joseph C.T. Chen, Michael J. Levy, K. Ungersboeck, Andrey V. Oblyapin, Audun Stubhaug, L. Casentini, B. Abdennebi, Krupa Shanker, E. Franchin, Jacques Feldmar, René Anxionnat, Catherine Fischer, Kirk Moffitt, Wen-Ching Liu, M. Zanusso, In Ki Mun, Volker M. Tronnier, K. Roessler, K. Seitz, Luc Picard, Eric Maurincomme, Grégoire Malandain, Vadim Yakhnitsa, Andreas Staubert, Peter W. Carmel, C. Manelfe, E. Blondet, T. Taira, M. Guerrero, Mario M. Bonsanto, Kazuhiro Katada, Y. Masutani, Kim J. Burchiel, Tetsuo Kanno, G. Palù, Michael Söderman, J.C. Acevedo, Matthew A. Howard, Laurent Launay, G. Antoniadis, Karen Waddell, Y. Lajat, Patrick Mertens, Jin Woo Chang, Ch. Matula, Franck Sturtz, Luis Garcia-Larrea, K. Yamashiro, Igor O. Volkov, Carl-Olav Stiller, Y. Yoshii, D. Hellwig, Olof Flodmark, Jian-Guo Cui, Ruth Govrin-Lippmann, Mark A. Granner, Philip L. Gildenberg, W. Wagner, Joon Hyong Cho, G. Lanner, A. Cavaggioni, L. Benes, P. Calvi, I. Berry, A. Perneczky, R. Andrews, Michael Knauth, M.R. Gaab, H. Bertalanffy, M. Iwahara, J.R. Schvarcz, P. Shamsgovara, W.Th. Koos, W. Dietrich, Peter McL. Black, Juriy Z. Polonskiy, M. Wallace, C. Vial, Friedrich K. Albert, Serge Bracard, Björn A. Meyerson, Joseph A. Maldjian, Vladimir A. Shoustin, J.P. Ranjeva, P.-Å. Ridderheim, N. Tomiyama, M. Tremoulet, S.A. Rath, Roland Peyron, D. Menegalli-Boggelli, Sang Sup Chung, Jamal M. Taha, Kazuhiko Nonomura, C. Giorgi, Marie-Claude Gregoire, Stefan Kunze, Doros Platika, A. Ishida, M. Daniel Noh, Yong Gou Park, J.H. Song, Vladimir B. Nizkovolos, J. Mukawa, H.W.S. Schroeder, K. Ericson, J. Sabatier, J.F. Kahamba, W. Tschiltschke, O. Alberti, Alf Sollevi, Per Kristian Eide, C.W. Dempsey, Eben Alexander, Ron Kikinis, and R. Deinsberger

Subjects
Transplantation, Pathology, medicine.medical_specialty, business.industry, Genetic enhancement, Medicine, Surgery, Neurology (clinical), business, Bioinformatics
Published
1997
Full Text
View/download PDF

