On November 1, the TU Ilmenau is launching an international research project to develop a medical technology procedure that uses EEG data from the brain in combination with a rehabilitation robot to promote the rehabilitation of stroke patients. So-called brain-computer interfaces are intended to help restore the limited mobility of the legs caused by a stroke. The research project, which the TU Ilmenau is carrying out together with the University of Innsbruck, is being funded by the German Research Foundation with 331,000 euros for three years.
Stroke is one of the most common causes of disability worldwide. Improving rehabilitation after a stroke is therefore a high priority for medical technology research. Rehabilitation has been shown to be highly effective, particularly for motor impairments following a stroke, and helps patients to regain the mobility of their limbs.
EEG - a great help in the rehabilitation of stroke patients
Electroencephalography, i.e. diagnosis by measuring the electrical activity of the brain, plays an important role in the rehabilitation of stroke patients. With the help of EEG, brain signals can be recorded and analyzed very precisely over time, which makes it possible to investigate rapid changes in brain activity. EEG is non-invasive, i.e. it is carried out without penetrating or injuring body tissue, the procedure is very mobile, easy to use and also comparatively inexpensive.
Capturing thoughts with brain-computer interfaces
This makes EEG the ideal tool for brain-computer interfaces (BCIs) - digital interfaces between the brain and the medical computer program. BCIs in turn provide doctors with direct visual and sensory feedback during the rehabilitation of stroke patients, for example as soon as the patient has successfully completed a cognitive task, such as imagining a movement. What experts call "motor imagery" makes EEG-based brain-computer interfaces an extremely valuable medical tool for the rehabilitation of stroke patients.
Until now, however, BCIs have mainly been used for the motor rehabilitation of the upper limbs, i.e. the arms, in the event of a stroke. The signal processing required for the rehabilitation of the lower limbs, the legs and the pelvis, is much more complex.
In the research project "Online EEG analysis for neurofeedback in lower limb neurorehabilitation after stroke", the research team from TU Ilmenau and the University of Innsbruck aims to develop novel algorithms to improve motor imagery in lower limb rehabilitation using BCIs. The team will develop novel classification algorithms based on artificial neural networks, so-called Convolutional Neural Networks, and incorporate the online analysis of EEG sources and their connections. Professor Jens Haueisen, project leader and head of the Institute of Biomedical Engineering and Computer Science at TU Ilmenau, wants to significantly improve the accuracy of motor imagery of the lower limb:
"With the help of Motor Imagery, we record EEG data on the one hand from healthy test subjects and on the other hand from stroke patients while they imagine their legs moving. We hope that this will provide us with new knowledge about information processing in the brain and significantly improve the accuracy of BCIs. With the new rehabilitation options gained in this way, we hope to be able to give stroke patients back some of their quality of life."
Prof. Jens Haueisen
Head of the Institute of Biomedical Engineering and Informatics
+49 3677 69-2861
jens.haueisen@tu-ilmenau.de
