Lung Tuberculosis Detection Using Convolutional Neural Network with Modified Densenet Architecture
Lung Tuberculosis Detection Using Convolutional Neural Network with Modified Densenet Architecture |
||
 |
 |
|
| © 2025 by IJETT Journal | ||
| Volume-73 Issue-5 |
||
| Year of Publication : 2025 | ||
| Author : D. Saranya, S. Saraswath |
||
| DOI : 10.14445/22315381/IJETT-V73I5P108 | ||
How to Cite?
D. Saranya, S. Saraswath, "Lung Tuberculosis Detection Using Convolutional Neural Network with Modified Densenet Architecture," International Journal of Engineering Trends and Technology, vol. 73, no. 5, pp.70-91, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I5P108
Abstract
Pulmonary tuberculosis is primarily caused by Mycobacterium Tuberculosis (TB) infection. The disease is a common clinical respiratory illness with high infectious and fatal incidence, ranking third among all the illnesses globally and gravely threatening the patient’s health and life. TB is regarded as a communicable chest disease. The World Health Organization has led several TB control projects across the world. In this paper, lung TB detection is proposed using the framework. The datasets were collected from the Kaggle repository. The raw image has been de-noised using the Non-Local Wavelet (NLW) algorithm, and segmentation has also been done using the CNN algorithm. The best features are selected by using Adversarial feature selection, which allows for strengthening the model’s robustness to feature selection. Finally, the classification of TB has used Convolutional Neural Networks (CNN) with the modified dense architecture and improved Adam optimization. Adversarial methods, NLW and CNN with modified Dense Architecture and improved Adam Optimization techniques are utilized to increase the model efficiency and accuracy. TB diagnosis from lung images is very accurate in this technique. Montgomery and Shenzhen lung imaging datasets are used to segment and categorize the lung TB. With excellent reliability and performance, the proposed framework offers several opportunities to improve the automated TB screening systems.
Keywords
Classification, Convolutional Neural network, Lung tuberculosis, Non-Local Wavelet, Segmentation.
References
[1] Tej Bahadur Chandra et al., “Automatic Detection of Tuberculosis-Related Abnormalities in Chest X-Ray Images using Hierarchical Feature Extraction Scheme,” Expert Systems with Applications, vol. 158, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Suliman Mohamed Fati, Ebrahim Mohammed Senan, and Narmine ElHakim, “Deep and Hybrid Learning Technique for Early Detection of Tuberculosis based on X-Ray Images using Feature Fusion,” Applied Sciences, vol. 12, no. 14, pp. 1-23, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Fatma Taher, and Naoufel Werghi, and Hussain Al-Ahmad, “Computer-Aided Diagnosis System for Early Lung Cancer Detection,” Algorithms, vol. 8, no. 4, pp. 1088-1110, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Sushil Ghildiyal, Saibal Manna and N. Ruban, “Layer-Based Deep Net Models for Automated Classification of Pulmonary Tuberculosis from Chest Radiographs,” International Journal of Medical Engineering and Informatics, vol. 15, no. 1, pp. 58-69, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Satyavratan Govindarajan, and Ramakrishnan Swaminathan, “Extreme Learning Machine-Based Differentiation of Pulmonary Tuberculosis in Chest Radiographs using Integrated Local Feature Descriptors,” Computer Methods and Programs in Biomedicine, vol. 204, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Rui Shen, Irene Cheng, and Anup Bas, “A Hybrid Knowledge-Guided Detection Technique for Screening of Infectious Pulmonary Tuberculosis from Chest Radiographs,” IEEE Transactions on Biomedical Engineering, vol. 57, no. 11, pp. 2646-2656, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Wei He et al., “Use of Low-Dose Computed Tomography to Assess Pulmonary Tuberculosis among Healthcare Workers in a Tuberculosis Hospital,” Infectious Diseases of Poverty, vol. 6, no. 2, pp. 90-99, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Li Wang et al., “Distinguishing Non-Tuberculous Mycobacteria from Mycobacterium Tuberculosis Lung Disease from CT Images using a Deep Learning Framework,” European Journal of Nuclear Medicine and Molecular Imaging, vol. 48, no. 13, pp. 4293-4306, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Jawad