Proposes tree-based semantic losses for hierarchical multi-class medical image segmentation, showing consistent gains over baselines on full-supervision brain parcellation and sparse-annotation hyperspectral imaging tasks.
Trustwor- thy clinical ai solutions: A unified review of uncertainty quantification in deep learning models for medical image analysis,
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
-
Label tree semantic losses for rich multi-class medical image segmentation
Proposes tree-based semantic losses for hierarchical multi-class medical image segmentation, showing consistent gains over baselines on full-supervision brain parcellation and sparse-annotation hyperspectral imaging tasks.