Applying intuitive EEG-controlled grasp neuroprostheses in individuals with spinal cord injury: Preliminary results from the MoreGrasp clinical feasibility study

Müller-Putz, Gernot; Ofner, Patrick; Pereira, Joana; Pinegger, Andreas; Schwarz, Andreas; Zube, Marcel; Eck, Ute; Hessing, Björn; Schneiders, Matthias; Rupp, Rüdiger

doi:10.1109/embc.2019.8856491

Cited by 22 publications

(31 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several BCI systems for motor rehabilitation or motor control [1][2][3][4][5][6] and other basic neuroscience studies strongly rely on the ability to precisely and effectively distinguish different fine hand movements. One example is the investigation of the neural mechanisms underlying the writing and the music performance [7,8] or during real-life performance in ecologically valid situations outside the laboratory [9].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Classification of Fine Hand Movements from Low Frequency EEG

et al. 2021

View full text Add to dashboard Cite

The classification of different fine hand movements from electroencephalogram (EEG) signals represents a relevant research challenge, e.g., in BCI applications for motor rehabilitation. Here, we analyzed two different datasets where fine hand movements (touch, grasp, palmar, and lateral grasp) were performed in a self-paced modality. We trained and tested a newly proposed CNN, and we compared its classification performance with two well-established machine learning models, namely, shrinkage-linear discriminant analysis (LDA) and Random Forest (RF). Compared to previous literature, we included neuroscientific evidence, and we trained our Convolutional Neural Network (CNN) model on the so-called movement-related cortical potentials (MRCPs). They are EEG amplitude modulations at low frequencies, i.e., (0.3,3) Hz that have been proved to encode several properties of the movements, e.g., type of grasp, force level, and speed. We showed that CNN achieved good performance in both datasets (accuracy of 0.70±0.11 and 0.64±0.10, for the two datasets, respectively), and they were similar or superior to the baseline models (accuracy of 0.68±0.10 and 0.62±0.07 with sLDA; accuracy of 0.70±0.15 and 0.61±0.07 with RF, with comparable performance in precision and recall). In addition, compared to the baseline, our CNN requires a faster pre-processing procedure, paving the way for its possible use in online BCI applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Classification of Fine Hand Movements from Low Frequency EEG

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Brain signals are directly recorded e.g., non-invasively via electroencephalography (EEG) at the scalp of the user and circumvent any damaged parts of the spinal cord. It has been shown that BCIs can be successfully applied for communication ( Birbaumer et al, 1999 ; Kaufmann et al, 2014 ; Halder et al, 2015 ; Pinegger et al, 2015 ; Scherer et al, 2015 ), however, they can also be used to generate control signals for assistive devices such robotic arms ( Meng et al, 2016 ) or even upper limb motor neuroprostheses ( Pfurtscheller et al, 2003 ; Müller-Putz et al, 2005 , 2019 ; Rohm et al, 2013 ).…”

Section: Introductionmentioning

confidence: 99%

“…One of our goals of the Horizon 2020 Project MoreGrasp 1 was to develop a grasp neuroprosthesis for people with SCI which could be operated via a BCI at their homes. As such, we took decisive efforts in designing mobile, state-of-the-art EEG recording systems to provide MoreGrasp end users with BCI technology at their homes ( Müller-Putz et al, 2019 ). Based on these developments, we were able to introduce two market ready recording systems: the water-based electrodes EEG-Versatile TM and the dry electrodes EEG-Hero TM .…”

Section: Introductionmentioning

confidence: 99%

Analyzing and Decoding Natural Reach-and-Grasp Actions Using Gel, Water and Dry EEG Systems

