Virtual versus reality: external validation of COVID-19 classifiers using XCAT phantoms for chest radiography

Lavsen Dahal; Fakrul Islam Tushar; Ehsan Abadi; Rafael B. Fricks; Maciej Mazurowski; W. Paul Segars; Ehsan Samei; Joseph Y. Lo

doi:10.1117/12.2612975

4 April 2022 Virtual versus reality: external validation of COVID-19 classifiers using XCAT phantoms for chest radiography

Lavsen Dahal, Fakrul Islam Tushar, Ehsan Abadi, Rafael B. Fricks, Maciej Mazurowski, W. Paul Segars, Ehsan Samei, Joseph Y. Lo

Author Affiliations +

Proceedings Volume 12031, Medical Imaging 2022: Physics of Medical Imaging; 120310U (2022) https://doi.org/10.1117/12.2612975
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Abstract

Many published studies use deep learning models to predict COVID-19 from chest x-ray (CXR) images, often reporting high performances. However, the models do not generalize well on independent external testing. Common limitations include the lack of medical imaging data and disease labels, leading to training on small datasets or drawing classes from different institutions. To address these concerns, we designed an external validation study of deep learning classifiers for COVID-19 in CXR images including XCAT phantoms as well. We hypothesize that a simulated CXR image dataset obtained from the XCAT phantom allows for better control of the dataset including pixel-level ground truth. This setup allows for multiple advantages: First, we can validate the publicly available models using simulated chest x-rays. Secondly, we can also address clinically relevant questions with this setup such as effect of dose levels and sizeof COVID-19 pneumonia in performance of deep learning classifier. We

Conference Presentation

Citation Download Citation

Lavsen Dahal, Fakrul Islam Tushar, Ehsan Abadi, Rafael B. Fricks, Maciej Mazurowski, W. Paul Segars, Ehsan Samei, and Joseph Y. Lo "Virtual versus reality: external validation of COVID-19 classifiers using XCAT phantoms for chest radiography", Proc. SPIE 12031, Medical Imaging 2022: Physics of Medical Imaging, 120310U (4 April 2022); https://doi.org/10.1117/12.2612975

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available