Search

Your search keyword '"Service d'ophtalmologie [Brest]"' showing total 46 results
Start Over Author "Service d'ophtalmologie [Brest]"
46 results on '"Service d'ophtalmologie [Brest]"'

1. Automation of dry eye disease quantitative assessment: A review

Author

Ikram Brahim, Mathieu Lamard, Anas‐Alexis Benyoussef, Gwenolé Quellec, Université de Brest (UBO), 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), Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and European Project: 806975,NECESSITY

Subjects
ophthalmology, [SDV]Life Sciences [q-bio], Humans, Dry Eye Syndromes, artificial intelligence, dry eye disease, quantification, automation
Abstract

International audience; Dry eye disease (DED) is a common eye condition worldwide and a primary reason for visits to the ophthalmologist. DED diagnosis is performed through a combination of tests, some of which are unfortunately invasive, nonreproducible and lack accuracy. The following review describes methods that diagnose and measure the extent of eye dryness, enabling clinicians to quantify its severity. Our aim with this paper is to review classical methods as well as those that incorporate automation. For only four ways of quantifying DED, we take a deeper look into what main elements can benefit from automation and the different ways studies have incorporated it. Like numerous medical fields, Artificial Intelligence (AI) appears to be the path towards quality DED diagnosis. This review categorises diagnostic methods into the following: classical, semi-automated and promising AI-based automated methods.

Published
2022
Full Text
View/download PDF

2. Transformation d’un mélanocytome méningé en mélanome : étude clinique, histopathologique et cytogénétique

Author

Romuald Seizeur, Amélie Bourhis, Marianne Bourhis, Pascale Marcorelles, Elsa Magro, Isabelle Quintin-Roué, Arnaud Uguen, Sylvia Redon, CCSD, Accord Elsevier, Service d'Anatomie et Pathologie, Brest, Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), CHRU Brest - Laboratoire d'Anatomo-Pathologie (CHU - AnaPath), Laboratoire de Génétique Moléculaire et d'Histocompatibilité [Brest], Hôpital Morvan [Brest]-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université de Bretagne Occidentale - UFR Médecine et Sciences de la Santé (UBO UFR MSS), Université de Brest (UBO), Service de neurochirurgie [Brest], Hôpital de la Cavale Blanche - CHRU Brest (CHU - BREST ), Lymphocytes B, Autoimmunité et Immunothérapies (LBAI), Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-LabEX IGO Immunothérapie Grand Ouest, and Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Institut Brestois Santé Agro Matière (IBSAM)

Subjects
0301 basic medicine, medicine.medical_specialty, Pathology, [SDV.IMM] Life Sciences [q-bio]/Immunology, Meningeal melanocytoma, Meningeal melanoma, [SDV]Life Sciences [q-bio], Mélanocytome méningé, Pathology and Forensic Medicine, Malignant transformation, Cytogenetics, 03 medical and health sciences, 0302 clinical medicine, medicine, Cytogénétique, business.industry, Mélanome méningé, Melanoma, Meningeal Melanoma, medicine.disease, 3. Good health, [SDV] Life Sciences [q-bio], Tumor Subtype, 030104 developmental biology, 030220 oncology & carcinogenesis, [SDV.IMM]Life Sciences [q-bio]/Immunology, Immunohistochemistry, Melanocytoma, business
Abstract

International audience; Meningeal melanocytic tumors are rare. We report an exceptional case of transformation of a meningeal melanocytoma in a malignant melanoma. The course of the disease extents from 61-years to 85-years and ends with the death of the patient. Besides histopathological and immunohistochemical data, we also report the array CGH study of the melanocytoma and melanoma components suggesting the malignant transformation from whole chromosome gains in the melanocytoma to additional segmental aberrations in the malignant melanoma. Beyond the rarity of this tumor subtype, this case report highlights the potential interest of molecular analyses for diagnostic and prognostic purposes in the field of meningeal melanocytic tumors.

Published
2019

3. [Meningeal melanoma arising from a preexisting meningeal melanocytoma: A clinical, pathological and cytogenetic study about one case]

Author

Bourhis, Amélie, Quintin-Roué, Isabelle, Redon, Sylvia, Bourhis, Marianne, Magro, Elsa, Seizeur, Romuald, Marcorelles, Pascale, Uguen, Arnaud, Service d'Anatomie et Pathologie, Brest, Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), CHRU Brest - Laboratoire d'Anatomo-Pathologie (CHU - AnaPath), Laboratoire de Génétique Moléculaire et d'Histocompatibilité [Brest], Hôpital Morvan [Brest]-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université de Bretagne Occidentale - UFR Médecine et Sciences de la Santé (UBO UFR MSS), Université de Brest (UBO), Service de neurochirurgie [Brest], Hôpital de la Cavale Blanche - CHRU Brest (CHU - BREST ), Lymphocyte B et Auto-immunité (LBAI), and Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Brestois Santé Agro Matière (IBSAM)

Subjects
Male, Reoperation, Meningeal melanoma, [SDV]Life Sciences [q-bio], Mélanocytome méningé, Vision Disorders, Cytogenetics, Fatal Outcome, Biomarkers, Tumor, Meningeal Neoplasms, Humans, Cytogénétique, Melanoma, Comparative Genomic Hybridization, Mélanome méningé, Middle Aged, Neoplasm Proteins, Meningeal melanocytoma, Cell Transformation, Neoplastic, Somatosensory Disorders, Melanocytes, [SDV.IMM]Life Sciences [q-bio]/Immunology, Tomography, X-Ray Computed, Melanoma-Specific Antigens, Follow-Up Studies, gp100 Melanoma Antigen
Abstract

International audience; Meningeal melanocytic tumors are rare. We report an exceptional case of transformation of a meningeal melanocytoma in a malignant melanoma. The course of the disease extents from 61-years to 85-years and ends with the death of the patient. Besides histopathological and immunohistochemical data, we also report the array CGH study of the melanocytoma and melanoma components suggesting the malignant transformation from whole chromosome gains in the melanocytoma to additional segmental aberrations in the malignant melanoma. Beyond the rarity of this tumor subtype, this case report highlights the potential interest of molecular analyses for diagnostic and prognostic purposes in the field of meningeal melanocytic tumors.

Published
2019

4. CATARACTS: Challenge on automatic tool annotation for cataRACT surgery

Author

Guilherme Aresta, Chandan Panda, Gwenole Quellec, Senthil Ramamurthy, Xiaowei Hu, Adrian Galdran, Navdeep Dahiya, Fenqiang Zhao, Pheng-Ann Heng, Evangello Flouty, William G. Macready, Danail Stoyanov, Sailesh Conjeti, Anirban Mukhopadhyay, Sabrina Dill, Stefan Zachow, Jogundas Armaitis, Mathieu Lamard, Pedro Alves Costa, Shunren Xia, Jonas Prellberg, Manish Sahu, Satoshi Kondo, Pierre-Henri Conze, Muneer Ahmad Dedmari, Chenhui Qiu, Arash Vahdat, Gabija Maršalkaitė, Zhengbing Bian, Jonas Bialopetravičius, Duc My Vo, Soumali Roychowdhury, Béatrice Cochener, Odysseas Zisimopoulos, Teresa Araújo, Sang-Woong Lee, Hassan Al Hajj, Aurélio Campilho, Institut National de la Santé et de la Recherche Médicale (INSERM), Université de Brest (UBO), Département lmage et Traitement Information (IMT Atlantique - ITI), IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), 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 Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM), The Chinese University of Hong Kong [Hong Kong], Technische Universität Munchen - Université Technique de Munich [Munich, Allemagne] (TUM), Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
Decision support system, Computer science, medicine.medical_treatment, media_common.quotation_subject, instrumentation [Cataract Extraction], Psychological intervention, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Video Recording, Health Informatics, Context (language use), Cataract Extraction, 02 engineering and technology, 03 medical and health sciences, Annotation, 0302 clinical medicine, Deep Learning, Cataracts, 0202 electrical engineering, electronic engineering, information engineering, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Radiology, Nuclear Medicine and imaging, Quality (business), ddc:610, media_common, Radiological and Ultrasound Technology, business.industry, Deep learning, Cataract surgery, medicine.disease, Surgical Instruments, Computer Graphics and Computer-Aided Design, Data science, 030221 ophthalmology & optometry, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Algorithms
Abstract

International audience; Surgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow analysis, with potential applications in report generation, surgical training and even real-time decision support. Most existing tool annotation algorithms focus on laparo-scopic surgeries. However, with 19 million interventions per year, the most common surgical procedure in the world is cataract surgery. The CATARACTS challenge was organized in 2017 to evaluate tool annotation algorithms in the specific context of cataract surgery. It relies on more than nine hours of videos, from 50 cataract surgeries, in which the presence of 21 surgical tools was manually annotated by two experts. With 14 participating teams, this challenge can be considered a success. As might be expected,-H. Conze et al. / Medical Image Analysis 52 (2019) 24-41 25 the submitted solutions are based on deep learning. This paper thoroughly evaluates these solutions: in particular, the quality of their annotations are compared to that of human interpretations. Next, lessons learnt from the differential analysis of these solutions are discussed. We expect that they will guide the design of efficient surgery monitoring tools in the near future.

Published
2019

5. Cataracte et implants intraoculaires, des progrès spectaculaires

Author

Albane Cassan, Béatrice Cochener, Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
03 medical and health sciences, Medical–Surgical Nursing, 0302 clinical medicine, business.industry, [SDV]Life Sciences [q-bio], 030221 ophthalmology & optometry, Medicine, business, 030217 neurology & neurosurgery
Published
2017

6. Monitoring tool usage in surgery videos using boosted convolutional and recurrent neural networks

Author

Pierre-Henri Conze, Gwenole Quellec, Mathieu Lamard, Béatrice Cochener, Hassan Al Hajj, 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 Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM), Université de Brest (UBO), Département lmage et Traitement Information (IMT Atlantique - ITI), IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque, 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), and IMT Atlantique (IMT Atlantique)

Subjects
FOS: Computer and information sciences, Decision support system, medicine.medical_specialty, Boosting (machine learning), Computational complexity theory, Computer science, Computer Vision and Pattern Recognition (cs.CV), Video Recording, Computer Science - Computer Vision and Pattern Recognition, Health Informatics, 02 engineering and technology, Cataract Extraction, Convolutional neural network, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, 0202 electrical engineering, electronic engineering, information engineering, medicine, Image Processing, Computer-Assisted, Humans, Radiology, Nuclear Medicine and imaging, Cholecystectomy, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Radiological and Ultrasound Technology, Frame (networking), Novelty, Computer Graphics and Computer-Aided Design, Surgery, Recurrent neural network, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Neural Networks, Computer, Monitoring tool, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms
Abstract

