PathSegmentor is a text-prompted segmentation foundation model for pathology images, trained on a new 160-category, 275k-sample benchmark, and reports higher Dice scores than specialized and prior foundation baselines.
IEEE Reviews in Biomedical Engineering 9, 234–263 (2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Segment Anything in Pathology Images with Natural Language
PathSegmentor is a text-prompted segmentation foundation model for pathology images, trained on a new 160-category, 275k-sample benchmark, and reports higher Dice scores than specialized and prior foundation baselines.