Diagnosing COVID-19 Severity from Chest X-Ray Images Using ViT and CNN Architectures

TL;DR

This study evaluates the effectiveness of CNNs and ViTs in predicting COVID-19 severity from chest X-ray images, achieving high accuracy and providing a large, merged dataset for future research.

Contribution

It introduces a large COVID-19 severity dataset and compares transfer learning models, highlighting DenseNet161's classification accuracy and ViT's regression performance.

Findings

DenseNet161 achieved 80% accuracy in severity classification.

ViT achieved a mean absolute error of 0.5676 in severity regression.

The dataset and source code are publicly available.

Abstract

The COVID-19 pandemic strained healthcare resources and prompted discussion about how machine learning can alleviate physician burdens and contribute to diagnosis. Chest x-rays (CXRs) are used for diagnosis of COVID-19, but few studies predict the severity of a patient's condition from CXRs. In this study, we produce a large COVID severity dataset by merging three sources and investigate the efficacy of transfer learning using ImageNet- and CXR-pretrained models and vision transformers (ViTs) in both severity regression and classification tasks. A pretrained DenseNet161 model performed the best on the three class severity prediction problem, reaching 80% accuracy overall and 77.3%, 83.9%, and 70% on mild, moderate and severe cases, respectively. The ViT had the best regression results, with a mean absolute error of 0.5676 compared to radiologist-predicted severity scores. The project's source code is publicly available.