Contrastive Domain Disentanglement for Generalizable Medical Image Segmentation

TL;DR

This paper introduces a contrastive domain disentanglement network that decomposes medical images into anatomical and modality factors, uses style contrastive loss for domain separation, and employs domain augmentation to improve generalization across unseen datasets.

Contribution

The paper proposes a novel Contrastive Domain Disentangle (CDD) network with style contrastive loss and domain augmentation for improved generalizable medical image segmentation.

Findings

Outperforms state-of-the-art methods in domain generalization

Effective disentanglement of anatomical and modality features

Enhanced model robustness across multi-site datasets

Abstract

Efficiently utilizing discriminative features is crucial for convolutional neural networks to achieve remarkable performance in medical image segmentation and is also important for model generalization across multiple domains, where letting model recognize domain-specific and domain-invariant information among multi-site datasets is a reasonable strategy for domain generalization. Unfortunately, most of the recent disentangle networks are not directly adaptable to unseen-domain datasets because of the limitations of offered data distribution. To tackle this deficiency, we propose Contrastive Domain Disentangle (CDD) network for generalizable medical image segmentation. We first introduce a disentangle network to decompose medical images into an anatomical representation factor and a modality representation factor. Then, a style contrastive loss is proposed to encourage the modality representations from the same domain to distribute as close as possible while different domains are estranged from each other. Finally, we propose a domain augmentation strategy that can randomly generate new domains for model generalization training. Experimental results on multi-site fundus image datasets for optic cup and disc segmentation show that the CDD has good model generalization. Our proposed CDD outperforms several state-of-the-art methods in domain generalizable segmentation.