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...
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |