{"ID":2874979,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.03214","arxiv_id":"2509.03214","title":"RTGMFF: Enhanced fMRI-based Brain Disorder Diagnosis via ROI-driven Text Generation and Multimodal Feature Fusion","abstract":"Functional magnetic resonance imaging (fMRI) is a powerful tool for probing brain function, yet reliable clinical diagnosis is hampered by low signal-to-noise ratios, inter-subject variability, and the limited frequency awareness of prevailing CNN- and Transformer-based models. Moreover, most fMRI datasets lack textual annotations that could contextualize regional activation and connectivity patterns. We introduce RTGMFF, a framework that unifies automatic ROI-level text generation with multimodal feature fusion for brain-disorder diagnosis. RTGMFF consists of three components: (i) ROI-driven fMRI text generation deterministically condenses each subject's activation, connectivity, age, and sex into reproducible text tokens; (ii) Hybrid frequency-spatial encoder fuses a hierarchical wavelet-mamba branch with a cross-scale Transformer encoder to capture frequency-domain structure alongside long-range spatial dependencies; and (iii) Adaptive semantic alignment module embeds the ROI token sequence and visual features in a shared space, using a regularized cosine-similarity loss to narrow the modality gap. Extensive experiments on the ADHD-200 and ABIDE benchmarks show that RTGMFF surpasses current methods in diagnostic accuracy, achieving notable gains in sensitivity, specificity, and area under the ROC curve. Code is available at https://github.com/BeistMedAI/RTGMFF.","short_abstract":"Functional magnetic resonance imaging (fMRI) is a powerful tool for probing brain function, yet reliable clinical diagnosis is hampered by low signal-to-noise ratios, inter-subject variability, and the limited frequency awareness of prevailing CNN- and Transformer-based models. Moreover, most fMRI datasets lack textual...","url_abs":"https://arxiv.org/abs/2509.03214","url_pdf":"https://arxiv.org/pdf/2509.03214v2","authors":"[\"Junhao Jia\",\"Yifei Sun\",\"Yunyou Liu\",\"Cheng Yang\",\"Changmiao Wang\",\"Feiwei Qin\",\"Yong Peng\",\"Wenwen Min\"]","published":"2025-09-03T11:05:57Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false,"code_links":[{"ID":610176,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2874979,"paper_url":"https://arxiv.org/abs/2509.03214","paper_title":"RTGMFF: Enhanced fMRI-based Brain Disorder Diagnosis via ROI-driven Text Generation and Multimodal Feature Fusion","repo_url":"https://github.com/BeistMedAI/RTGMFF","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}