School of Data Science, Fudan University, Shanghai, 200433, China.
School of Data Science, Fudan University, Shanghai, 200433, China. Electronic address: https://www.sdspeople.fudan.edu.cn/zhuangxiahai/.
Med Image Anal. 2023 Oct;89:102889. doi: 10.1016/j.media.2023.102889. Epub 2023 Jul 5.
Due to the cross-domain distribution shift aroused from diverse medical imaging systems, many deep learning segmentation methods fail to perform well on unseen data, which limits their real-world applicability. Recent works have shown the benefits of extracting domain-invariant representations on domain generalization. However, the interpretability of domain-invariant features remains a great challenge. To address this problem, we propose an interpretable Bayesian framework (BayeSeg) through Bayesian modeling of image and label statistics to enhance model generalizability for medical image segmentation. Specifically, we first decompose an image into a spatial-correlated variable and a spatial-variant variable, assigning hierarchical Bayesian priors to explicitly force them to model the domain-stable shape and domain-specific appearance information respectively. Then, we model the segmentation as a locally smooth variable only related to the shape. Finally, we develop a variational Bayesian framework to infer the posterior distributions of these explainable variables. The framework is implemented with neural networks, and thus is referred to as deep Bayesian segmentation. Quantitative and qualitative experimental results on prostate segmentation and cardiac segmentation tasks have shown the effectiveness of our proposed method. Moreover, we investigated the interpretability of BayeSeg by explaining the posteriors and analyzed certain factors that affect the generalization ability through further ablation studies. Our code is released via https://zmiclab.github.io/projects.html.
由于不同医学成像系统引起的跨域分布偏移，许多深度学习分割方法在未见数据上表现不佳，这限制了它们在实际中的应用。最近的研究表明，在域泛化上提取域不变表示的好处。然而，域不变特征的可解释性仍然是一个巨大的挑战。为了解决这个问题，我们通过对图像和标签统计进行贝叶斯建模，提出了一种可解释的贝叶斯框架（BayeSeg），以增强医学图像分割的模型泛化能力。具体来说，我们首先将图像分解为空间相关变量和空间变化变量，并为它们分配层次贝叶斯先验，以明确地迫使它们分别对域稳定的形状和特定于域的外观信息进行建模。然后，我们将分割建模为仅与形状相关的局部平滑变量。最后，我们开发了一个变分贝叶斯框架来推断这些可解释变量的后验分布。该框架是用神经网络实现的，因此被称为深度贝叶斯分割。在前列腺分割和心脏分割任务上的定量和定性实验结果表明了我们提出的方法的有效性。此外，我们通过解释后验来研究 BayeSeg 的可解释性，并通过进一步的消融研究分析了影响泛化能力的某些因素。我们的代码可通过 https://zmiclab.github.io/projects.html 获取。
