IMAGES IN CARDIOTHORACIC IMAGING C oronavirus disease 2019, COVID-19, has recently gained global proportions (1–3). Tis short report illus- trates the use of voxel-level deep learning–based CT seg- mentation of pulmonary opacities (4) for improving quan- tifcation of the disease. A separate set of CT images from 10 cases of COVID-19 confrmed by real-time reverse transcriptase polymerase chain reaction test results was se- lected for training purposes. Expert manual segmentation of the lungs and pulmonary opacities was used as reference. A convolutional neural network based on U-Net architec- ture (5) was developed to predict the expert segmentation. We used this pipeline to analyze the contrasting evolution This copy is for personal use only. To order printed copies, contact reprints@rsna.org Longitudinal Assessment of COVID-19 Using a Deep Learning–based Quantitative CT Pipeline: Illustration of Two Cases Yukun Cao • Zhanwei Xu • Jianjiang Feng • Cheng Jin • Xiaoyu Han • Hanping Wu • Heshui Shi From the Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China (Y.C., X.H., H.S.); Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China (Y.C., X.H., H.S.); Department of Automation, Tsinghua University, Beijing, China (Z.X., J.F., C.J.); and Department of Radiology, Michigan Medicine, University of Michigan, Ann Arbor, Mich (H.W.). Received February 25, 2020; revision requested March 2; revision received March 13; accepted March 16. Address correspondence to H.S. (e-mail: heshuishi@hust.edu.cn). Conficts of interest are listed at the end of this article. Radiology: Cardiothoracic Imaging 2020; 2(2):e200082 • https://doi.org/10.1148/ryct.2020200082 • Content code: • © RSNA, 2020 Figure 1: Evolution of COVID-19 in a 48-year-old woman across 16 days of treatment. A, Axial unenhanced chest CT images at four time points (dates annotated in each panel) show peripheral ground-glass opacities and consolidation. B, Color overlay of voxel-level segmenta- tion at the same level and time points as in A show pulmonary opacities displayed in yellow and normal lung in blue. C, Coronal reconstructions at the same time points as in A show progressive improvement of the lung opacities. D, Three-dimensional volume-rendered reconstructions at the same time points as in A show pulmonary opacities displayed in yellow, normal lung and vessels in light gray, and tracheobronchial tree in green. The volumetric assessment of the pulmonary opacities derived from the deep learning–based quantitative CT analysis is annotated at different time points on the volume-rendered images. LOV = lung opacification volume.