This paper investigates the automatic monitoring of tool usage during a surgery, with potential applications in report generation, surgical training and real-time decision support. Two surgeries are considered: cataract surgery, the most common surgical procedure, and cholecystectomy, one of the most common digestive surgeries. Tool usage is monitored in videos recorded either through a microscope (cataract surgery) or an endoscope (cholecystectomy). Following state-of-the-art video analysis solutions, each frame of the video is analyzed by convolutional neural networks (CNNs) whose outputs are fed to recurrent neural networks (RNNs) in order to take temporal relationships between events into account. Novelty lies in the way those CNNs and RNNs are trained. Computational complexity prevents the end-to-end training of "CNN+RNN" systems. Therefore, CNNs are usually trained first, independently from the RNNs. This approach is clearly suboptimal for surgical tool analysis: many tools are very similar to one another, but they can generally be differentiated based on past events. CNNs should be trained to extract the most useful visual features in combination with the temporal context. A novel boosting strategy is proposed to achieve this goal: the CNN and RNN parts of the system are simultaneously enriched by progressively adding weak classifiers (either CNNs or RNNs) trained to improve the overall classification accuracy. Experiments were performed in a dataset of 50 cataract surgery videos and a dataset of 80 cholecystectomy videos. Very good classification performance are achieved in both datasets: tool usage could be labeled with an average area under the ROC curve of $A_z = 0.9961$ and $A_z = 0.9939$, respectively, in offline mode (using past, present and future information), and $A_z = 0.9957$ and $A_z = 0.9936$, respectively, in online mode (using past and present information only)., Accepted for publication in Medical Image Analysis

Published
2018

7. Optical flow estimation in ocular endoscopy videos using flownet on simulated endoscopy data

Author

A. Guerre, Gwenole Quellec, Pierre-Henri Conze, Béatrice Cochener, Mathieu Lamard, 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 Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM), Université de Brest (UBO), Département lmage et Traitement Information (IMT Atlantique - ITI), IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
Flownet, Microscope, genetic structures, Computer science, 0206 medical engineering, Optical flow, Image processing, 02 engineering and technology, Fundus (eye), Convolutional neural network, Retina, 030218 nuclear medicine & medical imaging, law.invention, 03 medical and health sciences, 0302 clinical medicine, law, Motion estimation, medicine, Computer vision, Convolution neural network, Ground truth, business.industry, Diabetic retinopathy, medicine.disease, 020601 biomedical engineering, Endoscopic surgery, eye diseases, Transfer learning, Optical flow estimation, medicine.anatomical_structure, Artificial intelligence, sense organs, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; In recent years, endoscopy has been increasingly used for ocular surgeries whenever viewing with a microscope is altered by occlusion or opacity. However, ocular endoscopy suffers from several limitations, including reduced field of view and limited resolution, which may compromise its usability. Hopefully, image processing techniques such as mosaicking and super-resolution could help in alleviating these problems, by artificially enlarging the field and increasing resolution. All these techniques rely on the ability to estimate the optical flow between consecutive frames, which is particularly challenging for those images. This paper investigates the use of the state-of-the-art FlowNet algorithm for motion estimation in ocular endoscopy videos. Because FlowNet is strongly supervised, an artificial dataset of consecutive image pairs with ground truth optical flow is generated using eye fundus photographs from Kaggle's Diabetic Retinopathy Detection dataset. A FlowNet model, initialized on the public Flying Chairs dataset, is fine-tuned on these images. Initial experiments show that, unlike any other optical flow estimation method, this model can successfully capture motion between ocular endoscopy image pairs.

Published
2018

8. Healing of resistant corneal neurotrophic ulcers using a matrix regenerating agent

Author

C. Zagnoli, S. Derrien, C. Hugny-Larroque, Béatrice Cochener, Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
Male, medicine.medical_specialty, genetic structures, [SDV]Life Sciences [q-bio], Keratitis, Cornea, 03 medical and health sciences, 0302 clinical medicine, medicine, Humans, Regeneration, In patient, Amnion, Treatment Failure, Surgical treatment, Corneal Ulcer, Aged, Glycosaminoglycans, Aged, 80 and over, Salvage Therapy, Wound Healing, Medical treatment, business.industry, Middle Aged, medicine.disease, eye diseases, 3. Good health, Surgery, Ophthalmology, Treatment Outcome, Adjunctive treatment, 030221 ophthalmology & optometry, Neurotrophic corneal ulcer, Female, sense organs, Ophthalmic Solutions, business
Abstract

Summary Purpose To assess the success rate of a matrix regenerating agent (RGTA) in the treatment of chronic corneal ulcers resistant to conventional treatments. Methods Uncontrolled prospective observational study in patients with corneal neurotrophic ulcer (Stage 2 or 3 of the Mackie classification), unresponsive to standard medical or surgical treatments and managed with RGTA as an adjunctive treatment. Corneal ulcers were evaluated using slit-lamp examination and optical coherence tomography after 2 weeks, 1 month, 2 months and 3 months. Success was defined as complete corneal healing. Results RGTA was administered to 20 patients (20 eyes) with chronic corneal ulcers of various causes, including keratoplasty (7 eyes, 35.0%), herpetic keratitis (5 eyes, 25.0%) and intracorneal ring (3 eyes, 15.0%). Total corneal healing was observed in 13/20 patients (65.0%) within 1 to 3 months. RGTA was discontinued due to partial healing/ulcer stagnation in 6 patients (30.0%), and aggravation of the ulcer in 1 patient (5.0%). Relapses were reported in 4 patients (20.0%) several months after cessation of RGTA treatment. No adverse reactions were noted. Conclusions In the event of failure of conventional treatments, RGTA may be an alternative medical treatment for patients with chronic corneal ulcers, avoiding the need to resort to surgical treatment.

Published
2018

9. Comparison of 2002 AECG and 2016 ACR/EULAR classification criteria and added value of salivary gland ultrasonography in a patient cohort with suspected primary Sjögren’s syndrome

Author

Steeve Genestet, Sebastian Costa, Rozenn Le Berre, Alain Saraux, Béatrice Cochener, Sylvie Boisramé-Gastrin, Dewi Guellec, Yves Renaudineau, Jacques-Olivier Pers, Divi Cornec, Sandrine Jousse-Joulin, Thierry Marhadour, Valérie Devauchelle-Pensec, Maëlle Le Goff, Centre National de Référence CERAINO, Service de Rhumatologie (Hôpital de la Cavale Blanche), Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Lymphocyte B et Auto-immunité (LBAI), Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Brestois Santé Agro Matière (IBSAM), Université de Brest (UBO), Service de Médecine Interne Gériatrique (BREST - SMIG), Explorations fonctionnelles neurologiques, Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), CHRU Brest - Service d'Odontologie (CHU - BREST - Odontologie), and Laboratoire d'Immunologie et Immunothérapie

Subjects
Adult, Male, musculoskeletal diseases, medicine.medical_specialty, lcsh:Diseases of the musculoskeletal system, Classification criteria, Cross-sectional study, Concordance, [SDV]Life Sciences [q-bio], education, Salivary Glands, Cohort Studies, 03 medical and health sciences, 0302 clinical medicine, Rheumatology, Internal medicine, Diagnosis, medicine, Humans, 030212 general & internal medicine, skin and connective tissue diseases, 10. No inequality, ComputingMilieux_MISCELLANEOUS, Aged, Ultrasonography, 030203 arthritis & rheumatology, Salivary gland, business.industry, Middle Aged, medicine.disease, stomatognathic diseases, Cross-Sectional Studies, Sjogren's Syndrome, medicine.anatomical_structure, Sjögren’s syndrome, Cohort, Female, lcsh:RC925-935, business, Primary, Rheumatism, Research Article, Cohort study
Abstract

Background The objective was to evaluate concordance between 2002 American-European Consensus Group (AECG) and 2016 American College of Rheumatology (ACR)/European League Against Rheumatism (EULAR) classification criteria for primary Sjögren’s syndrome (pSS) and to assess how salivary gland ultrasonography (SGUS) might improve the classification of patients. Methods Patients with suspected pSS underwent a standardised evaluation, including SGUS, at inclusion into the single-centre Brittany DIApSS cohort. Agreement between the two criteria sets was assessed using Cohen’s κ coefficient. Characteristics of discordantly categorised patients were detailed. Results We prospectively included 290 patients between 2006 and 2016, among whom 125 (43%) met ACR/EULAR criteria and 114 (39%) also met AECG criteria; thus, 11 (4%) patients fulfilled only ACR/EULAR, no patients AECG only, and 165 (57%) patients neither criteria set. Concordance was excellent (κ = 0.92). Compared to patients fulfilling both criteria sets, the 11 patients fulfilling only ACR/EULAR criteria had similar age and symptom duration but lower frequencies of xerophthalmia and xerostomia (p

Published
2017

10. Évaluation prospective de l’état dentaire et parodontal chez des patients présentant une suspicion de syndrome de Gougerot-Sjögren

Author

Sandrine Jousse-Joulin, Divi Cornec, Alain Saraux, Jacques-Olivier Pers, Malo Le Gall, Anne-Marie Roguedas-Contios, Valérie Devauchelle-Pensec, Sylvie Boisramé, Béatrice Cochener, Department of Odontology, Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), LabEX IGO Immunothérapie Grand Ouest, Service de Rhumatologie [CHU de la Cavale-Blanche], Hôpital de la Cavale Blanche - CHRU Brest (CHU - BREST ), Immunologie et Pathologie (EA2216), Université de Brest (UBO)-IFR148, Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and Service de dermatologie (Dermato - BREST)

Subjects
030203 arthritis & rheumatology, 03 medical and health sciences, 0302 clinical medicine, Rheumatology, business.industry, Medicine, [SDV.IMM]Life Sciences [q-bio]/Immunology, 030206 dentistry, business, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2016

11. Fast Wavelet-Based Image Characterization for Highly Adaptive Image Retrieval

Author

Béatrice Cochener, Christian Roux, Guy Cazuguel, Gwenole Quellec, Mathieu Lamard, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Direction Scientifique (DS), Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque

Subjects
Discrete wavelet transform, Computer science, Stationary wavelet transform, Wavelet Analysis, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Information Storage and Retrieval, Relevance feedback, Cascade algorithm, 02 engineering and technology, Content-based image retrieval, Facial recognition system, Pattern Recognition, Automated, Wavelet packet decomposition, Wavelet, Image texture, Artificial Intelligence, Image Interpretation, Computer-Assisted, Content-based image retrieval (CBIR), 0202 electrical engineering, electronic engineering, information engineering, Wavelet transformation, Computer vision, Visual Word, Image retrieval, Feature detection (computer vision), [SDV.IB] Life Sciences [q-bio]/Bioengineering, business.industry, Wavelet transform, 020207 software engineering, Pattern recognition, Image Enhancement, Computer Graphics and Computer-Aided Design, Adaptive filter, Wavelet adaptation, Radiology Information Systems, Automatic image annotation, Subtraction Technique, Computer Science::Computer Vision and Pattern Recognition, [SDV.IB]Life Sciences [q-bio]/Bioengineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Algorithms, Software
Abstract

Adaptive wavelet-based image characterizations have been proposed in previous works for content-based image retrieval (CBIR) applications. In these applications, the same wavelet basis was used to characterize each query image: This wavelet basis was tuned to maximize the retrieval performance in a training data set. We take it one step further in this paper: A different wavelet basis is used to characterize each query image. A regression function, which is tuned to maximize the retrieval performance in the training data set, is used to estimate the best wavelet filter, i.e., in terms of expected retrieval performance, for each query image. A simple image characterization, which is based on the standardized moments of the wavelet coefficient distributions, is presented. An algorithm is proposed to compute this image characterization almost instantly for every possible separable or nonseparable wavelet filter. Therefore, using a different wavelet basis for each query image does not considerably increase computation times. On the other hand, significant retrieval performance increases were obtained in a medical image data set, a texture data set, a face recognition data set, and an object picture data set. This additional flexibility in wavelet adaptation paves the way to relevance feedback on image characterization itself and not simply on the way image characterizations are combined.

