Beyond Augmentation: Cross-Modal Transformer Fusion with Bi-directional Attention for Low-Data Aneurysm Screening
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911597000130560 |
|---|---|
| author | Titikhsha, Antara Tak, Divyanshu |
| author_facet | Titikhsha, Antara Tak, Divyanshu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Augmentation: Cross-Modal Transformer Fusion with Bi-directional Attention for Low-Data Aneurysm Screening Titikhsha, Antara Tak, Divyanshu Computer Vision and Pattern Recognition 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. |
| title | Beyond Augmentation: Cross-Modal Transformer Fusion with Bi-directional Attention for Low-Data Aneurysm Screening |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.22185 |