Unsupervised Domain Adaptation for Cross-Modality Retinal Vessel Segmentation via Disentangling Representation Style Transfer and Collaborative Consistency Learning

TL;DR

This paper introduces DCDA, a novel framework for unsupervised domain adaptation in cross-modality retinal vessel segmentation, effectively handling large domain shifts between OCTA and OCT images.

Contribution

The paper proposes a new cross-modality unsupervised domain adaptation framework with disentangling style transfer and collaborative learning modules, addressing large domain gaps.

Findings

Achieves Dice scores close to target-trained models.

Significantly outperforms existing state-of-the-art methods.

Effective for large domain shifts in medical image segmentation.

Abstract

Various deep learning models have been developed to segment anatomical structures from medical images, but they typically have poor performance when tested on another target domain with different data distribution. Recently, unsupervised domain adaptation methods have been proposed to alleviate this so-called domain shift issue, but most of them are designed for scenarios with relatively small domain shifts and are likely to fail when encountering a large domain gap. In this paper, we propose DCDA, a novel cross-modality unsupervised domain adaptation framework for tasks with large domain shifts, e.g., segmenting retinal vessels from OCTA and OCT images. DCDA mainly consists of a disentangling representation style transfer (DRST) module and a collaborative consistency learning (CCL) module. DRST decomposes images into content components and style codes and performs style transfer and image reconstruction. CCL contains two segmentation models, one for source domain and the other for target domain. The two models use labeled data (together with the corresponding transferred images) for supervised learning and perform collaborative consistency learning on unlabeled data. Each model focuses on the corresponding single domain and aims to yield an expertized domain-specific segmentation model. Through extensive experiments on retinal vessel segmentation, our framework achieves Dice scores close to target-trained oracle both from OCTA to OCT and from OCT to OCTA, significantly outperforming other state-of-the-art methods.