Published
2012

12. Optimal Wavelet Transform for the Detection of Microaneurysms in Retina Photographs

Author

P.M. Josselin, Christian Roux, Béatrice Cochener, Gwenole Quellec, Guy Cazuguel, Mathieu Lamard, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (UMR 3192) (Lab-STICC), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Département Réseaux, Sécurité et Multimédia (RSM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Brest (UBO)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), and Quellec, Gwénolé

Subjects
genetic structures, Computer science, Retinal Artery, 02 engineering and technology, Pattern Recognition, Automated, 030218 nuclear medicine & medical imaging, chemistry.chemical_compound, 0302 clinical medicine, Wavelet, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, genetic algorithm, Photography, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Fluorescein Angiography, Retinoscopy, Microaneurysm, [SDV.MHEP] Life Sciences [q-bio]/Human health and pathology, Radiological and Ultrasound Technology, medicine.diagnostic_test, Wavelet transform, Diabetic retinopathy, Fluorescein angiography, Computer Science Applications, medicine.anatomical_structure, microaneurysms, 020201 artificial intelligence & image processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms, Retinopathy, Lifting scheme, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, optimal wavelet transform, Sensitivity and Specificity, Article, 03 medical and health sciences, Aneurysm, Artificial Intelligence, Image Interpretation, Computer-Assisted, medicine, Humans, Electrical and Electronic Engineering, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, template matching, Retina, Diabetic Retinopathy, Modality (human–computer interaction), business.industry, Template matching, Reproducibility of Results, Retinal, medicine.disease, chemistry, Artificial intelligence, business, [SDV.MHEP]Life Sciences [q-bio]/Human health and pathology, Software
Abstract

11 pages; International audience; In this paper, we propose an automatic method to detect microaneurysms in retina photographs. Microaneurysms are the most frequent and usually the first lesions to appear as a consequence of diabetic retinopathy. So, their detection is necessary for both screening the pathology and follow up (progression measurement). Automating this task, which is currently performed manually, would bring more objectivity and reproducibility. We propose to detect them by locally matching a lesion template in subbands of wavelet transformed images. To improve the method performance, we have searched for the best adapted wavelet within the lifting scheme framework. The optimization process is based on a genetic algorithm followed by Powell's direction set descent. Results are evaluated on 120 retinal images analyzed by an expert and the optimal wavelet is compared to different conventional mother wavelets. These images are of three different modalities: there are color photographs, green filtered photographs, and angiographs. Depending on the imaging modality, microaneurysms were detected with a sensitivity of respectively 89.62%, 90.24%, and 93.74% and a positive predictive value of respectively 89.50%, 89.75%, and 91.67%, which is better than previously published methods.

Published
2008

13. Evaluation of the efficacy and safety of a standardised intracameral combination of mydriatics and anaesthetics for cataract surgery

Author

Joseph Colin, Oliver Findl, Dahbia Hartani, Sihem Lazreg, Marie-José Tassignon, Jorge L. Alió, Conceição Lobo, François Malecaze, Marc Labetoulle, Anders Behndig, Béatrice Cochener, AP-HP Hôpital Bicêtre (Le Kremlin-Bicêtre), Virulence et Latence des Herpesvirus (HERPES), Département Virologie (Dpt Viro), Institut de Biologie Intégrative de la Cellule (I2BC), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Institut de Biologie Intégrative de la Cellule (I2BC), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Medizinische Universität Wien = Medical University of Vienna, Centre Hospitalier Universitaire de Toulouse (CHU Toulouse), Vissum-Instituto Oftalmologico de Alicante, Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Centre d'ophtalmologie, CHU Mustapha, Hôpital Pellegrin Tripode, Antwerp University Hospital [Edegem] (UZA), Ume University Hospital, Umea University Hospital, Virulence et Latence des Herpesvirus ( HERPES ), Département Virologie ( Dpt Viro ), Institut de Biologie Intégrative de la Cellule ( I2BC ), Université Paris-Sud - Paris 11 ( UP11 ) -Commissariat à l'énergie atomique et aux énergies alternatives ( CEA ) -Université Paris-Saclay-Centre National de la Recherche Scientifique ( CNRS ) -Université Paris-Sud - Paris 11 ( UP11 ) -Commissariat à l'énergie atomique et aux énergies alternatives ( CEA ) -Université Paris-Saclay-Centre National de la Recherche Scientifique ( CNRS ) -Institut de Biologie Intégrative de la Cellule ( I2BC ), Université Paris-Sud - Paris 11 ( UP11 ) -Commissariat à l'énergie atomique et aux énergies alternatives ( CEA ) -Université Paris-Saclay-Centre National de la Recherche Scientifique ( CNRS ) -Université Paris-Sud - Paris 11 ( UP11 ) -Commissariat à l'énergie atomique et aux énergies alternatives ( CEA ) -Université Paris-Saclay-Centre National de la Recherche Scientifique ( CNRS ), Moorfields Eye Hospital, London and Dept. of Ophthalmology, Medical University of Vienna, Vienna, Hôpital Purpan [Toulouse], Université de Brest ( UBO ) -Centre Hospitalier Régional Universitaire de Brest ( CHRU Brest ), Antwerp University Hospital [Edegem], CHU Toulouse [Toulouse], and Intracameral Mydrane Study 2 Grp

Subjects
Male, Mydriatics, Time Factors, Lidocaine, genetic structures, medicine.medical_treatment, [SDV]Life Sciences [q-bio], Cornea, Phenylephrine, Tropicamide, 0302 clinical medicine, Lens Implantation, Intraocular, Tropicamida, Mydriasis, Medicine, Prospective Studies, 030212 general & internal medicine, Anesthetics, Local, Aged, 80 and over, Drugs, Clinical Science, Middle Aged, Clinical Trial, Sensory Systems, 3. Good health, Treatment Outcome, Patient Satisfaction, Anesthesia, Drug Therapy, Combination, Female, medicine.symptom, Conjunctiva, Ophthalmologic Surgical Procedure, medicine.drug, Adult, medicine.medical_specialty, Midríase, 03 medical and health sciences, Cellular and Molecular Neuroscience, Ophthalmology, Humans, Aged, Inflammation, Phacoemulsification, Dose-Response Relationship, Drug, [ SDV ] Life Sciences [q-bio], business.industry, Lidocaína, Facoemulsificação, Cataract surgery, eye diseases, Clinical trial, 030221 ophthalmology & optometry, Human medicine, sense organs, Ophthalmic Solutions, business, Fenilefrina, Follow-Up Studies
Abstract

BACKGROUND/AIMS: To compare the efficacy and safety of intracameral (IC) administration at the beginning of cataract surgery, of Mydrane, a standardised ophthalmic combination of tropicamide 0.02%, phenylephrine 0.31% and lidocaine 1%, to a standard topical regimen. METHODS: In this international phase III, prospective, randomised study, the selected eye of 555 patients undergoing phacoemulsification with intraocular lens (IOL) implantation received 200 μL of Mydrane (Mydrane group) just after the first incision or a topical regimen of one drop each of tropicamide 0.5% and phenylephrine 10% repeated three times (reference group). The primary efficacy variable was achievement of capsulorhexis without additional mydriatics. The non-inferiority of Mydrane to the topical regimen was tested. The main outcome measures were pupil size, patient perception of ocular discomfort and safety. RESULTS: Capsulorhexis without additional mydriatics was performed in 98.9% of patients and 94.7% in the Mydrane and reference groups, respectively. Both groups achieved adequate mydriasis (>7 mm) during capsulorhexis, phacoemulsification and IOL insertion. IOL insertion was classified as 'routine' in a statistically greater number of eyes in the Mydrane group compared with the reference group (p=0.047). Patients in the Mydrane group reported statistically greater comfort than the reference group before IOL insertion (p=0.034). Safety data were similar between groups. CONCLUSIONS: Mydrane is an effective and safe alternative to standard eye drops for initiating and maintaining intraoperative mydriasis and analgesia. Patients who received IC Mydrane were significantly more comfortable before IOL insertion than the reference group. Surgeons found IOL insertion less technically challenging with IC Mydrane. TRIAL REGISTRATION NUMBER: NCT02101359; Results. info:eu-repo/semantics/publishedVersion

Published
2015

14. Automated surgical step recognition in normalized cataract surgery videos

Author

Gwenole Quellec, Béatrice Cochener, Katia Charrière, Guy Cazuguel, Gouenou Coatrieux, Mathieu Lamard, Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), 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 Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM), Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
Databases, Factual, Eye Movements, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Computer science, medicine.medical_treatment, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Video Recording, [SDV.MHEP.CHI]Life Sciences [q-bio]/Human health and pathology/Surgery, Cataract Extraction, Similarity measure, Motion (physics), Cataract surgery, Pattern Recognition, Automated, Automation, medicine, Step recognition, Humans, Computer vision, Zoom, ComputingMethodologies_COMPUTERGRAPHICS, business.industry, Video, Video tracking, Artificial intelligence, Focus (optics), business, Scale (map), Algorithms
Abstract

International audience; Huge amounts of surgical data are recorded during video-monitored surgery. Content-based video retrieval systems intent to reuse those data for computer-aided surgery. In this paper, we focus on real-time recognition of cataract surgery steps: the goal is to retrieve from a database surgery videos that were recorded during the same surgery step. The proposed system relies on motion features for video character- ization. Motion features are usually impacted by eye motion or zoom level variations, which are not necessarily relevant for surgery step recognition. Those problems certainly limit the performance of the retrieval system. We therefore propose to refine motion feature extraction by applying pre-processing steps based on a novel pupil center and scale tracking method. Those pre-processing steps are evaluated for two different motion features. In this paper, a similarity measure adapted from Piciarelli's video surveillance system is evaluated for the first time in a surgery dataset. This similarity measure provides good results and for both motion features, the proposed pre- processing steps improved the retrieval performance of the system significantly.

