Covid-19 Detection From Chest X-Ray Images Using Explainable Deep Learning Framework

Read full text Summarise with VIRAT
Cited by: 0
References: 7

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

COVID-19 continues to be a significant worldwide health issue, especially in resource-constrained environments where rapid and accurate diagnosis is critical.Traditional RT-PCR testing, although considered the gold standard, often suffers from limited availability, delayed turnaround times, and reduced sensitivity in early stages.This study suggests an Explainable Deep Learning Framework for COVID-19 detection using chest X-ray in order to get around these restrictions (CXR) images.The system integrates a pre-trained EfficientNet-B0 convolutional neural network, radiograph-aware preprocessing, and Grad-CAM-based explainability for transparent classification.The framework performs binary classification (COVID-19 vs Normal) and is deployed as a lightweight, web-based inference system using Flask for real-time predictions.Experimental results demonstrate an accuracy of 97.8%, precision of 97.1%, and recall of 98.5%, showing strong potential for rapid triage and clinical support.

Fields of Study & Subjects

COVID-19 diagnosis using AI Explainable Artificial Intelligence (XAI) Artificial Intelligence in Healthcare and Education

Publication details

Journal / source
International Research Journal of Modernization in Engineering Technology and Science
Publication date
23 March 2026
Language
EN