Rasheed, and Raed M. Shubair, “Screening Lung Diseases using Cascaded Feature Generation and Selection Strategies,” Healthcare, vol. 10, no. 7, pp. 1-17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Chenggong Yan et al., “Cycle-Consistent Generative Adversarial Network: Effect on Radiation Dose Reduction and Image Quality Improvement in Ultralow-Dose CT for Evaluation of Pulmonary Tuberculosis,” Korean Journal of Radiology, vol. 22, no. 6, pp. 983-991, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Xavier Alphonse Inbaraj et al., “A Novel Machine Learning Approach for Tuberculosis Segmentation and Prediction using Chest-X-Ray (CXR) Images,” Applied Sciences, vol. 11, no. 19, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Kushagra Kushagra, Rajneesh Kumar, and Shaveta Jain, “A Deep Learning Model to Diagnose Lung Disease using Genetic Algorithm-Based Feature Selection Method,” 2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), Greater Noida, India, pp. 1251-1255, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Paras Lakhani, and Baskaran Sundaram, “Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by using Convolutional Neural Networks,” Radiology, vol. 284, no. 2, pp. 574-582, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[14] M.B. Mizan, M.A.M. Hasan, and S.R. Hassan, “A Comparative Study of Tuberculosis Detection using Deep Convolutional Neural Network,” 2020 2nd International Conference on Advanced Information and Communication Technology (ICAICT), Dhaka, Bangladesh, pp. 157-161, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Shilpa Gite, Abhinav Mishra, and Ketan Kotecha, “Enhanced Lung Image Segmentation using Deep Learning,” Neural Computing and Applications, vol. 35, no. 31, pp. 22839-22853, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Muhaza Liebenlito, Yanne Irene, and Abdul Hamid, “Classification of Tuberculosis and Pneumonia in Human Lung based on Chest X-Ray Image using Convolutional Neural Network,” InPrime: Indonesian Journal of Pure and Applied Mathematics, vol. 2, no. 1, pp. 24-32, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Lanjuan Li, Haiyang Huang, and Xinyu Jin, “AE-CNN Classification of Pulmonary Tuberculosis based on CT Images,” 2018 9th International Conference on Information Technology in Medicine and Education (ITME), Hangzhou, China, pp. 39-42, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Xinsen Zhou et al., “Enhanced Differential Evolution Algorithm for Feature Selection in Tuberculous Pleural Effusion Clinical Characteristics Analysis,” Artificial Intelligence in Medicine, vol. 153, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Syed Kashif Badshah, and Noor Badshah, “Classification of Medical Images through Convolutional Neural Network Modification Method,” International Journal of Innovations in Science & Technology, vol. 6, no. 5, pp. 216-226, 2024.
[Google Scholar] [Publisher Link]
[20] Sugandha Agarwal, O.P. Singh, and Deepak Nagaria, “Analysis and Comparison of Wavelet Transforms for Denoising MRI Image,” Biomedical and Pharmacology Journal, vol. 10, no. 2, pp. 831-836, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Muhammad Awais Malik et al., “A Novel Method for Lung Segmentation of Chest with Convolutional Neural Network,” Prognostic Models in Healthcare: AI and Statistical Approaches, Singapore, pp. 239-260, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Ziming Wang et al., “Research on Computer-Aided Detection and Segmentation of Pulmonary Nodules based on Deep Learning and Generative Adversarial Networks,” 2020 IEEE 8th International Conference on Information, Communication and Networks (ICICN), Xi'an, China, pp. 172-176, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Kartik Nair et al., “Analysing X-Ray Images to Detect Lung Diseases using DenseNet-169 Technique,” Proceedings of the 7th International Conference on Innovations and Research in Technology and Engineering (ICIRTE-2022), Mumbai, India, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Kanwarpartap Singh Gill et al., “Influence of Adam Optimizer with Sequential Convolutional Model for Detection of Tuberculosis,” 2022 International Conference on Computational Modelling, Simulation and Optimization (ICCMSO), Pathum Thani, Thailand, pp. 340-344, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Mostofa Ahsan, Rahul