Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.
Brain-Computer Interfaces (BCIs) provide a mean to access the damaged motor network of the brain after stroke, and could be used to drive and promote beneficial plasticity. Among the available therapeutic approaches, Functional Electrical Stimulation (FES) is often applied during rehabilitation to directly engage muscles of the affected side of the body, especially when the residual functionality is weak or absent. In this paper, we describe a BCI system for stroke rehabilitation that decodes the attempt to execute a sustained hand extension movement from non-invasive human EEG and activates FES of affected arm muscles, accordingly. The system allows the physical therapist to monitor current brain activity through an EEG-guided visualization. Preliminary results on 4 chronic stroke patients show consistency in the EEG features selected for further training. Three of the patients completed the testing, and they all show recovery of target muscle function. Our results support the idea that BCI can be used to promote beneficial plasticity even during chronic phase, and justify further testing on a larger population.
Loading
Loading
Loading
Loading
Loading
Andrea Biasiucci, Ricardo Andres Chavarriaga Lozano, Robert Leeb, Hesam Sagha
Touradj Ebrahimi, Ulrich Hoffmann, Jean-Marc Vesin
Touradj Ebrahimi, Ulrich Hoffmann, Jean-Marc Vesin