ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT
An Anatomy-Routed Contrastive Learning for 3D Chest CT (ARC-CT), a region-aware framework that addresses limitations using only reports extracted from reports by an LLM, with no manual annotations or bounding boxes, outperforms both comparable efficient baselines and larger transformer models.
H. Isik, Mehmet Alp Ozaydin, S. Kurugol et al.
· 0 citations