Bayesian logistic shape model inference: Application to cochlear image segmentation |
| |
| Institution: | 1. Inria, Epione Team, Université Côte d’Azur, Sophia Antipolis, France;2. Head and Neck University Institute, Nice University Hospital, 31 Avenue de Valombrose, Nice 06100, France;3. Department of Radiology, Centre Hospitalier Universitaire de Nice, 31 Avenue de Valombrose, Nice 06100, France;4. Oticon Medical, 14 Chemin de Saint-Bernard Porte, Vallauris 06220, France;1. BCN MedTech, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain;2. LS2N, UMR CNRS 6004, Ecole Centrale de Nantes, Nantes, France;3. Institute of Clinical Radiology, LMU München, Munich, Germany;4. Department of Trauma Surgery, Klinikum rechts der Isar, Technische Universität München, Munich, Germany;5. Computer Aided Medical Procedures, Technische Universität München, Munich, Germany;6. Johns Hopkins University, Baltimore, USA;7. ICREA, Barcelona, Spain;1. Computer Aided Medical Procedures, Technische Universität München, Boltzmannstraße 3, Garching bei München 85748, Germany;2. Carl Zeiss Meditec AG, Rudolf-Eber-Str. 11, Oberkochen 73447, Germany;3. Computer Aided Medical Procedures, Johns Hopkins University, 3400 North Charles Street, Baltimore, MD 21218, USA;4. German Center for Vertigo and Balance Disorders, Ludwig-Maximilians Universität München, Marchioninistr. 15, München 81377, Germany;5. Carl Zeiss Meditec AG, Göschwitzer Str. 51-52, Jena 07745, Germany;6. Vienna Institute for Research in Ocular Surgery, A Karl-Landsteiner Institute, Hanusch Hospital, Vienna, Austria;1. Department of Mathematics and Statistics, University of Cyprus, Cyprus;2. Department of Accounting and Business Analytics, Alberta School of Business, University of Alberta, Canada;3. Department of Statistics, London School of Economics, United Kingdom;1. National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Marshall Laboratory of Biomedical Engineering, AI Research Center for Medical Image Analysis and Diagnosis, Shenzhen University, Shenzhen 518060, China;2. Affiliated Brain Hospital of Guangzhou Medical University (Guangzhou Huiai Hospital), Guangzhou, China;3. Department of Child Psychiatry and Rehabilitation, Affiliated Shenzhen Maternity & Child Healthcare Hospital, Southern Medical University, Shenzhen, China;4. Health Science Center, First Affiliated Hospital of Shenzhen University, Shenzhen University, Shenzhen 518050, China;5. Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, PA 19104, United States;6. Center for the Study of Applied Psychology, Guangdong Key Laboratory of Mental Health and Cognitive Science and School of Psychology, South China Normal University, Guangzhou 510631, China;1. Instituto de Telecomunicações, Morro do Lena - Alto do Vieiro, Leiria 2411-901, Portugal;2. University of Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, Pinhal de Marrocos, Coimbra 3030-290, Portugal;3. ESTG, Polytechnic of Leiria, Morro do Lena - Alto do Vieiro, Leiria 2411-901, Portugal;1. National Laboratory for Scientific Computing, LNCC/MCTI, Petrópolis, Brazil;2. Consejo Nacional de Investigaciones Científicas, CONICET, Argentina;3. Universidad Nacional del Centro, UNICEN, Tandil, Argentina;4. Hospital Israelita Albert Einstein, São Paulo, Brazil;5. National Institute of Science and Technology in Medicine Assisted by Scientific Computing, INCT-MACC, Petrópolis, RJ, Brazil;6. Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland;7. Interventional Cardiology Department, MedStar Washington Hospital Center, Washington, DC, USA;8. Georgetown University School of Medicine, Washington, DC, USA |
| |
| Abstract: | Incorporating shape information is essential for the delineation of many organs and anatomical structures in medical images. While previous work has mainly focused on parametric spatial transformations applied to reference template shapes, in this paper, we address the Bayesian inference of parametric shape models for segmenting medical images with the objective of providing interpretable results. The proposed framework defines a likelihood appearance probability and a prior label probability based on a generic shape function through a logistic function. A reference length parameter defined in the sigmoid controls the trade-off between shape and appearance information. The inference of shape parameters is performed within an Expectation-Maximisation approach in which a Gauss-Newton optimization stage provides an approximation of the posterior probability of the shape parameters. This framework is applied to the segmentation of cochlear structures from clinical CT images constrained by a 10-parameter shape model. It is evaluated on three different datasets, one of which includes more than 200 patient images. The results show performances comparable to supervised methods and better than previously proposed unsupervised ones. It also enables an analysis of parameter distributions and the quantification of segmentation uncertainty, including the effect of the shape model. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