Published
2015

15. Normalizing videos of anterior eye segment surgeries

Author

Katia Charrière, Mathieu Lamard, Guy Cazuguel, Gwenole Quellec, Béatrice Cochener, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
genetic structures, Computer science, medicine.medical_treatment, Video Recording, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Cataract Extraction, Cataract, Pupil, Decision Support Techniques, Cornea, Videos normalization, Image Interpretation, Computer-Assisted, medicine, Humans, Computer vision, Zoom, Iris (anatomy), business.industry, Anterior eye segment, Cataract surgery, eye diseases, Anterior Eye Segment, Sclera, medicine.anatomical_structure, Surgery, sense organs, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; Anterior eye segment surgeries are usually video-recorded. If we are able to efficiently analyze surgical videos in real-time, new decision support tools will emerge. The main anatomical landmarks in these videos are the pupil boundaries and the limbus, but segmenting them is challenging due to the variety of colors and textures in the pupil, the iris, the sclera and the lids. In this paper, we present a solution to reliably normalize the center and the scale in videos, without explicitly segmenting these landmarks. First, a robust solution to track the pupil center is presented: it uses the fact that the pupil boundaries, the limbus and the sclera / lid interface are concentric. Second, a solution to estimate the zoom level is presented: it relies on the illumination pattern reflected on the cornea. The proposed solution was assessed in a dataset of 186 real-live cataract surgery videos. The distance between the true and estimated pupil centers was equal to 8.0+/-6.9% of the limbus radius. The correlation between the estimated zoom level and the true limbus size in images was high: R = 0.834

Published
2014

16. Indexing of cataract surgery video by content based video retrieval (CBVR)

Author

Martiano, David, Charriere, Katia, Lamard, Mathieu, Quellec, Gwénolé, Cazuguel, Guy, Cochener, Béatrice, Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque, Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), and Université de Brest (UBO)

Subjects
Cataract surgery video, CBVR, Content Based Video Retrieval, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Indexing, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC]
Abstract

International audience; Many surgical computer-aided projects ( CAD ) have emerged in recent years, but none interested in cataract surgery . The aim of our study was to develop a method able to recognize in real time the video stream, identified surgical activities and classify them in a database. We propose to analyze the video stream using a new method describing different levels of granularity : procedure, phases, steps and activities.

Published
2014

17. Multimedia data mining for automatic diabetic retinopathy screening

Author

Christian Roux, Agnès Chabouis, Bruno Lay, Guy Cazuguel, Etienne Decencière, Gwenole Quellec, Mathieu Lamard, Béatrice Cochener, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Centre de Morphologie Mathématique (CMM), MINES ParisTech - École nationale supérieure des mines de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Société ADCIS (ADCIS), Société ADCIS, Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), 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), and Université de Brest (UBO)

Subjects
Telemedicine, Databases, Factual, genetic structures, Image quality, Teleophthalmology, 02 engineering and technology, Multimedia data mining, Sensitivity and Specificity, Retina, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Photography, 0202 electrical engineering, electronic engineering, information engineering, Data Mining, Humans, Medicine, Retinal pathology, Diabetic Retinopathy, business.industry, Diabetic retinopathy screening, Exudates and Transudates, Diabetic retinopathy, medicine.disease, Aneurysm, eye diseases, 3. Good health, Multimedia, ROC Curve, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Optometry, 020201 artificial intelligence & image processing, Abnormality, business, Algorithms
Abstract

International audience; — This paper presents TeleOphta, an automatic sys-tem for screening diabetic retinopathy in teleophthalmology networks. Its goal is to reduce the burden on ophthalmologists by automatically detecting non referable examination records, i.e. examination records presenting no image quality problems and no pathological signs related to diabetic retinopathy or any other retinal pathology. TeleOphta is an attempt to put into practice years of algorithmic developments from our groups. It combines image quality metrics, specific lesion detectors and a generic pathological pattern miner to process the visual content of eye fundus photographs. This visual information is further combined with contextual data in order to compute an abnormality risk for each examination record. The TeleOphta system was trained and tested on a large dataset of 25,702 examination records from the OPHDIAT screening network in Paris. It was able to automatically detect 68% of the non referable examination records while achieving the same sensitivity as a second ophthalmologist. This suggests that it could safely reduce the burden on ophthalmologists by 56%.

Published
2013

18. Motion-based video retrieval with application to computer-assisted retinal surgery

Author

Christian Roux, Guy Cazuguel, Gwenole Quellec, Zakarya Droueche, Béatrice Cochener, Mathieu Lamard, Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
Dynamic time warping, business.product_category, Databases, Factual, Computer science, 0206 medical engineering, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Video Recording, Information Storage and Retrieval, 02 engineering and technology, Ophthalmologic Surgical Procedures, Retina, Motion-based video retrieval, Motion, Histogram, CBVR, Image Interpretation, Computer-Assisted, 0202 electrical engineering, electronic engineering, information engineering, Humans, Segmentation, Computer vision, Digital camera, Block-matching algorithm, Motion compensation, business.industry, 020207 software engineering, Epiretinal Membrane, Video processing, 020601 biomedical engineering, Video compression picture types, Uncompressed video, Surgery, Computer-Assisted, Video tracking, Subtraction Technique, Video denoising, Artificial intelligence, Multiview Video Coding, business, Algorithms
Abstract

International audience; In this paper, we address the problem of computer-aided ophthalmic surgery. In particular, a novel Content-Based Video Retrieval (CBVR) system is presented : given a video stream captured by a digital camera monitoring the current surgery, the system retrieves, within digital archives, videos that resemble the current surgery monitoring video. The search results may be used to guide surgeons' decisions, for example, let the surgeon know what a more experienced fellow worker would do in a similar situation. With this goal, we propose to use motion information contained in MPEG- 4 AVC/H.264 video standard to extract features from videos. We propose two approaches, one of which is based on motion histogram created for every frame of a compressed video sequence to extract motion direction and intensity statistics. The other combine segmentation and tracking to extract region displacements between consecutive frames and therefore char- acterize region trajectories. To compare videos, an extension of the fast dynamic time warping to multidimensional time series was adopted. The system is applied to a dataset of 69 video-recorded retinal surgery steps. Results are promising: the retrieval efficiency is higher than 69%.

Published
2013

19. A polynomial model of surgical gestures for real-time retrieval of surgery videos

Author

Gwenole Quellec, Guy Cazuguel, Christian Roux, Zakarya Droueche, Mathieu Lamard, Béatrice Cochener, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), 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 Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque

Subjects
medicine.medical_specialty, Motion analysis, Surgical gestures modeling, Retrieval, business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, 02 engineering and technology, Space (commercial competition), Motion (physics), Surgery, Polynomial and rational function modeling, 0202 electrical engineering, electronic engineering, information engineering, medicine, Key (cryptography), 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, Surgery videos, business, Gesture
Abstract

International audience; This paper introduces a novel retrieval frame- work for surgery videos. Given a query video, the goal is to retrieve videos in which similar surgical gestures ap- pear. In this framework, the motion content of short video subsequences is modeled, in real-time, using spatiotempo- ral polynomials. The retrieval engine needs to be trained: key spatiotemporal polynomials, characterizing semantically- relevant surgical gestures, are identified through multiple- instance learning. Then, videos are compared in a high-level space spanned by these key spatiotemporal polynomials. The framework was applied to a dataset of 900 manually-delimited clips from 100 cataract surgery videos. High classification performance (Az = 0.816 ± 0.118) and retrieval performance (MAP = 0.358) were observed.

Published
2012

20. Studying Disagreements among Retinal Experts through Image Analysis

Author

Béatrice Cochener, Agnès Chabouis, Gwenole Quellec, Mathieu Lamard, Christian Roux, Guy Cazuguel, Zakarya Droueche, Bruno Lay, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Société ADCIS (ADCIS), Société ADCIS, Direction de la politique Médicale - Assistance Publique-Hôpitaux de Paris (DPM - AP-HP), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Direction Scientifique (DS), and Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)

Subjects
Information retrieval, Contextual image classification, Computer science, business.industry, Image classification, Diabetic retinopathy, medicine.disease, Machine learning, computer.software_genre, Retina, 030218 nuclear medicine & medical imaging, Image (mathematics), Experts disagreement, 03 medical and health sciences, 0302 clinical medicine, Image Processing, Computer-Assisted, medicine, Humans, Artificial intelligence, business, computer, Algorithms, 030217 neurology & neurosurgery
Abstract

International audience; In recent years, many image analysis algorithms have been presented to assist Diabetic Retinopathy (DR) screening. The goal was usually to detect healthy examination records automatically, in order to reduce the number of records that should be analyzed by retinal experts. In this paper, a novel application is presented: these algorithms are used to 1) discover image characteristics that sometimes cause an expert to disagree with his/her peers and 2) warn the expert whenever these characteristics are detected in an examination record. In a DR screening program, each examination record is only analyzed by one expert, therefore analyzing disagreements among experts is challenging. A statistical framework, based on Parzen- windowing and the Patrick-Fischer distance, is presented to solve this problem. Disagreements among eleven experts from the Ophdiat screening program were analyzed, using an archive of 25,702 examination records.

Published
2012

21. Comprehensive Wavelet-Based Image Characterization for Content-Based Image Retrieval

Author

Gwenole Quellec, Béatrice Cochener, Guy Cazuguel, Christian Roux, Mathieu Lamard, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), 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 Bretagne-Pays de la Loire (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM)

Subjects
Discrete wavelet transform, CBIR, Image fusion, Computer science, business.industry, Stationary wavelet transform, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image characterisation, Wavelet transform, 020206 networking & telecommunications, Pattern recognition, 02 engineering and technology, Wavelets, Content-based image retrieval, Wavelet packet decomposition, Wavelet, Image texture, Computer Science::Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business
Abstract

International audience; A novel image characterization based on the wavelet transform is presented in this paper. Previous works on wavelet-based image characterization have focused on adapting a wavelet basis to an image or an image dataset. We propose in this paper to take one step further: images are characterized with all possible wavelet bases, with a given support. A simple image signature based on the standardized moments of the wavelet coefficient distributions is proposed. This signature can be computed for each possible wavelet filter fast. An image signature map is thus obtained. We propose to use this signature map as an image characterization for Content-Based Image Retrieval (CBIR). High retrieval performance was achieved on a medical, a face detection and a texture dataset: a precision at five of 0.625+-0.178, 0.978+-0.045 and 0.640+-0.161 was obtained for these datasets, respectively.

Published
2012

22. Contribution of salivary gland ultrasonography to the diagnosis of Sjögren's syndrome: towards new diagnostic criteria?

Author

Cornec, Divi, Jousse-Joulin, Sandrine, Saraux, Alain, Marhadour, Thierry, Cochener, Béatrice, Nowak, Emmanuel, Boisramé-Gastrin, Sylvie, Pers, Jacques-Olivier, Devauchelle-Pensec, Valérie, Immunologie et Pathologie (EA2216), Université de Brest (UBO)-IFR148, CHRU Brest - Service de Rhumatologie (CHU - BREST - Rhumato), Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Centre d'Investigation Clinique (CIC - Brest), Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM), CHRU Brest - Service d'Odontologie (CHU - BREST - Odontologie), and Michel, Geneviève

Subjects
[SDV.IMM] Life Sciences [q-bio]/Immunology, [SDV.IMM]Life Sciences [q-bio]/Immunology, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2012

23. Weakly supervised classification of medical images

Author

M. Laniard, Gwenole Quellec, Michael D. Abràmoff, Béatrice Cochener, Guy Cazuguel, C. Roux, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Departments of Ophthalmology and Visual Sciences, University of Iowa (DOVS), University of Iowa [Iowa City], Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Direction Scientifique (DS), Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque

Subjects
Contextual image classification, business.industry, Image classification, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, 02 engineering and technology, Weak supervision, Machine learning, computer.software_genre, Retinal image, 030218 nuclear medicine & medical imaging, Image (mathematics), 03 medical and health sciences, Statistical classification, 0302 clinical medicine, ComputingMethodologies_PATTERNRECOGNITION, Diabetic retinopathy, 0202 electrical engineering, electronic engineering, information engineering, Medicine, 020201 artificial intelligence & image processing, Manual segmentation, Artificial intelligence, business, computer, Image resolution
Abstract

International audience; A weakly supervised image classification framework is presented in this paper. Given reference images marked by clinicians as relevant or irrelevant, we learn to automatically detect relevant patterns, i.e. patterns that only appear in relevant images. After training, relevant patterns are sought in unseen images in order to classify each image as relevant or irrelevant. No manual segmentations are required. Because manual segmentation of medical images is extremely time-consuming, existing classification algorithms are usually trained on limited reference datasets. With the proposed framework, much larger medical datasets are now available for training. The proposed approach has been successfully applied to diabetic retinopathy detection in a retinal image dataset (A_z=0.855).

