Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures

Abstract BackgroundTuberculosis (TB) remains a significant global health challenge, as current diagnostic methods are often resource-intensive, time-consuming, and inaccessible in many high-burden communities, necessitating more efficient and accurate diagnostic methods to imp...

Full description

Saved in:
Bibliographic Details
Main Authors: Alex Mirugwe, Lillian Tamale, Juwa Nyirenda
Format: Article
Language:English
Published: JMIR Publications 2025-07-01
Series:JMIRx Med
Online Access:https://xmed.jmir.org/2025/1/e66029
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117122940731392
author Alex Mirugwe
Lillian Tamale
Juwa Nyirenda
author_facet Alex Mirugwe
Lillian Tamale
Juwa Nyirenda
author_sort Alex Mirugwe
collection DOAJ
description Abstract BackgroundTuberculosis (TB) remains a significant global health challenge, as current diagnostic methods are often resource-intensive, time-consuming, and inaccessible in many high-burden communities, necessitating more efficient and accurate diagnostic methods to improve early detection and treatment outcomes. ObjectiveThis study aimed to evaluate the performance of 6 convolutional neural network architectures—Visual Geometry Group-16 (VGG16), VGG19, Residual Network-50 (ResNet50), ResNet101, ResNet152, and Inception-ResNet-V2—in classifying chest x-ray (CXR) images as either normal or TB-positive. The impact of data augmentation on model performance, training times, and parameter counts was also assessed. MethodsThe dataset of 4200 CXR images, comprising 700 labeled as TB-positive and 3500 as normal cases, was used to train and test the models. Evaluation metrics included accuracy, precision, recall, F1 ResultsVGG16 outperformed the other architectures, achieving an accuracy of 99.4%, precision of 97.9%, recall of 98.6%, F1 ConclusionsSimpler models like VGG16 offer a favorable balance between diagnostic accuracy and computational efficiency for TB detection in CXR images. These findings highlight the need to tailor model selection to task-specific requirements, providing valuable insights for future research and clinical implementations in medical image classification.
format Article
id doaj-art-bced5e21c67f4db8a4d62cc28982f9d6
institution OA Journals
issn 2563-6316
language English
publishDate 2025-07-01
publisher JMIR Publications
record_format Article
series JMIRx Med
spelling doaj-art-bced5e21c67f4db8a4d62cc28982f9d62025-08-20T02:36:09ZengJMIR PublicationsJMIRx Med2563-63162025-07-016e66029e6602910.2196/66029Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network ArchitecturesAlex Mirugwehttp://orcid.org/0000-0002-3194-4333Lillian Tamalehttp://orcid.org/0009-0002-6179-5436Juwa Nyirendahttp://orcid.org/0009-0007-1215-9341 Abstract BackgroundTuberculosis (TB) remains a significant global health challenge, as current diagnostic methods are often resource-intensive, time-consuming, and inaccessible in many high-burden communities, necessitating more efficient and accurate diagnostic methods to improve early detection and treatment outcomes. ObjectiveThis study aimed to evaluate the performance of 6 convolutional neural network architectures—Visual Geometry Group-16 (VGG16), VGG19, Residual Network-50 (ResNet50), ResNet101, ResNet152, and Inception-ResNet-V2—in classifying chest x-ray (CXR) images as either normal or TB-positive. The impact of data augmentation on model performance, training times, and parameter counts was also assessed. MethodsThe dataset of 4200 CXR images, comprising 700 labeled as TB-positive and 3500 as normal cases, was used to train and test the models. Evaluation metrics included accuracy, precision, recall, F1 ResultsVGG16 outperformed the other architectures, achieving an accuracy of 99.4%, precision of 97.9%, recall of 98.6%, F1 ConclusionsSimpler models like VGG16 offer a favorable balance between diagnostic accuracy and computational efficiency for TB detection in CXR images. These findings highlight the need to tailor model selection to task-specific requirements, providing valuable insights for future research and clinical implementations in medical image classification.https://xmed.jmir.org/2025/1/e66029
spellingShingle Alex Mirugwe
Lillian Tamale
Juwa Nyirenda
Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures
JMIRx Med
title Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures
title_full Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures
title_fullStr Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures
title_full_unstemmed Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures
title_short Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures
title_sort improving tuberculosis detection in chest x ray images through transfer learning and deep learning comparative study of convolutional neural network architectures
url https://xmed.jmir.org/2025/1/e66029
work_keys_str_mv AT alexmirugwe improvingtuberculosisdetectioninchestxrayimagesthroughtransferlearninganddeeplearningcomparativestudyofconvolutionalneuralnetworkarchitectures
AT lilliantamale improvingtuberculosisdetectioninchestxrayimagesthroughtransferlearninganddeeplearningcomparativestudyofconvolutionalneuralnetworkarchitectures
AT juwanyirenda improvingtuberculosisdetectioninchestxrayimagesthroughtransferlearninganddeeplearningcomparativestudyofconvolutionalneuralnetworkarchitectures