A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19)

Abstract

To control the spread of Corona Virus Disease , screening large numbers of suspected cases for appropriate quarantine and treatment is a priority.Pathogenic laboratory testing is the diagnostic gold standard but it is time consuming with significant false negative results. Fast and accurate diagnostic methods are urgently needed to combat the disease. Based on COVID-19 radiographical changes in CT images, we aimed to develop a deep learning method that could extract COVID-19's graphical features in order to provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control.Methods：We collected 1,119 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the Inception transfer-learning model to establish the algorithm, followed by internal and external validation. Results:The internal validation achieved a total accuracy of 89.5% with specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images that first two nucleic acid test results were negative, 46 were predicted as COVID-19 positive by the algorithm, with the accuracy of 85.2%. Conclusion:These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis.

Systematic review and critical appraisal of prediction models for diagnosis and prognosis of COVID-19 infection

“…Barstugan, Ozkaya, et al 31 unclear unclear unclear high Chen, Wu, et al 26 high unclear low high *1 Gozes, Frid-Adar, et al 25 unclear unclear high high Jin, Chen, et al 11 high unclear unclear high *2 Jin, Wang, et al 33 high unclear high high *1 Li, Qin, et al 34 low unclear low high Shan, Gao, et al 28 unclear unclear high high *2 Shi, Xia, et al 36 high unclear low high Wang, Kang, et al 29 high unclear low high Xu, Jiang, et al 27 high unclear high high Ying, Zheng, et al 23 unclear unclear low high Zheng, Deng, et al 38 unclear unclear high high…”

Development and Evaluation of an AI System for COVID-19 Diagnosis

“…As a very recent disease, we have not yet found AI studies for COVID-19 diagnosis in peer-reviewed publications, but a few reports about COVID-19 diagnosis algorithms based on chest CT in preprint form [14,15]. Wang et al [14] describe a COVID-19 diagnosis system with specificity of 67% and sensitivity of 74% on 216 slices extracted from CT volumes of patients (the whole dataset consists of 44 positive and 55 negative cases, but split strategy of dataset is unclear).…”

“…As a very recent disease, we have not yet found AI studies for COVID-19 diagnosis in peer-reviewed publications, but a few reports about COVID-19 diagnosis algorithms based on chest CT in preprint form [14,15]. Wang et al [14] describe a COVID-19 diagnosis system with specificity of 67% and sensitivity of 74% on 216 slices extracted from CT volumes of patients (the whole dataset consists of 44 positive and 55 negative cases, but split strategy of dataset is unclear). Chen et al [15] describe a COVID-19 diagnosis system with a performance comparable to that of an expert radiologist, however the system is validated based on a quite small dataset with only 19 confirmed COVID-19 patients and only one radiologist is compared.…”

Improving Coronavirus (COVID-19) Diagnosis using Deep Transfer Learning

“…They employed 2D and 3D deep learning models to visualizes the virus effects on the lungs and achieved 98.2% sensitivity. In [26] Song et al [20] presented another study investigated COVID-19 pneumonia from 51 patients of Wuhan, China. In [21], they proposed a deep neural network named Details Relation Extraction neural network (DRE-Net) to obtain the image level predictions by extracting the deep details from CT images.…”