Deep Small Bowel Segmentation with Cylindrical Topological Constraints

TL;DR

This paper introduces a novel deep learning method for small bowel segmentation that enforces cylindrical topological constraints using persistent homology, improving accuracy and topological correctness.

Contribution

It proposes a new network augmentation with an inner cylinder prediction to address touching issues, applying topological constraints for better segmentation.

Findings

Improved segmentation metrics over baseline methods

Statistically significant results from paired t-test

Effective topological correctness in segmentation

Abstract

We present a novel method for small bowel segmentation where a cylindrical topological constraint based on persistent homology is applied. To address the touching issue which could break the applied constraint, we propose to augment a network with an additional branch to predict an inner cylinder of the small bowel. Since the inner cylinder is free of the touching issue, a cylindrical shape constraint applied on this augmented branch guides the network to generate a topologically correct segmentation. For strict evaluation, we achieved an abdominal computed tomography dataset with dense segmentation ground-truths. The proposed method showed clear improvements in terms of four different metrics compared to the baseline method, and also showed the statistical significance from a paired t-test.