Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces MovieSTAGE, a multiscale framework for ADHD classification using movie-fMRI data, by integrating hypergraph-structured functional connectivity (FC) within scenes, unsigned FC-profile differences across transitions, and whole-movie FC. The method significantly outperforms baseline approaches by aligning predictive modeling with narrative events, achieving AUROCs of up to 0.75 and balanced accuracies of 67.6% on a three-class ADHD classification task. These results highlight the incremental predictive value of event-aligned representations when combined with global FC, suggesting new network-level hypotheses for ADHD.
Aligning fMRI analysis with movie narrative structure unlocks significant gains in ADHD classification accuracy, outperforming generic whole-run connectivity models.
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.