Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation

by   Shishuai Hu, et al.

Deep learning-based medical image segmentation models suffer from performance degradation when deployed to a new healthcare center. To address this issue, unsupervised domain adaptation and multi-source domain generalization methods have been proposed, which, however, are less favorable for clinical practice due to the cost of acquiring target-domain data and the privacy concerns associated with redistributing the data from multiple source domains. In this paper, we propose a Channel-level Contrastive Single Domain Generalization (C^2SDG) model for medical image segmentation. In C^2SDG, the shallower features of each image and its style-augmented counterpart are extracted and used for contrastive training, resulting in the disentangled style representations and structure representations. The segmentation is performed based solely on the structure representations. Our method is novel in the contrastive perspective that enables channel-wise feature disentanglement using a single source domain. We evaluated C^2SDG against six SDG methods on a multi-domain joint optic cup and optic disc segmentation benchmark. Our results suggest the effectiveness of each module in C^2SDG and also indicate that C^2SDG outperforms the baseline and all competing methods with a large margin. The code will be available at <>.


page 2

page 8

page 12


Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning

Unsupervised domain adaptation (UDA) has increasingly gained interests f...

Frequency-mixed Single-source Domain Generalization for Medical Image Segmentation

The annotation scarcity of medical image segmentation poses challenges i...

Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation

Although recent years have witnessed the great success of convolutional ...

Domain and Content Adaptive Convolution for Domain Generalization in Medical Image Segmentation

The domain gap caused mainly by variable medical image quality renders a...

MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalization

Accurate segmentation of clustered microcalcifications in mammography is...

Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation

Single-source domain generalization (SDG) in medical image segmentation ...

Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentation

Accurate and robust medical image segmentation is fundamental and crucia...

Please sign up or login with your details

Forgot password? Click here to reset