22. Subject Index Vol. 68, 1997

Author

Nicholas Ayache, Thomas M. Moriarty, G. Antoniadis, Bengt Linderoth, F. Lavenne, Roman Mirsky, Jacques Feldmar, C. Giorgi, Y. Muragaki, Ch. Matula, Michael J. Levy, J.R. Schvarcz, H. Goerzer, T. Taira, K. Ungersboeck, Serge Bracard, Björn A. Meyerson, D.E. Richardson, P. Charles Garell, Marc Sindou, Andrey V. Oblyapin, Audun Stubhaug, N. Hopf, F.E. Roux, E. Blondet, K. Roessler, Sang Sup Chung, Jamal M. Taha, Kazuhiko Nonomura, Igor O. Volkov, C.W. Dempsey, L. Mahfouf, Olof Flodmark, In Ki Mun, Tetsuo Kanno, C.R. Wirtz, Volker M. Tronnier, N. Tomiyama, Grégoire Malandain, W. Tschiltschke, N.L. Dorward, Jin Woo Chang, O. Alberti, Y. Terada, Matthew A. Howard, A. Ishida, D. Hellwig, Alf Sollevi, Per Kristian Eide, Andrey D. Anichkov, François Mauguière, Karen Waddell, M. Tremoulet, R. Andrews, Jeffrey Labuz, N.D. Kitchen, Eben Alexander, N. Soliman, A.T. Bergenheim, K. Takakura, Kirk Moffitt, J.H. Song, L. Casentini, M. Daniel Noh, Yong Gou Park, Catherine Fischer, Jacques Favre, Xiaozhuo Chen, Juriy Z. Polonskiy, M. Wallace, C. Vial, Yong Ko, Marshall Devor, Margareta B. Møller, G. Lanner, Blaine S. Nashold, R. Mah, Joseph A. Maldjian, J. Mukawa, D. Albe-Fessard, Kyung Hoe Lee, B. Abdennebi, Ron Kikinis, D.S. Casolino, E. Emery, Peter W. Carmel, C. Manelfe, Ruth Govrin-Lippmann, W. Wagner, Z. Harry Rappaport, P. Calvi, Luis Garcia-Larrea, Krupa Shanker, Eric Maurincomme, H.W.S. Schroeder, A. Perneczky, Y. Yoshii, J. Winters, K. Ericson, Joseph C.T. Chen, Luc Picard, Vadim Yakhnitsa, Mario M. Bonsanto, Michael Söderman, Vladimir B. Nizkovolos, Bernard Laurent, Vladimir A. Shoustin, J. Sabatier, I. Berry, Michael Schulder, H. Iseki, P.-Å. Ridderheim, Andreas Staubert, J.F. Kahamba, M.C. Spendel, Wen-Ching Liu, Erwan Kerrien, F. Colombo, K. Yamashiro, S.A. Rath, H. Bertalanffy, D.G.T. Thomas, A. Cavaggioni, R. Deinsberger, W.Th. Koos, P. Shamsgovara, J.P. Ranjeva, K. Seitz, Michael Knauth, Y. Lajat, Franck Sturtz, M. Zanusso, W. Dietrich, Friedrich K. Albert, L. Benes, Marie-Claude Gregoire, Stefan Kunze, William T. O'Connor, Peter McL. Black, René Anxionnat, Roland Peyron, D. Menegalli-Boggelli, Kazuhiro Katada, Joon Hyong Cho, Märta Segerdahl, M. Iwahara, Arcady V. Korzenev, M. Guerrero, Dennis E. Bullard, Doros Platika, Ferenc M. Jolesz, Laurent Launay, Kim J. Burchiel, H.-P. Richter, Th. Czech, Janine Shulok, Chul-Won Park, P. Grunert, Y. Masutani, Carl-Olav Stiller, A. Galvagni, Philip L. Gildenberg, M.R. Gaab, Mark A. Granner, K. Boulanouar, T. Dohi, M. Aichholzer, B.L. Bauer, T. Tanikawa, Jian-Guo Cui, Frédéric Bonnefoi, T. Nedjahi, W.R. Niendorf, R.R. Tasker, D. Heyman, J.C. Acevedo, E. Franchin, G. Palù, H. Ralph Snodgrass, Patrick Mertens, and R. Papasin

Subjects
medicine.medical_specialty, Index (economics), business.industry, Medicine, Surgery, Subject (documents), Medical physics, Neurology (clinical), business
Published
1997
Full Text
View/download PDF

23. OPTIMIZED MULTI-ATLAS PROSTATE SEGMENTATION FROM 3D CT IMAGES

Author

Julien Bert, Oscar Acosta, Yitian Zhou, Renaud de Crevoisier, Laurent Launay, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM), Université de Brest (UBO), Laboratoire Traitement du Signal et de l'Image (LTSI), Université de Rennes (UR)-Institut National de la Santé et de la Recherche Médicale (INSERM), CRLCC Eugène Marquis (CRLCC), Jonchère, Laurent, Institut National de la Santé et de la Recherche Médicale (INSERM)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut Brestois Santé Agro Matière (IBSAM), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Rennes 1 (UR1), and Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)

Subjects
[SDV.IB] Life Sciences [q-bio]/Bioengineering, Contouring, prostate, inter-observer variability, radiotherapy planning, Computer science, Atlas (topology), business.industry, 0206 medical engineering, Pattern recognition, 02 engineering and technology, Multi-atlas segmentation, Similarity measure, 020601 biomedical engineering, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Histogram of oriented gradients, Feature (computer vision), Region of interest, Segmentation, [SDV.IB]Life Sciences [q-bio]/Bioengineering, Artificial intelligence, business, CT
Abstract

International audience; The purpose of this study was to evaluate and optimize the performance of a multi-atlas based method for the segmentation of prostate in CT scans improving it up to the limit of the inter-observer variability. We assessed and optimized the atlas selection, the Non-Rigid Registration (NRR) and the label fusion steps by introducing new similarity measures based on image features and a multi-scale weighted majority voting. Cross validation results on 45 CT images suggested that the similarity measure based on the local feature histogram of oriented gradients outperformed classical intensity-based metrics for atlas selection. Besides, the NiftyReg optimized in a region of interest was found to be the optimal NRR algorithm. For the label fusion, the multi-scale weighted majority voting outperformed other approaches. All those improvements led to Dice scores of 0.84 +/- 0.03, which are comparable to the inter-observer variability for manual contouring.

Catalog

Books, media, physical & digital resources
See catalog results