The thesis will be carried out within the frame of the interdisciplinary project “Brain Computer Interface” (BCI) at CEA/LETI/CLINATEC® (Grenoble, France). The overall goal of the project is to improve the autonomy of individuals with severe motor disability. The BCI system is based on the measurement and processing of neuronal activity from the cerebral cortex (ElectroCorticoGram, ECoG) of subject executing motor imagery task. Clinical trial of chronical ECoG based motor BCI system is in progress affording a unique opportunity of long term ECoG based BCI clinical study. The crucial step of BCI is identification of decoding model. The mission of PhD fellow will be participating at exploring a feasibility of enhanced decoding/control system for motor BCI integrating error neural response observed at sensorimotor cortex using WIMAGINE® recording device during closed loop clinical BCI study: test the detectability using AI approaches of error related neuronal responses or other neural responses from sensorimotor cortex with implantable chronic recording device WIMAGINE®; develop enhanced BCI decoder integrating error related neuronal response to decoder; develop an algorithm for enhanced decoder identification online and in real time; implement enhanced decoder (MATLAB/C/C++) and integrate it to CLINATEC® BCI software platform; test and optimized the enhanced decoder in closed loop BCI setting with patient(s). The candidate will be integrated into the signal processing team and will collaborate with software and electrical engineers, biologists and medical doctors.
The thesis will be carried out within the frame of the interdisciplinary project “Brain Computer Interface” (BCI) at CEA/LETI/CLINATEC® on MINATEC® Campus (Grenoble, France). CLINATEC® is a research institute being built by CEA (Commissariat à l’Energie Atomique et aux Energies Alternatives) to bring the preclinical and clinical proof of concept of medical devices based on advanced technologies.
The overall goal of the “Brain Computer Interface” project at CEA/LETI/CLINATEC® is to improve the autonomy of individuals with severe motor disability thanks to self-paced BCI systems used in institution or at home. The BCI system is based on the measurement and processing of neuronal activity from the cerebral cortex of subject executing motor imagery task. A fully implantable chronic recording device WIMAGINE® records the electrical activity of the sensory-motor cortex at the level of cortex surface ElectroCorticoGram (ECoG). The collected data are sent to an external receiving station to process the information and to detect the changes of the brain activity induced by the patient’s intention to execute a movement. After the signal decoding the commands are sent to activate the effector. Clinical trial of chronical intracranial (ECoG-based) motor BCI system is in progress affording a unique opportunity of long term closed loop ECoG-based clinical BCI study.
Robust and accurate decoding of neuronal activity in real time is a key point of BCI systems as they are benefit patients if the decoder reflect the user’s intentions with short delay and with a fidelity enabling him to efficiently interact with his environment. Set of decoding algorithms were developed by signal processing team of CLINATEC® to solve the problem of stable neuronal activity decoding. They are published in articles, defended by patents, tested offline and online in preclinical experiments in ECoG NHP, in MEG experiments with healthy subjects, and, finally in a clinical trial with quadriplegic subject. The decoding algorithms intends to decode neural patterns emerging in sensorimotor cortex and related to limbs movement. Other neural patterns were reported recently to be observed in sensory motor cortex in closed loop BCI experiments in humane and in NHP studies. In particular, error response detection in sensorimotor cortex was reported recently to improve decoding performance in both intracranial and microelectrode array -based intracortical BCIs.
The mission of PhD fellow will be participating at exploring a feasibility of enhanced decoding/control system for motor BCI integrating error neural response observed at sensorimotor cortex using WIMAGINE® recording device during closed loop clinical BCI study:
The candidate will be integrated into the signal processing team and will collaborate with software and electrical engineers, biologists and medical doctors. He/she will participate in the BCI experiments in the context of a clinical trial to test and to optimize the algorithms.
Master degree or equivalent with strong knowledge in Signal processing, Applied mathematics, Machine learning, with skills in Matlab/C/C++ software development.
CEA/ DRT / LETI / CLINATEC
CEA/GRENOBLE 17 rue des Martyrs 38054 Grenoble CEDEX 9
AKSENOVA Tetiana / Téléphone : 04.38.78.03.20 /Email : firstname.lastname@example.org
1.Hochberg LR, Bacher D, Jarosiewicz B, Masse NY, Simeral JD, Vogel J, Haddadin S, Liu J, Cash SS, van der Smagt P, Donoghue JP., Reach and grasp by people with tetraplegia using a neurally controlled robotic arm, Nature, 2012; 485(7398):372-5.
2.Eliseyev, A., Mestais, C., Charvet, G., Sauter, F., Abroug, N., Arizumi, N., ... & Benabid, A. L. (2014, August). CLINATEC® BCI platform based on the ECoG-recording implant WIMAGINE® and the innovative signal-processing: Preclinical results. In Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE (pp. 1222-1225). IEEE.
3.Mestais, C. S., Charvet, G., Sauter-Starace, F., Foerster, M., Ratel, D., & Benabid, A. L. (2015). WIMAGINE: Wireless 64-Channel ECoG Recording Implant for Long Term Clinical Applications. Neural Systems and Rehabilitation Engineering, IEEE Transactions on, 23(1), 10-21.
4.Eliseyev, A., Auboiroux, V., Costecalde, T., Langar, L., Charvet, G., Mestais, C., ... & Benabid, A. L. (2017). Recursive Exponentially Weighted N-way Partial Least Squares Regression with Recursive-Validation of Hyper-Parameters in Brain-Computer Interface Applications. Scientific reports, 7(1), 16281.
5.Schaeffer, M. C., & Aksenova, T. (2017). Switching Markov decoders for asynchronous trajectory reconstruction from ECoG signals in monkeys for BCI applications. Journal of Physiology-Paris.
6.Gürel, T., & Mehring, C. (2012). Unsupervised adaptation of brain-machine interface decoders. Frontiers in neuroscience, 6.
7.Milekovic, T., Ball, T., Schulze-Bonhage, A., Aertsen, A., & Mehring, C. (2013). Detection of error related neuronal responses recorded by electrocorticography in humans during continuous movements. PloS one, 8(2), e55235.
8.Even-Chen, N., Stavisky, S. D., Pandarinath, C., Nuyujukian, P., Blabe, C. H., Hochberg, L. R., ... & Shenoy, K. V. (2017). Feasibility of Automatic Error Detect-and-undo system in Human Intracortical Brain-Computer Interfaces. IEEE Transactions on Biomedical Engineering.
(c) GdR 720 ISIS - CNRS - 2011-2018.