An interpretable deep learning workflow for discovering subvisual abnormalities in CT scans of COVID-19 inpatients and survivors

Longxi Zhou, Xianglin Meng, Yuxin Huang, Kai Kang, Juexiao Zhou, Yuetan Chu, Haoyang Li, Dexuan Xie, Jiannan Zhang, Weizhen Yang, Na Bai, Yi Zhao, Mingyan Zhao, Guohua Wang, Lawrence Carin, Xigang Xiao, Kaijiang Yu, Zhaowen Qiu, Xin Gao

Abstract: Respiratory complications after a COVID infection are a growing concern, but follow-up chest CT scans of COVID-19 survivors hardly present any recognizable lesions. A deep learning-based method was developed that calculates a scan-specific optimal window and removes irrelevant tissues such as airways and blood vessels from images with segmentation models, so that subvisual abnormalities in lung scans become visible.