Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures

arXiv:2404.03010v1 Announce Type: cross
Abstract: Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-focused losses mark an improvement, they introduce significant computational and …

abstract arxiv computer computer vision concrete connectivity cross-entropy cs.cv cs.lg deep learning dice eess.iv entropy focus functions loss recall roads segmentation standard type vision