SegX masks saliency maps with a clinical segmentation mask, and SegU uses the resulting overlap as a certainty score; experiments show modest overlap gains and weak uncertainty discrimination.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SegX: Improving Interpretability of Clinical Image Diagnosis with Segmentation-based Enhancement
SegX masks saliency maps with a clinical segmentation mask, and SegU uses the resulting overlap as a certainty score; experiments show modest overlap gains and weak uncertainty discrimination.