Enhancing Tuberculosis Classification Performance in Chest X-Rays through Efficient Net B0 and CLAHE
DOI:
https://doi.org/10.70404/jikteks.v4i03.729Keywords:
Tuberculosis Detection, EfficientNet-B0, CLAHE, Deep Learning, Medical ImagingAbstract
Tuberculosis (TB) remains a significant global health challenge, requiring rapid and accurate diagnostic tools to prevent transmission. Chest X-ray (CXR) imaging is a primary screening method, yet manual interpretation is often subjective and prone to inconsistency. This study proposes an efficient automated detection framework using the EfficientNet-B0 architecture integrated with Contrast Limited Adaptive Histogram Equalization (CLAHE). The research utilizes the Shenzhen Dataset, employing CLAHE to enhance the visibility of pulmonary features by mitigating non-uniform illumination in radiographs. The model was modified with a Global Average Pooling (GAP) layer and a 0.5 dropout rate to optimize performance for binary classification. Experimental results demonstrate that the proposed framework achieved an Accuracy of 87.21%, a Sensitivity of 89.70%, and an Area Under the Curve (AUC) of 0.9350. Furthermore, the model exhibits high computational efficiency with a compact size of 20.5 MB and only 5.3 million parameters, significantly outperforming heavier architectures like ResNet-50. This study concludes that the combination of CLAHE-based enhancement and EfficientNet-B0 provides a robust and lightweight solution for TB screening, particularly suitable for deployment in resource-constrained clinical environments.
Downloads
References
M. Oloko-Oba and S. Viriri, “Tuberculosis Detection: A Comprehensive Review of State-of-the-Art Models,” IAENG Int. J. Comput. Sci., vol. 49, no. 3, 2022, [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85138008487&partnerID=40&md5=02074f8538f8246198f5ee96334fda66
R. Shukla, “AI X-ray for tuberculosis screening in remote Nepal: Benefits and challenges from a doctor’s perspective,” J. Public health Res., vol. 14, no. 4, 2025, doi: 10.1177/22799036251399279.
İ. Sarbay, G. Güler, A. Turna, and İ. Sarbay, “Giant Thoracic Aortic Aneurysm Confused with Large Pleural Effusion on the Chest X-Ray,” Indian J. Surg., vol. 86, no. 3, pp. 646–647, 2024, doi: 10.1007/s12262-023-03926-6.
S. Moore, “Chest X-Ray,” in A Medication Guide to Internal Medicine Tests and Procedures, 2021, pp. 72–77. doi: 10.1016/B978-0-323-79007-9.00016-7.
A. Karera, F. Davidson, and P. Engel-Hills, “Operational challenges and collaborative solutions in radiology image interpretation: perspectives from imaging departments in a low-resource setting,” J. Med. Radiat. Sci., vol. 71, no. 4, pp. 564–572, 2024, doi: 10.1002/jmrs.815.
A. Karera, P. Engel-Hills, and F. Davidson, “Radiology image interpretation services in a low-resource setting: Medical doctors’ experiences and the potential role of radiographers,” Radiography, vol. 30, no. 2, pp. 560–566, 2024, doi: 10.1016/j.radi.2024.01.009.
N. S. Vardanaa, N. Devi, M. Murale, R. K. Prasanth, and D. Nilesh, “Multi-Label Classification for Diagnosis of Tuberculosis from Chest X-Ray Images,” in Proceedings - IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2022, 2022. doi: 10.1109/ACCAI53970.2022.9752472.
S. Cuenca-Dominguez et al., “Advancing Healthcare: Early Tuberculosis Detection in Chest X-Rays Through Select Convolutional Neural Networks,” in Lecture Notes in Networks and Systems, 2024, pp. 272–284. doi: 10.1007/978-3-031-69228-4_18.
A. I. Gupta, S. Dhir, A. K. Gupta, S. Gupta, and V. Jangra, “Leveraging Deep Learning Techniques for Tuberculosis Detection from X-Ray Images,” in 2025 International Conference on Automation and Computation, AUTOCOM 2025, 2025, pp. 1485–1491. doi: 10.1109/AUTOCOM64127.2025.10957697.
