Learning Topological Interactions for Multi-Class Medical Image Segmentation

TL;DR

This paper introduces a convolution-based topological interaction module that enhances multi-class medical image segmentation by encoding class relationships like containment and exclusion, improving accuracy across various datasets and modalities.

Contribution

The authors propose a novel, efficient topological interaction module integrated into deep networks, enabling end-to-end training and better encoding of class relationships in medical images.

Findings

Improved segmentation accuracy on multiple datasets.

Effective in 2D and 3D medical imaging modalities.

Generalizes across different imaging types like CT and Ultrasound.

Abstract

Deep learning methods have achieved impressive performance for multi-class medical image segmentation. However, they are limited in their ability to encode topological interactions among different classes (e.g., containment and exclusion). These constraints naturally arise in biomedical images and can be crucial in improving segmentation quality. In this paper, we introduce a novel topological interaction module to encode the topological interactions into a deep neural network. The implementation is completely convolution-based and thus can be very efficient. This empowers us to incorporate the constraints into end-to-end training and enrich the feature representation of neural networks. The efficacy of the proposed method is validated on different types of interactions. We also demonstrate the generalizability of the method on both proprietary and public challenge datasets, in both 2D and 3D settings, as well as across different modalities such as CT and Ultrasound. Code is available at: https://github.com/TopoXLab/TopoInteraction