Indian Journal of Radiology Indian Journal of Radiology  

   Login   | Users online: 187

Home Bookmark this page Print this page Email this page Small font sizeDefault font size Increase font size     

 

ORIGINAL ARTICLE Table of Contents   
Year : 2021  |  Volume : 31  |  Issue : 5  |  Page : 53-60
Comparing a deep learning model's diagnostic performance to that of radiologists to detect Covid -19 features on chest radiographs


1 Department of Internal Medicine, Saroja Multispecialty Hospital, Thrissur, Kerala, India
2 Department of Computer Science Alumni, West Virginia University, WV, USA
3 K.V.G Medical College, Sullia, Rajiv Gandhi University of Health Sciences, Bangalore, India
4 Department of General Medicine, Father Muller Medical College Hospital, Mangalore, Karnataka, India
5 Jubilee Centre of Medical Research, Jubilee Mission Medical College and Research Institute, Thrissur, Kerala, India
6 Department of Radiodiagnosis, K.V.G Medical College and Hospital, Sullia, Karnataka, India
7 Department of Radiodiagnosis, Travancore Scans, Thiruvananthapuram, Kerala, India
8 Osteoporosis and Bone Metabolism Unit, Department of Endocrinology, Division of Internal Medicine, Singapore General Hospital, Singapore

Correspondence Address:
Prof. Manju Chandran
Senior Consultant and Director, Osteoporosis and Bone Metabolism Unit Department of Endocrinology, Division of Internal Medicine, Singapore General Hospital
Singapore
Dr. Sabitha Krishnamoorthy
MD FACP ABIM, Department of Internal Medicine, Saroja Multispecialty Hospital, Thrissur, Kerala
India
Login to access the Email id

Source of Support: None, Conflict of Interest: None


DOI: 10.4103/ijri.IJRI_914_20

Rights and Permissions

Background: Whether the sensitivity of Deep Learning (DL) models to screen chest radiographs (CXR) for CoVID-19 can approximate that of radiologists, so that they can be adopted and used if real-time review of CXRs by radiologists is not possible, has not been explored before. Objective: To evaluate the diagnostic performance of a doctor-trained DL model (Svita_DL8) to screen for COVID-19 on CXR, and to compare the performance of the DL model with that of expert radiologists. Materials and Methods: We used a pre-trained convolutional neural network to develop a publicly available online DL model to evaluate CXR examinations saved in .jpeg or .png format. The initial model was subsequently curated and trained by an internist and a radiologist using 1062 chest radiographs to classify a submitted CXR as either normal, COVID-19, or a non-COVID-19 abnormal. For validation, we collected a separate set of 430 CXR examinations from numerous publicly available datasets from 10 different countries, case presentations, and two hospital repositories. These examinations were assessed for COVID-19 by the DL model and by two independent radiologists. Diagnostic performance was compared between the model and the radiologists and the correlation coefficient calculated. Results: For detecting COVID-19 on CXR, our DL model demonstrated sensitivity of 91.5%, specificity of 55.3%, PPV 60.9%, NPV 77.9%, accuracy 70.1%, and AUC 0.73 (95% CI: 0.86, 0.95). There was a significant correlation (r = 0.617, P = 0.000) between the results of the DL model and the radiologists' interpretations. The sensitivity of the radiologists is 96% and their overall diagnostic accuracy is 90% in this study. Conclusions: The DL model demonstrated high sensitivity for detecting COVID-19 on CXR. Clinical Impact: The doctor trained DL tool Svita_DL8 can be used in resource-constrained settings to quickly triage patients with suspected COVID-19 for further in-depth review and testing.


[FULL TEXT] [PDF]*
Print this article     Email this article

 Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
 Related articles
  Citation Manager
 Access Statistics
  Reader Comments
  Email Alert *
  Add to My List *
 * Requires registration (Free)
 

 Article Access Statistics
    Viewed963    
    Printed6    
    Emailed0    
    PDF Downloaded40    
    Comments [Add]    

Recommend this journal