A. Rachmad, M. Syarief, J. Hutagalung, S. Hernawati, E. M. S. Rochman, and Y. P. Asmara, “Comparison of CNN Architectures for Mycobacterium Tuberculosis Classification in Sputum Images,” Ing. des Syst. d’Information, vol. 29, no. 1, pp. 49–56, 2024, doi: 10.18280/isi.290106.
S. Y. Prasetyo, “Automated Pulmonary Tuberculosis Detection in Chest Radiographs using Pretrained DCNN Models,” in Proceedings of 2024 International Conference on Information Management and Technology, ICIMTech 2024, 2024, pp. 195–200. doi: 10.1109/ICIMTech63123.2024.10780811.
C. Chen, X. Guo, H. Cheng, G. Yang, and H. Dong, “SUNeXt: Lightweight Medical Image Segmentation Network Based on Grouped Feature Fusion and Shifted Large Kernel Convolution,” IET Image Process., vol. 19, no. 1, 2025, doi: 10.1049/ipr2.70168.
C. Dong, F. Tang, R. Mao, X. Gao, and S. K. Zhou, “Thinning a Medical Image Segmentation Model via Dual-Level Multiscale Fusion,” in Frontiers in Artificial Intelligence and Applications, 2025, pp. 739–746. doi: 10.3233/FAIA250874.
M. Mahmoud, Y. Wen, X. Pan, Y. Liufu, and Y. Guan, “Evaluation of recent lightweight deep learning architectures for lung cancer CT classification,” Front. Oncol., vol. 15, 2025, doi: 10.3389/fonc.2025.1647701.
J. Di, M. Wu, J. Fu, W. Li, X. Jin, and J. Liu, “Comparative Analysis of Time-Series Forecasting Models for eLoran Systems: Exploring the Effectiveness of Dynamic Weighting,” Sensors, vol. 25, no. 14, 2025, doi: 10.3390/s25144462.
V.-T. Hoang, V.-D. Hoang, and K.-H. Jo, “Rethinking Mobile Inverted Bottleneck Convolution for EfficientNet,” in Lecture Notes in Networks and Systems, 2023, pp. 435–445. doi: 10.1007/978-3-031-19694-2_39.
V.-T. Hoang and K.-H. Jo, “Practical Analysis on Architecture of EfficientNet,” in International Conference on Human System Interaction, HSI, 2021. doi: 10.1109/HSI52170.2021.9538782.
J. P. Schwarz Schuler, S. Romani, M. Abdel-Nasser, H. Rashwan, and D. Puig, “Grouped Pointwise Convolutions Significantly Reduces Parameters in EfficientNet,” in Frontiers in Artificial Intelligence and Applications, 2021, pp. 383–391. doi: 10.3233/FAIA210158.
K. Kokufuta and T. Maruyama, “Real-time processing of contrast limited adaptive histogram equalization on FPGA,” in Proceedings - 2010 International Conference on Field Programmable Logic and Applications, FPL 2010, 2010, pp. 155–158. doi: 10.1109/FPL.2010.37.
C. Zhang, Z. Zhang, J. Liu, Y. Gao, L. Huang, and Y. Fan, “High Throughput and Low Latency Hardware of Contrast Limited Adaptive Histogram Equalization Algorithm,” in Proceedings of 2022 IEEE 16th International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2022, 2022. doi: 10.1109/ICSICT55466.2022.9963186.
C. S. V, R. K, and S. Praveen P, “An Efficient Deep Learning Framework using CapsNet and SOM for Multidrug-Resistant Tuberculosis Detection and Analysis in CXR Images,” Procedia Comput. Sci., vol. 258, pp. 3251–3263, 2025, doi: https://doi.org/10.1016/j.procs.2025.04.583.
H. Lee, H. Choo, D.-T. Le, and J. Bum, “Chest Radiographs Enhancement with Contrast Limited Adaptive Histogram,” in Proceedings of the 2023 17th International Conference on Ubiquitous Information Management and Communication, IMCOM 2023, 2023. doi: 10.1109/IMCOM56909.2023.10035649
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muh. Hajar Akbar, Aldi Aldi, Waode Hartina, Imam Mustafaenal Akhyar, Elsa Nur Khotima
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
