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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Slika, Bouthaina, Dornaika, Fadi, Merdji, Hamid, Hammoudi, Karim
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916452328538112
author Slika, Bouthaina
Dornaika, Fadi
Merdji, Hamid
Hammoudi, Karim
author_facet Slika, Bouthaina
Dornaika, Fadi
Merdji, Hamid
Hammoudi, Karim
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2303_11935
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Vision Transformer-based Model for Severity Quantification of Lung Pneumonia Using Chest X-ray Images
Slika, Bouthaina
Dornaika, Fadi
Merdji, Hamid
Hammoudi, Karim
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
I.4.0; I.4.9; I.4.7; I.2.0
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.
title Vision Transformer-based Model for Severity Quantification of Lung Pneumonia Using Chest X-ray Images
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
I.4.0; I.4.9; I.4.7; I.2.0
url https://arxiv.org/abs/2303.11935