A transfer learning framework based on motor imagery rehabilitation for stroke

Xu, Fangzhou; Miao, Yunjing; Sun, Yanyu; Guo, Dongju; Xu, Jiali; Wang, Yuandong; Li, Jincheng; Li, Han; Dong, Gege; Rong, Fenqi; Leng, Jiancai; Zhang, Yang

doi:10.1038/s41598-021-99114-1

Cited by 29 publications

(22 citation statements)

References 29 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They evaluated intra-and inter-subject transfer learning calibrations using data from seven stroke patients and found that their scheme benefitted low-precision sessions the most. In [56], Xu et al studied transfer learning with a combination of healthy and stroke data, collected from eleven healthy and five stroke patients. They used EEGNet for transfer learning based on fine-tuning and achieved an average accuracy of 66.36%.…”

Section: Transfer Learning In Stroke Patientsmentioning

confidence: 99%

Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain–computer interface

Nagarajan,

Robinson,

Ang

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective: Motor imagery (MI) brain-computer interfaces (BCI) based on electroencephalogram (EEG) have been developed primarily for stroke rehabilitation, however, due to limited stroke data, current deep learning methods for cross-subject classification rely on healthy data. This study aims to assess the feasibility of applying MI-BCI models pre-trained using data from healthy individuals to detect MI in stroke patients. Approach: We introduce a new transfer learning approach where features from two-class MI data of healthy individuals are used to detect MI in stroke patients. We compare the results of the proposed method with those obtained from analyses within stroke data. Experiments were conducted using Deep ConvNet and state-of-the-art subject-specific machine learning MI classifiers, evaluated on OpenBMI two-class MI-EEG data from healthy subjects and two-class MI versus rest data from stroke patients. Main Results: Results of our study indicate that through domain adaptation of a model pre-trained using healthy subjects’ data, an average MI detection accuracy of 71.15% (±12.46%) can be achieved across 71 stroke patients. We demonstrate that the accuracy of the pre-trained model increased by 18.15% after transfer learning (p < 0.001). Additionally, the proposed transfer learning method outperforms the subject-specific results achieved by Deep ConvNet and FBCSP, with significant enhancements of 7.64% (p < 0.001) and 5.55% (p < 0.001) in performance, respectively. Notably, the healthy-to-stroke transfer learning approach achieved similar performance to stroke-to-stroke transfer learning, with no significant difference (p > 0.05). Explainable AI analyses using transfer models determined channel relevance patterns that indicate contributions from the bilateral motor, frontal, and parietal regions of the cortex towards MI detection in stroke patients. Significance: Transfer learning from healthy to stroke can enhance the clinical use of BCI algorithms by overcoming the challenge of insufficient clinical data for optimal training.

show abstract

Section: Transfer Learning In Stroke Patientsmentioning

confidence: 99%

Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain–computer interface

Nagarajan,

Robinson,

Ang

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…Some studies have investigated the use of motor imagery electroencephalogram (MI-EEG) signal classification for developing prosthetic limbs that can be controlled by the user's intention to move their limbs [3,4]. Other studies have focused on developing MI-EEG classification models for stroke rehabilitation, where the models can be used to evaluate the effectiveness of rehabilitation programs and track patients' progress [5][6][7]. Given the potential contributions of MI-EEG for the development of motor imagery BCI applications, there appears to be a need for methodologies that can present solutions for performing well across diverse individuals and conditions.…”

Section: Introductionmentioning

confidence: 99%

Improving cross-subject classification performance of motor imagery signals: a data augmentation-focused deep learning framework

Ozelbas,

Tülay,

Ozekes

2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Motor Imagery Brain-Computer Interfaces (MI-BCIs) have gained a lot of attention in recent years thanks to their potential to enhance rehabilitation and control of prosthetic devices for individuals with motor disabilities. However, accurate classification of motor imagery signals remains a challenging task due to the high inter-subject variability and non-stationarity in the electroencephalogram (EEG) data. In the context of MI-BCIs, with limited data availability, the acquisition of EEG data can be difficult. In this study, several data augmentation techniques have been compared with the proposed data augmentation technique Adaptive Cross-Subject Segment Replacement (ACSSR). This technique, in conjunction with the proposed deep learning framework, allows for a combination of similar subject pairs to take advantage of one another and boost the classification performance of MI-BCIs. The proposed framework features a multi-domain feature extractor based on Common Spatial Patterns (CSP) with a sliding window and a parallel two-branch Convolutional Neural Network (CNN). The performance of the proposed methodology has been evaluated on the multi-class BCI Competition IV Dataset 2a through repeated 10- fold cross-validation. Experimental results indicated that the implementation of the ACSSR method (80.46%) in the proposed framework has led to a considerable improvement in the classification performance compared to the classification without data augmentation (77.63%), and other fundamental data augmentation techniques used in the literature. The study contributes to the advancements for the development of effective MI-BCIs by showcasing the ability of the ACSSR method to address the challenges in motor imagery signal classification tasks.

show abstract

“…The speller systems are the most popular and widespread type of BCI applications that can help patients to write their thoughts just by focusing on the virtual keyboard through brain signals without using their hands [ [4] , [5] , [6] ]. These applications are suitable for patients who are unable to use their muscles normally, such as amyotrophic lateral sclerosis (ALS), spinal cord injury (SCI), Duchenne muscular dystrophy (DMD), and stroke [ 7 , 8 ]. Electroencephalogram (EEG) is often used for measuring non-invasive brain signals in BCI applications such as steady-state visually evoked potential (SSVEP) [ 9 , 10 ], P300-based event-related potential (ERP) [ 11 ], sensorimotor rhythm (SMR) [ 12 ], and slow cortical potential (SCP) [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

A spatial-temporal linear feature learning algorithm for P300-based brain-computer interfaces

Aghili¹,

Kilani²,

Khushaba³

et al. 2023

Heliyon

View full text Add to dashboard Cite

A transfer learning framework based on motor imagery rehabilitation for stroke

Cited by 29 publications

References 29 publications

Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain–computer interface

Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain–computer interface

Improving cross-subject classification performance of motor imagery signals: a data augmentation-focused deep learning framework

A spatial-temporal linear feature learning algorithm for P300-based brain-computer interfaces

Contact Info

Product

Resources

About