{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:15:15Z","timestamp":1793132115903,"version":"4.5.0"},"reference-count":29,"publisher":"Termedia Sp. z.o.o.","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pol J Radiol"],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Tuberculosis (TB) is a severe bacterial infectious lung disease. Millions of people die or experience severe health complications due to TB each year. Accurate, automated, and effective detection of TB is key to curing and preventing person-to-person transmission. In this regard, deep learning (DL) and machine learning (ML) techniques applied to chest X-ray (CXR) images have proved effective. Here, we present our DL- and ML-based approach for TB detection using CXR images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Material and methods<\/jats:title>\n                    <jats:p>We implemented convolutional neural network (CNN)-based pre-trained DL models, such as DenseNet121, DenseNet169, DenseNet201, ResNet152, and VGG19, as feature extractors. ML models, including support vector machine (SVM), XGBoost, logistic regression, and a DL-based custom model, were used as classifiers. A total of 2,391 CXR images from three publicly available datasets were considered.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We found three models achieving the highest value in different evaluation metrics: accuracy (99.91%) with ResNet152 and SVM; recall (99.22%), precision (99.23%), and F1-score (99.22%) with DenseNet169 and the custom classifier; and area under the curve (99.99%) with DenseNet201 and the custom classifier. Among these models, we propose DenseNet169 with the custom classifier as the best performer for potential clinical application, as it reflected a high and well-balanced performance across all evaluation metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study evaluated pre-trained CNN-based DL and ML models on pre-processed CXR images for the detection of TB. The DenseNet169 model with a custom classifier stands out with its high and well-balanced performance, offering a significant contribution to the effective and automated detection of TB.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.5114\/pjr\/213688","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T08:48:20Z","timestamp":1772441300000},"page":"46-55","source":"Crossref","is-referenced-by-count":1,"title":["An automated tuberculosis detection approach using deep learning and machine learning techniques from chest X-ray images: a\u00a0step towards effective diagnosis"],"prefix":"10.5114","volume":"91","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9735-8102","authenticated-orcid":false,"given":"Abu Saleh Mohammad","family":"Nabil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3581-7366","authenticated-orcid":false,"given":"Md. Musfiqur Rahman Mridha","family":"Mridha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9610-9867","authenticated-orcid":false,"given":"Md. Shahid Ahammed","family":"Shakil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3232-2164","authenticated-orcid":false,"given":"Iffath Tanjim","family":"Moon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1500-8841","authenticated-orcid":false,"given":"Md. Fayzul","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6995-7574","authenticated-orcid":false,"given":"Md. Jamil","family":"Chaudhary","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1291-5474","authenticated-orcid":false,"given":"Sakib","family":"Imtiaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8895-8886","authenticated-orcid":false,"given":"Md. Taufiq","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"3061","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"ref-1680013","unstructured":"World Health Organization. Tuberculosis. Available at: https:\/\/www.who.int\/health-topics\/tuberculosis (Accessed: 20.05.2025)."},{"key":"ref-1680014","unstructured":"Centers for Disease Control and Prevention. Signs and symptoms of tuberculosis. Available at: https:\/\/www.cdc.gov\/tb\/signs-symptoms\/index.html (Accessed: 20.05.2025)."},{"key":"ref-1680015","unstructured":"Shmerling RH. Are early detection and treatment always best? Harvard Health 2021. Available at: https:\/\/www.health.harvard.edu\/blog\/are-early-detection-and-treatment-always-best-2021012821816 (Accessed: 20.05.2025)."},{"key":"ref-1680016","unstructured":"Tuberculosis deaths worldwide 2010-2023. Statista. 