MovieSTAGE: Scene, Transition, and Global Encoding for Movie-fMRI ADHD Classification

2026-10-06

AI Summary

This study addresses the limitation of existing fMRI models that rely on full-period connectivity or generic representations without aligning to narrative events, proposing an event-aligned multiscale hypergraph framework for ADHD classification. Methodologically, it introduces scene and transition encodings to temporally align neural activity with narrative events, integrating intra-scene hypergraph structures, inter-scene discrepancies, and global functional connectivity for multiscale modeling. Furthermore, hypergraph neural networks (HGNNs), clustering-guided segmentation, and hierarchical cross-validation are combined to enhance predictive granularity. Experimental results demonstrate that the proposed approach achieves state-of-the-art AUROC (0.75) and balanced accuracy across three tasks, with permutation testing confirming the significant incremental value of event-aligned representations.

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.

Problem

• movie-fMRI
• ADHD classification
• functional connectivity
• narrative event alignment
• brain dynamics

Innovation

• Movie-fMRI
• Hypergraph Neural Network
• Multiscale Framework
• Event-aligned Encoding
• ADHD Classification