Presentation
7 April 2023 Bayesian neural networks for severity assessment of COVID-19 pneumonia from chest x-ray using a multi-reader and binational dataset
Author Affiliations +
Abstract
We present a new approach based on Bayesian neural networks (BNNs) for severity assessment of lung diseases using chest X-rays (CXRs). In contrast to reqular NNs, our model can provide uncertainty of the prediction for an input CXR which is crucial for clinical implementation of machine learning-assisted tools in radiology. With no loss of generality, we apply this method for severity assessment of COVID-19 pneumonia using multi-reader datasets from the USA and Korea. Our results show that the BNN can classify COVID-19 pneumonia with performance comparable to human experts while providing prediction uncertainty. We also compare the uncertainty of the model over different severity classes with inter-reader variability among the radiologists.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mohammadreza Zandehshahvar, Marly van Assen, Eun Young Kim, Yashar Kiarashi, Vikranth Keerthipati, Arthur E. Stillman, Peter Filev, Amir H. Davarpanah, Eugene A. Berkowitz, Stefan Tigges, Scott J. Lee, Brianna L. Vey, Carlo De Cecco, and Ali Adibi "Bayesian neural networks for severity assessment of COVID-19 pneumonia from chest x-ray using a multi-reader and binational dataset", Proc. SPIE 12465, Medical Imaging 2023: Computer-Aided Diagnosis, 124650G (7 April 2023); https://doi.org/10.1117/12.2653346
Advertisement
Advertisement
KEYWORDS
Chest imaging

Neural networks

Data modeling

Lung

Machine learning

Monte Carlo methods

Radiology

Back to Top