Unified and Semantically Grounded Domain Adaptation for Medical Image Segmentation

TL;DR

This paper introduces a unified, semantically grounded framework for medical image segmentation domain adaptation that works effectively in both source-accessible and source-free settings by modeling anatomical regularities as a domain-agnostic probabilistic manifold.

Contribution

It proposes a novel architecture that learns a domain-agnostic anatomical manifold, enabling adaptable and interpretable segmentation across different domain settings without explicit cross-domain alignment.

Findings

Achieves state-of-the-art results on cardiac and abdominal datasets.

Source-free performance closely matches source-accessible methods.

Provides a principled, anatomically informed approach to domain adaptation.

Abstract

Most prior unsupervised domain adaptation approaches for medical image segmentation are narrowly tailored to either the source-accessible setting, where adaptation is guided by source-target alignment, or the source-free setting, which typically resorts to implicit adaptation mechanisms such as pseudo-labeling and network distillation. This substantial divergence in methodological designs between the two settings reveals an inherent flaw: the lack of an explicit, structured construction of anatomical knowledge that naturally generalizes across domains and settings. To bridge this longstanding divide, we introduce a unified, semantically grounded framework that supports both source-accessible and source-free adaptation. Fundamentally distinct from all prior works, our framework's adaptability emerges naturally as a direct consequence of the model architecture, without relying on explicit cross-domain alignment strategies. Specifically, our model learns a domain-agnostic probabilistic manifold as a global space of anatomical regularities, mirroring how humans establish visual understanding. Thus, the structural content in each image can be interpreted as a canonical anatomy retrieved from the manifold and a spatial transformation capturing individual-specific geometry. This disentangled, interpretable formulation enables semantically meaningful prediction with intrinsic adaptability. Extensive experiments on challenging cardiac and abdominal datasets show that our framework achieves state-of-the-art results in both settings, with source-free performance closely approaching its source-accessible counterpart, a level of consistency rarely observed in prior works. The results provide a principled foundation for anatomically informed, interpretable, and unified solutions for domain adaptation in medical imaging. The code is available at https://github.com/wxdrizzle/remind