Spatially-Aware Evaluation of Segmentation Uncertainty

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zeevi, Tal, Lieffrig, Eléonore V., Staib, Lawrence H., Onofrey, John A.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915352577835008
author Zeevi, Tal
Lieffrig, Eléonore V.
Staib, Lawrence H.
Onofrey, John A.
author_facet Zeevi, Tal
Lieffrig, Eléonore V.
Staib, Lawrence H.
Onofrey, John A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16589
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatially-Aware Evaluation of Segmentation Uncertainty
Zeevi, Tal
Lieffrig, Eléonore V.
Staib, Lawrence H.
Onofrey, John A.
Computer Vision and Pattern Recognition
Artificial Intelligence
Performance
Machine Learning
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.
title Spatially-Aware Evaluation of Segmentation Uncertainty
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Performance
Machine Learning
url https://arxiv.org/abs/2506.16589