(Deep) Machine learning for the prediction of patient coma outcome based on multimodality neuroimaging

See a detailled description in the attached pdf

Scientific context

The IMAGINA project funded in October 2018 by the french National Research Agency (ANR) targets the challenging issue of providing an accurate diagnosis of patients being in acute coma. IMAGINA gathers specialists with complementary expertise in image processing and machine learning (CREATIS), computational neurosciences (CRNL), medicine (HCL) and medical imaging (CERMEP).

CREATIS is in charge of developing an automated diagnosis tool that will evaluate the patient coma status (degree of consciousness disorder) by combining the information provided by multimodal imaging with the most advanced machine learning methods.

Objectives

The objective of this master project is to initiate the first developments in deep learning for the statistical analysis of the multimodality (MRI/TEP) imaging database of coma patients acquired on the Lyon hybrid PET/MR scanner. This includes encoding the multidimensional and multimodal medical images into a unified deep framework, especially exploring the potential of sparse convolutional networks and existing interpretation tools such as attention networks and activation mapping techniques to provide visual insights about the origin of the model predictions.

Skills

Candidate should have strong background either in machine learning and/or deep learning or image processing and some experience in both fields as well as good programming skills.

We are looking for an enthusiastic and autonomous student with strong motivation and interest in multidisciplinary research (image processing and machine learning in a medical context). The candidate will also have the opportunity to interact with a PhD student also working within the IMAGINA project.