Enhancing Tuberculosis Detection from Chest X-Ray Images Using Deep Learning: Evaluating Multi-Architecture Performance and Efficiency
Received: 17 November 2025 | Revised: 8 December 2025, 25 December 2025, 13 January 2026, 1 February 2026, and 2 February 2026 | Accepted: 4 February 2026 | Online: 4 April 2026
Corresponding author: Hadi Almohab
Abstract
Tuberculosis (TB) remains a critical global health challenge, with early detection often hindered by limited diagnostic resources and variability in manual Chest X-Ray (CXR) interpretation. This study evaluates the diagnostic performance and computational efficiency of four deep learning architectures—VGG16, DenseNet121, MobileNetV2, and a custom lightweight CNN—trained for 10 to 100 epochs on a multi-source dataset comprising 4,200 CXR images. Stratified data splitting and data augmentation were employed to address class imbalance and improve generalization. Among the evaluated models, VGG16 achieved the highest classification performance, with 99.21% accuracy, an F1-score of 0.98, and a ROC-AUC of 0.99. In contrast, MobileNetV2 provided a favorable trade-off between accuracy (98.73%) and inference efficiency, achieving the fastest prediction time of 12 ms per image, supporting its potential use in resource-constrained environments. Although the results indicate that transfer learning with optimized training protocols can support accurate and efficient AI-assisted TB screening, this study is limited by the lack of patient-level data separation, statistical cross-validation, and model explainability. Future work will address these limitations by incorporating explainable AI methods, statistically robust validation strategies, and evaluation on independent and diverse clinical datasets.
Keywords:
tuberculosis classification, deep learning, chest X-ray, transfer learning, Convolutional Neural Networks (CNNs), medical image analysisDownloads
References
"Global Tuberculosis Report 2023". Geneva: World Health Organization, 2023. [Online]. Available: https://iris.who.int/items/60aa1a1d-04f9-46e2-9897-9836594b8d21.
T. K. A. Teibo et al., ''Barriers That Interfere with Access to Tuberculosis Diagnosis and Treatment across Countries Globally: A Systematic Review,'' ACS Infectious Diseases, vol. 10, no. 8, pp. 2600–2614, Aug. 2024. DOI: https://doi.org/10.1021/acsinfecdis.4c00466
R. Kancherla, A. Sharma, and P. Garg, ''Diagnosing Respiratory Variability: Convolutional Neural Networks for Chest X-ray Classification Across Diverse Pulmonary Conditions,'' Journal of Imaging Informatics in Medicine, vol. 38, no. 5, pp. 2677–2687, Oct. 2025. DOI: https://doi.org/10.1007/s10278-024-01355-9
K. Sarawagi et al., ''Self-Trained Convolutional Neural Network (CNN) for Tuberculosis Diagnosis in Medical Imaging,'' Cureus, vol. 16, no. 6, June 2024. DOI: https://doi.org/10.7759/cureus.63356
M. H. Rabby, O. Islam, Assaduzzaman, and M. Dutta, ''Tuberculosis Disease Detection from Chest X-rays Using Deep Learning Techniques,'' in 2023 26th International Conference on Computer and Information Technology (ICCIT), Cox's Bazar, Bangladesh, Sept. 2023, pp. 1–6. DOI: https://doi.org/10.1109/ICCIT60459.2023.10441031
R. Rani and S. Gupta, ''Deep Learning-Based Tuberculosis Detection Using Fine-Tuned VGG16 on Chest X-Ray Images,'' in 2024 3rd International Conference for Advancement in Technology (ICONAT), GOA, India, Sept. 2024, pp. 1–5. DOI: https://doi.org/10.1109/ICONAT61936.2024.10775087
R. Sivaramakrishnan et al., ''Comparing deep learning models for population screening using chest radiography,'' in Medical Imaging 2018: Computer-Aided Diagnosis, Houston, TX, USA, Feb. 2018, vol. 10575, pp. 322–332. DOI: https://doi.org/10.1117/12.2293140
X. Chu, Y. Wang, C. Shen, J. Chen, and W. Chu, ''Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching.'' arXiv, Mar. 17, 2022.