Published
2012

24. A Multiple-Instance Learning Framework for Diabetic Retinopathy Screening

Author

Michael D. Abràmoff, Mathieu Lamard, Béatrice Cochener, Guy Cazuguel, Ali Erginay, Etienne Decencière, Gwenole Quellec, Bruno Lay, Optimisation Continue des Actions Thérapeutiques par l'Intégration d'Informations Multimodales, Université de Brest (UBO)-Télécom Bretagne-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université de Brest (UBO), University of Iowa [Iowa City], Centre de Morphologie Mathématique (CMM), Mines Paris - PSL (École nationale supérieure des mines de Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Service d'Ophtalmologie, Hôpital Lariboisière, AP-HP (Service d'Ophtalmologie), Hôpital Lariboisière-Fernand-Widal [APHP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Departments of Ophthalmology and Visual Sciences, University of Iowa (DOVS), MINES ParisTech - École nationale supérieure des mines de Paris, Société ADCIS (ADCIS), and Société ADCIS

Subjects
[SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Image classifier, Health Informatics, 02 engineering and technology, Sensitivity and Specificity, Pattern Recognition, Automated, 030218 nuclear medicine & medical imaging, multiple-instance learning, 03 medical and health sciences, 0302 clinical medicine, Artificial Intelligence, Image Interpretation, Computer-Assisted, 0202 electrical engineering, electronic engineering, information engineering, medicine, Humans, Mass Screening, Radiology, Nuclear Medicine and imaging, Computer vision, [SDV.MHEP.OS]Life Sciences [q-bio]/Human health and pathology/Sensory Organs, Radiological and Ultrasound Technology, Lesion detection, Contextual image classification, Extramural, business.industry, Diabetic retinopathy screening, Reproducibility of Results, Pattern recognition, pathology screening, Diabetic retinopathy, Image Enhancement, medicine.disease, Computer Graphics and Computer-Aided Design, lesion detection, Retinal image, diabetic retinopathy, [SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, [SDV.MHEP.OS] Life Sciences [q-bio]/Human health and pathology/Sensory Organs, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Classifier (UML), Algorithms, Retinoscopy
Abstract

International audience; A novel multiple-instance learning framework, for automated image classification, is presented in this paper. Given reference images marked by clinicians as relevant or irrelevant, the image classifier is trained to detect patterns, of arbitrary size, that only appear in relevant images. After training, similar patterns are sought in new images in order to classify them as either relevant or irrelevant images. Therefore, no manual segmentations are required. As a consequence, large image datasets are available for training. The proposed framework was applied to diabetic retinopathy screening in 2-D retinal image datasets: Messidor (1,200 images) and e-ophtha, a dataset of 25,702 examination records from the Ophdiat screening network (107,799 images). In this application, an image (or an examination record) is relevant if the patient should be referred to an ophthalmologist. Trained on one half of Messidor, the classifier achieved high performance on the other half of Messidor (A_z=0.881) and on e-ophtha (A_z=0.761). We observed, in a subset of 273 manually segmented images from e-ophtha, that all eight types of diabetic retinopathy lesions are detected.

Published
2012

25. Recherche en temps réel de séquences vidéo similaires par le contenu

Author

Christian Roux, Guy Cazuguel, Gwenole Quellec, Mohammed Zakarya Droueche, Béatrice Cochener, Mathieu Lamard, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), 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 Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque, Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Direction Scientifique (DS), and Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)

Subjects
Flexibility (engineering), Dynamic time warping, Information retrieval, Computer science, Real-time processing, Recherche de vidéos en temps réel, Ondelettes, Electrical and Electronic Engineering, Wavelets, Distance measures, Temps réel, Content-based video retrieval, Video retrieval
Abstract

International audience; Nous proposons dans cet article une méthode originale pour rechercher, dans des séquences vidéo, des sous-séquences similaires. En introduisant de la flexibilité temporelle dans la caractérisation des sous-séquences, cette méthode permet d'éviter l'utilisation de mesures de distance flexibles (telles le Dynamic Time Warping) qui ont l'inconvénient d'être lentes. La méthode proposée permet donc de rechercher, en temps réel, des sous-séquences vidéos similaires parmi plusieurs centaines de milliers d'exemples. La méthode proposée est adaptative ; un algorithme d'apprentissage rapide est présenté. Les performances ont été évaluées avec succès sur une base de données de 1707 clips vidéos (> 800.000 sous-séquences). A terme, notre objectif est de proposer un système de génération d'alertes et/ou de préconisations, en temps réel, dans le cadre de l'aide à la chirurgie suivie par vidéo.

Published
2012

26. De nouveaux critères de diagnostic du Syndrome de Gougerot-Sjögren : valeur diagnostique de l'échographie des glandes salivaires et des sous-populations lymphocytaires B

Author

Cornec, Divi, Saraux, Alain, Jousse-Joulin, Sandrine, Marhadour, Thierry, Cochener, Béatrice, Boisramé-Gastrin, Sylvie, Pers, Jacques-Olivier, Youinou, Pierre, Devauchelle-Pensec, Valérie, Immunologie et Pathologie (EA2216), Université de Brest (UBO)-IFR148, CHRU Brest - Service de Rhumatologie (CHU - BREST - Rhumato), Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), CHRU Brest - Service d'Odontologie (CHU - BREST - Odontologie), Laboratoire d'Immunologie et Immunothérapie, and Michel, Geneviève

Subjects
[SDV.IMM] Life Sciences [q-bio]/Immunology, [SDV.IMM]Life Sciences [q-bio]/Immunology, ComputingMilieux_MISCELLANEOUS
Abstract

National audience

Published
2011

27. Fouille d'images multi-instance et multi-échelle appliquée au dépistage de la rétinopathie diabétique

Author

Quellec, Gwénolé, Cazuguel, Guy, Lamard, Mathieu, Cochener, Béatrice, Roux, Christian, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Direction Scientifique (DS), Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque

Abstract

International audience; Nous présentons dans cet article une nouvelle caractérisation d'images permettant de mesurer la qualité des images ou encore de détecter des lésions complexes ou rares, deux problèmes communs aux systèmes de dépistage automatique de la Rétinopathie Diabétique (RD). Cette caractérisation d'images, basée sur la transformée en ondelettes, permet la recherche d'anomalies dans les images à différentes échelles. La recherche repose sur un apprentissage multi-instance : des experts indiquent les examens présentant des anomalies, sans indiquer leur localisation dans les images, et l'algorithme apprend à détecter ces anomalies automatiquement. L'efficacité de l'algorithme a été montrée sur une base de données de 25.702 examens de dépistage : les examens ininterprétables (resp. les patients atteints de RD proliférante) sont détectés avec une aire A_z=0,907 (resp. A_z=0,792) sous la courbe ROC.

Published
2011

28. Content-Based Medical Video Retrieval Based on Region Motion Trajectories

Author

Béatrice Cochener, Guy Cazuguel, Mathieu Lamard, C. Roux, Zakarya Droueche, Gwenole Quellec, 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 Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Brestois Santé Agro Matière (IBSAM), Université de Brest (UBO), Optimisation Continue des Actions Thérapeutiques par l'Intégration d'Informations Multimodales, Université de Brest (UBO)-Télécom Bretagne-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Rhodia, Centre de Recherches d'Aubervilliers (RHODIA), RHODIA, Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
Dynamic time warping, business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, k-means clustering, K-means clustering, 02 engineering and technology, Kalman filter, computer.file_format, Motion (physics), MPEG-4, Match moving, 020204 information systems, Video Motion estimation, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Computer vision, Artificial intelligence, Cluster analysis, business, computer, Content-based video retrieval
Abstract

International audience; In this paper, we address the problem of contentbased medical video retrieval. We propose the use of motion tracking to generate video features. First, we extract motion vectors derived from the 'MPEG-4 AVC/H.264' standard. Second, motion segmentation of the image sequence is performed by a combination of k-means clustering and motion consistency verification. Third, we used the well-known Kalman filter to track region motion between consecutive frames. This produced region's correspondences are concatenated to construct the region's motion trajectories. Finally, to compare videos, we adopted an extension of dynamic time warping (EDTW) to multidimensional time series. Results are promising: a retrieval precision at 5 of 62 % was achieved.

Published
2011

29. Fouille d'images multi-instance et multi-résolution appliquée au dépistage de la rétinopathie diabétique

Author

Quellec, Gwénolé, Abràmoff, Michael D., CAZUGUEL, Guy, Lamard, Mathieu, Cochener, Béatrice, Roux, Christian, Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Departments of Ophthalmology and Visual Sciences, University of Iowa (DOVS), University of Iowa [Iowa City], Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Direction Scientifique (DS), and Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)

Subjects
Fouille d'images, Ophtalmologie, Multi-instance, Multiresolution, Rétinopathies diabétiques
Abstract

International audience; Objectifs : Des études récentes ont montré l'intérêt potentiel de l'interprétation automatique des photographies de fond d'oeil pour le dépistage de la rétinopathie diabétique (RD). Une nouvelle approche est proposée pour résoudre deux problèmes communs à tous les systèmes de dépistage automatique de la RD : la mesure de la qualité des images et la détection des lésions complexes ou rares. Matériel et Méthodes : Une nouvelle caractérisation d'images, basée sur la transformée en ondelettes, est proposée pour rechercher les anomalies dans les images à différentes résolutions (la notion de normalité étant spécifique à chaque problème). L'algorithme de recherche repose sur un apprentissage multi-instance : des experts indiquent les examens présentant des anomalies, sans indiquer leur localisation dans les images, et l'algorithme apprend à détecter ces anomalies automatiquement. L'algorithme a été validé sur une base de données constituée de 25.702 examens de dépistage, soit au total 107.799 images. Résultats : L'algorithme est capable de détecter les examens dont la qualité des images est insuffisante avec une aire Az=0,907 sous la courbe ROC. Il permet en outre de détecter les patients atteints de RD proliférante avec une aire Az=0,792 et de les différencier des patients atteints de RD non-proliférante avec une aire Az=0,819. Discussion : Cette approche, couplée avec une détection automatique des premiers signes de la RD (des lésions fréquentes de petites tailles), permettra un dépistage automatique plus robuste de la RD ainsi que des autres pathologies rencontrées dans les centres de dépistage.

