A deep-learning pipeline for the diagnosis and discrimination of viral, non-viral and COVID-19 pneumonia from chest X-ray images

作者：Wang, Guangyu; Liu, Xiaohong; Shen, Jun; Wang, Chengdi; Li, Zhihuan; Ye, Linsen; Wu, Xingwang; Chen, Ting; Wang, Kai; Zhang, Xuan; Zhou, Zhongguo; Yang, Jian; Sang, Ye; Deng, Ruiyun; Liang, Wenhua; Yu, Tao; Gao, Ming; Wang, Jin; Yang, Zehong; Cai, Huimin; Lu, Guangming; Zhang, Lingyan; Yang, Lei; Xu, Wenqin; Wang, Winston; Olevera, Andrea; Ziyar, Ian; Zhang, Charlotte; Li, Oulan; Liao, Weihua; Liu, Jun; Chen, Wen; Chen, Wei; Shi, Jichan; Zheng, Lianghong; Zhang, Longjiang; Yan, Zhihan

来源：Nature Biomedical Engineering, 2021, 5(6): 509-+.

DOI：10.1038/s41551-021-00704-1

• MEDICAL IMAGING DATA
• AI SYSTEM
• RADIOGRAPHS
• DATABASE

An automated deep-learning pipeline for chest-X-ray-image standardization, lesion visualization and disease diagnosis can identify viral pneumonia caused by COVID-19, assess its severity, and discriminate it from other types of pneumonia. @@@ Common lung diseases are first diagnosed using chest X-rays. Here, we show that a fully automated deep-learning pipeline for the standardization of chest X-ray images, for the visualization of lesions and for disease diagnosis can identify viral pneumonia caused by coronavirus disease 2019 (COVID-19) and assess its severity, and can also discriminate between viral pneumonia caused by COVID-19 and other types of pneumonia. The deep-learning system was developed using a heterogeneous multicentre dataset of 145,202 images, and tested retrospectively and prospectively with thousands of additional images across four patient cohorts and multiple countries. The system generalized across settings, discriminating between viral pneumonia, other types of pneumonia and the absence of disease with areas under the receiver operating characteristic curve (AUCs) of 0.94-0.98; between severe and non-severe COVID-19 with an AUC of 0.87; and between COVID-19 pneumonia and other viral or non-viral pneumonia with AUCs of 0.87-0.97. In an independent set of 440 chest X-rays, the system performed comparably to senior radiologists and improved the performance of junior radiologists. Automated deep-learning systems for the assessment of pneumonia could facilitate early intervention and provide support for clinical decision-making.

• 单位
  四川大学; 1; 清华大学; 中山大学; 南京大学; 广州医学院; 安徽医科大学; 南方医科大学