M
Matthieu Le
Researcher at French Institute for Research in Computer Science and Automation
Publications - 16
Citations - 452
Matthieu Le is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Image segmentation & Bayesian probability. The author has an hindex of 10, co-authored 16 publications receiving 379 citations. Previous affiliations of Matthieu Le include Harvard University.
Papers
More filters
Journal ArticleDOI
Radiotherapy planning for glioblastoma based on a tumor growth model: improving target volume delineation
Jan Unkelbach,Bjoern H. Menze,Bjoern H. Menze,Ender Konukoglu,Florian Dittmann,Matthieu Le,Matthieu Le,Nicholas Ayache,Helen A. Shih +8 more
TL;DR: The tumor growth model provides a method to account for anisotropic growth patterns of glioma, and may therefore provide a tool to make target delineation more objective and automated.
Patent
Automated segmentation utilizing fully convolutional networks
TL;DR: In this article, the authors used CNNs to autonomously segment parts of an anatomical structure represented by image data, such as 3D MRI data, in order to localize pathologies or functional characteristics of the myocardial muscle.
Journal ArticleDOI
Extended Modality Propagation: Image Synthesis of Pathological Cases
TL;DR: A novel generative model for the synthesis of multi-modal medical images of pathological cases based on a single label map that allows the generation of a large dataset of synthetic cases, which could prove useful for the training, validation, or benchmarking of image processing algorithms.
Journal ArticleDOI
Personalized Radiotherapy Planning Based on a Computational Tumor Growth Model
Matthieu Le,Hervé Delingette,Jayashree Kalpathy-Cramer,Elizabeth R. Gerstner,Tracy T. Batchelor,Jan Unkelbach,Nicholas Ayache +6 more
TL;DR: Two methods to derive the radiotherapy prescription dose distribution are introduced, which are based on minimizing integral tumor cell survival using the maximum a posteriori or the expected tumor cell density and it is shown how the method allows the user to compute a patient specific radiotherapy planning conformal to the tumor infiltration.
Book ChapterDOI
FastVentricle: Cardiac Segmentation with ENet
TL;DR: FastVentricle as mentioned in this paper is an FCN architecture for ventricular segmentation based on the recently developed ENet architecture, which is 4 × times faster and runs with 6 times less memory than the previous state-of-the-art segmentation architecture while maintaining excellent clinical accuracy.