Detection of Pulmonary Tuberculosis in Chest X-Ray Images Using CNN-VGG19: Evidence from a Local Indonesian Clinical Dataset

Emil Agusalim Habi  Talib; Mar'atul Azizah; Muhammad Faisal; Abd Rakhim  Nanda; Nizirwan Anwar; Indriyanti  Azis; Rizki Yusliana  Bakti; M.  Agusalim; Desi  Anggreani

doi:10.29207/resti.v10i5.7607

Authors

Emil Agusalim Habi Talib Universitas Muhammadiyah Makassar
Mar'atul Azizah Universitas Muhammadiyah Makassar
Muhammad Faisal Universitas Muhammadiyah Makassar
Abd Rakhim Nanda Universitas Muhammadiyah Makassar
Nizirwan Anwar Universitas Esa Unggul
Indriyanti Azis Universitas Muhammadiyah Makassar
Rizki Yusliana Bakti Universitas Muhammadiyah Makassar
M. Agusalim Universitas Muhammadiyah Makassar
Desi Anggreani Universitas Muhammadiyah Makassar

DOI:

https://doi.org/10.29207/resti.v10i5.7607

Keywords:

chest X-ray (CXR), convolutional neural network (CNN), pulmonary tuberculosis, transfer learning, VGG19

Abstract

Pulmonary tuberculosis (TB) remains a major public health challenge, especially in developing countries where early and accurate diagnosis is critical. Although deep learning models have shown promising performance in TB detection using chest X-ray (CXR) images, most studies rely on large-scale public datasets that may not adequately represent the variability and limitations of real-world clinical data. This study aimed to evaluate the robustness and generalization capabilities of the CNN-VGG19 architecture when applied to small-scale clinical datasets. The dataset consisted of 434 CXR images collected from Haji Makassar Hospital, Indonesia, and categorized into tuberculosis, pleural effusion, and normal classes. A transfer learning approach was applied, and model performance was evaluated using analyses of accuracy, precision, recall, F1 score, and confusion matrices, with comparisons to ResNet50 and InceptionV3 under identical experimental conditions. The results showed that CNN-VGG19 achieved an accuracy of 0.8807 and a macro F1 score of 0.8800, outperforming the comparative models. These findings suggest that CNN-VGG19 provides stable performance in a data-constrained environment and highlight the impact of class overlap on classification performance.

Downloads

Download data is not yet available.

References

[1] M. Oloko-Oba and S. Viriri, “A Systematic Review of Deep Learning Techniques for Tuberculosis Detection From Chest Radiograph,” Front. Med., vol. 9, no. March, pp. 1–11, 2022, doi: 10.3389/fmed.2022.830515.

[2] 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, pp. e66029–e66029, 2025, doi: 10.2196/66029.

[3] 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 J. Radiol., vol. 87, no. 1, pp. 118–124, 2022, doi: 10.5114/pjr.2022.113435.

[4] L. Mangeri, O. S. Gnana Prakasi, P. Kanmani, and N. Puppala, “Chest Diseases Prediction from X-ray Images using CNN Models: A Study,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 10, pp. 236–243, 2021, doi: 10.14569/IJACSA.2021.0121026.

[5] C. Ieracitano et al., “A fuzzy-enhanced deep learning approach for early detection of Covid-19 pneumonia from portable chest X-ray images,” Neurocomputing, vol. 481, pp. 202–215, 2022, doi: 10.1016/j.neucom.2022.01.055.

[6] R. Mohan, S. Kadry, V. Rajinikanth, A. Majumdar, and O. Thinnukool, “Automatic Detection of Tuberculosis Using VGG19 with Seagull-Algorithm,” Life, vol. 12, no. 11, 2022, doi: 10.3390/life12111848.

[7] S. Matarneh, F. Elghaish, F. Pour Rahimian, E. Abdellatef, and S. Abrishami, “Evaluation and optimization of pre-trained CNN models for asphalt pavement crack detection and classification,” Autom. Constr., vol. 160, no. December 2023, p. 105297, 2024, doi: 10.1016/j.autcon.2024.105297.

[8] M. Venkateswarlu and V. R. R. Chirra, “CNN-ViT: A multi-feature learning based approach for driver drowsiness detection,” Array, vol. 27, no. June, p. 100425, 2025, doi: 10.1016/j.array.2025.100425.

[9] V. Sharma, Nillmani, S. K. Gupta, and K. K. Shukla, “Deep learning models for tuberculosis detection and infected region visualization in chest X-ray images,” Intell. Med., vol. 4, no. 2, pp. 104–113, 2024, doi: 10.1016/j.imed.2023.06.001.

[10] M. A. Sayed et al., “Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architecture,” Informatics Med. Unlocked, vol. 55, no. February, p. 101648, 2025, doi: 10.1016/j.imu.2025.101648.

[11] I. A. Kandhro et al., “Performance evaluation of E-VGG19 model: Enhancing real-time skin cancer detection and classification,” Heliyon, vol. 10, no. 10, p. e31488, 2024, doi: 10.1016/j.heliyon.2024.e31488.

[12] A. Sharma, K. Singh, and D. Koundal, “A novel fusion based convolutional neural network approach for classification of COVID-19 from chest X-ray images,” Biomed. Signal Process. Control, vol. 77, no. April, p. 103778, 2022, doi: 10.1016/j.bspc.2022.103778.

