PriUS enforces uncertainty estimates in segmentation models via evidential learning to match image contrast, corruption levels, and shape complexity, yielding more consistent uncertainty on ACDC, ISIC, and WHS datasets while preserving segmentation accuracy.
Multi-scale patch and multi-modality atlases for whole heart segmentation of mri
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 2verdicts
UNVERDICTED 2roles
dataset 1polarities
use dataset 1representative citing papers
TCSA-UDA aligns image features to text-based class semantics and class prototypes to reduce cross-modality domain shift in unsupervised medical image segmentation.
citing papers explorer
-
Principle-Guided Supervision for Interpretable Uncertainty in Medical Image Segmentation
PriUS enforces uncertainty estimates in segmentation models via evidential learning to match image contrast, corruption levels, and shape complexity, yielding more consistent uncertainty on ACDC, ISIC, and WHS datasets while preserving segmentation accuracy.
-
TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation
TCSA-UDA aligns image features to text-based class semantics and class prototypes to reduce cross-modality domain shift in unsupervised medical image segmentation.