R. Ströbel, M. Mau, A. Puchta, and J. Fleischer, ''Improving Time Series Regression Model Accuracy via Systematic Training Dataset Augmentation and Sampling,'' Machine Learning and Knowledge Extraction, vol. 6, no. 2, pp. 1072–1086, May 2024. DOI: https://doi.org/10.3390/make6020049
J. Plested and T. Gedeon, ''An Analysis of the Interaction Between Transfer Learning Protocols in Deep Neural Networks,'' in Neural Information Processing, Sydney, Australia, 2019, pp. 312–323. DOI: https://doi.org/10.1007/978-3-030-36708-4_26
Y. Huang, H. Zhao, Y. Zhou, T. Riedel, and M. Beigl, ''Standardizing Your Training Process for Human Activity Recognition Models – A Comprehensive Review in the Tunable Factors,'' in Mobile and Ubiquitous Systems: Computing, Networking and Services, 2024, pp. 15–27. DOI: https://doi.org/10.1007/978-3-031-63992-0_2
P. Gang et al., ''Effect of Data Augmentation and Lung Mask Segmentation for Automated Chest Radiograph Interpretation of Some Lung Diseases,'' in Neural Information Processing, Sydney, Australia, 2019, pp. 333–340. DOI: https://doi.org/10.1007/978-3-030-36808-1_36
H. Almohab, A. D. W. M. Sidik, and A. P. Junfithrana, ''Development and Evaluation of an AI-Driven Convolutional Neural Network (CNN) Model for Automated Pneumonia Detection Using Chest X-Ray Image,'' in 2024 10th International Conference on Computing, Engineering and Design (ICCED), Jeddah, Saudi Arabia, Sept. 2024, pp. 1–6. DOI: https://doi.org/10.1109/ICCED64257.2024.10983686
C. Shorten and T. M. Khoshgoftaar, ''A survey on Image Data Augmentation for Deep Learning,'' Journal of Big Data, vol. 6, no. 1, July 2019, Art. no. 60. DOI: https://doi.org/10.1186/s40537-019-0197-0
P. A. Priya and E. R. Vimina, ''Tuberculosis Detection from CXR: An Approach Using Transfer Learning with Various CNN Architectures,'' in International Conference on Communication, Computing and Electronics Systems, Coimbatore, India, 2021, pp. 407–418. DOI: https://doi.org/10.1007/978-981-33-4909-4_31
E. Showkatian, M. Salehi, H. Ghaffari, R. Reiazi, and N. Sadighi, ''Deep learning-based automatic detection of tuberculosis disease in chest X-ray images,'' Polish journal of radiology, vol. 87, pp. e118–e124, Jan. 2022. DOI: https://doi.org/10.5114/pjr.2022.113435
K. K. M. Rahman, S. Zulaikha, B. Dhafer, and R. Ahmed, ''Advancing tuberculosis screening: A tailored CNN approach for accurate chest X-ray analysis and practical clinical integration,'' Intelligence-Based Medicine, vol. 11, Jan. 2025, Art. no. 100196. DOI: https://doi.org/10.1016/j.ibmed.2024.100196
R. Chelghoum, A. Ikhlef, A. Hameurlaine, and S. Jacquir, ''Transfer Learning Using Convolutional Neural Network Architectures for Brain Tumor Classification from MRI Images,'' in Artificial Intelligence Applications and Innovations, Neos Marmaras, Greece, 2020, pp. 189–200. DOI: https://doi.org/10.1007/978-3-030-49161-1_17
M. Mamalakis et al., ''DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays,'' Computerized Medical Imaging and Graphics, vol. 94, Dec. 2021, Art. no. 102008. DOI: https://doi.org/10.1016/j.compmedimag.2021.102008
M. Cabanillas-Carbonell, ''Mobile Application to Improve the Follow-up and Control Process in Patients with Tuberculosis.,'' International Journal of Interactive Mobile Technologies, vol. 18, no. 3, Feb. 2024, Art. no. 75. DOI: https://doi.org/10.3991/ijim.v18i03.46875
P. Dasarwar, U. Yadav, K. Morris, N. Chavhan, S. Bondre, and S. Kalamkar, ''Revolutionizing Tuberculosis Prediction: A Cutting-Edge Approach,'' Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 22929–22936, June 2025. DOI: https://doi.org/10.48084/etasr.10449
A. Azizi, M. Azizi, and M. Nasri, ''Artificial Intelligence Techniques in Medical Imaging: A Systematic Review,'' International Journal of Online & Biomedical Engineering, vol. 19, no. 17, Dec. 2023, Art. no. 66. DOI: https://doi.org/10.3991/ijoe.v19i17.42431
W. Chokchaithanakul, P. Punyabukkana, and E. Chuangsuwanich, ''Adaptive Image Preprocessing and Augmentation for Tuberculosis Screening on Out-of-Domain Chest X-Ray Dataset,'' IEEE Access, vol. 10, pp. 132144–132152, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3229591
