Automated Diagnosis and Biomarkers for Neuropathologies from Whole-Brain Neuroimaging

This project investigates how classification pipelines for neuropahtologies can integrate different modalities of magnetic resonance imaging (MRI), namely functional, structural and recent advances like sodium [Maarouf Neurology 2017, Grapperon Radiology 2019]. It also builds on previous work on functional MRI (fMRI) that showed how the brain dynamics can be predictive for diagnosis and prognosis, i.e. using both spatial and temporal information in fMRI signals [Gilson Network Neuroscience 2020, Adhikari Brain Communication 2021]. This multidisciplinary project will use modern machine learning techniques to combine the various types of neuroimaging data. The classification pipeline will be tested firtsly on various neurological pathologies like amyotrophic lateral sclerosis, multiple sclerosis, Alzheimer disease, in close collaborations with the CRMBM imaging center. Possible extensions toward neuropschiatric disorders will also be considered.

Starting date

Student/Post-doc Profiles

Skills to acquire:

• neuropathtologies: whole-brain imaging, multimodal IRM, processing pipeline,
• applied mathematics: machine learning, statistical inference, signal processing, dynamic system, network theory
• computer science: programming in Python, high-performance computing

Research Environment

The research will be conducted at the Institut des Neurosciences de la Timone (INT), in Marseille. The project will be conducted in close collaboration with the experimental team that collected the data. The Aix-Marseille University, the CNRS/INSERM laboratories and the APHM hospital center also offer a multidisciplinary environment for neuroscience. Projects range from behavior and cognition to neuropathologies, with strong interactions between the experimental and theoretical teams.

References:

• Gilson M, Zamora-López G, Pallarés V, Adhikari MH, Senden M, Tauste Campo A, Mantini D, Corbetta M, Deco G, Insabato A (2020) Model-based whole-brain effective connectivity to study distributed cognition in health and disease. Netw Neurosci 4: 338-373; doi: 10.1162/netn_a_00117
• Adhikari MH, Griffis J, Siegel JS, Thiebaut de Schotten M, Deco G, Instabato A, Gilson M**, Corbetta M** (2021) Effective connectivity extracts clinically relevant prognostic information from resting state activity in stroke. Brain Commun 3: fcab233; doi: 10.1093/braincomms/fcab233; medrxiv preprint
• Maarouf A, Audoin B, Pariollaud F, Gherib S, Rico A, Soulier E, Confort-Gouny S, Guye M, Schad L, Pelletier J, Ranjeva JP, Zaaraoui W (2017) Increased total sodium concentration in gray matter better explains cognition than atrophy in MS. Neurology 88: 289-295
• Grapperon AM, Ridley B, Verschueren A, Maarouf A, Confort-Gouny S, Fortanier E, Schad L, Guye M, Ranjeva JP, Attarian S, Zaaraoui W (2019) Quantitative Brain Sodium MRI Depicts Corticospinal Impairment in Amyotrophic Lateral Sclerosis. Radiology 292: 422-428