Development of a CNN-based decision support system for lung disease diagnosis using chest radiographs

Chest radiographs, or chest X-rays (CXRs), are widely used as first-line diagnostic tools for detecting various chest diseases. However, accurately interpreting CXRs remains challenging, as human diagnostic performance is influenced by individual expertise and other factors, often resulting in delay...

Full description

Saved in:
Bibliographic Details
Main Authors: B. T. Magar, M. A. Rahman, P. K. Saha, M. Ahmad, M. A. Rashid, H. Higa
Format: Article
Language:English
Published: AIP Publishing LLC 2025-03-01
Series:AIP Advances
Online Access:http://dx.doi.org/10.1063/5.0252595
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770200544575488
author B. T. Magar
M. A. Rahman
P. K. Saha
M. Ahmad
M. A. Rashid
H. Higa
author_facet B. T. Magar
M. A. Rahman
P. K. Saha
M. Ahmad
M. A. Rashid
H. Higa
author_sort B. T. Magar
collection DOAJ
description Chest radiographs, or chest X-rays (CXRs), are widely used as first-line diagnostic tools for detecting various chest diseases. However, accurately interpreting CXRs remains challenging, as human diagnostic performance is influenced by individual expertise and other factors, often resulting in delays, high costs, and potential misinterpretations. To address these limitations, automated computer-based detection systems offer the potential to enhance diagnostic accuracy, reduce costs, and enable timely disease identification. This study presents CXRNet, a novel, efficient convolutional neural network (CNN)-based framework designed for multi-class classification of common chest diseases, including cardiomegaly, COVID-19, pneumonia, tuberculosis, and normal. The proposed CXRNet is a 16-layer architecture trained on frontal CXR images collected from diverse sources to ensure robust generalization across datasets. The model incorporates advanced strategies to overcome the limitations of previous approaches. Extensive testing under three different data distribution conditions demonstrated the model’s superior performance, achieving an average accuracy of 95.7%, precision of 95.3%, recall of 95.3%, and an F1-score of 95.3% for multi-class classification. Furthermore, for binary classification tasks, CXRNet achieved over 98% average accuracy across all conditions, outperforming existing methods. These results highlight the potential of CXRNet as a reliable decision support system for efficient and accurate chest disease diagnosis, paving the way for real-time clinical applications.
format Article
id doaj-art-67f78a202c154b9398cdf709a8d5c54d
institution DOAJ
issn 2158-3226
language English
publishDate 2025-03-01
publisher AIP Publishing LLC
record_format Article
series AIP Advances
spelling doaj-art-67f78a202c154b9398cdf709a8d5c54d2025-08-20T03:03:07ZengAIP Publishing LLCAIP Advances2158-32262025-03-01153035052035052-1210.1063/5.0252595Development of a CNN-based decision support system for lung disease diagnosis using chest radiographsB. T. Magar0M. A. Rahman1P. K. Saha2M. Ahmad3M. A. Rashid4H. Higa5Department of Biomedical Engineering, Military Institute of Science and Technology (MIST), Dhaka 1216, BangladeshDepartment of Biomedical Engineering, Military Institute of Science and Technology (MIST), Dhaka 1216, BangladeshDepartment of Biomedical Engineering, Florida International University, Miami, Florida 33174, USADepartment of EEE, Khulna University of Engineering and Technology (KUET), Khulna 9203, BangladeshDepartment of EEE, Noakhali Science and Technology University, Noakhali 3814, BangladeshDepartment of Electrical and Systems Engineering, University of the Ryukyus, Okinawa, JapanChest radiographs, or chest X-rays (CXRs), are widely used as first-line diagnostic tools for detecting various chest diseases. However, accurately interpreting CXRs remains challenging, as human diagnostic performance is influenced by individual expertise and other factors, often resulting in delays, high costs, and potential misinterpretations. To address these limitations, automated computer-based detection systems offer the potential to enhance diagnostic accuracy, reduce costs, and enable timely disease identification. This study presents CXRNet, a novel, efficient convolutional neural network (CNN)-based framework designed for multi-class classification of common chest diseases, including cardiomegaly, COVID-19, pneumonia, tuberculosis, and normal. The proposed CXRNet is a 16-layer architecture trained on frontal CXR images collected from diverse sources to ensure robust generalization across datasets. The model incorporates advanced strategies to overcome the limitations of previous approaches. Extensive testing under three different data distribution conditions demonstrated the model’s superior performance, achieving an average accuracy of 95.7%, precision of 95.3%, recall of 95.3%, and an F1-score of 95.3% for multi-class classification. Furthermore, for binary classification tasks, CXRNet achieved over 98% average accuracy across all conditions, outperforming existing methods. These results highlight the potential of CXRNet as a reliable decision support system for efficient and accurate chest disease diagnosis, paving the way for real-time clinical applications.http://dx.doi.org/10.1063/5.0252595
spellingShingle B. T. Magar
M. A. Rahman
P. K. Saha
M. Ahmad
M. A. Rashid
H. Higa
Development of a CNN-based decision support system for lung disease diagnosis using chest radiographs
AIP Advances
title Development of a CNN-based decision support system for lung disease diagnosis using chest radiographs
title_full Development of a CNN-based decision support system for lung disease diagnosis using chest radiographs
title_fullStr Development of a CNN-based decision support system for lung disease diagnosis using chest radiographs
title_full_unstemmed Development of a CNN-based decision support system for lung disease diagnosis using chest radiographs
title_short Development of a CNN-based decision support system for lung disease diagnosis using chest radiographs
title_sort development of a cnn based decision support system for lung disease diagnosis using chest radiographs
url http://dx.doi.org/10.1063/5.0252595
work_keys_str_mv AT btmagar developmentofacnnbaseddecisionsupportsystemforlungdiseasediagnosisusingchestradiographs
AT marahman developmentofacnnbaseddecisionsupportsystemforlungdiseasediagnosisusingchestradiographs
AT pksaha developmentofacnnbaseddecisionsupportsystemforlungdiseasediagnosisusingchestradiographs
AT mahmad developmentofacnnbaseddecisionsupportsystemforlungdiseasediagnosisusingchestradiographs
AT marashid developmentofacnnbaseddecisionsupportsystemforlungdiseasediagnosisusingchestradiographs
AT hhiga developmentofacnnbaseddecisionsupportsystemforlungdiseasediagnosisusingchestradiographs