Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization

Changjie Lu, Shen Zheng, Gaurav Gupta; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2588-2597

Abstract


Unsupervised domain adaptation approaches have recently succeeded in various medical image segmentation tasks. The reported works often tackle the domain shift problem by aligning the domain-invariant features and minimizing the domain-specific discrepancies. That strategy works well when the difference between a specific domain and between different domains is slight. However, the generalization ability of these models on diverse imaging modalities remains a significant challenge. This paper introduces UDA-VAE++, an unsupervised domain adaptation framework for cardiac segmentation with a compact loss function lower bound. To estimate this new lower bound, we develop a novel Structure Mutual Information Estimation (SMIE) block with a global estimator, a local estimator, and a prior information matching estimator to maximize the mutual information between the reconstruction and segmentation tasks. Specifically, we design a novel sequential reparameterization scheme that enables information flow and variance correction from the low-resolution latent space to the high-resolution latent space. Comprehensive experiments on benchmark cardiac segmentation datasets demonstrate that our model outperforms previous state-of-the-art qualitatively and quantitatively.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2022_CVPR, author = {Lu, Changjie and Zheng, Shen and Gupta, Gaurav}, title = {Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {2588-2597} }