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

By Jun Chen, Lianlian Wu, Jun Zhang, Liang Zhang, D. Gong, Yilin Zhao, Shan Hu, Yonggui Wang, Xiao Hu, Biqing Zheng and 8 more. medRxiv, 2020

324 citations recorded by the source corpus.

Background: Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. Our research aimed to construct a system based on deep learning for detecting COVID-19 pneumonia on high resolution CT, relieve working pressure of radiologists and contribute to the control of the epidemic. Methods: 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 (Wuhan, Hubei province, China) were retrospectively collected and processed. Twenty-seven consecutive patients undergoing CT scans in Feb, 5, 2020 in Renmin Hospital of Wuhan University were prospectively collected to evaluate and compare the efficiency of radiologists against 2019-CoV pneumonia with that of the model. Findings: The model achieved a per-patient sensitivity of 100%, specificity of 93.55%, accuracy of 95.24%, PPV of 84.62%, and NPV of 100%; a per-image sensitivity of 94.34%, specificity of 99.16%, accuracy of 98.85%, PPV of 88.37%, and NPV of 99.61% in retrospective dataset. For 27 prospective patients, the model achieved a comparable performance to that of expert radiologist. With the assistance of the model, the reading time of radiologists was greatly decreased by 65%. Conclusion: The deep learning model showed a comparable performance with expert radiologist, and greatly improve the efficiency of radiologists in clinical practice. It holds great potential to relieve the pressure of frontline radiologists, improve early diagnosis, isolation and treatment, and thus contribute to the control of the epidemic.

Subfields: Infectious Diseases, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/d5928d3fc4acf1f737c137836344310c3557b9ae

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Infectious Diseases

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images (2020, background): “A number of studies have proposed deep learning systems based on chest CT imaging to distinguish COVID-19 cases from non-COVID-19 cases (which may include both normal and abnormal cases) [16, 20, 21, 22, 23, 24, 25, 26, 27, 17, 28, 29, 30].”
COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data (2020, result): “Several studies have shown promising results in using deep learning models to automated diagnosis of COVID-19 from CT images [6], [11], [12].”
Deep Learning for Classification and Localization of COVID-19 Markers in Point-of-Care Lung Ultrasound (2020, methodology): “In [27], a U-Net type network is used to regress”
Diagnosing COVID-19 pneumonia from x-ray and CT images using deep learning and transfer learning algorithms (2020, methodology): “Although the COVID-19 emerged in China, it has now been identified in many other countries around the globe [1], [2].”
Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19 (2020, methodology): “The popular segmentation networks for COVID-19 include classic U-Net [51]–[56], UNet++ [57], [58], VB-Net [59].”
Mapping the Landscape of Artificial Intelligence Applications against COVID-19 (2020, background): “Similarly, Chen et al. (2020b)† found that by training a UNet++ neural network (Zhou et al., 2018) on over 6,000 CT image slices of both healthy and infected patients labeled by expert radiologists, it was possible to achieve performance comparable to that of an expert radiologist.”
The Role of Imaging in the Detection and Management of COVID-19: A Review (2020, methodology): “Chen et al. [70] used UNet ++ [82] to extract abnormal lung areas in CT images.”
A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images (2020, methodology): “The UNet ++ [24] was also used for detection [25] and segmentation [26] of the infection lesions from CT scans.”
Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging (2020, unknown): “[49] 2D Unet++ COVID-19, viral, baterial and Pneu.”
AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system (2020, unknown): “Chen et al. [36] train a U-Net++ based segmentation model to provide COVID-19 related lesions.”
Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning (2020, background): “COVID-19 became an epidemic all over the World (Huang et al., 2020; Wu et al., 2020).”