Chest X-Ray Based Pulmonary Tuberculosis Classification Using Transfer Learning with DenseNet121 and Convolutional Block Attention Module (CBAM)
DOI:
https://doi.org/10.30871/jaic.v10i2.12523Keywords:
Pulmonary Tuberculosis, DenseNet121, CBAM, Image Classification, Deep LearningAbstract
Pulmonary tuberculosis is one of the infectious diseases with a high morbidity rate, requiring an accurate and efficient diagnostic support system based on chest X-ray images. This study aims to develop and evaluate a pulmonary tuberculosis classification model using the DenseNet121 architecture and DenseNet121 combined with the Convolutional Block Attention Module (CBAM) with a transfer learning approach. The research design is experimental using a dataset of 3.008 chest X-ray images consisting of 2.494 tuberculosis and 514 normal images, divided into two data partitioning scenarios, namely 60:20:20 and 70:15:15 for training, validation, and testing data. The training process was carried out for 20 epochs using the Adam optimizer. Model performance evaluation was carried out using accuracy, precision, recall, F1-score, and confusion matrix metrics. The results showed that the DenseNet121 model without the attention mechanism achieved an accuracy of 99% in both data division scenarios. Meanwhile, the DenseNet121 + CBAM model produced improved performance with accuracy, precision, recall, and F1-score values of 1.00 on the test data, with no False Positive or False Negative errors found. These findings indicate that the integration of CBAM can improve the model's ability to extract relevant features and increase the sensitivity of pulmonary tuberculosis detection. Overall, this study shows that the application of the attention mechanism in the DenseNet121 architecture has the potential to improve the performance of chest X-ray-based pulmonary tuberculosis classification systems.
Downloads
References
[1] A. Rasyid and L. Heryawan, “Klasifikasi Penyakit Tuberculosis (TB) Organ Paru Manusia Berdasarkan Citra Rontgen Thorax Menggunakan Metode Convolutional Neural Network (CNN),” Jurnal Manajemen Informasi Kesehatan Indonesia (JMIKI), vol. 11, no. 1, Mar. 2023, doi: 10.33560/jmiki.v11i1.484.
[2] M. B. Sastramandala, R. N. Sari, and N. Novrina, “Pemanfaatan Deep Learning menggunakan Convolutional Neural Network Terhadap Penyakit Tuberkulosis melalui Citra Rontgen,” Jurnal Minfo Polgan, vol. 14, no. 1, pp. 631–642, May 2025, doi: 10.33395/jmp.v14i1.14818.
[3] S. Iqbal, A. N. Qureshi, J. Li, and T. Mahmood, “On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks,” Archives of Computational Methods in Engineering, vol. 30, no. 5, pp. 3173–3233, Jun. 2023, doi: 10.1007/s11831-023-09899-9.
[4] G. M. M. Alshmrani, Q. Ni, R. Jiang, H. Pervaiz, and N. M. Elshennawy, “A deep learning architecture for multi-class lung diseases classification using chest X-ray (CXR) images,” Alexandria Engineering Journal, vol. 64, pp. 923–935, Feb. 2023, doi: 10.1016/j.aej.2022.10.053.
[5] B. S. Nusantara and M. Akbar, “Klasifikasi Penyakit Tuberculosis Berdasarkan Citra Rontgen Thorax Menggunakan Multi-Scale Convolutional Neural Network,” sudo Jurnal Teknik Informatika, vol. 3, no. 1, pp. 1–8, May 2024, doi: 10.56211/sudo.v3i1.483.
[6] F. Shahira, B. S. Negara, F. Yanto, and S. Sanjaya, “Optimasi Hyperparameter Deep Learning untuk Deteksi X-Ray Paru-Paru Menggunakan Bayesian Optimization,” JIEET (Journal Information Engineering and Educational Technology), vol. 9, no. 1, pp. 56–63, 2025.
[7] V. Acharya et al., “AI-Assisted Tuberculosis Detection and Classification from Chest X-Rays Using a Deep Learning Normalization-Free Network Model,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/2399428.
[8] R. K. Pasha and K. Budiman, “Optimasi Model CNN Berbasis Transfer Learning Untuk Klasifikasi Pneumonia pada Citra X-Ray Dada,” SMATIKA JURNAL, vol. 15, no. 01, pp. 167–178, Jun. 2025, doi: 10.32664/smatika.v15i01.1985.
[9] J. Devasia, H. Goswami, S. Lakshminarayanan, M. Rajaram, and S. Adithan, “Deep learning classification of active tuberculosis lung zones wise manifestations using chest X-rays: a multi label approach,” Sci. Rep., vol. 13, no. 1, Dec. 2023, doi: 10.1038/s41598-023-28079-0.
[10] S. Hansun, A. Argha, S. T. Liaw, B. G. Celler, and G. B. Marks, “Machine and Deep Learning for Tuberculosis Detection on Chest X-Rays: Systematic Literature Review,” J. Med. Internet Res., vol. 25, 2023, doi: 10.2196/43154.
[11] O. Rochmawanti, F. Utaminingrum, and F. A. Bachtiar, “Analisis Performa Pre-Trained Model Convolutional Neural Network Dalam Mendeteksi Penyakit Tuberkulosis,” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 8, pp. 805–814, Aug. 2021, doi: 10.25126/jtiik.202184441.
[12] F. A. P. R. Putri, J. P. Tanjung, and N. P. Dharshini, “Implementation of Transfer Learning on CNN using DenseNet121 and ResNet50 for Brain Tumor Classification,” JITE (Journal of Informatics and Telecommunication Engineering), vol. 8, no. 2, pp. 325–334, Jan. 2025, doi: 10.31289/jite.v8i2.13952.
[13] C. Halim, N. Geordie, E. Putra, N. A. Nugroho, and D. Suhartono, “Chest X-ray Image Classification to Identify Lung Diseases Using Convolutional Neural Network and Convolutional Block Attention Module,” International Journal On Informatics Visualization, vol. 7, no. 3, pp. 651–658, Sep. 2023, [Online]. Available: www.joiv.org/index.php/joiv
[14] 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,” Intelligent Medicine, vol. 4, no. 2, pp. 104–113, May 2024, doi: 10.1016/j.imed.2023.06.001.
[15] Q. Said, I. Ernawati, M. Mega Santoni, and J. R. Fatmawati, “Identifikasi Tuberkulosis Paru Berdasarkan Foto Sinar-X Thorax Menggunakan Jaringan Syaraf Tiruan Backpropagation,” JURNAL INFORMATIK, vol. 17, no. 1, pp. 27–37, 2021.
[16] D. Kurniawan, M. Wahyudi, L. Pujiastuti, U. Bina Sarana Informatika, and S. Antar Bangsa, “Deteksi dan Prediksi Cerdas Penyakit Paru-Paru dengan Algoritma Random Forest,” Indonesian Journal Computer Science, vol. 3, no. 1, pp. 51–56, 2024.
[17] E. Çallı, E. Sogancioglu, B. van Ginneken, K. G. van Leeuwen, and K. Murphy, “Deep learning for chest X-ray analysis: A survey,” Med. Image Anal., vol. 72, p. 102125, Aug. 2021, doi: 10.1016/j.media.2021.102125.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ikfina Kamaliya Rizqi, Catur Supriyanto
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
