Improving Smear-Negative Tuberculosis Detection Using Data Augmentation and Faster R-CNN

Nur Azizah; Po Abas Sunarya; Untung Rahardja; Achmad Benny Mutiara; Prihandoko Prihandoko; Charlotte Pasha

doi:10.34306/ijcitsm.v6i1.233

Authors

Nur Azizah University of Raharja https://orcid.org/0000-0002-5333-5520
Po Abas Sunarya University of Raharja https://orcid.org/0000-0002-3869-2837
Untung Rahardja Universiti Teknologi Malaysia https://orcid.org/0000-0002-2166-2412
Achmad Benny Mutiara University of Gunadarma https://orcid.org/0000-0003-0220-8289
Prihandoko Prihandoko University of Gunadarma https://orcid.org/0000-0003-4087-221X
Charlotte Pasha Eduaward Incorporation https://orcid.org/0009-0004-7831-3864

DOI:

https://doi.org/10.34306/ijcitsm.v6i1.233

Keywords:

Data Augmentation, SNPT, Faster R-CNN, ResNet Architecture, Chest X-ray Imaging

Abstract

Smear-Negative Pulmonary Tuberculosis (SNPT) remains a major diagnostic challenge due to the low bacterial load that frequently causes false negative results in sputum microscopy. Chest X-ray imaging is commonly used as a complementary diagnostic tool however its interpretation relies heavily on expert radiologists and is prone to subjectivity. Recent developments in deep learning particularly object detection models provide promising opportunities to improve diagnostic accuracy. This study aims to develop and evaluate a deep learning based approach for SNPT detection in chest X-ray images using a Faster R-CNN model with a ResNet architecture. The proposed method applies data augmentation techniques including flipping rotation scaling and random brightness adjustment to enhance training data diversity and reduce overfitting. The model was implemented using PyTorch and evaluated using accuracy precision recall and F1 score. Experimental results indicate that data augmentation substantially improves performance achieving 76.60% accuracy and 68.57% F1 score compared to 53.06% accuracy and 51.06% F1 score without augmentation. Improved recall reflects higher sensitivity in detecting SNPT cases. These findings indicate that data augmentation enhances the robustness and generalization of Faster R-CNN models for SNPT detection and supports the potential of AI assisted diagnostic systems in tuberculosis screening programs.

References

I. D. Apostolopoulos, N. D. Papathanasiou, and D. J. Apostolopoulos, “A deep learning methodology for the detection of abnormal parathyroid glands via scintigraphy with 99mtc-sestamibi,” Diseases, vol. 10, no. 3, p. 56, 2022.

C. F. G. D. Santos and J. P. Papa, “Avoiding overfitting: A survey on regularization methods for convolutional neural networks,” ACM Computing Surveys (Csur), vol. 54, no. 10s, pp. 1–25, 2022.

J. Peng and Y. Wang, “Medical image segmentation with limited supervision: a review of deep network models,” Ieee Access, vol. 9, pp. 36 827–36 851, 2021.

M. Alfarizi, M. Al-Farish, M. Taufiqurrahman, G. Ardiansah, and M. Elgar, “The use of python as a programming language for machine learning and deep learning,” Student Scientific Work of Monotheism (KARIMAH TAUHID), vol. 2, no. 1, pp. 1–6, 2023.

T. Rahman, A. Khandakar, Y. Qiblawey, A. Tahir, S. Kiranyaz, S. B. A. Kashem, M. T. Islam, S. Al Maadeed, S. M. Zughaier, M. S. Khan et al., “Exploring the effect of image enhancement techniques on covid-19 detection using chest x-ray images,” Computers in biology and medicine, vol. 132, p. 104319, 2021.

E. Susetyono, D. S. Priyarsono, A. Sukmawati, and P. Nurhayati, “A structural model of risk governance and maturity in ultra microfinance soes,” International Journal of Cyber and IT Service Management (IJCITSM), vol. 5, no. 2, pp. 156–170, 2025.

United Nations. (2025) Goal 3: Ensure healthy lives and promote well-being for all at all ages. United Nations Department of Economic and Social Affairs. Accessed December 17 2025. [Online]. Available: https://sdgs.un.org/goals/goal3

A. J. Kalita, A. Boruah, T. Das, N. Mazumder, S. K. Jaiswal, G.-Y. Zhuo, A. Gogoi, N. M. Kakoty, and F.-J. Kao, “Artificial intelligence in diagnostic medical image processing for advanced healthcare applications,” in Biomedical Imaging: Advances in Artificial Intelligence and Machine Learning. Springer, 2024, pp. 1–61.

