Skip to main content

Research Repository

Advanced Search

A novel 3D unsupervised domain adaptation framework for cross-modality medical image segmentation

Yao, Kai; Su, Zixian; Huang, Kaizhu; Yang, Xi; Sun, Jie; Hussain, Amir; Coenen, Frans


Kai Yao

Zixian Su

Kaizhu Huang

Xi Yang

Jie Sun

Frans Coenen


We consider the problem of volumetric (3D) unsupervised domain adaptation (UDA) in cross-modality medical image segmentation, aiming to perform segmentation on the unannotated target domain (e.g. MRI) with the help of labeled source domain (e.g. CT). Previous UDA methods in medical image analysis usually suffer from two challenges: 1) they focus on processing and analyzing data at 2D level only, thus missing semantic information from the depth level; 2) one-to-one mapping is adopted during the style-transfer process, leading to insufficient alignment in the target domain. Different from the existing methods, in our work, we conduct a first of its kind investigation on multi-style image translation for complete image alignment to alleviate the domain shift problem, and also introduce 3D segmentation in domain adaptation tasks to maintain semantic consistency at the depth level. In particular, we develop an unsupervised domain adaptation framework incorporating a novel quartet self-attention module to efficiently enhance relationships between widely separated features in spatial regions on a higher dimension, leading to a substantial improvement in segmentation accuracy in the unlabeled target domain. In two challenging cross-modality tasks, specifically brain structures and multi-organ abdominal segmentation, our model is shown to outperform current state-of-the-art methods by a significant margin, demonstrating its potential as a benchmark resource for the biomedical and health informatics research community.

Journal Article Type Article
Online Publication Date Mar 24, 2022
Publication Date 2022-10
Deposit Date Jul 8, 2022
Publicly Available Date Jul 8, 2022
Journal IEEE Journal of Biomedical and Health Informatics
Print ISSN 2168-2194
Electronic ISSN 2168-2208
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
Volume 26
Issue 10
Pages 4976-4986
Keywords Cross-modality learning, Image segmentation, Style transfer, Unsupervised domain adaptation
Public URL


A Novel 3D Unsupervised Domain Adaptation Framework For Cross-modality Medical Image Segmentation (accepted version) (1.7 Mb)

You might also like

Downloadable Citations