Published
2011

30. Case retrieval in medical databases by fusing heterogeneous information

Author

Guy Cazuguel, Mathieu Lamard, Christian Roux, Béatrice Cochener, Gwenole Quellec, Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Brest (UBO)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque

Subjects
[MATH.MATH-PR] Mathematics [math]/Probability [math.PR], Databases, Factual, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Computer science, Information Storage and Retrieval, 02 engineering and technology, computer.software_genre, 030218 nuclear medicine & medical imaging, Pattern Recognition, Automated, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Image Processing, Computer-Assisted, [INFO.INFO-DB] Computer Science [cs]/Databases [cs.DB], MESH: Pattern Recognition, Automated, Diagnosis, Computer-Assisted, Heterogeneous information retrieval, Radiological and Ultrasound Technology, Database, MESH: Image Processing, Computer-Assisted, Computer Science Applications, Radiology Information Systems, Feature (computer vision), MESH: Radiology Information Systems, 020201 artificial intelligence & image processing, Data mining, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms, Mammography, Diagnostic Imaging, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, MESH: Bayes Theorem, Digital content, MESH: Mammography, MESH: Algorithms, Image processing, 03 medical and health sciences, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Humans, Relevance (information retrieval), Electrical and Electronic Engineering, MESH: Diabetic Retinopathy, Medical databases, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Image fusion, MESH: Humans, [INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB], Information retrieval, Diabetic Retinopathy, MESH: Diagnostic Imaging, MESH: Diagnosis, Computer-Assisted, MESH: Information Storage and Retrieval, Bayesian network, Bayes Theorem, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], MESH: Databases, Factual, [MATH.MATH-PR]Mathematics [math]/Probability [math.PR], Metadata, [SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, Database Management Systems, Information fusion, computer, Software, MESH: Database Management Systems
Abstract

International audience; A novel content-based heterogeneous information retrieval framework, particularly well suited to browse medical databases and support new generation computer aided diagnosis (CADx) systems, is presented in this paper. It was designed to retrieve possibly incomplete documents, consisting of several images and semantic information, from a database; more complex data types such as videos can also be included in the framework. The proposed retrieval method relies on image processing, in order to characterize each individual image in a document by their digital content, and information fusion. Once the available images in a query document are characterized, a degree of match, between the query document and each reference document stored in the database, is defined for each attribute (an image feature or a metadata). A Bayesian network is used to recover missing information if need be. Finally, two novel information fusion methods are proposed to combine these degrees of match, in order to rank the reference documents by decreasing relevance for the query. In the first method, the degrees of match are fused by the Bayesian network itself. In the second method, they are fused by the Dezert-Smarandache theory: the second approach lets us model our confidence in each source of information (i.e., each attribute) and take it into account in the fusion process for a better retrieval performance. The proposed methods were applied to two heterogeneous medical databases, a diabetic retinopathy database and a mammography screening database, for computer aided diagnosis. Precisions at five of 0.809 ± 0.158 and 0.821 ± 0.177, respectively, were obtained for these two databases, which is very promising.

Published
2010

31. Content Based Medical Image Retrieval Based on BEMD: use of Generalized Gaussian Density to model BIMFs coefficients

Author

JAI ANDALOUSSI, Said, Lamard, Mathieu, CAZUGUEL, Guy, Tairi, Hamid, MEKNASSI, Mohammed, Cochener, Béatrice, Roux, Christian, Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Département de mathématiques et informatique - Faculté des sciences, Université de Fès, Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
BEMD, Generalized Gaussian density, Content-based image retrieval
Abstract

International audience; In this paper, we address the problem of medical diagnosis aid through content based image retrieval methods (CBIR). We propose to characterize images without extracting local features, by using global information extracted from the image Bidimensional Empirical Mode Decomposition (BEMD). This method decompose image into a set of functions named Bidimensional Intrinsic Mode Functions (BIMF) and a residue. The generalized Gaussian density function (GGD) is used for modelling the coefficients derived from each BIMF, and to measure similarity between images we compute the similarity between GGDs by using the Kullback-Leibler Divergence (KLD). Retrieval efficiency is given for different databases including a diabetic retinopathy , mammography and a face database. Results are promising: the retrieval efficiency is higher than 95% for some cases .

Published
2010

32. Reconstruction 3D du segment antérieur du globe oculaire par l'utilisation de données radio-fréquence échographique et d'un modèle déformable

Author

Lamard, Mathieu, Kohandani Tafreshi, Marzieh, Josselin, Pierre Marie, Cazuguel, Guy, Cochener, Béatrice, Optimisation Continue des Actions Thérapeutiques par l'Intégration d'Informations Multimodales, Université de Brest (UBO)-Télécom Bretagne-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), and Télécom Bretagne, Bibliothèque

Subjects
Modèle déformable, Reconstruction 3D, Globe oculaire, Ultra-sons
Abstract

Cette étude vise à reconstruire le segment antérieur du globe oculaire (SA) afin de mieux définir la taille des implants phakes. La méthode proposée adapte un modèle générique 3D sur les données radio fréquence (RF).

Published
2010

33. Effects of rituximab therapy on quality of life in patients with primary Sjögren's syndrome

Author

Devauchelle-Pensec V, Morvan J, Ac, Rat, Jousse-Joulin S, Pennec Y, Jo, Pers, Jamin C, Yves Renaudineau, Quintin-Roué I, Cochener B, Youinou P, Saraux A, CHRU Brest - Service de Rhumatologie (CHU - BREST - Rhumato), Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Maladies chroniques, santé perçue, et processus d'adaptation (APEMAC), Université Paris Descartes - Paris 5 (UPD5)-Université de Lorraine (UL), Centre d'Investigation Clinique - Epidemiologie Clinique/essais Cliniques Nancy, Cancéropôle du Grand Est-Institut National de la Santé et de la Recherche Médicale (INSERM), Service d'Epidémiologie et Evaluations Cliniques [CHRU Nancy] (Pôle S2R), Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy), Service de Rhumatologie [CHRU Nancy], Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), Hôpital Morvan [Brest], CHRU Brest - Laboratoire d'Anatomo-Pathologie (CHU - AnaPath), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Immunologie et Pathologie (EA2216), Université de Brest (UBO)-IFR148, Centre d'Investigation Clinique (CIC - Brest), Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM), Université de Lorraine (UL), Lymphocyte B et Auto-immunité (LBAI), Université de Brest (UBO)-Institut Brestois Santé Agro Matière (IBSAM), Laboratoire de dynamique et structures des matériaux moléculaires (LDSMM), Université de Lille, Sciences et Technologies-Université du Littoral Côte d'Opale-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Immunologie et Immunothérapie, Laboratoire de Traitement de l'Information Medicale (LaTIM), 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 d’Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520 (IEMN), Centre National de la Recherche Scientifique (CNRS)-Université de Lille-Université Polytechnique Hauts-de-France (UPHF)-Ecole Centrale de Lille-Université Polytechnique Hauts-de-France (UPHF)-Institut supérieur de l'électronique et du numérique (ISEN), Unite mixte de recherche en droit comparé (UMRDC), Université Panthéon-Sorbonne (UP1)-Centre National de la Recherche Scientifique (CNRS), Centre Hospitalier Universitaire, CHRU Brest - Service de Rhumatologie ( CHU - BREST - Rhumato ), Centre Hospitalier Régional Universitaire de Brest ( CHRU Brest ), Maladies chroniques, santé perçue, et processus d'adaptation ( APEMAC ), Université Paris Descartes - Paris 5 ( UPD5 ) -Université de Lorraine ( UL ), Cancéropôle du Grand Est-Institut National de la Santé et de la Recherche Médicale ( INSERM ), Service d'Epidémiologie et Evaluations Cliniques [CHRU Nancy] ( Pôle S2R ), Centre Hospitalier Régional Universitaire de Nancy ( CHRU Nancy ), Institut d’Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520 ( IEMN ), Ecole Centrale de Lille-Institut supérieur de l'électronique et du nunérique (ISEN)-Université de Valenciennes et du Hainaut-Cambresis ( UVHC ) -Université de Lille-Centre National de la Recherche Scientifique ( CNRS ), Unite mixte de recherche en droit comparé ( UMRDC ), Université Panthéon-Sorbonne ( UP1 ) -Centre National de la Recherche Scientifique ( CNRS ), CHRU Brest - Laboratoire d'Anatomo-Pathologie ( CHU - AnaPath ), Université de Brest ( UBO ), Université de Brest ( UBO ) -Centre Hospitalier Régional Universitaire de Brest ( CHRU Brest ), Immunologie et Pathologie ( EA2216 ), Université de Brest ( UBO ) -IFR148, Centre d'Investigation Clinique ( CIC - Brest ), and Université de Brest ( UBO ) -Institut National de la Santé et de la Recherche Médicale ( INSERM )

Subjects
Male, MESH: Antirheumatic Agents, Health Status, Severity of Illness Index, Antibodies, Monoclonal, Murine-Derived, hemic and lymphatic diseases, Surveys and Questionnaires, MESH : Female, MESH: Health Status, MESH: Treatment Outcome, MESH: Middle Aged, MESH : Questionnaires, MESH : Adult, Middle Aged, MESH : Antirheumatic Agents, humanities, Sjogren's Syndrome, Treatment Outcome, [SDV.MHEP.RSOA]Life Sciences [q-bio]/Human health and pathology/Rhumatology and musculoskeletal system, MESH: Young Adult, Antirheumatic Agents, MESH : Severity of Illness Index, Female, MESH: Rituximab, MESH: Pain, Rituximab, MESH : Pain, Adult, Adolescent, MESH : Male, MESH : Young Adult, Pain, MESH : Treatment Outcome, Young Adult, MESH : Adolescent, [ SDV.MHEP ] Life Sciences [q-bio]/Human health and pathology, MESH: Severity of Illness Index, Humans, MESH : Middle Aged, MESH : Health Status, MESH: Surveys and Questionnaires, MESH: Adolescent, MESH: Humans, MESH: Questionnaires, MESH : Humans, MESH: Quality of Life, MESH: Adult, MESH : Quality of Life, MESH: Male, MESH : Antibodies, Monoclonal, Murine-Derived, stomatognathic diseases, MESH: Sjogren's Syndrome, MESH: Antibodies, Monoclonal, Murine-Derived, Quality of Life, MESH : Sjogren's Syndrome, MESH: Female, [SDV.MHEP]Life Sciences [q-bio]/Human health and pathology
Abstract

International audience; OBJECTIVES: To assess the efficacy of the anti-CD20 antibody rituximab in improving physical function and health-related quality of life (HRQoL) in patients with active primary Sjögren's syndrome (pSS), as well as the duration and sources of HRQoL improvements. METHODS: Sixteen patients with pSS received rituximab infusions (375 mg/m2) at weeks 0 and 1 and were followed up for 36 weeks. All patients fulfilled 2002 American-European Consensus Group criteria for pSS and had active disease defined as scores >50 mm on two of four 100-mm visual analogue scales (VAS) evaluating global disease activity, fatigue, pain, and dryness. Standardised evaluations including the Short Form 36 Health Survey (SF-36) were conducted. SF-36 score changes from baseline to weeks 12, 24, and 36 were assessed. RESULTS: Baseline mean SF-36 scores were considerably decreased, compared to the general same-age population. Role-physical (14.1 ± 27.4), role-emotional (12.5 ± 29.9), vitality (26.2 ± 14.3), and general health (32.6 ± 11.2) were the dimensions with the worst scores. Twelve weeks after rituximab, the mental component summary score was improved in 15 patients (mean improvement, 31.2 ± 36.4, p=0.001) and the physical component summary score in 14 patients (mean improvement, 16.9 ± 26.2, p=0.049). Further improvements occurred from week 12 to week 24, and most of the gains were sustained at week 36. Improvements in the physical and mental component summary scores failed to correlate with improvements in the VAS scores. CONCLUSIONS: Substantial alterations in HRQoL were noted in patients with pSS. Rituximab infusions without corticosteroid therapy produced meaningful improvements in HRQoL. Controlled studies of rituximab are needed.