[13] F. I. AlZobi et al., “Optimized soft-voting CNN ensemble using particle swarm optimization for endometrial cancer histopathology classification,” Comput. Methods Programs Biomed. Updat., vol. 8, no. August, p. 100217, 2025, doi: 10.1016/j.cmpbup.2025.100217.

[14] M. Faisal et al., “A Machine Learning-Driven Framework for Evaluating and Clustering City-Level Carbon Trading Strategies,” Int. J. Math. Eng. Manag. Sci., vol. 10, no. 6, pp. 2171–2200, 2025, doi: 10.33889/IJMEMS.2025.10.6.101.

[15] M. Gour and S. Jain, “Uncertainty-aware convolutional neural network for COVID-19 X-ray images classification,” Comput. Biol. Med., vol. 140, no. July 2021, p. 105047, 2022, doi: 10.1016/j.compbiomed.2021.105047.

[16] M. Faisal et al., “A Hybrid MOO, MCGDM, and Sentiment Analysis Methodologies for Enhancing Regional Expansion Planning: A Case Study Luwu - Indonesia,” Int. J. Math. Eng. Manag. Sci., vol. 10, no. 1, pp. 163–188, 2025, doi: 10.33889/IJMEMS.2025.10.1.010.

[17] P. Arafin and A. H. M. M. Billah, “Deep learning-based concrete defects classification and detection using semantic segmentation,” 2024, doi: 10.1177/14759217231168212.

[18] M. A. Rahman et al., “Classification of fungal genera from microscopic images using artificial intelligence,” J. Pathol. Inform., vol. 14, 2023, doi: 10.1016/j.jpi.2023.100314.

[19] H. Nurrani, A. K. Nugroho, and S. Heranurweni, “Image Classification of Vegetable Quality using Support Vector Machine based on Convolutional Neural Network,” J. RESTI, vol. 7, no. 1, pp. 168–178, 2023, doi: 10.29207/resti.v7i1.4715.

[20] R. D. Ramadhani, A. N. A. Thohari, C. Kartiko, A. Junaidi, T. G. Laksana, and N. A. S. Nugraha, “Optimization of the Accuracy of Convolutional Neural Network Methods for Waste Type Identification,” J. RESTI, vol. 5, no. 2, pp. 312–318, 2021, doi: 10.29207/resti.v5i2.2754.

[21] M. N. Ichsan, N. Armita, A. E. Minarno, F. D. S. Sumadi, and Hariyady, “Increased Accuracy on Image Classification of Game Rock Paper Scissors using CNN,” J. RESTI, vol. 6, no. 4, pp. 606–611, 2022, doi: 10.29207/resti.v6i4.4222.

[22] R. K. Bhukya, D. D. Kayande, A. Jadhav, R. Dawane, and D. Athawale, “Automated Classification of Skin Diseases Using CNNs and Outbreak Implications,” Procedia Comput. Sci., vol. 260, pp. 201–208, 2025, doi: 10.1016/j.procs.2025.03.194.

[23] M. Assaduzzaman, M. Dutta, A. Saha, and S. G. Paul, “ALSA-3: Customized CNN model through ablation study for Alzheimer’s disease classification,” Informatics Med. Unlocked, vol. 50, no. September, p. 101584, 2024, doi: 10.1016/j.imu.2024.101584.

[24] N. L. Yadav, S. Singh, R. Kumar, and D. K. Nishad, Transfer learning with fuzzy decision support for multi-class lung disease classification: performance analysis of pre-trained CNN models. 2025. doi: 10.1038/s41598-025-19114-3.

[25] P. Aggarwal, N. K. Mishra, B. Fatimah, P. Singh, A. Gupta, and S. D. Joshi, “COVID-19 image classification using deep learning: Advances, challenges and opportunities,” Comput. Biol. Med., vol. 144, no. March, p. 105350, 2022, doi: 10.1016/j.compbiomed.2022.105350.

[26] Y. Wang and C. A. Hargreaves, “A Review Study of the Deep Learning Techniques used for the Classification of Chest Radiological Images for COVID-19 Diagnosis,” Int. J. Inf. Manag. Data Insights, vol. 2, no. 2, p. 100100, 2022, doi: 10.1016/j.jjimei.2022.100100.

[27] S. Kumar and H. Kumar, “Classification of COVID-19 X-ray images using transfer learning with visual geometrical groups and novel sequential convolutional neural networks,” MethodsX, vol. 11, no. July, p. 102295, 2023, doi: 10.1016/j.mex.2023.102295.

[28] T. Le, F. Shi, M. Ge, R. Dong, and D. Shan, “Tuberculosis detection based on VGG19 transfer learning and Zebra Optimization Algorithm,” EAI Endorsed Trans. Pervasive Heal. Technol., vol. 10, pp. 1–7, 2024, doi: 10.4108/eetpht.10.5981.

[29] R. Wajgi et al., “Optimized tuberculosis classification system for chest X-ray images: Fusing hyperparameter tuning with transfer learning approaches,” Eng. Reports, vol. 6, no. 11, pp. 1–18, 2024, doi: 10.1002/eng2.12906.