[1049| Stroke Research Group

Our lab focuses on the development of new therapeutic strategies to improve clinical outcome after stroke. To this aim, we investigate the mechanisms underpinning recovery, using innovative machine learning models combining clinical, imaging, physiological, and biological variables.

Pharamacological manipulation of brain networks to improve recovery after stroke

How do brain networks anticipate, endure, respond, and adapt to limit the consequences of a stroke? Our lab is interested in investigating how changes in network architecture are clinically relevant acutely and during recovery. We are currently conducting a Randomized Clinical Trial to investigate whether Maraviroc supports plasticity in the peri-infarct cortex to ultimately improve functional outcome. To address these issues, we use the most recent developments in structural, functional, and dynamic MRI connectivity analysis.

Intermanual transfer to promote motor recovery after stroke

Generalization refers to our ability to apply what has been learned in one context to other situations. For example, tennis players pick up on table tennis faster than people who have never played racket sports before. Intermanual transfer is an example of generalization that is observed when learning to perform a motor task with one hand results in improved performance of the untrained hand. We investigate, based on an innovative behavioral and imaging approach in human, whether the intermanual transfer is of clinical importance to promote motor recovery after stroke.

Deep learning to improve outcome prediction and therapeutic strategies after stroke 

Early after stroke, predicting long-term outcome is essential to select the most efficient therapy. Our objective is to improve outcome prediction using machine learning models combining imaging, physiological, biological and clinical variables. We currently develop new therapeutic strategies based on our experience in the development of deep learning models.