Benchmarking ten segmentation models on a nine-image histology dataset and a 153-image generalization set reveals unstable rankings, overlapping confidence intervals, and dataset-specific performance hierarchies, advocating uncertainty-aware evaluation in low-data medical research.
arXiv preprint arXiv:2401.14248
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
-
Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets
Benchmarking ten segmentation models on a nine-image histology dataset and a 153-image generalization set reveals unstable rankings, overlapping confidence intervals, and dataset-specific performance hierarchies, advocating uncertainty-aware evaluation in low-data medical research.