Chen Han, Jiang Yifan, Loew Murray, Ko Hanseok
School of Electrical Engineering, Korea University, Seoul, 02841 South Korea.
Department of Biomedical Engineering, George Washington University, Washington, DC USA.
Appl Intell (Dordr). 2022;52(6):6340-6353. doi: 10.1007/s10489-021-02691-x. Epub 2021 Sep 7.
Automatic segmentation of infection areas in computed tomography (CT) images has proven to be an effective diagnostic approach for COVID-19. However, due to the limited number of pixel-level annotated medical images, accurate segmentation remains a major challenge. In this paper, we propose an unsupervised domain adaptation based segmentation network to improve the segmentation performance of the infection areas in COVID-19 CT images. In particular, we propose to utilize the synthetic data and limited unlabeled real COVID-19 CT images to jointly train the segmentation network. Furthermore, we develop a novel domain adaptation module, which is used to align the two domains and effectively improve the segmentation network's generalization capability to the real domain. Besides, we propose an unsupervised adversarial training scheme, which encourages the segmentation network to learn the domain-invariant feature, so that the robust feature can be used for segmentation. Experimental results demonstrate that our method can achieve state-of-the-art segmentation performance on COVID-19 CT images.
计算机断层扫描（CT）图像中感染区域的自动分割已被证明是一种针对COVID-19的有效诊断方法。然而，由于像素级标注的医学图像数量有限，准确分割仍然是一个重大挑战。在本文中，我们提出了一种基于无监督域适应的分割网络，以提高COVID-19 CT图像中感染区域的分割性能。具体而言，我们建议利用合成数据和有限的未标记真实COVID-19 CT图像来联合训练分割网络。此外，我们开发了一种新颖的域适应模块，用于对齐两个域并有效提高分割网络对真实域的泛化能力。此外，我们提出了一种无监督对抗训练方案，鼓励分割网络学习域不变特征，以便将鲁棒特征用于分割。实验结果表明，我们的方法可以在COVID-19 CT图像上实现最先进的分割性能。
