Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography

Jun Chen,Liang Zhang,Kuo Zhang,Dexin Gong,Yilin Zhao,Mengjiao Zhang,Yonggui Wang,Xiao Hu,Lianlian Wu,Xi Chen,Lilei Yu,Shulan Huang,Shan Hu,Ming Yang,Yijie Zhu ,Fan Cheng,Qiuxiang Chen,Binbin Zheng ,Youming Xu,Huiling Wu,Jun Zhang,Zaili Dong ,Xiao Yang,Honggang Yu

doi:10.1038/s41598-020-76282-0

Abstract

Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. We aimed to construct a system based on deep learning for detecting COVID-19 pneumonia on high resolution CT. For model development and validation, 46,096 anonymous images from 106 admitted patients, including 51 patients of laboratory confirmed COVID-19 pneumonia and 55 control patients of other diseases in Renmin Hospital of Wuhan University were retrospectively collected. Twenty-seven prospective consecutive patients in Renmin Hospital of Wuhan University were collected to evaluate the efficiency of radiologists against 2019-CoV pneumonia with that of the model. An external test was conducted in Qianjiang Central Hospital to estimate the system’s robustness. The model achieved a per-patient accuracy of 95.24% and a per-image accuracy of 98.85% in internal retrospective dataset. For 27 internal prospective patients, the system achieved a comparable performance to that of expert radiologist. In external dataset, it achieved an accuracy of 96%. With the assistance of the model, the reading time of radiologists was greatly decreased by 65%. The deep learning model showed a comparable performance with expert radiologist, and greatly improved the efficiency of radiologists in clinical practice.

Highlights

Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia
The nucleic acid detection was considered determinant for identifying the COVID-19 infection and more rapid detection kit for the novel coronavirus has come into mass production, computed tomography (CT) scan is still the most efficient modality for detecting and evaluating the severity of p neumonia[5]
Among 4382 CT images from 11 patients of COVID-19 pneumonia and 9369 images from 31 control patients, the model correctly diagnosed the patients with a per-patient sensitivity of 100%, specificity of 93.55%, accuracy of 95.24%, positive prediction value (PPV) of 84.62%, and negative prediction value (NPV) of 100%

Summary

Introduction

Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. Twenty-seven prospective consecutive patients in Renmin Hospital of Wuhan University were collected to evaluate the efficiency of radiologists against 2019-CoV pneumonia with that of the model. Of COVID-19 were reported within 1 day on Feb 13, 2020 in Wuhan, including 13,332 cases of clinical d iagnoses[8] This highlighted the importance of CT in the diagnosis of COVID-19 pneumonia. Because the lung infection foci are small in the early stage of the COVID-19 infection, thinner layer (2.5 mm, 1.25 mm or even 0.625 mm) scanning were usually needed instead of conventional CT scan (5 mm) for diagnosis, which would be more timeconsuming All these made radiologists overloaded, delay the diagnosis and isolation of patients, affect patient’s treatment and prognosis, and affect the control of COVID-19 epidemic

Objectives

Methods

Results

Conclusion