DeepAI AI Chat
Log In Sign Up

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

by   Suprosanna, et al.
Technische Universität München

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, e.g. preserving connectedness: in case of vascular networks, missing a connected vessel entirely alters the blood-flow dynamics. We introduce a novel similarity measure termed clDice, which is calculated on the intersection of the segmentation masks and their (morphological) skeletons. Crucially, we theoretically prove that clDice guarantees topological correctness for binary 2D and 3D segmentation. Extending this, we propose a computationally efficient, differentiable soft-clDice as a loss function for training arbitrary neural segmentation networks. We benchmark the soft-clDice loss for segmentation on four public datasets (2D and 3D). Training on soft-clDice leads to segmentation with more accurate connectivity information, higher graph similarity, and better volumetric scores.


page 2

page 14

page 18

page 19

page 20


Topology-Preserving Deep Image Segmentation

Segmentation algorithms are prone to make topological errors on fine-sca...

Topological Similarity Index and Loss Function for Blood Vessel Segmentation

Blood vessel segmentation is one of the most studied topics in computer ...

Optimization with soft Dice can lead to a volumetric bias

Segmentation is a fundamental task in medical image analysis. The clinic...

The Topology-Overlap Trade-Off in Retinal Arteriole-Venule Segmentation

Retinal fundus images can be an invaluable diagnosis tool for screening ...

Cascaded multitask U-Net using topological loss for vessel segmentation and centerline extraction

Vessel segmentation and centerline extraction are two crucial preliminar...

Topologically faithful image segmentation via induced matching of persistence barcodes

Image segmentation is a largely researched field where neural networks f...

Enforcing connectivity of 3D linear structures using their 2D projections

Many biological and medical tasks require the delineation of 3D curvilin...

Code Repositories


Implementation of clDice - a Novel Connectivity-Preserving Loss Function for Vessel Segmentation (2019) in Keras/Tensorflow

view repo