United Nations. (2025) Goal 9: Build resilient infrastructure promote inclusive and sustainable industrialization and foster innovation. United Nations Department of Economic and Social Affairs. Accessed December 17 2025.

J. Chakaya, M. Khan, F. Ntoumi, E. Aklillu, R. Fatima, P. Mwaba, N. Kapata, S. Mfinanga, S. E. Hasnain, P. D. Katoto et al., “Global tuberculosis report 2020–reflections on the global tb burden, treatment and prevention efforts,” International journal of infectious diseases, vol. 113, pp. S7–S12, 2021.

A. C. Abadan, E. Kurniyaningrum, A. Rinanti, and D. Pontan, “Evaluation zero runoff concept in highrise buildings,” IAIC Transactions on Sustainable Digital Innovation (ITSDI), vol. 6, no. 1, pp. 95–105, 2024.

Y. Zhan, Y. Wang, W. Zhang, B. Ying, and C. Wang, “Diagnostic accuracy of the artificial intelligence methods in medical imaging for pulmonary tuberculosis: a systematic review and meta-analysis,” Journal of Clinical Medicine, vol. 12, no. 1, p. 303, 2022.

S. Erniwati, V. Afifah, and B. Imran, “Mask region-based convolutional neural network in object detection: A review,” IJACI: International Journal of Advanced Computing and Informatics, vol. 1, no. 2, pp. 106–117, 2025.

A. S. Bein and A. Williams, “Development of deep learning algorithms for improved facial recognition in security applications,” IAIC Transactions on Sustainable Digital Innovation (ITSDI), vol. 5, no. 1, pp. 19–23, 2023.

T. Kumar, R. Brennan, A. Mileo, and M. Bendechache, “Image data augmentation approaches: A comprehensive survey and future directions,” IEEE Access, 2024.

R. Nuraeni, M. Hardini, J. Parker, and M. G. Ilham, “Swot analysis of ai-based learning recommendation systems for student engagement,” International Transactions on Artificial Intelligence, vol. 4, no. 1, pp. 1–12, 2025.

I. M. Abdulkareem, F. K. AL-Shammri, N. A. A. Khalid, and N. A. Omran, “A proposed approach for object detection and recognition by deep learning models using data augmentation.” International Journal of Online & Biomedical Engineering, vol. 20, no. 5, 2024.

M. A. Al-qaness, J. Zhu, D. AL-Alimi, A. Dahou, S. H. Alsamhi, M. Abd Elaziz, and A. A. Ewees, “Chest x-ray images for lung disease detection using deep learning techniques: A comprehensive survey.” Archives of Computational Methods in Engineering, vol. 31, no. 6, 2024.

A. Upadhyay, N. S. Chandel, K. P. Singh, S. K. Chakraborty, B. M. Nandede, M. Kumar, A. Subeesh, K. Upendar, A. Salem, and A. Elbeltagi, “Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture,” Artificial Intelligence Review, vol. 58, no. 3, p. 92, 2025.

D. R. Beddiar, M. Oussalah, U. Muhammad, and T. Sepp¨anen, “A deep learning based data augmentation method to improve covid-19 detection from medical imaging,” Knowledge-Based Systems, vol. 280, p. 110985, 2023.

A. Shahzadi, A. Tariq, and N. Mehmood, “Computer vision based extraction of experimental parameter mediated by time series analysis,” Physics Education, vol. 60, no. 3, p. 035011, 2025.

P. Pandey, S. Chaudhary, and X. Nie, “Deep learning technique for interpretable diagnosis of polycystic ovary syndrome in ultrasound imaging,” Aptisi Transactions on Technopreneurship (ATT), vol. 7, no. 3, pp. 779–792, 2025.

A. Mumuni and F. Mumuni, “Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods,” Knowledge and Information Systems, pp. 1–51, 2025.

S. Rajpal, N. Lakhyani, A. K. Singh, R. Kohli, and N. Kumar, “Using handpicked features in conjunction with resnet-50 for improved detection of covid-19 from chest x-ray images,” Chaos, Solitons & Fractals, vol. 145, p. 110749, 2021.

M. Furqan and A. Ramadhan, “Characteristics of tuberculosis patients in the binuang health center in the 2021-2022 period,” Journal of Endocrinology, Tropical Medicine, and Infectious Disease (JETROMI), vol. 6, no. 3, pp. 114–122, 2024.

R. E. Indrajit, M. V. A. Sin, E. A. Nabila, W. N. Wahid, and N. Septiani, “Optimizing business process efficiency through artificial intelligence integration in industry 4.0,” Sundara Advanced Research on Artificial Intelligence, vol. 1, no. 2, pp. 47–55, 2025.

