Treffer: A Novel Transfer Learning-Based Hybrid EEG-fNIRS Brain-Computer Interface for Intracerebral Hemorrhage Rehabilitation.
Front Neurosci. 2023 Jan 09;16:1062889. (PMID: 36699533)
Stroke Vasc Neurol. 2022 Jul 19;:. (PMID: 35853669)
Stroke. 2003 Sep;34(9):2181-6. (PMID: 12907818)
IEEE Trans Instrum Meas. 2023;72:. (PMID: 38957474)
Adv Sci (Weinh). 2025 Nov;12(43):e05426. (PMID: 40831229)
Clin Neurophysiol. 2012 Jul;123(7):1328-37. (PMID: 22244309)
Sci Data. 2024 Jan 25;11(1):131. (PMID: 38272904)
Transl Stroke Res. 2025 Jun;16(3):975-989. (PMID: 38558011)
Front Hum Neurosci. 2024 Feb 01;18:1320457. (PMID: 38361913)
Sensors (Basel). 2023 Jun 28;23(13):. (PMID: 37447849)
Bioengineering (Basel). 2023 Dec 06;10(12):. (PMID: 38135985)
Int J Surg. 2024 Sep 01;110(9):5745-5762. (PMID: 39166947)
ACS Nano. 2023 Dec 26;17(24):24487-24513. (PMID: 38064282)
Stroke. 2016 Jun;47(6):e98-e169. (PMID: 27145936)
Natl Sci Rev. 2022 May 24;9(10):nwac099. (PMID: 36196114)
Circ Res. 2022 Apr 15;130(8):1204-1229. (PMID: 35420918)
IEEE J Biomed Health Inform. 2024 Apr;28(4):1971-1981. (PMID: 38265900)
Sci Data. 2024 Oct 25;11(1):1168. (PMID: 39455586)
Stroke. 2007 Apr;38(4):1293-7. (PMID: 17332444)
J Stroke Cerebrovasc Dis. 2021 Aug;30(8):105876. (PMID: 34049014)
Stroke. 2017 Jul;48(7):1908-1915. (PMID: 28550098)
IEEE Trans Neural Syst Rehabil Eng. 2022;30:329-339. (PMID: 35130163)
J Neural Eng. 2019 Apr;16(2):026007. (PMID: 30524056)
Neurophotonics. 2022 Oct;9(4):041411. (PMID: 35874933)
IEEE Trans Neural Netw Learn Syst. 2024 Nov;35(11):15479-15493. (PMID: 37379192)
Vision Res. 2001;41(10-11):1257-60. (PMID: 11322970)
Arch Phys Med Rehabil. 2015 Mar;96(3 Suppl):S71-8. (PMID: 25721550)
Comput Biol Med. 2020 Aug;123:103843. (PMID: 32768038)
IEEE Trans Neural Syst Rehabil Eng. 2016 Nov 11;25(10):1735-1745. (PMID: 27849545)
Front Hum Neurosci. 2018 Jun 28;12:246. (PMID: 30002623)
Physiother Theory Pract. 2022 Sep;38(9):1126-1134. (PMID: 33026895)
J Neurosci Methods. 2019 Jan 15;312:1-11. (PMID: 30452976)
Neurorehabil Neural Repair. 2022 Dec;36(12):747-756. (PMID: 36426541)
IEEE Trans Neural Syst Rehabil Eng. 2022;30:1737-1744. (PMID: 35731756)
Neurol Sci. 2024 Jan;45(1):55-63. (PMID: 37697027)
BMC Neurol. 2023 Mar 31;23(1):136. (PMID: 37003976)
Weitere Informationen
Motor imagery (MI)-based neurorehabilitation shows promise for intracerebral hemorrhage (ICH) recovery, yet conventional unimodal brain-computer interfaces (BCIs) face critical limitations in cross-subject generalization. This study presents a multimodal electroencephalography (EEG)-functional near-infrared spectroscopy (fNIRS) fusion framework incorporating a Wasserstein metric-driven source domain selection method that quantifies inter-subject neural distribution divergence. Through comparative neuroactivation analysis of 17 normal controls and 13 ICH patients during MI tasks, the transfer learning model achieved 74.87% mean classification accuracy on patient data when trained with optimally selected normal templates. Cross-validation on two public hybrid EEG-fNIRS datasets demonstrated generalizability, increasing baseline accuracy to 82.30% and 87.24%, respectively. The proposed system synergistically combines the millisecond temporal resolution of EEG with the hemodynamic spatial specificity of fNIRS, establishing the first clinically viable multimodal analytical protocol for ICH rehabilitation. This paradigm advances neurotechnology translation by paving the way for personalized rehabilitation regimens through robust cross-subject neural pattern transfer while addressing the critical barrier of neurophysiological heterogeneity in post-ICH populations.
(© 2025 The Author(s). Advanced Science published by Wiley‐VCH GmbH.)