{"ID":2863659,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24860","arxiv_id":"2509.24860","title":"ELPG-DTFS: Prior-Guided Adaptive Time-Frequency Graph Neural Network for EEG Depression Diagnosis","abstract":"Timely and objective screening of major depressive disorder (MDD) is vital, yet diagnosis still relies on subjective scales. Electroencephalography (EEG) provides a low-cost biomarker, but existing deep models treat spectra as static images, fix inter-channel graphs, and ignore prior knowledge, limiting accuracy and interpretability. We propose ELPG-DTFS, a prior-guided adaptive time-frequency graph neural network that introduces: (1) channel-band attention with cross-band mutual information, (2) a learnable adjacency matrix for dynamic functional links, and (3) a residual knowledge-graph pathway injecting neuroscience priors. On the 128-channel MODMA dataset (53 subjects), ELPG-DTFS achieves 97.63% accuracy and 97.33% F1, surpassing the 2025 state-of-the-art ACM-GNN. Ablation shows that removing any module lowers F1 by up to 4.35, confirming their complementary value. ELPG-DTFS thus offers a robust and interpretable framework for next-generation EEG-based MDD diagnostics.","short_abstract":"Timely and objective screening of major depressive disorder (MDD) is vital, yet diagnosis still relies on subjective scales. Electroencephalography (EEG) provides a low-cost biomarker, but existing deep models treat spectra as static images, fix inter-channel graphs, and ignore prior knowledge, limiting accuracy and in...","url_abs":"https://arxiv.org/abs/2509.24860","url_pdf":"https://arxiv.org/pdf/2509.24860v1","authors":"[\"Jingru Qiu\",\"Jiale Liang\",\"Xuanhan Fan\",\"Mingda Zhang\",\"Zhenli He\"]","published":"2025-09-29T14:44:37Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Graph Neural Network\"]","has_code":false}