clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

By Suprosanna Shit, J. Paetzold, A. Sekuboyina, I. Ezhov, Alexander Unger, A. Zhylka, Josien P. W. Pluim, Ulrich Bauer, Bjoern H Menze. Computer Vision and Pattern Recognition, 2020

549 citations recorded by the source corpus.

Accurate segmentation of tubular, network-like structures, such as vessels, neurons, or roads, is relevant to many fields of research. For such structures, the topology is their most important characteristic; particularly preserving connectedness: in the case of vascular networks, missing a connected vessel entirely alters the blood-flow dynamics. We introduce a novel similarity measure termed centerlineDice (short clDice), which is calculated on the inter-section of the segmentation masks and their (morphological) skeleta. We theoretically prove that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation. Extending this, we pro-pose a computationally efficient, differentiable loss function (soft-clDice) for training arbitrary neural segmentation networks. We benchmark the soft-clDice loss on five public datasets, including vessels, roads and neurons (2D and 3D). Training on soft-clDice leads to segmentation with more accurate connectivity information, higher graph similarity, and better volumetric scores.

Subfields: Biophysics, Computational Theory and Mathematics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2a4b0f6f50ab629a183a77ac8b69851208e5f3bc

Citations in the corpus