Multi-Scale Convolutional Neural Network-Based Classification of Tuberculosis Chest X-ray Images
DOI:
https://doi.org/10.64479/iarci.v1i2.60Keywords:
Tuberculosis, CNN, Multi-Scale, thorax, X-RayAbstract
Tuberculosis (TB) is an infectious disease caused by the bacterium Mycobacterium tuberculosis, which mainly attacks the lung organs. One of the most commonly used methods of TB diagnosis is thorax X-ray imaging. The images of the examination results are visually analyzed by medical personnel to identify certain patterns or characteristics that indicate TB disease. However, the manual analysis process takes time and depends on the doctor's experience. Therefore, this study utilizes Artificial Intelligence (AI) technology as a diagnostic tool to provide alternative solutions that are faster and more efficient in determining TB status in patients. This study proposes the use of the Multi-Scale Convolutional Neural Network (CNN) method to classify tuberculosis disease based on thorax X-ray images. The data used was in the form of lung X-ray images that acted as inputs at the image processing stage. The dataset collected consisted of 790 images divided into two classes, namely normal lungs and lungs indicated by tuberculosis. The CNN architecture includes three convolutional layers with a kernel size of 3×3, three max pooling layers of 2×2, and one fully connected layer with a softmax activation function. Each convolutional layer uses 128 filters, and the model learning process is optimized using the Adam Optimizer algorithm. The training process was carried out for 15 epochs and resulted in an accuracy rate of 81%. Furthermore, at the model evaluation stage, an accuracy of 79% was obtained, indicating that the proposed method has sufficient performance in classifying tuberculosis disease.
Downloads
References
[1] N. Roswita Paramata, P. Ayuningtias Mahdang, and Yusuf, “Upaya Penurunan Angka Infeksi TBC Melalui Pemberian Edukasi dan Pendampingan Kader Kesehatan dan Pengawas Menelan Obat (PMO) Efforts to reduce TB infection rates through providing education and assistance to health cadres and drug swallowing supervisors,” Jur J. Kolaboratif Sains, vol. 7, no. 10, pp. 3659–3666, 2024, doi: 10.56338/jks.v7i10.6213.
[2] A. Shrivas and S. Singh, “Tuberculosis Diagnosis and Management: Recent Advances,” J. Glob. Infect. Dis., vol. 17, no. 1, pp. 3–9, 2025, doi: 10.4103/jgid.jgid_112_24.
[3] Diah Putri Kartikasari, Fiqri Dian Priyatna Sinaga, Tiara Ayu Triarta Tambak, Zahra Humaira Kudadiri, and M. Khalil Gibran, “Ekstraksi Fitur Citra Grayscale dengan Convolutional Neural Networks,” J. Tek. Inform. dan Teknol. Inf., vol. 5, no. 1, pp. 198–205, 2025, doi: 10.55606/jutiti.v5i1.5175.
[4] X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, A review of convolutional neural networks in computer vision, vol. 57, no. 4. Springer Netherlands, 2024. doi: 10.1007/s10462-024-10721-6.
[5] N. P. Sari, “Analisis Performa Algoritma CNN dalam Klasifikasi Citra Medis Berbasis Deep Learning Analysis Of CNN Algorithm In Deep Learning-Based Medical Image Classification,” J. Komput., vol. 2, no. 2, pp. 87–92, 2024.
[6] I. D. Mienye, T. G. Swart, G. Obaido, M. Jordan, and P. Ilono, “Deep Convolutional Neural Networks in Medical Image Analysis: A Review,” Inf., vol. 16, no. 3, pp. 1–28, 2025, doi: 10.3390/info16030195.
[7] Y. G. Tejeda and H. A. Mayer, “Deep Learning with CNNs: A Compact Holistic Tutorial with Focus on Supervised Regression (Preprint),” pp. 1–42, 2024, doi: 10.3390/make6040132.
[8] H. Xiong et al., “A novel method based on a multiscale convolution neural network for identifying lung nodules,” Sci. Rep., vol. 15, no. 1, pp. 1–15, 2025, doi: 10.1038/s41598-025-21582-6.
[9] A. R. Hakim and D. M. U. Atmaja, “Implementation of Cnn for Classifying Patchouli Leaf Images Based on Accuracy and Evaluation,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 10, no. 4, pp. 728–734, 2025, doi: 10.33480/jitk.v10i4.6207.
[10] S. Oktavia, F. Hidayati, O. Lesmana, and M. B. Butar, “Hubungan Kondisi Fisik Lingkungan Rumah dengan Kejadian Tuberkulosis Paru di Indonesia ( Analisis Data Survei Kesehatan Indonesia Tahun 2023 ),” vol. 4, no. 4, pp. 3581–3588, 2025.
[11] D. D. K. Mahardika, “No 主観的健康感を中心とした在宅高齢者における 健康関連指標に関する共分散構造分析Title,” vol. 6, no. February, pp. 4–6, 2024.
[12] Rodiah, D. T. Susetianingtias, and E. Patriya, “Model Convolutional Neural Network (CNN) Custom Sequential untuk Klasifikasi Citra Ikan Hias Carassius Auratus pada Industri Akuakultur,” Decod. J. Pendidik. Teknol. Inf., vol. 5, no. 3, pp. 813–825, 2025, [Online]. Available: https://journal.umkendari.ac.id/decode/article/view/1229
[13] M. Krichen, “Convolutional Neural Networks: A Survey,” Computers, vol. 12, no. 8, pp. 1–41, 2023, doi: 10.3390/computers12080151.
[14] A. Zafar et al., “Convolutional Neural Networks: A Comprehensive Evaluation and Benchmarking of Pooling Layer Variants,” Symmetry (Basel)., vol. 16, no. 11, 2024, doi: 10.3390/sym16111516.
[15] B. S. Nusantara and M. Akbar, “Klasifikasi Penyakit Tuberculosis Berdasarkan Citra Rontgen Thorax Menggunakan Multi-Scale Convolutional Neural Network,” sudo J. Tek. Inform., vol. 3, no. 1, pp. 1–8, 2024, doi: 10.56211/sudo.v3i1.483.
[16] V. M. Risma and E. Utami, “Tuberculosis Diagnosis From X-Ray Images Using Deep Learning And Contrast Enhancement Techniques,” J. Tek. Inform., vol. 6, no. 2, pp. 981–994, 2025, doi: 10.52436/1.jutif.2025.6.2.4315.
[17] The Lancet Regional Health – Southeast Asia, “Eliminating tuberculosis by addressing access and equity,” Lancet Reg. Heal. - Southeast Asia, vol. 31, p. 100520, 2024, doi: 10.1016/j.lansea.2024.100520.
