{"ID":2826652,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.22185","arxiv_id":"2512.22185","title":"Beyond Augmentation: Cross-Modal Transformer Fusion with Bi-directional Attention for Low-Data Aneurysm Screening","abstract":"Intracranial aneurysm rupture causes subarachnoid hemorrhage with mortality near 50%, making early detection critical. Although CTA enables rapid screening, detecting small aneurysms within the complex three-dimensional branching of the Circle of Willis remains expertise-dependent. Existing automated systems are constrained by class imbalance, skull-base artifacts that mimic vascular contrast, and reliance on global binary classification without structured localization, limiting surgical relevance and interpretability. We propose CMTF-Net, a cross-modal target fusion framework that reframes aneurysm screening as anatomically structured reasoning. By supervising 14 vascular territories independently, the network encodes Circle of Willis geometry while allowing multi-segment activation, aligning model design with clinical workflow. CMTF-Net achieves near-perfect AUC-ROC with narrow confidence intervals and sustained precision under imbalance. Grad-CAM and causal maps show spatially localized activation along major arteries, supporting interpretable, anatomically grounded screening in low-data settings.","short_abstract":"Intracranial aneurysm rupture causes subarachnoid hemorrhage with mortality near 50%, making early detection critical. Although CTA enables rapid screening, detecting small aneurysms within the complex three-dimensional branching of the Circle of Willis remains expertise-dependent. Existing automated systems are constr...","url_abs":"https://arxiv.org/abs/2512.22185","url_pdf":"https://arxiv.org/pdf/2512.22185v2","authors":"[\"Antara Titikhsha\",\"Divyanshu Tak\"]","published":"2025-12-20T01:44:30Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}