BrainRehab 2013 Abstracts


Full Papers
Paper Nr: 2
Title:

Efficiency of SSVEF Recognition from the Magnetoencephalogram - A Comparison of Spectral Feature Classification and CCA-based Prediction

Authors:

Christoph Reichert, Matthias Kennel, Rudolf Kruse, Hermann Hinrichs and Jochem W. Rieger

Abstract: Steady-state visual evoked potentials (SSVEP) are a popular method to control brain–computer interfaces (BCI). Here, we present a BCI for selection of virtual reality (VR) objects by decoding the steady-state visual evoked fields (SSVEF), the magnetic analogue to the SSVEP in the magnetoencephalogram (MEG). In a conventional approach, we performed online prediction by Fourier transform (FT) in combination with a multivariate classifier. As a comparative study, we report our approach to increase the BCI-system performance in an offline evaluation. Therefore, we transferred the canonical correlation analysis (CCA), originally employed to recognize relatively low dimensional SSVEPs in the electroencephalogram (EEG), to SSVEF recognition in higher dimensional MEG recordings. We directly compare the performance of both approaches and conclude that CCA can greatly improve system performance in our MEG-based BCI-system. Moreover, we find that application of CCA to large multi-sensor MEG could provide an effective feature extraction method that automatically determines the sensors that are informative for the recognition of SSVEFs.

Short Papers
Paper Nr: 1
Title:

Dynamics of a Stimulation-evoked ECoG Potential During Stroke Rehabilitation - A Case Study

Authors:

Armin Walter, Georgios Naros, Martin Spüler, Wolfgang Rosenstiel, Alireza Gharabaghi and Martin Bogdan

Abstract: Cortical stimulation is being investigated as a possible tool to support stroke rehabilitation. In particular the analysis of stimulation-evoked neural activity during the rehabilitation process might be helpful to gain a better understanding of the brain reorganization associated with functional recovery after stroke. In this paper, the stimulation-evoked brain activity from a patient with implanted epidural electrodes undergoing an intervention using of brain-computer interfaces combined with cortical stimulation for stroke rehabilitation has been analyzed. We identified a component of the evoked cortical activity that exhibited several characteristics that have not been described before: A significant latency decrease over the course of the rehabilitation training, a significantly smaller latency if the patient attempted to move his paralyzed hand compared to rest and a significant correlation of the latency with the spectral power of the ECoG signal. In addition to the latency, other parameters such as the peak amplitude of the evoked activity were tested as well, but showed a smaller effect size. We hypothesize that such “dynamic” components of the evoked activity that appear to be correlated with the rehabilitation process and the ongoing brain signal could be a target for future closed-loop stimulation systems.

Paper Nr: 3
Title:

ECoG Real Time Signal Processing for Clinical Self paced BCI Application

Authors:

Nana Arizumi, Guillaume Charvet, Andrey Eliseyev, Jérémy Pradal, Serpil Cokgungor, Nicolas Tarrin, Corinne Mestais, Tetiana Aksenova and Alim-Louis Benabid

Abstract: The overall goal of the Brain Computer Interface (BCI) project led at CEA/LETI/CLINATEC® is to improve the quality of life of quadriplegic subjects. BCI will allow them to control effectors such as an exoskeleton, through recording and processing of the electrical activity of their brain. To do this, a wireless 64-channel ElectroCorticoGram (ECoG) recording device WIMAGINE® (Wireless Implantable Multi-channel Acquisition system for Generic Interface with NEurons) has been designed for long-term human implantation to interface an electrode array to an external computer. To decode the ECoG data, high resolution algorithm has been constructed at CLINATEC®. Once the data are treated, they are used to control the external effectors. To reach the overall goal, it is crucial to construct a whole software system working in real time. In order to prepare the BCI software system for the clinical trials, we demonstrated online real time Electrocorticogram (ECoG) signal processing using Monkey ECoG recordings corresponding to an arm movement. The algorithm of N-way Partial Least Square (NPLS) regression family is applied to extract linear model from the recordings. The model is used to control the robotic arm JACO (KINOVA) as a demonstrator.

Paper Nr: 4
Title:

A Serious Game Application using EEG-based Brain Computer Interface

Authors:

Francisco José Perales and Esperança Amengual

Abstract: Serious games have demonstrated their effectiveness as a therapeutic resource to deal with motor, sensory and cognitive disabilities. In this article we consider Brain Computer Interfaces (BCI) as a new interaction mechanism that could be used in serious games to improve their rehabilitation activity thanks to the ability of neurofeedback to stimulate the cortical plasticity. We present the brief state-of-the-art of BCI serious games and the factors to be considered in order to develop this particular kind of software that could be highly complex and require experts with different knowledge and skills. We propose a new approach based on the detection of focus features in the game activity. We introduce a system able to assess the Alpha band variations in particular game tasks. Our initial target users are children with cerebral palsy and motor disa-bilities. The system is currently under evaluation with control users before to be operated with the target users in rehabilitation centers.

Paper Nr: 5
Title:

Monitoring Depth of Hypnosis under Propofol General Anaesthesia - Granger Causality and Hidden Markov Models

Authors:

Nicoletta Nicolaou and Julius Georgiou

Abstract: Intra-operative awareness is experienced when a patient regains consciousness during surgery. This work presents a Brain-Computer Interface system that can be used as part of routine surgery for monitoring the patient state of hypnosis in order to prevent intra-operative awareness. The underlying state of hypnosis is estimated using causality-based features extracted from the spontaneous electrical brain activity (EEG) of the patient and a probabilistic classification framework (Hidden Markov Models). The proposed method is applied to EEG activity from 20 patients under propofol anaesthesia. The mean discrimination performance obtained was 98% and 85% for wakefulness and anaesthesia respectively, with an overall performance accuracy of 92%. The use of a probabilistic framework increases the anaesthetist’s confidence on the estimated state of hypnosis based on the marginal probabilities of the underlying state.