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

2026-03-07

AI Summary

This work addresses the performance degradation in optic disc and cup segmentation caused by scarce annotations and imaging discrepancies across medical devices. To tackle this challenge, the authors propose a dual-domain collaborative unsupervised domain adaptation framework that jointly optimizes cross-domain alignment and intra-domain generalization within a unified architecture. The method introduces bidirectional cross-domain consistency regularization, dynamic mask-guided feature exchange, and Fourier amplitude-mixed pseudo-label learning to effectively suppress inter-domain interference and enhance semantic consistency. Built upon a teacher–student paradigm with a coarse-to-fine dynamic mask generation mechanism, the approach significantly outperforms existing methods on two multi-domain fundus datasets, achieving more robust segmentation performance.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• Unsupervised Domain Adaptation
• Optic Disc Segmentation
• Optic Cup Segmentation
• Domain Shift
• Cross-domain Interference

Innovation

• Unsupervised Domain Adaptation
• Dual-Domain Synergy
• Cross-domain Consistency
• Frequency-driven Pseudo Labeling
• Optic Disc and Cup Segmentation