Spatially-Aware Evaluation of Segmentation Uncertainty
This work addresses a domain-specific problem in medical imaging by providing more clinically relevant uncertainty evaluation for segmentation tasks.
The paper tackled the problem of evaluating segmentation uncertainty by addressing the lack of spatial context in existing metrics, proposing three spatially aware metrics that improved alignment with clinical factors and discrimination between uncertainty patterns in prostate zonal segmentation data.
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.