TopoTTA: Topology-Enhanced Test-Time Adaptation for Tubular Structure Segmentation

TL;DR

TopoTTA introduces a novel test-time adaptation framework specifically designed for tubular structure segmentation, effectively addressing domain shifts in topology and local features to improve segmentation accuracy.

Contribution

It is the first TTA framework tailored for TSS, utilizing topological meta difference convolutions and a hard sample generation strategy to enhance topological consistency.

Findings

Achieves an average of 31.81% improvement in clDice across multiple datasets.

Effectively handles topological distribution shifts in tubular structure segmentation.

Serves as a plug-and-play solution for CNN-based TSS models.

Abstract

Tubular structure segmentation (TSS) is important for various applications, such as hemodynamic analysis and route navigation. Despite significant progress in TSS, domain shifts remain a major challenge, leading to performance degradation in unseen target domains. Unlike other segmentation tasks, TSS is more sensitive to domain shifts, as changes in topological structures can compromise segmentation integrity, and variations in local features distinguishing foreground from background (e.g., texture and contrast) may further disrupt topological continuity. To address these challenges, we propose Topology-enhanced Test-Time Adaptation (TopoTTA), the first test-time adaptation framework designed specifically for TSS. TopoTTA consists of two stages: Stage 1 adapts models to cross-domain topological discrepancies using the proposed Topological Meta Difference Convolutions (TopoMDCs), which enhance topological representation without altering pre-trained parameters; Stage 2 improves topological continuity by a novel Topology Hard sample Generation (TopoHG) strategy and prediction alignment on hard samples with pseudo-labels in the generated pseudo-break regions. Extensive experiments across four scenarios and ten datasets demonstrate TopoTTA's effectiveness in handling topological distribution shifts, achieving an average improvement of 31.81% in clDice. TopoTTA also serves as a plug-and-play TTA solution for CNN-based TSS models.