S
Stéphane Chemouny
Publications - 9
Citations - 273
Stéphane Chemouny is an academic researcher. The author has contributed to research in topics: Segmentation & Graphical model. The author has an hindex of 7, co-authored 8 publications receiving 249 citations.
Papers
More filters
Book ChapterDOI
Joint tumor segmentation and dense deformable registration of brain MR images
TL;DR: A novel graph-based concurrent registration and segmentation framework that is modular with respect to the data and regularization term and efficient linear programming is used to solve both problems simultaneously.
Journal ArticleDOI
Concurrent tumor segmentation and registration with uncertainty-based sparse non-uniform graphs.
Sarah Parisot,William M. Wells,William M. Wells,Stéphane Chemouny,Hugues Duffau,Nikos Paragios,Nikos Paragios +6 more
TL;DR: A graph-based concurrent brain tumor segmentation and atlas to diseased patient registration framework modeled using a unified pairwise discrete Markov Random Field model on a sparse grid superimposed to the image domain is presented.
Journal ArticleDOI
A Probabilistic Atlas of Diffuse WHO Grade II Glioma Locations in the Brain
Sarah Parisot,Sarah Parisot,Amélie Darlix,Cédric Baumann,Sonia Zouaoui,Yordanka Yordanova,Marie Blonski,Valérie Rigau,Stéphane Chemouny,Luc Taillandier,Luc Bauchet,Hugues Duffau,Nikos Paragios,Nikos Paragios +13 more
TL;DR: A probabilistic atlas mapping the preferential locations of diffuse WHO grade II gliomas in the brain is constructed through a sparse graph whose nodes correspond to clusters of tumors clustered together based on their spatial proximity, and characterizes which preferential location the tumor belongs to and consequently which behavior it could be associated to.
Proceedings ArticleDOI
Automatic detection of liver tumors
TL;DR: Very promising classification results using an important volume of clinically annotated data (86% sensitivity, 82% specificity) demonstrate the potentials of the proposed advanced non-linear machine learning techniques.
Proceedings ArticleDOI
Graph-based detection, segmentation & characterization of brain tumors
TL;DR: The method exploits prior knowledge in the form of a sparse graph representing the expected spatial positions of tumor classes along with image-based classification techniques along with spatial smoothness constraints towards producing a reliable detection map within a unified graphical model formulation.