Brain-Computer Interface in Stroke Rehabilitation

Ang, Kai Keng; Guan, Cuntai

doi:10.5626/jcse.2013.7.2.139

Cited by 184 publications

(130 citation statements)

References 43 publications

Supporting

Mentioning

118

Contrasting

Unclassified

Order By: Relevance

“…Out of those that survive the initial injury, up to 85% are initially left with motor disabilities such as a hemiplegic arm. Despite the rehabilitation efforts, 55-75% of the patients remain with some disability [3][4][5][6] months after the injury [10]; therefore, there is an incitement to optimize the rehabilitation process, e.g. by introducing new interventions to add to the current therapies, to maximize the outcome of the rehabilitation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting and classifying three different hand movement types through electroencephalography recordings for neurorehabilitation

Jochumsen

Niazi

Dremstrup

et al. 2015

Med Biol Eng Comput

View full text Add to dashboard Cite

Brain-computer interfaces can be used for motor substitution and recovery; therefore, detection and classification of movement intention is crucial for optimal control. In this study, palmar, lateral and pinch grasps were differentiated from the idle state and classified from single-trial EEG using only information prior the movement onset. Fourteen healthy subjects performed the three grasps 100 times while EEG was recorded from 25 electrodes. Temporal and spectral features were extracted from each electrode, and feature reduction was performed using sequential forward selection (SFS) and principal component analysis (PCA).The detection problem was investigated as the ability to discriminate between movement preparation and the idle state. Furthermore, all task pairs and the three movements together were classified. The best detection performance across movements (79±8%) was obtained by combining temporal and spectral features. The best movement-movement discrimination was obtained using spectral features; 76±9% (2-class) and 63±10% (3-class). For movement detection and discrimination, the performance was similar across grasp types and task pairs; SFS outperformed PCA. The results show it is feasible to detect different grasps and classify the distinct movements using only information prior to the movement onset; which may enable brain-computer interface-based neurorehabilitation of upper limb function through Hebbian learning mechanisms.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Over the recent years, brain-computer interface (BCI) technology has been proposed for neurorehabilitation by inducing cortical plasticity which is the proposed mechanism for motor learning/recovery [5,7,11,34].…”

Section: Introductionmentioning

confidence: 99%

Detecting and classifying three different hand movement types through electroencephalography recordings for neurorehabilitation

Jochumsen

Niazi

Dremstrup

et al. 2015

Med Biol Eng Comput

View full text Add to dashboard Cite

show abstract

“…The difficulty was that the user had to learn how to control his/her brain activity; the machine did not adapt to the user's neural signal. Today 90 years after Berger's first experiments EEG-based BCI systems have been successfully used for various applications (see Dunne et al, 2013), e.g., communication (Farwell and Donchin, 1988;Birbaumer et al, 1999;Nijboer et al, 2008;Treder and Blankertz, 2010), neurological rehabilitation (Birbaumer and Cohen, 2007;Daly and Wolpaw, 2008;Kaiser et al, 2011;Ang et al, 2011;Lim et al, 2012;Ang and Guan, 2013;Courtine et al, 2013), wheelchair control (Leeb et al, 2007;Galán et al, 2008;Rebsamen et al, 2010;del R. Millán et al, 2010;Carlson and del R. Millán, 2013), prosthesis control (Guger et al, 1999;Müller-Putz et al, 2005;Jackson et al, 2006;McFarland and Wolpaw, 2008;Hahne et al, 2012), game playing (Lalor et al, 2005;Nijholt and Tan, 2007;Tangermann et al, 2008;Nijholt et al, 2009;Lotte, 2011;Bonnet et al, 2013) and many additional non-medical applications del R. Millán et al, 2009;Blankertz et al, 2010b;Haufe et al, 2011;van Erp et al, 2012;Porbadnigk et al, 2013).…”

