Few-shot Unsupervised Domain Adaptation for Multi-modal Cardiac Image Segmentation

TL;DR

This paper introduces a few-shot unsupervised domain adaptation method for cardiac image segmentation that effectively adapts models using only one unlabeled target sample, addressing data scarcity in medical imaging.

Contribution

The paper proposes FUDA, a novel approach that generates diverse target-style images from a single sample using RAIN and trains segmentation models with these images, advancing UDA in data-limited scenarios.

Findings

Improves Dice score by 0.33 in target domain

Achieves 0.28 Dice score improvement in one-shot setting

Demonstrates effectiveness with only one unlabeled target sample

Abstract

Unsupervised domain adaptation (UDA) methods intend to reduce the gap between source and target domains by using unlabeled target domain and labeled source domain data, however, in the medical domain, target domain data may not always be easily available, and acquiring new samples is generally time-consuming. This restricts the development of UDA methods for new domains. In this paper, we explore the potential of UDA in a more challenging while realistic scenario where only one unlabeled target patient sample is available. We call it Few-shot Unsupervised Domain adaptation (FUDA). We first generate target-style images from source images and explore diverse target styles from a single target patient with Random Adaptive Instance Normalization (RAIN). Then, a segmentation network is trained in a supervised manner with the generated target images. Our experiments demonstrate that FUDA improves the segmentation performance by 0.33 of Dice score on the target domain compared with the baseline, and it also gives 0.28 of Dice score improvement in a more rigorous one-shot setting. Our code is available at \url{https://github.com/MingxuanGu/Few-shot-UDA}.