Gomes, and Anne Denton, “Application of a Convolutional Neural Network using Transfer Learning for Tuberculosis Detection,” 2019 IEEE International Conference on Electro Information Technology (EIT), Brookings, SD, USA, pp. 427-433, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Hossein Arabi, and Habib Zaidi, “Spatially Guided Nonlocal Mean Approach for Denoising of PET Images,” Medical Physics, vol. 47, no. 4, pp. 1656-1669, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Kapil Joshi et al., “Multi-Focus Image Fusion using Non-Local Mean Filtering and Stationary Wavelet Transform,” International Journal of Innovative Technology and Exploring Engineering, vol. 9, no. 1, pp. 344-350, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Jinsol Ko, Soyeon Park, and Hyun Goo Woo, “Optimization of Vision Transformer-based Detection of Lung Diseases from Chest X-Ray Images,” BMC Medical Informatics and Decision Making, vol. 24, no. 1, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Evans Kotei, and Ramkumar Thirunavukarasu, “Tuberculosis Detection from Chest X-Ray Image Modalities based on Transformer and Convolutional Neural Network,” IEEE Access, vol. 12, pp. 97417-97427, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Jian Liu, and Yidi Huang, “Comparison of Different CNN Models in Tuberculosis Detecting,” KSII Transactions on Internet and Information Systems (TIIS), vol. 14, no. 8, pp. 3519-3533, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Latheesh Mangeri et al., “Chest Diseases Prediction from X-Ray Images using CNN Models: A Study,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 10, pp. 236-243, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Ahmed T. Sahlol et al., “A Novel Method for Detection of Tuberculosis in Chest Radiographs using Artificial Ecosystem-Based Optimisation of Deep Neural Network Features,” Symmetry, vol. 12, no. 7, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Ladislav Stanke et al., “Towards to Optimal Wavelet Denoising Scheme-A Novel Spatial and Volumetric Mapping of Wavelet-Based Biomedical Data Smoothing,” Sensors, vol. 20, no. 18, pp. 1-24, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Sergii Stirenko et al., “Chest X-Ray Analysis of Tuberculosis by Deep Learning with Segmentation and Augmentation,” 2018 IEEE 38th International Conference on Electronics and Nanotechnology (ELNANO), Kyiv, Ukraine, pp. 422-428, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[35] S.N. Hankare, and S.S. Shirguppikar, Detection of Tuberculosis and Lung Cancer using CNN, Handbook of Smart Materials, Technologies, and Devices: Applications of Industry 4.0, Springer, pp. 1-11, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Sahebgoud Hanamantray Karaddi, and Lakhan Dev Sharma, “Automated Multi-Class Classification of Lung Diseases from CXR-Images using Pre-Trained Convolutional Neural Networks,” Expert Systems with Applications, vol. 211, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[37] N.B. Mahesh Kumar, K. Premalatha, and S. Suvitha, “Lung Disease detection using Self-Attention Generative Adversarial Capsule Network Optimized with Sunflower Optimization Algorithm,” Biomedical Signal Processing and Control, vol. 79, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Anup Pattnaik et al., “Predicting Tuberculosis Related Lung Deformities from CT Scan Images using 3D CNN,” CLEF (Working Notes), vol. 2380, pp. 1-16, 2019.
[Google Scholar] [Publisher Link]
[39] Aeri Rachmad, Nur Chamidah, and Riries Rulaningtyas, “Image Enhancement Sputum Containing Mycobacterium Tuberculosis using a Spatial Domain Filter,” IOP Conference Series: Materials Science and Engineering, vol. 546, no. 5, pp. 1-8, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[40] Tawsifur Rahman et al., “Reliable Tuberculosis Detection using Chest X-Ray with Deep Learning, Segmentation and Visualization,” IEEE Access, vol. 8, pp. 191586-191601, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[41] Jodh Singh et al., “Lung Tuberculosis Detection using Anti-Aliased Convolutional Networks,” Procedia Computer Science, vol. 173, pp. 281-290, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[42] Marina Yusoff et al., “Tuberculosis X-Ray Images Classification based Dynamic Update Particle Swarm Optimization with CNN,” Journal of Hunan University Natural Sciences, vol. 48, no. 9, pp. 504-514, 2021.