B. Moryani, K. Sood, and K. Chaudhary, ''A Deep Learning Approach for the Classification of Tuberculosis and Pneumonia Using NIH Dataset *,'' in 2023 International Symposium on Networks, Computers and Communications (ISNCC), Doha, Qatar, July 2023, pp. 1–8. DOI: https://doi.org/10.1109/ISNCC58260.2023.10323983
T. K. Kim, P. H. Yi, G. D. Hager, and C. T. Lin, ''Refining dataset curation methods for deep learning-based automated tuberculosis screening,'' Journal of Thoracic Disease, vol. 12, no. 9, pp. 5078–5085, Sept. 2020. DOI: https://doi.org/10.21037/jtd.2019.08.34
A. Adli and P. Tyrrell, ''Impact of Training Sample Size on the Effects of Regularization in a Convolutional Neural Network-based Dental X-ray Artifact Prediction Model,'' Journal of Undergraduate Life Sciences, vol. 14, no. 1, Dec. 2020. DOI: https://doi.org/10.33137/juls.v14i1.35883
Y. Tian and Y. Zhang, ''A comprehensive survey on regularization strategies in machine learning,'' Information Fusion, vol. 80, pp. 146–166, Apr. 2022. DOI: https://doi.org/10.1016/j.inffus.2021.11.005
J. Liang, S. Gonzalez, H. Shahrzad, and R. Miikkulainen, ''Regularized evolutionary population-based training,'' in Proceedings of the Genetic and Evolutionary Computation Conference, Lille, France, Mar. 2021, pp. 323–331. DOI: https://doi.org/10.1145/3449639.3459292
A. Mirugwe, L. Tamale, and J. Nyirenda, ''Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures,'' JMIRx Med, vol. 6, no. 1, July 2025, Art. no. e66029. DOI: https://doi.org/10.2196/66029
R. Wajgi et al., ''Optimized tuberculosis classification system for chest X-ray images: Fusing hyperparameter tuning with transfer learning approaches,'' Engineering Reports, vol. 6, no. 11, 2024, Art. no. e12906. DOI: https://doi.org/10.1002/eng2.12906
T. Rahman et al., ''Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization,'' IEEE Access, vol. 8, pp. 191586–191601, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.3031384
''Tuberculosis (TB) Chest X-ray Database.'' Kaggle, [Online]. Available: https://www.kaggle.com/datasets/tawsifurrahman/tuberculosis-tb-chest-xray-dataset.
R. Geethamani and A. Ranichitra, ''Enhancing Tuberculosis Detection: Leveraging RF-HOG Model for Automated Diagnosis from Chest X-ray Images,'' Procedia Computer Science, vol. 230, pp. 21–32, Jan. 2023. DOI: https://doi.org/10.1016/j.procs.2023.12.057
A. Soni, A. Rai, and S. K. Ahirwar, ''Mycobacterium Tuberculosis Detection using Support Vector Machine Classification Approach,'' in 2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), Bhopal, India, June 2021, pp. 408–413. DOI: https://doi.org/10.1109/CSNT51715.2021.9509635
M. Ahsan, R. Gomes, and A. Denton, ''Application of a Convolutional Neural Network using transfer learning for tuberculosis detection,'' in 2019 IEEE International Conference on Electro Information Technology (EIT), Brookings, SD, USA, Feb. 2019, pp. 427–433. DOI: https://doi.org/10.1109/EIT.2019.8833768
S. Bahri, R. Wajhillah, and M. F. Adiwisastra, ''Diagnosa Tuberculosis Paru Berbasis Citra X-ray Menggunakan Convolutional Neural Network,'' IJCIT Indonesian Journal on Computer and Information Technology, vol.. 6, no. Sept. pp. 181–186, 2021. DOI: https://doi.org/10.31294/ijcit.v6i2.11844
T. H. Kim, M. Krichen, S. Ojo, M. A. Alamro, and G. A. Sampedro, ''TSSG-CNN: A Tuberculosis Semantic Segmentation-Guided Model for Detecting and Diagnosis Using the Adaptive Convolutional Neural Network,'' Diagnostics, vol. 14, no. 11, June 2024. DOI: https://doi.org/10.3390/diagnostics14111174
M. Raičević, N. Kavarić, T. Popović, D. Babić, and I. Jovović, ''Tuberculosis Detection From Chest X- Rays Using Convolutional Neural Network,'' in 2025 29th International Conference on Information Technology (IT), Zabljak, Montenegro, Oct. 2025, pp. 1–4. DOI: https://doi.org/10.1109/IT64745.2025.10930261
G. Siddharth, A. Ambekar, and N. Jayakumar, ''Enhanced CoAtNet based hybrid deep learning architecture for automated tuberculosis detection in human chest X-rays,'' BMC Medical Imaging, vol. 25, no. 1, Sept. 2025, Art. no. 379. DOI: https://doi.org/10.1186/s12880-025-01901-z
Downloads
How to Cite
License
Copyright (c) 2026 Deden Witarsyah, Hadi Almohab, Riswan Septriayadi Sianturi, Dedy Syamsuar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
