A Convolutional Neural Network Combining Multi-scale Convolution and Functional Connectivity for Predicting rTMS Efficacy in MUD
Annals of Biomedical Engineering · 20.07.2026
DOI: 10.1007/s10439-026-04286-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Annals of Biomedical Engineering, online erschienen am 20.07.2026. Verfasst von Yongcong Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Rehabilitation, Southwest Hospital, Third Military Medical University (Army Medical University), Chongqing, 400038, China. Die Arbeit nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Chongqing Young and Middle Aged Medical High-End Talent Project, Chongqing Major Special Project for Technology Innovation and Application Development.
Abstract (Originalsprache)
PURPOSE: Repetitive transcranial magnetic stimulation (rTMS) is a promising neuromodulation approach for treating methamphetamine use disorder (MUD), but its therapeutic outcomes exhibit considerable variability. Therefore, this study proposed a deep learning model for predicting treatment response based on neuroscience findings, which may guide therapeutic decisions and prevent healthcare resource wastage. METHODS: Resting-state electroencephalography (EEG) was acquired from 17 subjects with MUD prior to a 4-week rTMS treatment regimen. After treatment, subjects were classified as either responders or non-responders according to standardized clinical assessments. A convolutional neural network (MSFC-CNN) was developed that parallelly integrated multi-scale (MS) and functional connectivity (FC) modules. The MS module employed multi-scale kernels to extract temporal features at varying resolutions, enhanced by a frequency-domain self-attention mechanism that adaptively recalibrated spatiotemporal feature weights across different frequency bands. The FC module performed 2D convolution on functional connectivity matrices to leverage inter-channel dependencies and strengthen spatial representation learning. Predictions from both modules were fused at the decision level to generate the final classification. RESULTS: MSFC-CNN achieved an average prediction accuracy of 88.06% [95% CI 80.36%, 95.75%] for classifying responders from non-responders. The proposed model statistically outperformed classical and state-of-the-art comparison methods (see "Results" for paired tests and effect sizes). Feature visualization and ablation studies further validated the contributions of each module within the network architecture. Additionally, the model also showed discriminative ability on the auxiliary MUD vs. HC task. CONCLUSION: As an initial exploration, the proposed MSFC-CNN provides methodological support for predicting treatment responses in MUD based on EEG.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Rehabilitation, Southwest Hospital, Third Military Medical University (Army Medical University), Chongqing, 400038, China.
- School of Medicine, Shanghai University, Shanghai, 200444, China.
- Department of Rehabilitation Medicine, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200336, China.
- Shanghai Songze Compulsory Isolation Drug Rehabilitation Center, Shanghai, 201700, China.
- Department of Rehabilitation, Southwest Hospital, Third Military Medical University (Army Medical University), Chongqing, 400038, China. wangxiaoxia@tmmu.edu.cn.
- Department of Basic Psychology, School of Psychology, Army Medical University, Chongqing, 400038, China. wangxiaoxia@tmmu.edu.cn.
Förderung
- National Natural Science Foundation of China
- Chongqing Young and Middle Aged Medical High-End Talent Project
- Chongqing Major Special Project for Technology Innovation and Application Development
- Key Natural Science Project of the Research Development Fund of Chengdu Medical College
Zitieren
APA
Li, Y., Ma, J., Shu, T., Yang, H., Xie, L., He, W., Zhang, C., Wang, X., & Hou, J. (2026). A Convolutional Neural Network Combining Multi-scale Convolution and Functional Connectivity for Predicting rTMS Efficacy in MUD. Annals of Biomedical Engineering. https://doi.org/10.1007/s10439-026-04286-4
Vancouver
Li Y, Ma J, Shu T, Yang H, Xie L, He W, et al. A Convolutional Neural Network Combining Multi-scale Convolution and Functional Connectivity for Predicting rTMS Efficacy in MUD. Annals of Biomedical Engineering. 2026. doi:10.1007/s10439-026-04286-4
BibTeX
@article{Li2026,
author = {Li, Yongcong and Ma, Jun and Shu, Tian and Yang, Hong and Xie, Lijuan and He, Weitao and Zhang, Chaojing and Wang, Xiaoxia and Hou, Jingming},
title = {A Convolutional Neural Network Combining Multi-scale Convolution and Functional Connectivity for Predicting rTMS Efficacy in MUD},
journal = {Annals of Biomedical Engineering},
year = {2026},
doi = {10.1007/s10439-026-04286-4}
}
EUVIMED