Vision Transformer-based Model for Severity Quantification of Lung Pneumonia Using Chest X-ray Images

TL;DR

This paper introduces ViTReg-IP, a Vision Transformer-based model that efficiently quantifies COVID-19 severity from chest X-rays with high accuracy and generalizability, requiring fewer parameters and less computational resources.

Contribution

The paper presents a novel ViT-based regression model for COVID-19 severity assessment that outperforms existing methods in accuracy and efficiency, with demonstrated robustness across multiple datasets.

Findings

High accuracy in severity quantification

Strong generalization across datasets

Low computational cost

Abstract

To develop generic and reliable approaches for diagnosing and assessing the severity of COVID-19 from chest X-rays (CXR), a large number of well-maintained COVID-19 datasets are needed. Existing severity quantification architectures require expensive training calculations to achieve the best results. For healthcare professionals to quickly and automatically identify COVID-19 patients and predict associated severity indicators, computer utilities are needed. In this work, we propose a Vision Transformer (ViT)-based neural network model that relies on a small number of trainable parameters to quantify the severity of COVID-19 and other lung diseases. We present a feasible approach to quantify the severity of CXR, called Vision Transformer Regressor Infection Prediction (ViTReg-IP), derived from a ViT and a regression head. We investigate the generalization potential of our model using a variety of additional test chest radiograph datasets from different open sources. In this context, we performed a comparative study with several competing deep learning analysis methods. The experimental results show that our model can provide peak performance in quantifying severity with high generalizability at a relatively low computational cost. The source codes used in our work are publicly available at https://github.com/bouthainas/ViTReg-IP.