Learning a CNN on multiple sclerosis lesion segmentation with self-supervision

Best paper awardInternational audienceMultiple Sclerosis (MS) is a chronic, often disabling, auto-immune disease affecting the central nervous system and characterized by demyelination and neuropathic alterations. Magnetic Resonance (MR) images plays a pivotal role in the diagnosis and the screening of MS. MR images identify and localize demyelinat-ing lesions (or plaques) and possible associated atrophic lesions whose MR aspect is in relation with the evolution of the disease. We propose a novel MS lesions segmentation method for MR images, based on Convolutional Neural Networks (CNNs) and partial self-supervision and studied the pros and cons of using self-supervision for the current segmentation task. Investigating the transferability by freezing the firsts convolutional layers, we discovered that improvements are obtained when the CNN is retrained from the first layers. We believe such results suggest that MRI segmentation is a singular task needing high level analysis from the very first stages of the vision process, as opposed to vision tasks aimed at day-today life such as face recognition or traffic sign classification. The evaluation of segmentation quality has been performed on full image size binary maps assembled from predictions on image patches from an unseen database