Domain and Content Adaptive Convolution based Multi-Source Domain Generalization for Medical Image Segmentation

TL;DR

This paper introduces a novel multi-source domain generalization model with domain and content adaptive convolutions, significantly improving medical image segmentation across different modalities and unseen domains.

Contribution

The paper proposes the DCAC model with dynamic domain and content adaptive convolution modules, enhancing flexibility and performance in medical image segmentation tasks.

Findings

Outperforms baseline and state-of-the-art methods on multiple segmentation tasks

Effective adaptation to unseen domains through dynamic convolution modules

Demonstrates superior segmentation accuracy across various medical imaging modalities

Abstract

The domain gap caused mainly by variable medical image quality renders a major obstacle on the path between training a segmentation model in the lab and applying the trained model to unseen clinical data. To address this issue, domain generalization methods have been proposed, which however usually use static convolutions and are less flexible. In this paper, we propose a multi-source domain generalization model based on the domain and content adaptive convolution (DCAC) for the segmentation of medical images across different modalities. Specifically, we design the domain adaptive convolution (DAC) module and content adaptive convolution (CAC) module and incorporate both into an encoder-decoder backbone. In the DAC module, a dynamic convolutional head is conditioned on the predicted domain code of the input to make our model adapt to the unseen target domain. In the CAC module, a dynamic convolutional head is conditioned on the global image features to make our model adapt to the test image. We evaluated the DCAC model against the baseline and four state-of-the-art domain generalization methods on the prostate segmentation, COVID-19 lesion segmentation, and optic cup/optic disc segmentation tasks. Our results not only indicate that the proposed DCAC model outperforms all competing methods on each segmentation task but also demonstrate the effectiveness of the DAC and CAC modules. Code is available at \url{https://git.io/DCAC}.