Hybrid EEG-fNIRS MI dataset for ICH from Shi et al 2025

Hybrid EEG-fNIRS MI dataset for ICH from Shi et al 2025.

Dataset Overview

• Code: HefmiIch2025
• Paradigm: imagery
• DOI: 10.1038/s41597-025-06100-7
• Subjects: 37
• Sessions per subject: 3
• Events: lefthand=1, righthand=2
• Trial interval: [0, 10] s
• File format: MAT (pre-epoched)
• Data preprocessed: True

Acquisition

• Sampling rate: 256.0 Hz
• Number of channels: 32
• Channel types: eeg=32
• Channel names: FC1, AF3, AF4, CP1, CP2, CP6, Cz, C3, C4, T7, T8, FC2, FC5, FC6, Pz, CP5, PO3, PO4, Oz, Fp2, Fp1, Fz, F3, F4, F7, F8, P3, P4, P7, P8, O1, O2
• Montage: biosemi32
• Hardware: g.HIamp (g.tec medical engineering GmbH)
• Line frequency: 50.0 Hz
• Online filters: {}

Participants

• Number of subjects: 37
• Health status: mixed (17 healthy, 20 ICH patients)
• Clinical population: intracerebral hemorrhage (ICH)
• Age: min=20.0, max=65.0
• Gender distribution: female=8, male=29
• Handedness: right-handed
• Species: human

Experimental Protocol

• Paradigm: imagery
• Number of classes: 2
• Class labels: lefthand, righthand
• Trial duration: 27.0 s
• Study design: 2-class hand MI (left/right grasping) for ICH rehabilitation. 17 healthy + 20 ICH patients, 1-6 sessions per subject.
• Feedback type: none
• Stimulus type: directional arrow + auditory beep
• Stimulus modalities: visual, auditory
• Primary modality: visual
• Synchronicity: synchronous
• Mode: offline

HED Event Annotations

Schema: HED 8.4.0 | Browse: https://www.hedtags.org/hed-schema-browser

  left_hand
    ├─ Sensory-event, Experimental-stimulus, Visual-presentation
    └─ Agent-action
       └─ Imagine
          ├─ Move
          └─ Left, Hand

  right_hand
    ├─ Sensory-event, Experimental-stimulus, Visual-presentation
    └─ Agent-action
       └─ Imagine
          ├─ Move
          └─ Right, Hand

Paradigm-Specific Parameters

• Detected paradigm: motor_imagery
• Imagery tasks: lefthand, righthand
• Cue duration: 2.0 s
• Imagery duration: 10.0 s

Data Structure

• Trials: 3330
• Trials context: 37 subjects x ~3 sessions x 30 trials = ~3330

Signal Processing

• Classifiers: CSP+SVM, FBCSP+SVM, EEGBaseNet, TF+SVM
• Feature extraction: CSP, FBCSP, time-frequency features
• Frequency bands: preprocessing=[0.5, 30.0] Hz
• Spatial filters: CSP, FBCSP

Cross-Validation

• Method: 5-fold
• Folds: 5
• Evaluation type: within_subject

BCI Application

• Applications: rehabilitation
• Environment: clinical
• Online feedback: False

Tags

• Pathology: Healthy, Stroke
• Modality: Motor
• Type: Clinical, Research

Documentation

• DOI: 10.1038/s41597-025-06100-7
• License: CC-BY-NC-ND-4.0
• Investigators: Jian Shi, Danyang Chen, Xingwei Zhao, Zhixian Zhao, Shengjie Li, Yeguang Xu, Tao Ding, Zheng Zhu, Peng Zhang, Qing Ye, Yingxin Tang, Ping Zhang, Bo Tao, Zhouping Tang
• Institution: Huazhong University of Science and Technology
• Country: CN
• Data URL: https://figshare.com/articles/dataset/28955456
• Publication year: 2025

References

Shi, J., Chen, D., et al. (2025). HEFMI-ICH: a hybrid EEG-fNIRS motor imagery dataset for brain-computer interface in intracerebral hemorrhage. Scientific Data. https://doi.org/10.1038/s41597-025-06100-7 Appelhoff, S., Sanderson, M., Brooks, T., Vliet, M., Quentin, R., Holdgraf, C., Chaumon, M., Mikulan, E., Tavabi, K., Hochenberger, R., Welke, D., Brunner, C., Rockhill, A., Larson, E., Gramfort, A. and Jas, M. (2019). MNE-BIDS: Organizing electrophysiological data into the BIDS format and facilitating their analysis. Journal of Open Source Software 4: (1896). https://doi.org/10.21105/joss.01896

Pernet, C. R., Appelhoff, S., Gorgolewski, K. J., Flandin, G., Phillips, C., Delorme, A., Oostenveld, R. (2019). EEG-BIDS, an extension to the brain imaging data structure for electroencephalography. Scientific Data, 6, 103. https://doi.org/10.1038/s41597-019-0104-8

---

Generated by MOABB 1.5.0 (Mother of All BCI Benchmarks) https://github.com/NeuroTechX/moabb