MAP-RECOVER: Artificial intelligence-based prediction of post-stroke motor recovery using multimodal neuroimaging and brain-computer interfaces
Stroke is a leading cause of long-term motor disability, and many patients show limited benefit from conventional rehabilitation. This project aims to develop artificial intelligence methods to predict, early after stroke, which patients are most likely to benefit from brain-computer interface (BCI)-assisted rehabilitation.
The PhD candidate will use multimodal neuroimaging data, including ultra-high-field 7T fMRI, MEG, and ECoG recordings, to characterize brain lesions, motor networks, and the neural mechanisms underlying motor intention. Machine learning and deep learning approaches (e.g., convolutional neural networks, transformers, and multimodal fusion) will be developed to integrate these data, predict motor recovery, and identify biomarkers of rehabilitation potential. The models will be validated using clinical datasets from ongoing BCI rehabilitation studies.
Expected outcomes include predictive tools for personalized rehabilitation, improved patient selection for BCI therapies, and a better understanding of post-stroke neuroplasticity.
Candidate profile: Master's degree in Computational or Cognitive Neuroscience, Biomedical Engineering, Artificial Intelligence, or a related field. Strong programming skills in Python and experience with machine learning are required; knowledge of neuroimaging analysis tools is an asset.
The PhD will be carried out at Clinatec (CEA Grenoble, France) in collaboration with the Laboratory of Psychology and NeuroCognition (LPNC, CNRS, Université Grenoble Alpes).Link to post:https://www.linkedin.com/feed/update/urn:li:ugcPost:7480197083472338945