arXiv：cs.LG· Boseong Kim, Haejun Chung, Ikbeom Jang·· 4 小时前AI 评分32
MovieSTAGE：面向电影-fMRI ADHD 分类的场景、转场与全局编码
MovieSTAGE: Scene, Transition, and Global Encoding for Movie-fMRI ADHD Classification
AI 导读
MovieSTAGE 多尺度框架将场景内超图结构功能连接、相邻场景差异与全片功能连接结合，用于电影-fMRI 的 ADHD 分类。在 CMI-HBN Despicable Me 队列 260 名受试者上，病例对照、ADHD 亚型与三分类任务的 AUROC 分别为 0.69、0.73、0.75。
正文
Abstract:Naturalistic movie-fMRI provides a shared, temporally structured probe of brain dynamics, yet predictive models commonly rely on whole-run functional connectivity (FC) or temporally generic representations that are not aligned with narrative events. We introduce MovieSTAGE (Scene, Transition, and Global Encoding), a multiscale framework that combines hypergraph-structured FC-profile organization within scenes, unsigned FC-profile differences across adjacent scenes, and whole-movie FC. We evaluated 260 participants from the CMI-HBN Despicable Me cohort on case-control, ADHD-subtype, and three-class classification using 10 repetitions of stratified five-fold cross-validation, complete out-of-fold (OOF) predictions, and paired subject-cluster bootstrap and permutation tests. MovieSTAGE achieved AUROCs of 0.69, 0.73, and 0.75 and balanced accuracies of 67.6%, 69.8%, and 58.3%, respectively, yielding the highest mean point estimates among the evaluated methods. On the three-class task, the full model outperformed all two-branch variants, the HGNN scene encoder outperformed MLP, GAT, and BNT alternatives under matched settings, and the human-annotated partition outperformed duration-matched random and fixed-count GSBS controls. These controlled results support incremental predictive value from event-aligned scene and transition representations when combined with whole-movie FC in this cohort. Post-hoc model-derived analyses generated network-level hypotheses involving frontoparietal and default-mode systems.
| Comments: | Accepted to the 2026 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2026) |
| Subjects: | Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2610.09306 [cs.LG] |
| (or arXiv:2610.09306v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09306 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Boseong Kim [view email]
[v1]
Wed, 7 Oct 2026 02:04:07 UTC (1,225 KB)
来源：arXiv：cs.LG · arxiv.org