Section: Part I R E V I S I T I N G B C Imentioning

confidence: 99%

On robust spatial filtering of EEG in nonstationary environments

Samek

2016

It - Information Technology

View full text Add to dashboard Cite

bibliography 119 I N T R O D U C T I O NVariability is the law of life, and as no two faces are the same, so no two bodies are alike, and no two individuals react alike and behave alike under the abnormal conditions which we know as disease. (Sir William Osler, 1903) T he Canadian physician Sir William Osler (1849 -1919 revolutionized the medical world of the 19th century by advocating an approach to therapy which focuses on the needs of individual patients. He recognized the great variability among individuals with respect to their physical conditions, their mental status and their responses to drugs and concluded that focusing solely on clinical signs and symptoms does not result in the most effective therapy. The development of this novel patient-centered paradigm made him the father of personalized medicine; a branch of medicine that is also very popular today due to a better understanding of the genetic influences on a person's risk of acquiring certain diseases.In the last two decades personalized approaches have also revolutionized the field of Brain-Computer Interfacing (BCI). A BCI system (see e.g. Wolpaw et al., 2002;Dornhege et al., 2007;Wolpaw and Wolpaw, 2012) aims to decode the intention of a user from recordings of brain activity and to use this information for controlling a computer application or a robotic device. Today's BCIs extract user-specific features from electroencelographic (EEG) recordings and adapt to the user's signal characteristics. This subject-centered or machine learning approach not only largely reduces the calibration time in comparison to classical BCI systems based on neurofeedback training (Kamiya et al., 1969) but also increases classification accuracy. Unfortunately, EEG responses to a stimulus or a task not only differ from subject to subject but also from trial to trial and from day to day. This change in the signal properties over time is termed the intrinsic nonstationarity of EEG (Kaplan et al., 2005) and constitutes a major challenge for data analysis and classification by violating a basic assumption of many machine learning methods, namely that data are sampled from a fixed (but unknown) distribution (Vapnik, 1998;Hastie et al., 2001). The analysis of EEG is further aggravated by the presence of artifacts in the data, e.g., eye movements, muscular activity or loose electrodes. The lack of robustness to unexpected events and the nonstationary nature of EEG are major reasons in explaining why current BCI technology is seldom used in out-of-lab scenarios and clinical practice. Since artifacts and nonstationarity can not be fully eliminated, even with the best experimental protocol, robust and invariant feature 1 2 introduction representations are required for optimal signal analysis and high classification accuracy. structure of the thesisThis thesis is divided into three parts. The first part introduces the basic concepts of motor imagery-based Brain-Computer Interfacing and discusses the advantages and limitations of several state-of-the-art spatial filtering al...

show abstract

“…Clinical studies on the use of BCIs in rehabilitation have started to emerge [13,14], but before the BCI technology can be transferred from the lab to the clinic several issues must be addressed such as ease of setup and automation of subject training [15]. In the clinic, the BCI shall likely be operated by clinic personnel with limited time to setup the BCI which can be a time consuming task.…”

Section: Introductionmentioning

confidence: 99%

Universal Matched-Filter Template Versus Individualized Template for Single Trial Detection of Movement Intentions of Different Tasks

Akmal

Jochumsen

Navid

et al. 2016

Advances in Neural Networks

View full text Add to dashboard Cite

Brain-computer interfaces (BCIs) have been proposed for neurorehabilitation after stroke by inducing cortical plasticity. To transfer the technology from the controlled settings in the lab to the clinic several issues must be addressed. In this study, it was investigated how the performance was affected by using a universal task template to detect movement intentions associated with movements performed with two different levels of force and speed. The performance of the universal template was compared to an individualized template constructed for each task. Twelve healthy subjects performed four types of dorsi-flexions while continuous electroencephalography (EEG) was recorded from ten channels. The movement intentions were detected (∼200-300 ms before the movement onset) from the continuous EEG using a matched-filter approach. The true positive rate was significantly higher (P = 0.001) when using the individualized template where 68-76 % of the movements were correctly detected on the contrary to 65-70 % when using the universal template. The number of false positive detections per 5 min was lower (P = 0.036) when using the universal template (∼13) compared to the individualized template (∼14). Despite the lower performance when using the universal detection template, the performance of the detector is in the range of what has been reported previously for inducing cortical plasticity.

show abstract

Brain-Computer Interface in Stroke Rehabilitation

Cited by 184 publications

References 43 publications

Detecting and classifying three different hand movement types through electroencephalography recordings for neurorehabilitation

Detecting and classifying three different hand movement types through electroencephalography recordings for neurorehabilitation

On robust spatial filtering of EEG in nonstationary environments

Universal Matched-Filter Template Versus Individualized Template for Single Trial Detection of Movement Intentions of Different Tasks

Contact Info

Product

Resources

About