An Implementation of the Crack Topology Score with Extensions

TL;DR

This paper provides a faithful implementation of the Crack Topology Score (CTS) metric for crack segmentation evaluation, including optional preprocessing extensions, supporting PyTorch workflows and visualization, to improve structural correctness assessment.

Contribution

It introduces a faithful, extensible implementation of CTS with preprocessing options, supporting PyTorch and visualization, for better structural evaluation of crack segmentation.

Findings

Implementation supports PyTorch workflows

Extensions improve handling of artifacts

Code and resources will be publicly available

Abstract

The Crack Topology Score (CTS) is a recently proposed metric that focuses on evaluating the topological correctness of crack segmentation outputs. While pixel-wise metrics such as IoU or F1-score fail to capture structural validity, CTS offers a skeleton-based matching framework to measure the preservation of connectivity. This paper presents a faithful implementation of the CTS metric, along with optional preprocessing extensions designed to handle common prediction artifacts (e.g., small holes and edge noise) found in deep learning outputs. All extensions are disabled by default to ensure strict comparability with the original definition. The implementation supports PyTorch-based workflows and includes visualization tools for transparency. Code and archival resources will be made available at https://github.com/SH-Joo/crack-topology-score.