JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

LIGHTWEIGHT CNN ARCHITECTURES FOR THREE-CLASS TUBERCULOSIS X-RAY CLASSIFICATION

Esbergenov Hamidulla Seidabullaevich1, Nurimov Paraxat Baymuratovich2

1 Tashkent University of Information Technologies named after Muhammad ibn Musa al-Khwarizmi

2 National Research University “Tashkent Institute of Irrigation and Agricultural Mechanization Engineers”

Zenodo DOI: 10.5281/zenodo.19872829

Keywords

DeeP Learning class imbalance Tuberculosis detection transfer learning Grad-CAM EfficientNet-B3 DenseNet-121 TBX11K MobileNet-V3 convolutional neural networks chest X-ray classification

Abstract

Tuberculosis (TB) remains one of the leading infectious diseases worldwide, causing approximately 1.3 million deaths annually. Automated computer-aided diagnosis (CAD) systems based on chest X-ray (CXR) imaging offer a promising solution for early TB screening, particularly in resource-limited settings. We present a systematic comparison of three pretrained CNN backbones - DenseNet-121, EfficientNet-B3, and MobileNet-V3 - for three-class CXR classification (Healthy, Sick-but-non-TB, and TB) using the TBX11K benchmark dataset under identical training conditions. MobileNet-V3 achieves the highest macro AUC of 99.98% with a TB sensitivity of 99.37%, while EfficientNet-B3 achieves perfect TB sensitivity of 100.00%. Grad-CAM visualizations confirm clinically meaningful activation patterns, and external validation on a confirmed TB case demonstrates real-world applicability.

Views: 140 Published: 2026-04-28 Pages: 115-120 Volume: 4 Issue: 2

References

  1. Ravi, V., Acharya, V., Alazab, M. (2023). A multichannel EfficientNet deep learning-based stacking ensemble for lung disease detection. Cluster Computing, 26, 1181–1203.
  2. Lin, T.Y., et al. (2017). Focal loss for dense object detection. ICCV, pp. 2980–2988.
  3. World Health Organization. (2023). Global Tuberculosis Report 2023. WHO, Geneva.
  4. Liu, Y., Wu, Y.H., Ban, Y., Wang, H., Cheng, M.M. (2020). Rethinking Computer-Aided Tuberculosis Diagnosis. CVPR, pp. 2735–2744.
  5. Häggström, M. (2014). Chest radiograph of miliary tuberculosis [Radiograph]. Wikimedia Commons.
  6. Kotei, E., Thirunavukarasu, R. (2024). A comprehensive review on deep learning techniques for automatic detection of tuberculosis from chest X-ray images. Archives of Computational Methods in Engineering, 31, 455–474.
  7. Tan, M., Le, Q.V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. ICML, pp. 6105–6114.
  8. Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q. (2017). Densely connected convolutional networks. CVPR, pp. 4700–4708.
  9. Selvaraju, R.R., et al. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. ICCV, pp. 618–626.
  10. Howard, A., et al. (2019). Searching for MobileNetV3. ICCV, pp. 1314–1324.
  11. Das, P.K., et al. (2025). OSLTBDNet: Orthogonal softmax layer-based tuberculosis detection network with small dataset. Biomedical Signal Processing and Control. https://doi.org/10.1016/j.bspc.2025.000953
  12. Mirugwe, A., Tamale, L., Nyirenda, J. (2025). Improving Tuberculosis Detection Through Transfer Learning and Deep Learning. JMIRx Med, 6, e66029.
  13. Rajpurkar, P., et al. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv:1711.05225.