Application of ResNet-50 Convolutional Neural Network (CNN) Architecture for Early Detection of Pulmonary Tuberculosis in Chest X-Ray Images
International Journal of Mathematics, Statistics, and Computing · 10.06.2026 · 4 (2) · 63-70
DOI: 10.46336/ijmsc.v4i2.320 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Mathematics, Statistics, and Computing, online erschienen am 10.06.2026. Verfasst von Fahmi Sidiq und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Tuberculosis remains a major global health challenge, particularly in developing regions where access to rapid and accurate diagnostic tools is limited. Early detection of pulmonary tuberculosis is essential to reduce transmission and mortality rates. This study proposes the application of the ResNet-50 Convolutional Neural Network architecture for the automatic classification of chest X-ray images into tuberculosis and non-tuberculosis categories. The dataset used consists of 4,200 chest X-ray images, divided into training and testing sets with an 80:20 ratio. Preprocessing techniques, including image resizing, normalization, and data augmentation, were applied to improve data quality and model robustness. The model was trained using the Adam optimizer and binary cross-entropy loss function. The experimental results show that the proposed model achieved high performance, with an accuracy of 91.3%, precision of 90.1%, recall of 86.4%, and F1-score of 88.2%. These results indicate that the model is capable of effectively distinguishing between tuberculosis and normal cases, while maintaining a balance between sensitivity and specificity. Visualization techniques such as the confusion matrix and ROC curve further confirm the model’s reliability and classification capability. In conclusion, the ResNet-50 model demonstrates strong potential as a computer-aided diagnostic tool for early tuberculosis detection. Its implementation can support healthcare professionals in improving diagnostic efficiency and contribute to reducing the global burden of tuberculosis through timely and accurate diagnosis.
Zitieren
APA
Sidiq, F., Kalfin, & Yuningsih, S. H. (2026). Application of ResNet-50 Convolutional Neural Network (CNN) Architecture for Early Detection of Pulmonary Tuberculosis in Chest X-Ray Images. International Journal of Mathematics, Statistics, and Computing, 4(2), 63-70. https://doi.org/10.46336/ijmsc.v4i2.320
Vancouver
Sidiq F, Kalfin, Yuningsih SH. Application of ResNet-50 Convolutional Neural Network (CNN) Architecture for Early Detection of Pulmonary Tuberculosis in Chest X-Ray Images. International Journal of Mathematics, Statistics, and Computing. 2026;4(2):63-70. doi:10.46336/ijmsc.v4i2.320
BibTeX
@article{Sidiq2026,
author = {Sidiq, Fahmi and Kalfin and Yuningsih, Siti Hadiaty},
title = {Application of ResNet-50 Convolutional Neural Network (CNN) Architecture for Early Detection of Pulmonary Tuberculosis in Chest X-Ray Images},
journal = {International Journal of Mathematics, Statistics, and Computing},
year = {2026},
volume = {4},
number = {2},
pages = {63--70},
doi = {10.46336/ijmsc.v4i2.320}
}
EUVIMED