CRISP - Reliable Uncertainty Estimation for Medical Image Segmentation. (arXiv:2206.07664v1 [eess.IV])

Web: http://arxiv.org/abs/2206.07664

Accurate uncertainty estimation is a critical need for the medical imaging
community. A variety of methods have been proposed, all direct extensions of
classification uncertainty estimations techniques. The independent pixel-wise
uncertainty estimates, often based on the probabilistic interpretation of
neural networks, do not take into account anatomical prior knowledge and
consequently provide sub-optimal results to many segmentation tasks. For this
reason, we propose CRISP a ContRastive Image Segmentation for uncertainty
Prediction method. At its core, CRISP implements a contrastive method …

arxiv image medical segmentation uncertainty