The project is set in the context of precision psychiatry and focuses on bipolar disorder (BP), a widespread psychiatric condition that is actively studied because of its prevalence in the population, estimated to be above 2%. Using two datasets that have been acquired at the MRI center (BP patients and healthy controls), we study multimodal neuroimaging biomarkers for bipolar disorder. The focus is on capturing the spatio-temporal structure of functional MRI signals, to be combined with structural and diffusion MRI. Building data representations using dimensionality reduction techniques, they will feed a prediction pipeline together with clinical scores and omics data. This is key to quantitatively study the heterogeneity in BP patients, in particular with respect to treatment response and patient subgroups. We rely on unique multimodal datasets collected at INT / APHM (Marseille hospital), together with larger datasets on specific modalities (MRI only, omics only, clinical only) to test new innovative algorithms for data fusion and dataset alignments. If successful, this approach will later be extended to other psychiatric diseases, like schizophrenia in the context of a French collaboration on psychiatric disorders.
This project exhibits challenges that need to be tackled at both conceptual and practical levels, using high-performance computing for big data.
The project will cover several areas on both computational and clinical sides. We provide an interdisciplinary environment with experts in three fields: computational neuroscience, machine learning and psychiatry. The supervision will be ensured by Matthieu Gilson (https://matthieugilson.eu/), Emmanuel Daucé (http://emmanuel.dauce.free.fr/) and Antoine Lefrère (https://www.researchgate.net/profile/Antoine-Lefrere). The PhD candidate will work in within two teams, BraiNets (https://www.int.univ-amu.fr/recherche-int/equipes/brainets) and CanoP (https://www.int.univ-amu.fr/recherche-int/equipes/canop).
The PhD will be held at Institut de Neurosciences de la Timone (INT), a laboratory dedicated to the study of the structure and functioning of the brain and spinal cord. INT conducts basic, translational and clinical research on a major cognitive functions. It hosts the Computational Neuroscience Center (CONECT, https://conect-int.github.io/), an incubator to promote theoretical and computational neuroscience.
Send the following documents to the email contact address. Candidates will be interviewed for 30 minutes, including a presention of themselves and their scientific trajectory (10 minutes).