X. Wang and J. Song, “Iciou: Improved loss based on complete intersection over union for bounding box regression,” IEEE Access, vol. 9, pp. 105 686–105 695, 2021.

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,” Journal of medical Internet research, vol. 25, p. e43154, 2023.

C.-L. Fan, “Evaluation model for crack detection with deep learning: Improved confusion matrix based on linear features,” Journal of Construction Engineering and Management, vol. 151, no. 3, p. 04024210, 2025.

I. Yusnita, A. Kadim, R. Lesmana, A. Sutarman, C. Yu, and S. Millah, “Examining the interaction of economic business strategies in the context of global market dynamics,” Startupreneur Business Digital (SABDA Journal), vol. 4, no. 1, pp. 93–103, 2025.

F. Javanmardi, S. R. Kadiri, and P. Alku, “A comparison of data augmentation methods in voice pathology detection,” Computer Speech & Language, vol. 83, p. 101552, 2024.

G. Tavaziva, M. Harris, S. K. Abidi, C. Geric, M. Breuninger, K. Dheda, A. Esmail, M. Muyoyeta, K. Reither, A. Majidulla et al., “Chest x-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: an individual patient data meta-analysis of diagnostic accuracy,” Clinical Infectious Diseases, vol. 74, no. 8, pp. 1390–1400, 2022.

N. Rahmasena, I. A. Marhana, M. Y. S. Suwandi, T. Kusmiati, and T. Jearanaiwitayakul, “Factors associated with acid fast bacilli and sputum culture conversion in patients with multidrug-resistant tuberculosis in surabaya,” Biomolecular and Health Science Journal, 2021.

K. Kant, D. B. Shah, N. Vaidya, K. Patel, and K. Solanki, “Smile prediction for mental health monitoring from video sequences using deep learning,” in International Conference on ICT for Sustainable Development. Springer, 2025, pp. 44–55.

R. Septiowati, “Analysis of the application information technology on employee work productivity pt rajendra kesatria perkasa depok,” International Journal of Cyber and IT Service Management (IJCITSM), vol. 6, no. 1, pp. 1–9, 2026.

P. Verma, V. Tripathi, and B. Pant, “Comparison of different optimizers implemented on the deep learning architectures for covid-19 classification,” Materials Today: Proceedings, vol. 46, pp. 11 098–11 102, 2021.

E. M. Adiba, F. Amir, I. L. Insani, Y. M. Zamhuri, D. Julianingsih et al., “Natural language processing of social media sentiment toward halal logos in indonesian smes,” in 2025 4th International Conference on Creative Communication and Innovative Technology (ICCIT). IEEE, 2025, pp. 1–7.

S. A. Alshoabi, K. M. Almas, S. A. Aldofri, A. M. Hamid, F. H. Alhazmi, W. M. Alsharif, O. M. Abdulaal, A. A. Qurashi, K. M. Aloufi, K. D. Alsultan et al., “The diagnostic deceiver: radiological pictorial review of tuberculosis,” Diagnostics, vol. 12, no. 2, p. 306, 2022.

Z. Huang, F. Bianchi, M. Yuksekgonul, T. J. Montine, and J. Zou, “A visual–language foundation model for pathology image analysis using medical twitter,” Nature medicine, vol. 29, no. 9, pp. 2307–2316, 2023.

D. Collie, C. Cousens, S. Wright, Z. Chang, J. Meehan, H. Brown, C. D. Gray, T. J. MacGillivray, D. J. Griffiths, C. E. Eckert et al., “Spatial encoding and growth-related change of sheep lung radiomic features,” Frontiers in Veterinary Science, vol. 12, p. 1495278, 2025.

T. Mahesh, S. B. Khan, K. K. Mishra, S. Alzahrani, and M. Alojail, “Enhancing diagnostic precision in breast cancer classification through efficientnetb7 using advanced image augmentation and interpretation techniques,” International Journal of Imaging Systems and Technology, vol. 35, no. 1, p. e70000, 2025.

D. Jonas, E. Maria, I. R. Widiasari, U. Rahardja, T. Wellem et al., “Design of a tam framework with emotional variables in the acceptance of health-based iot in indonesia,” ADI Journal on Recent Innovation, vol. 5, no. 2, pp. 146–154, 2024.

T. Anwar and S. Zakir, “Vehicle make and model recognition using mixed sample data augmentation techniques,” IAES International Journal of Artificial Intelligence, vol. 12, no. 1, p. 137, 2023.