Deep learning approaches for segmentation of multiple sclerosis lesions on brain MRI

Multiple Sclerosis (MS) is a demyelinating disease of the central nervous system which causes lesions in brain tissues, especially visible in white matter with magnetic resonance imaging (MRI). The diagnosis of MS lesions, which is often performed visually with MRI, is an important task as it can help characterizing the progression of the disease and monitoring the efficacy of a candidate treatment. automatic detection and segmentation of MS lesions from MRI images offer the potential for a faster and more cost-effective performance which could also be immune to expert bias segmentation. In this thesis, we study automated approaches to segment MS lesions from MRI images. The thesis begins with a review of the existing literature on MS lesion segmentation and discusses their general limitations. We then propose three novel approaches that rely on Convolutional Neural Networks (CNNs) to segment MS lesions. The first approach demonstrates that the parameters of a CNN learned from natural images, transfer well to the tasks of MS lesion segmentation. In the second approach, we describe a novel multi-branch CNN architecture with end-to-end training that can take advantage of each MRI modalities individually. In that work, we also investigated the combination of MRI modalities leading to the best segmentation performance. In the third approach, we show an effective and novel generalization method for MS lesion segmentation when data are collected from multiple MRI scanning sites and as suffer from (site-)domain shifts. Finally, this thesis concludes with open questions that may benefit from future work. This thesis demonstrates the potential role of CNNs as a common methodological building block to address clinical problems in MS segmentation.