A deep learning framework predicts segmentation quality from uncertainty maps and image features, achieving high Dice correlation on skin and liver segmentation without test-time ground truth.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation
A deep learning framework predicts segmentation quality from uncertainty maps and image features, achieving high Dice correlation on skin and liver segmentation without test-time ground truth.