Diagnosis of COVID-19 with simultaneous accurate prediction of cardiac abnormalities from chest computed tomographic images
Author/Creator ORCID
Date
Type of Work
Department
Program
Citation of Original Publication
Moitra, Moumita, Maha Alafeef, Arjun Narasimhan, Vikram Kakaria, Parikshit Moitra, and Dipanjan Pan. “Diagnosis of COVID-19 with Simultaneous Accurate Prediction of Cardiac Abnormalities from Chest Computed Tomographic Images.” PLOS ONE 18, no. 12 (December 14, 2023): e0290494. https://doi.org/10.1371/journal.pone.0290494.
Rights
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
CC BY 4.0 DEED Attribution 4.0 International
CC BY 4.0 DEED Attribution 4.0 International
Subjects
Abstract
COVID-19 has potential consequences on the pulmonary and cardiovascular health of millions of infected people worldwide. Chest computed tomographic (CT) imaging has remained the first line of diagnosis for individuals infected with SARS-CoV-2. However, differentiating COVID-19 from other types of pneumonia and predicting associated cardiovascular complications from the same chest-CT images have remained challenging. In this study, we have first used transfer learning method to distinguish COVID-19 from other pneumonia and healthy cases with 99.2% accuracy. Next, we have developed another CNN-based deep learning approach to automatically predict the risk of cardiovascular disease (CVD) in COVID-19 patients compared to the normal subjects with 97.97% accuracy. Our model was further validated against cardiac CT-based markers including cardiac thoracic ratio (CTR), pulmonary artery to aorta ratio (PA/A), and presence of calcified plaque. Thus, we successfully demonstrate that CT-based deep learning algorithms can be employed as a dual screening diagnostic tool to diagnose COVID-19 and differentiate it from other pneumonia, and also predicts CVD risk associated with COVID-19 infection.