Published
2010

34. Recherche d'image par le contenu appliquée à la rétinopathie diabétique

Author

Hadj Hafsi Bekri, Laura, Lamard, Mathieu, Quellec, Gwénolé, Cazuguel, Guy, Cochener, Béatrice, Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque

Subjects
[SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Recherche par le contenu, Rétinopathies diabétiques, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience

Published
2009

35. Diabetic Retinopathy Screening Method Using Adapted Wavelets Decompositions and Template Matching

Author

Lamard, Mathieu, Quellec, Gwénolé, Cazuguel, Guy, Roux, Christian, Abràmoff, Michael D., Cochener, Béatrice, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Direction Scientifique (DS), Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Departments of Ophthalmology and Visual Sciences, University of Iowa (DOVS), University of Iowa [Iowa City], Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque

Subjects
genetic structures, Adaptated wavelets, Diabetic retinopathy, Screening, Wavelets
Abstract

International audience; Purpose: We propose an automatic method to detect microaneurysms in retina photographs. Automating this task, which is currently performed manually, would bring more objectivity and reproducibility in the current clinical practice. Methods: The screening method follows several steps. As a template of microaneurysms we use a generalized Gaussian. This template and retina Images are decomposed in several subbands by using the wavelet transform. We propose to detect the lesions by locally matching the template in a selection of subbands. To improve the method performance, we have searched for the best adapted wavelet within the lifting scheme framework. Results: Results are evaluated on 120 retinal images analyzed by an expert and the optimal wavelet is compared to different conventional mother wavelets. Depending on the imaging modality (color photographs, green filtered photographs and angiographs), microaneurysms were detected with a sensitivity of respectively 89.62%, 90.24% and 93.74% and a positive predictive value of respectively 89.50%, 89.75% and 91.67%, which is better than previously published methods. Conclusions: In this study, we have proposed a new method for detecting microaneurysms in retina. Given its simplicity and relative genericity, this method may be an answer for large screening of Diabetic Retinopathy.

Published
2009

36. Multimodal Information Retrieval to Assist Diabetic Retinopathy Diagnosis

Author

Quellec, Gwénolé, Lamard, Mathieu, CAZUGUEL, Guy, Roux, Christian, Abràmoff, Michael D., Cochener, Béatrice, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Direction Scientifique (DS), Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Departments of Ophthalmology and Visual Sciences, University of Iowa (DOVS), University of Iowa [Iowa City], Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque

Abstract

International audience; Purpose: we propose to use different Case Based Reasoning (CBR) methods to retrieve diabetic patient files: should an ophthalmologist have doubts on his diagnosis, he can send the available data about his patient to the system, that selects the most similar cases, along with their medical interpretations, in order to assist his diagnosis. Methods: the system is applied to a diabetic retinopathy (DR) database, consisting of 67 patient files. Each patient file consists of up to 20 retinal images and up to 11 information fields about the patient's medical history; each patient has been graded according to its disease severity level (ICDRS classification). The objective is to retrieve patient files with the same grade. Information about each patient is incomplete and heterogeneous (there are both digital images and text information), so we proposed three different retrieval methods suitable to manage both issues: the first one is based on decision trees, the second one on a Bayesian network, and the third one on the DSmT theory. Images are characterized by their digital content: a feature vector is extracted from their wavelet transform to describe their textural content, and microaneurysms are detected. The retrieval methods are assessed by the mean precision at 5, i.e. the mean percentage of cases relevant for a query, among the topmost 5 results. Results: a mean precision at 5 of 81.0%, 70.4% and 81.8% was achieved with these three methods, respectively. The scores range from 58.9% for the less frequent grade to 87.4% for the most frequent; they range from 42.1% for sparse cases (10% of available data) to 91.2% for comprehensive cases. Conclusions: retrieving entire patient files, we can achieve a significantly higher precision than simply retrieving similar images (a mean precision at 5 of 46.1% is achieved in the latter case). The proposed multimodal retrieval methods are precise enough to be useful in a DR diagnosis aid system.

Published
2009

37. Multimodal medical case retrieval using Bayesian networks and the Dezert-Smarandache theory

Author

Christian Roux, Gwenole Quellec, L. Bekri, Guy Cazuguel, M. Laniard, Béatrice Cochener, Quellec, Gwénolé, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Brest (UBO)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Télécom Bretagne - Brest, Télécom Bretagne, Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT)

Subjects
Computer science, 020209 energy, 02 engineering and technology, Machine learning, computer.software_genre, Case based reasoning, Semantic network, Database index, Data retrieval, 0202 electrical engineering, electronic engineering, information engineering, Case-based reasoning, Dezert-Smarandache theory, Image retrieval, Cognitive models of information retrieval, [SDV.IB] Life Sciences [q-bio]/Bioengineering, Information retrieval, Diabetic Retinopathy, business.industry, Bayesian network, Bayesian networks, Image indexing, Human–computer information retrieval, 020201 artificial intelligence & image processing, [SDV.IB]Life Sciences [q-bio]/Bioengineering, Artificial intelligence, business, computer
Abstract

International audience; Most medical images are now digitized and stored with semantic information, leading to medical case databases. They may be used for aid to diagnosis, by retrieving similar cases to those in examination. But the information are often incomplete, uncertain and sometimes conflicting, so difficult to use. In this paper, we present a Case Based Reasoning (CBR) system for medical case retrieval, derived from the Dezert-Smarandache theory, which is well suited to handle those problems. We introduce a case retrieval specific frame of discernment theta, which associates each element of theta with a case in the database; we take advantage of the flexibility offered by the DSmT's hybrid models to finely model the database. The system is designed so that heterogeneous sources of information can be integrated in the system: in particular images, indexed by their digital content, and symbolic information. The method is evaluated on two classified databases: one for diabetic retinopathy follow-up (DRD) and one for screening mammography (DDSM). On these databases, results are promising: the retrieval precision at five reaches 81.8% on DRD and 84.8% on DDSM.

Published
2008

38. Recherche de cas médicaux multimodaux à l'aide d'arbres de décision

Author

Guy Cazuguel, Gwenole Quellec, Béatrice Cochener, Mathieu Lamard, L. Bekri, Christian Roux, Latim, Latim, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Brest (UBO)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Département Réseaux, Sécurité et Multimédia (RSM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT)

Subjects
[SDV.IB] Life Sciences [q-bio]/Bioengineering, 010104 statistics & probability, 0202 electrical engineering, electronic engineering, information engineering, Biomedical Engineering, Biophysics, 020201 artificial intelligence & image processing, [SDV.IB]Life Sciences [q-bio]/Bioengineering, 02 engineering and technology, 0101 mathematics, 01 natural sciences
Abstract

National audience; Nous proposons dans cet article un système de raisonnement à base de cas pour la recherche de dossiers patients similaires à un cas donné en requête. Nous nous intéressons à des dossiers patients constitués de plusieurs images accompagnées d'informations contextuelles (telles que l'âge, le sexe et les antécédents médicaux du patient). Plusieurs sources d'informations (parfois incomplètes) sont en effet généralement nécessaires pour diagnostiquer une pathologie. Nous proposons un outil de recherche basé sur les arbres de décision, qui sont bien adaptés pour traiter de l'information hétérogène et incomplète. Pour prendre en compte des images dans ce système, nous leur associons une signature définie à partir de leur contenu numérique. La méthode est évaluée sur une base de rétinopathies diabétiques classifiées. Sur cette base de données, les résultats sont intéressants : la précision atteint 79,5 % pour une fenêtre de retrouvaille de cinq cas, doublant pratiquement les résultats obtenus en n'utilisant que le contenu numérique d'une image.

Published
2008

39. Multimodal medical case retrieval using the Dezert-Smarandache theory

Author

Béatrice Cochener, Christian Roux, Guy Cazuguel, Gwenole Quellec, Mathieu Lamard, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Brest (UBO)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Télécom Bretagne - Brest, Télécom Bretagne, Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Quellec, Gwénolé, and Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT)

Subjects
Computer science, Digital content, 0206 medical engineering, Information Storage and Retrieval, 02 engineering and technology, computer.software_genre, Case based reasoning, Article, Pattern Recognition, Automated, Image Interpretation, Computer-Assisted, Contextual information, 0202 electrical engineering, electronic engineering, information engineering, medicine, Mammography, Case-based reasoning, Dezert-Smarandache theory, Flexibility (engineering), [SDV.IB] Life Sciences [q-bio]/Bioengineering, Information retrieval, Diabetic Retinopathy, medicine.diagnostic_test, Frame (networking), Image Enhancement, 020601 biomedical engineering, Radiology Information Systems, Image indexing, Subtraction Technique, Database Management Systems, 020201 artificial intelligence & image processing, [SDV.IB]Life Sciences [q-bio]/Bioengineering, Data mining, Element (category theory), computer
Abstract

4 pages; International audience; Most medical images are now digitized and stored with semantic information, leading to medical case databases. They may be used for aid to diagnosis, by retrieving similar cases to those in examination. But the information are often incomplete, uncertain and sometimes conflicting, so difficult to use. In this paper, we present a Case Based Reasoning (CBR) system for medical case retrieval, derived from the Dezert-Smarandache theory, which is well suited to handle those problems. We introduce a case retrieval specific frame of discernment theta, which associates each element of theta with a case in the database; we take advantage of the flexibility offered by the DSmT's hybrid models to finely model the database. The system is designed so that heterogeneous sources of information can be integrated in the system: in particular images, indexed by their digital content, and symbolic information. The method is evaluated on two classified databases: one for diabetic retinopathy follow-up (DRD) and one for screening mammography (DDSM). On these databases, results are promising: the retrieval precision at five reaches 81.8% on DRD and 84.8% on DDSM.

Published
2008

40. Multimedia medical case retrieval using decision trees

Author

Christian Roux, Guy Cazuguel, Gwenole Quellec, Béatrice Cochener, L. Bekri, Mathieu Lamard, Département Réseaux, Sécurité et Multimédia (RSM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Brest (UBO)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), and Quellec, Gwénolé

Subjects
Databases, Factual, Medical Records Systems, Computerized, Computer science, Digital content, Decision tree, MEDLINE, Image processing, 02 engineering and technology, Article, 03 medical and health sciences, 0302 clinical medicine, Text mining, Data retrieval, 0202 electrical engineering, electronic engineering, information engineering, Image Processing, Computer-Assisted, Humans, Case-based reasoning, Medical history, Decision Making, Computer-Assisted, [SDV.IB] Life Sciences [q-bio]/Bioengineering, Information retrieval, Diabetic Retinopathy, business.industry, 030221 ophthalmology & optometry, 020201 artificial intelligence & image processing, [SDV.IB]Life Sciences [q-bio]/Bioengineering, business
Abstract

International audience; In this paper, we present a Case Based Reasoning (CBR) system for the retrieval of medical cases made up of a series of images with contextual information (such as the patient age, sex and medical history). Indeed, medical experts generally need varied sources of information (which might be incomplete) to diagnose a pathology. Consequently, we derive a retrieval framework from decision trees, which are well suited to process heterogeneous and incomplete information. To be integrated in the system, images are indexed by their digital content. The method is evaluated on a classified diabetic retinopathy database. On this database, results are promising: the retrieval sensitivity reaches 79.5% for a window of 5 cases, which is almost twice as good as the retrieval of single images alone. As a comparison, the retrieval sensitivity is 52.3% for a standard multimodal case retrieval using a linear combination of heterogeneous distances.