[Google Scholar] [Publisher Link]
[43] Ladan Ebadi et al., “A Review of Applying Second-Generation Wavelets for Noise Removal from Remote Sensing Data,” Environmental Earth Sciences, vol. 70, no. 6, pp. 2679-2690, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[44] Ahmed Iqbal, Muhammad Usman, and Zohair Ahmed, “Tuberculosis Chest X-Ray Detection using CNN-Based Hybrid Segmentation and Classification Approach,” Biomedical Signal Processing and Control, vol. 84, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[45] Geetamma Tummalapalli, Ch. Babji Prasad, and Jami Kousik, “Analysing the Performance of DenseNet in the Context of Tuberculosis Disease,” 2024 International Conference on Advancements in Power, Communication and Intelligent Systems (APCI), Kannur, India, pp. 1-7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[46] Wan Siti Halimatul Munirah Wan Ahmad, W. Mimi Diyana W. Zaki, and Mohammad Faizal Ahmad Fauzi, “Lung Segmentation on Standard and Mobile Chest Radiographs using Oriented Gaussian Derivatives Filter,” Biomedical Engineering Online, vol. 14, no. 1, pp. 1-26, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[47] G. Geetha et al., “Multifocus Image Fusion using Multiresolution Approach with Bilateral Gradient based Sharpness Criterion,” Journal Computer Science & Information Technology, vol. 10, pp. 103-115, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[48] Preena Prasad, and J. Anitha, “Non-Local Means Denoising of CT, MRI and US Images: An Investigation of Performance Under Varying Noise Levels,” 1st International Conference on Recent Advancements in Computing Technologies & Engineering, Ghaziabad, India, vol. 3168, no. 1, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[49] Prabhishek Singh, and Manoj Diwakar, “Wavelet-Based Multi-Focus Image Fusion using Average Method Noise Diffusion (AMND),” Recent Advances in Computer Science and Communications, vol. 14, no. 8, pp. 2436-2448, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[50] Eka Mala Sari Rochman, and Herry Suprajitno, “Comparison of Clustering in Tuberculosis using Fuzzy C-Means and k-Means Methods,” Communications in Mathematical Biology and Neuroscience, vol. 2022, pp. 1-20, 2022.
[Google Scholar] [Publisher Link]
[51] Vinit Kumar Gunjan, Fahimuddin Shaik, and Amita Kashyap, “Detection and Analysis of Pulmonary TB using Bounding Box and K-Means Algorithm,” ICCCE 2020: Proceedings of the 3rd International Conference on Communications and Cyber Physical Engineering, Singapore, pp. 1587-1595, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[52] Mengyang Zhao et al., “Faster Mean-Shift: GPU-Accelerated Clustering for Cosine Embedding-Based Cell Segmentation and Tracking,” Medical Image Analysis, vol. 71, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[53] Sayali Abhijeet Salkade, and Sheetal Vikram Rathi, “An Adaptive Convolution Neural Network Model for Tuberculosis Detection and Diagnosis using Semantic Segmentation,” Polish Journal of Radiology, vol. 90, pp. 124-137, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[54] Abidin Çalışkan, “Diagnosis of Malaria Disease by Integrating Chi-Square Feature Selection Algorithm with Convolutional Neural Networks and Autoencoder Network,” Transactions of the Institute of Measurement and Control, vol. 45, no. 5, pp. 975-985, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[55] Szilárd Vajda et al., “Feature Selection for Automatic Tuberculosis Screening in Frontal Chest Radiographs,” Journal of Medical Systems, vol. 42, no. 8, pp. 1-11, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[56] Khin Yadanar Win et al., “Hybrid Learning of Hand-Crafted and Deep-Activated Features using Particle Swarm Optimization and Optimized Support Vector Machine for Tuberculosis Screening,” Applied Sciences, vol. 10, no. 17, pp. 1-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[57] Si-Yuan Lu et al., “CTBViT: A Novel ViT for Tuberculosis Classification with Efficient Block and Randomized Classifier,” Biomedical Signal Processing and Control, vol. 100, pp. 1-9, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[58] Mamta Patankar, Vijayshri Chaurasia, and Madhu Shandilya, “EDenseNetViT: Leveraging Ensemble Vision Transform Integrated Transfer Learning for Advanced Differentiation and Severity Scoring of Tuberculosis,” International Journal of Imaging Systems and Technology, vol. 35, no. 3, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[59] Benazeer Haque, Ebtasam Ahmad Siddiqui, and Abhinay Gupta, “Optimized Tuberculosis Image Classification in Chest X-Rays using Transfer Learning and Hyper Parameters,” 2025 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, pp. 1-6, 2025.
[CrossRef] [Google Scholar] [Publisher Link]