Cross-Domain Vessel Segmentation via Latent Similarity Mining and Iterative Co-Optimization

TL;DR

This paper introduces a novel framework for cross-domain retinal vessel segmentation that uses latent similarity mining and iterative co-optimization to improve performance across different data domains.

Contribution

It proposes a new domain transfer method combining latent vascular similarity and iterative co-optimization of generation and segmentation networks.

Findings

Achieves state-of-the-art results in cross-domain vessel segmentation.

Effectively handles significant modality discrepancies.

Enhances both image synthesis quality and segmentation accuracy.

Abstract

Retinal vessel segmentation serves as a critical prerequisite for automated diagnosis of retinal pathologies. While recent advances in Convolutional Neural Networks (CNNs) have demonstrated promising performance in this task, significant performance degradation occurs when domain shifts exist between training and testing data. To address these limitations, we propose a novel domain transfer framework that leverages latent vascular similarity across domains and iterative co-optimization of generation and segmentation networks. Specifically, we first pre-train generation networks for source and target domains. Subsequently, the pretrained source-domain conditional diffusion model performs deterministic inversion to establish intermediate latent representations of vascular images, creating domain-agnostic prototypes for target synthesis. Finally, we develop an iterative refinement strategy where segmentation network and generative model undergo mutual optimization through cyclic parameter updating. This co-evolution process enables simultaneous enhancement of cross-domain image synthesis quality and segmentation accuracy. Experiments demonstrate that our framework achieves state-of-the-art performance in cross-domain retinal vessel segmentation, particularly in challenging clinical scenarios with significant modality discrepancies.