Published
2007

41. Real-time retrieval of similar videos with application to computer-aided retinal surgery

Author

Guy Cazuguel, Béatrice Cochener, Zakarya Droueche, Mathieu Lamard, Gwenole Quellec, Christian Roux, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Direction Scientifique (DS), Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Service d'ophtalmologie [Brest], and Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)

Subjects
Dynamic time warping, business.product_category, Computer science, 0206 medical engineering, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Content-based Video retrieval, Retina, 0202 electrical engineering, electronic engineering, information engineering, medicine, Humans, Computer vision, Digital camera, Flexibility (engineering), Retinal surgery, business.industry, Temporal flexibility, 020601 biomedical engineering, Range (mathematics), medicine.anatomical_structure, Surgery, Computer-Assisted, Video tracking, Computer-aided, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

International audience; This paper introduces ongoing research on computer-aided ophthalmic surgery. In particular, a novel Content-Based Video Retrieval (CBVR) system is presented. Its purpose is the following: given a video stream captured by a digital camera monitoring the surgery, the system should retrieve, in real-time, similar video subsequences in video archives. In order to retrieve semantically-relevant videos, most existing CBVR systems rely on temporally flexible distance measures such as Dynamic Time Warping. These distance measures are slow and therefore do not allow real-time retrieval. In the proposed system, temporal flexibility is introduced in the way video subsequences are characterized, which allows the use of simple and fast distance measures. As a consequence, realtime retrieval of similar video subsequences, among hundreds of thousands of examples, is now possible. Besides, the proposed system is adaptive: a fast training procedure is presented. The system has been successfully applied to automated recognition of retinal surgery steps on a 69-video dataset: areas under the Receiver Operating Characteristic curves range from Az=0.809 to Az=0.989.

42. 3D visual fMRI using binocular stimulation

Author

Guillaume Koch, Elise Bannier, Agathe Baumann, Stéphanie Ferragut, Mathieu Lamard, Christian Barillot, Eric Stindel, Romuald Seizeur, Bannier, Elise, Université de Bretagne Occidentale - UFR Médecine et Sciences de la Santé (UBO UFR MSS), Université de Brest (UBO), Vision, Action et Gestion d'informations en Santé (VisAGeS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Université de Brest (UBO)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Service de chirurgie orthopédique, traumatologique et réparatrice [Brest], Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), Service de neurochirurgie [Brest], Hôpital de la Cavale Blanche - CHRU Brest (CHU - BREST ), CRITT Santé Bretagne, Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), and Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT)

Subjects
[SDV.IB] Life Sciences [q-bio]/Bioengineering, [SDV.IB]Life Sciences [q-bio]/Bioengineering, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

43. A General Framework For Detecting Diabetic Retinopathy Lesions In Eye Fundus Images

Author

Bruno Lay, Gwenole Quellec, Pascale Massin, Etienne Decencière, Béatrice Cochener, Christian Roux, Mathieu Lamard, Guy Cazuguel, Laboratoire de Traitement de l'Information Medicale (LaTIM), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest)-Université de Brest (UBO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut Mines-Télécom [Paris] (IMT), Université de Brest (UBO), Service d'ophtalmologie [Brest], Université de Brest (UBO)-Centre Hospitalier Régional Universitaire de Brest (CHRU Brest), 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), Département Image et Traitement Information (ITI), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Centre de Morphologie Mathématique (CMM), MINES ParisTech - École nationale supérieure des mines de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Société ADCIS (ADCIS), Société ADCIS, Centre Hospitalier Lariboisière, and Université Paris Diderot - Paris 7 (UPD7)

Subjects
Contextual image classification, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-space segmentation, Pattern recognition, 02 engineering and technology, Diabetic retinopathy, Image segmentation, medicine.disease, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Statistical classification, ComputingMethodologies_PATTERNRECOGNITION, 0302 clinical medicine, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, medicine, 020201 artificial intelligence & image processing, Manual segmentation, Computer vision, Artificial intelligence, business, Image resolution, ComputingMilieux_MISCELLANEOUS, Retinopathy
Abstract

A weakly supervised image classification framework is presented in this paper. Given reference images marked by clinicians as relevant or irrelevant, we learn to automatically detect relevant patterns, i.e. patterns that only appear in relevant images. After training, relevant patterns are sought in unseen images in order to classify each image as relevant or irrelevant. No manual segmentations are required. Because manual segmentation of medical images is extremely time-consuming, existing classification algorithms are usually trained on limited reference datasets. With the proposed framework, much larger medical datasets are now available for training. The proposed approach has been successfully applied to diabetic retinopathy detection in the Messidor dataset (A z =0.855). Moreover, we observed, in a new dataset of 473 manually segmented images, that all eight types of diabetic retinopathy lesions are detected.

44. Real-time recognition of surgical tasks in eye surgery videos.

Author

Quellec G, Charrière K, Lamard M, Droueche Z, Roux C, Cochener B, and Cazuguel G

Subjects
Algorithms, Artificial Intelligence, Computer Systems, Eye Diseases surgery, Humans, Image Enhancement methods, Reproducibility of Results, Sensitivity and Specificity, Image Interpretation, Computer-Assisted methods, Imaging, Three-Dimensional methods, Ophthalmologic Surgical Procedures methods, Pattern Recognition, Automated methods, Photography methods, Surgery, Computer-Assisted methods, Video Recording methods
Abstract

Nowadays, many surgeries, including eye surgeries, are video-monitored. We present in this paper an automatic video analysis system able to recognize surgical tasks in real-time. The proposed system relies on the Content-Based Video Retrieval (CBVR) paradigm. It characterizes short subsequences in the video stream and searches for video subsequences with similar structures in a video archive. Fixed-length feature vectors are built for each subsequence: the feature vectors are unchanged by variations in duration and temporal structure among the target surgical tasks. Therefore, it is possible to perform fast nearest neighbor searches in the video archive. The retrieved video subsequences are used to recognize the current surgical task by analogy reasoning. The system can be trained to recognize any surgical task using weak annotations only. It was applied to a dataset of 23 epiretinal membrane surgeries and a dataset of 100 cataract surgeries. Three surgical tasks were annotated in the first dataset. Nine surgical tasks were annotated in the second dataset. To assess its generality, the system was also applied to a dataset of 1,707 movie clips in which 12 human actions were annotated. High task recognition scores were measured in all three datasets. Real-time task recognition will be used in future works to communicate with surgeons (trainees in particular) or with surgical devices., (Copyright © 2014 Elsevier B.V. All rights reserved.)

Published
2014
Full Text
View/download PDF

45. Effect of intrastromal corneal ring segment shift on clinical outcome: one year results for low myopia.

Author

Cochener B, Savary-LeFloch G, and Colin J

Subjects
Adult, Astigmatism etiology, Astigmatism physiopathology, Corneal Stroma physiopathology, Corneal Topography, Foreign-Body Migration physiopathology, Humans, Myopia physiopathology, Prosthesis Implantation, Refraction, Ocular, Retrospective Studies, Treatment Outcome, Visual Acuity physiology, Biocompatible Materials, Corneal Stroma surgery, Foreign-Body Migration etiology, Myopia surgery, Prostheses and Implants adverse effects
Abstract

Purpose: To evaluate the effect of intrastromal corneal ring segment (ICRS) shift on clinical outcome., Setting: Chu Morvan Ophthalmology Service, Brest, France., Methods: Forty-seven eyes with myopia from -1.0 to -5.0 diopters (D) had ICRS surgery according to United States Food and Drug Administration protocol using a 2-segment implant design. Visual acuity, refractive, videotopographic, and biomicroscopic results in eyes that did not have contact between segments (Group A, n = 26) and in eyes that did have contact (Group B, n = 21) were compared., Results: Soon after surgery, migration of and subsequent contact between the implant segments occurred in 21 eyes (45%). Contact between the inferior ends was most common, occurring in 19 eyes; in the remaining 2 eyes, the superior ends of the implant touched. Superior contact was associated with superficial channels, wound-healing problems, and ICRS explantation. No segment shift was observed after the first postoperative week. No significant differences in visual acuity, qualitative vision, or density of intrastromal deposits were noted between the 2 groups. However, at 6 months there was more induced with-the-rule cylinder in Group B (mean +1.3 D +/- 0.7 [SD]) than in Group A (mean +0.7 +/- 0.5 D). Astigmatism was clinically significant in only 3 cases at 3 months., Conclusions: Induced cylinder remains a limitation of the ICRS procedure, and segment contact appears to influence the rate of induced cylinder. Overall, however, the ICRS procedure produces promising results. Research efforts are underway to address induced cylinder and channel deposits associated with ICRS surgery.

Published
2000
Full Text
View/download PDF

46. Excimer laser photorefractive keratectomy to correct astigmatism.

Author

Gallinaro C, Toulemont PJ, Cochener B, and Colin J

Subjects
Adolescent, Adult, Astigmatism pathology, Astigmatism physiopathology, Cornea pathology, Cornea physiopathology, Follow-Up Studies, Humans, Image Processing, Computer-Assisted, Lasers, Excimer, Middle Aged, Myopia physiopathology, Myopia surgery, Postoperative Complications, Refraction, Ocular, Visual Acuity, Astigmatism surgery, Cornea surgery, Photorefractive Keratectomy methods
Abstract

Purpose: To evaluate the efficacy of excimer laser photorefractive keratectomy (PRK) to correct astigmatism., Setting: Hôpital Morvan, Brest, France., Methods: A 193 nm excimer laser was used to perform toric ablation with an expanding slit to flatten the cornea in the steeper meridian and/or to correct myopia with an iris diaphragm in 72 eyes (55 patients): 68 eyes for compound myopic astigmatism and 4 for astigmatism only., Results: Preoperative cylinder was -2.14 diopters (D) +/- 1.99 (SD) (range -0.50 to -5.50 D); 6 months postoperatively, it was -1.75 +/- 1.34 D (range -0.25 to -5.25 D). Preoperative spherical equivalent was -5.33 +/- 3.22 D (range -0.25 to -14.50 D); 6 months postoperatively, it was -0.86 +/- 2.32 D (range 2.50 to -9.75 D). The axial error was within 30 degrees. Uncorrected visual acuity was 0.50 or better in 64.5% of patients., Conclusions: Overall patient satisfaction seemed the result of the myopic correction; cylindrical correction was incomplete. Future software refinements should improve the results. In particular, single elliptical ablation seems to offer theoretical advantages.

Published
1996
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results