ACMES team

 

Genethon is a pioneer in the development of gene therapy vectors that can benefit to several hundred neuromuscular diseases of genetic origin. Pre-clinical studies are conducted to gain precise knowledge of muscle physiology and to improve the understanding of the disease based on the analysis of histological sections, i.e. slices of organs observed by microscopy. In this starting PhD, our work aims at processing these large histological slices by exploiting deep learning to analyze and classify the neighborhoods of the pathological areas of interest using a 'frugal' computing platform, i.e., inexpensive local hardware resources so that a maximum number of clinicians can easily benefit from it while keeping a total control on data privacy. The core of our approach is to build a scaling processing architecture composed of a pair of differentiable blocks. First, an image-based block will extract a segmentation of the slices into related components. In a second step, a graph-based approach, built on the set of previously detected components, will be deployed to perform the classification. At each step, our goal will be to maximize the computational performance of the execution medium, in order to make our approach compatible with modest computational resources - an open problem in the context of deep learning, which is particularly computationally and energy intensive.