Topology-Preserving Image Segmentation with Spatial-Aware Persistent Feature Matching

TL;DR

This paper introduces a novel spatial-aware topological loss function that enhances the accuracy of tubular structure segmentation by combining persistent homology with spatial domain information, outperforming existing methods.

Contribution

It proposes an innovative loss function that integrates spatial domain data with persistent homology for improved topological segmentation accuracy.

Findings

Superior topological accuracy on tubular structure images

Outperforms state-of-the-art topological segmentation methods

Effective in diverse biomedical imaging scenarios

Abstract

Topological correctness is critical for segmentation of tubular structures, which pervade in biomedical images. Existing topological segmentation loss functions are primarily based on the persistent homology of the image. They match the persistent features from the segmentation with the persistent features from the ground truth and minimize the difference between them. However, these methods suffer from an ambiguous matching problem since the matching only relies on the information in the topological space. In this work, we propose an effective and efficient Spatial-Aware Topological Loss Function that further leverages the information in the original spatial domain of the image to assist the matching of persistent features. Extensive experiments on images of various types of tubular structures show that the proposed method has superior performance in improving the topological accuracy of the segmentation compared with state-of-the-art methods. Code is available at https://github.com/JRC-VPLab/SATLoss.