Spatially-Aware Evaluation of Segmentation Uncertainty

Tal Zeevi, EV Lieffrig, Lawrence H. Staib, James A. Onofrey

Spotlight Presentation, CVPR 2025 Workshop on Uncertainty Quantification
arXiv preprint arXiv:2506.16589, 2025

Paper

Abstract

Uncertainty maps highlight unreliable regions in segmentation predictions. However, most uncertainty evaluation metrics treat voxels independently, ignoring spatial context and anatomical structure. As a result, they may assign identical scores to qualitatively distinct patterns (e.g., scattered vs. boundary-aligned uncertainty). We propose three spatially aware metrics that incorporate structural and boundary information and conduct a thorough validation on medical imaging data from the prostate zonal segmentation challenge within the Medical Segmentation Decathlon. Our results demonstrate improved alignment with clinically important factors and better discrimination between meaningful and spurious uncertainty patterns.

Citation

@article{zeevi2025spatiallyaware,
  title={Spatially-Aware Evaluation of Segmentation Uncertainty},
  author={Zeevi, Tal and Lieffrig, EV and Staib, Lawrence H and Onofrey, James A},
  journal={arXiv preprint arXiv:2506.16589},
  year={2025}
}