DDS-UDA: Dual-Domain Synergy for Unsupervised Domain Adaptation in Joint Segmentation of Optic Disc and Optic Cup

TL;DR

DDS-UDA introduces a dual-module framework for unsupervised domain adaptation in joint optic disc and cup segmentation, effectively addressing cross-domain interference and intra-domain generalization in heterogeneous fundus imaging.

Contribution

It proposes a novel dual-domain synergy framework with cross-domain consistency and intra-domain pseudo label learning modules for improved UDA performance.

Findings

Outperforms existing UDA methods on multi-domain fundus datasets.

Enhances intra-domain generalization through spectral amplitude mixing.

Mitigates cross-domain interference with feature-level semantic exchange.

Abstract

Convolutional neural networks (CNNs) have achieved exciting performance in joint segmentation of optic disc and optic cup on single-institution datasets. However, their clinical translation is hindered by two major challenges: limited availability of large-scale, high-quality annotations and performance degradation caused by domain shift during deployment across heterogeneous imaging protocols and acquisition platforms. While unsupervised domain adaptation (UDA) provides a way to mitigate these limitations, most existing approaches do not address cross-domain interference and intra-domain generalization within a unified framework. In this paper, we present the Dual-Domain Synergy UDA (DDS-UDA), a novel UDA framework that comprises two key modules. First, a bi-directional cross-domain consistency regularization module is enforced to mitigate cross-domain interference through feature-level semantic information exchange guided by a coarse-to-fine dynamic mask generator, suppressing noise propagation while preserving structural coherence. Second, a frequency-driven intra-domain pseudo label learning module is used to enhance intra-domain generalization by synthesizing spectral amplitude-mixed supervision signals, which ensures high-fidelity feature alignment across domains. Implemented within a teacher-student architecture, DDS-UDA disentangles domain-specific biases from domain-invariant feature-level representations, thereby achieving robust adaptation to heterogeneous imaging environments. We conduct a comprehensive evaluation of our proposed method on two multi-domain fundus image datasets, demonstrating that it outperforms several existing UDA based methods and therefore providing an effective way for optic disc and optic cup segmentation.