ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT
Contrastive vision-language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated labels. However, two characteristics of chest CT challenge conventional global contrastive learning. First, many critical abnormalities are small or anatomically localized, and pooling an en- tire volume into a single embedding may dilute their visual evidence. Second, the standard contrastive objective treats every other scan in a batch as a negative. Because many chest CTs share abnormalities, this objective incorrectly pushes co-positive pairs a
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%VioletVision-3B →
“Fuzzy title match (0.73): “ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning ” ≈ “VioletVision-3B””
- PossiblePossibly related (embedding) · 53%Deep Learning Advances Lung Cancer Segmentation and Volumetric Analysis in CT Scans - Bioengineer.org →
- FuzzySimilar title/name (fuzzy) · 84%pytorch/vision →
“Fuzzy title match (0.92): “ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning ” ≈ “pytorch/vision””
- LinkedLinked via arxiv author · 85%Huseyin Umut Isik →
“ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT”
- LinkedLinked via arxiv author · 85%Mehmet Alp Ozaydin →
“ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT”
- LinkedLinked via arxiv author · 85%Sila Kurugol →
“ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT”
- LinkedLinked via arxiv author · 85%Şeyda Ertekin →
“ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT”