A framework using RoI-guided token reduction, hard-negative contrastive learning on RoIs, and DINOv2 ViT outperforms baselines in mammogram breast cancer classification.
Multi-vendor evaluation of arti- ficial intelligence as an independent reader for double reading in breast cancer screening on 275,900 mammo- grams
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Attend what matters: Leveraging vision foundational models for breast cancer classification using mammograms
A framework using RoI-guided token reduction, hard-negative contrastive learning on RoIs, and DINOv2 ViT outperforms baselines in mammogram breast cancer classification.