Schwarz

Escolano²,

Montesano

et al. 2020

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

Reaching and grasping is an essential part of everybody’s life, it allows meaningful interaction with the environment and is key to independent lifestyle. Recent electroencephalogram (EEG)-based studies have already shown that neural correlates of natural reach-and-grasp actions can be identified in the EEG. However, it is still in question whether these results obtained in a laboratory environment can make the transition to mobile applicable EEG systems for home use. In the current study, we investigated whether EEG-based correlates of natural reach-and-grasp actions can be successfully identified and decoded using mobile EEG systems, namely the water-based EEG-Versatile TM system and the dry-electrodes EEG-Hero TM headset. In addition, we also analyzed gel-based recordings obtained in a laboratory environment (g.USBamp/g.Ladybird, gold standard), which followed the same experimental parameters. For each recording system, 15 study participants performed 80 self-initiated reach-and-grasp actions toward a glass (palmar grasp) and a spoon (lateral grasp). Our results confirmed that EEG-based correlates of reach-and-grasp actions can be successfully identified using these mobile systems. In a single-trial multiclass-based decoding approach, which incorporated both movement conditions and rest, we could show that the low frequency time domain (LFTD) correlates were also decodable. Grand average peak accuracy calculated on unseen test data yielded for the water-based electrode system 62.3% (9.2% STD), whereas for the dry-electrodes headset reached 56.4% (8% STD). For the gel-based electrode system 61.3% (8.6% STD) could be achieved. To foster and promote further investigations in the field of EEG-based movement decoding, as well as to allow the interested community to make their own conclusions, we provide all datasets publicly available in the BNCI Horizon 2020 database ( http://bnci-horizon-2020.eu/database/data-sets ).

show abstract

“…Initial models are typically obtained from userand session-specific calibration data Guger et al, 2001;Pfurtscheller and Neuper, 2001), previous sessions (Perdikis et al, 2018), or sometimes other users (Kobler and Scherer, 2016;Zanini et al, 2018). As highlighted in Perdikis et al (2020), current research trends are clearly biased toward evaluating BCI operation within one or few sessions, while there is relatively little BCI literature on long-term user training (Pfurtscheller et al, 2000;Neuper et al, 2003;Wolpaw and McFarland, 2004;Kübler et al, 2005;Saeedi et al, 2017;Müller-Putz et al, 2019). Nevertheless, long-term user training with BCIs can also be applied in the context of rehabilitation of stroke patients (Ang et al, 2009;Mrachacz-Kersting et al, 2016;Mane et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Long-Term Mutual Training for the CYBATHLON BCI Race With a Tetraplegic Pilot: A Case Study on Inter-Session Transfer and Intra-Session Adaptation

Hehenberger

Kobler

Lopes-Dias

et al. 2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

CYBATHLON is an international championship where people with severe physical disabilities compete with the aid of state-of-the-art assistive technology. In one of the disciplines, the BCI Race, tetraplegic pilots compete in a computer game race by controlling an avatar with a brain-computer interface (BCI). This competition offers a perfect opportunity for BCI researchers to study long-term training effects in potential end-users, and to evaluate BCI performance in a realistic environment. In this work, we describe the BCI system designed by the team Mirage91 for participation in the CYBATHLON BCI Series 2019, as well as in the CYBATHLON 2020 Global Edition. Furthermore, we present the BCI’s interface with the game and the main methodological strategies, along with a detailed evaluation of its performance over the course of the training period, which lasted 14 months. The developed system was a 4-class BCI relying on task-specific modulations of brain rhythms. We implemented inter-session transfer learning to reduce calibration time, and to reinforce the stability of the brain patterns. Additionally, in order to compensate for potential intra-session shifts in the features’ distribution, normalization parameters were continuously adapted in an unsupervised fashion. Across the aforementioned 14 months, we recorded 26 game-based training sessions. Between the first eight sessions, and the final eight sessions leading up to the CYBATHLON 2020 Global Edition, the runtimes significantly improved from 255 ± 23 s (mean ± std) to 225 ± 22 s, respectively. Moreover, we observed a significant increase in the classifier’s accuracy from 46 to 53%, driven by more distinguishable brain patterns. Compared to conventional single session, non-adaptive BCIs, the inter-session transfer learning and unsupervised intra-session adaptation techniques significantly improved the performance. This long-term study demonstrates that regular training helped the pilot to significantly increase the distance between task-specific patterns, which resulted in an improvement of performance, both with respect to class separability in the calibration data, and with respect to the game. Furthermore, it shows that our methodological approaches were beneficial in transferring the performance across sessions, and most importantly to the CYBATHLON competitions.

show abstract

Applying intuitive EEG-controlled grasp neuroprostheses in individuals with spinal cord injury: Preliminary results from the MoreGrasp clinical feasibility study

Cited by 22 publications

References 17 publications

Deep Learning-Based Classification of Fine Hand Movements from Low Frequency EEG

Deep Learning-Based Classification of Fine Hand Movements from Low Frequency EEG

Analyzing and Decoding Natural Reach-and-Grasp Actions Using Gel, Water and Dry EEG Systems

Long-Term Mutual Training for the CYBATHLON BCI Race With a Tetraplegic Pilot: A Case Study on Inter-Session Transfer and Intra-Session Adaptation

Contact Info

Product

Resources

About