2023. Available at: https:\/\/www.statista.com\/statistics\/1459442\/tuberculosis-deaths-worldwide\/ (Accessed: 20.05.2025)."},{"key":"ref-1680017","unstructured":"Centers for Disease Control and Prevention. Reported tuberculosis in the United States, 2023. National data. Available at: https:\/\/www.cdc.gov\/tb-surveillance-report-2023\/summary\/national.html (Accessed: 20.05.2025)."},{"key":"ref-1680018","unstructured":"World Health Organization. TB incidence. Available at: https:\/\/www.who.int\/teams\/global-tuberculosis-programme\/tb-reports\/global-tuberculosis-report-2024\/tb-disease-burden\/1-1-tb-incidence (Accessed: 20.05.2025)."},{"key":"ref-1680019","unstructured":"Desikan P. Sputum smear microscopy in tuberculosis: is it still relevant? Indian J Med Res 2013; 137: 442-444."},{"key":"ref-1680020","unstructured":"Mayo Clinic. Tuberculosis: diagnosis and treatment. Available at: https:\/\/www.mayoclinic.org\/diseases-conditions\/tuberculosis\/diagnosis-treatment\/drc-20351256 (Accessed: 20.05.2025)."},{"key":"ref-1680021","doi-asserted-by":"crossref","unstructured":"Gao J, Jiang Q, Zhou B, Chen D. Convolutional neural networks for computer-aided detection or diagnosis in medical image analysis: an overview. Math Biosci Eng 2019; 16: 6536-6561.","DOI":"10.3934\/mbe.2019326"},{"key":"ref-1680022","unstructured":"GeeksforGeeks. Convolutional neural network (CNN) in machine learning. Available at: https:\/\/www.geeksforgeeks.org\/convolutional-neural-network-cnn-in-machine-learning\/ (Accessed: 04.05.2025)."},{"key":"ref-1680023","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.14538"},{"key":"ref-1680024","unstructured":"Maheswari N, Kumar B, Hemalatha K, Aswith G, Jyothi M. Enhancing tuberculosis detection through machine learning on chest X-ray scans. Int J Creat Res Thoughts 2024; 12: 2320-2882."},{"key":"ref-1680025","doi-asserted-by":"crossref","unstructured":"Huy VT, Lin CM. An improved densenet deep neural network model for tuberculosis detection using chest X-ray images. IEEE Access 2023; 11: 42839-42849.","DOI":"10.1109\/ACCESS.2023.3270774"},{"key":"ref-1680026","doi-asserted-by":"publisher","DOI":"10.5114\/pjr.2022.113435"},{"key":"ref-1680027","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/7424836"},{"key":"ref-1680028","doi-asserted-by":"crossref","unstructured":"Rahman T, Khandakar A, Kadir MA, Islam KR, Islam KF, Mazhar R, et al. Reliable tuberculosis detection using chest X-ray with deep learning, segmentation, and visualization. IEEE Access 2020; 8: 191586-191601.","DOI":"10.1109\/ACCESS.2020.3031384"},{"key":"ref-1680029","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14111174"},{"key":"ref-1680030","doi-asserted-by":"crossref","unstructured":"Reshma SR, Beegum TR. Microscope image processing for TB diag\u00adnosis using shape features and ellipse fitting. In: Proceedings of the 2017 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES); 2017 Aug 8-10; Kollam, India. Piscataway (NJ): IEEE; 2017. p. 1-7.","DOI":"10.1109\/SPICES.2017.8091342"},{"key":"ref-1680031","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13132230"},{"key":"ref-1680032","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.827299"},{"key":"ref-1680033","doi-asserted-by":"crossref","unstructured":"Dasanayaka C, Dissanayake MB. Deep learning methods for screening pulmonary tuberculosis using chest X-rays. Comput Methods Biomech Biomed Eng Imaging Vis 2021; 9: 39-49.","DOI":"10.1080\/21681163.2020.1808532"},{"key":"ref-1680034","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2011.09778"},{"key":"ref-1680035","unstructured":"Rahman T. Tuberculosis (TB) chest X-ray database [dataset]. Kaggle. Available at: https:\/\/www.kaggle.com\/datasets\/tawsifurrahman\/tuberculosis-tb-chest-xray-dataset (Accessed: 20.05.2025)."},{"key":"ref-1680036","unstructured":"raddar. Tuberculosis chest X-rays (Shenzhen) [dataset]. Kaggle. Available at: https:\/\/www.kaggle.com\/datasets\/raddar\/tuberculosis-chest-xrays-shenzhen (Accessed: 20.05.2025)."},{"key":"ref-1680037","unstructured":"raddar. Chest X-rays tuberculosis from India [dataset]. Kaggle; 2023. Available at: https:\/\/www.kaggle.com\/datasets\/raddar\/chest-xrays-tuberculosis-from-india (Accessed: 20.05.2025)."},{"key":"ref-1680038","doi-asserted-by":"crossref","unstructured":"Kina E. TLEABLCNN: Brain and Alzheimer\u2019s disease detection using attention based explainable deep learning and SMOTE using imbalanced brain MRI. IEEE Access 2025; 13: 27670-27683.","DOI":"10.1109\/ACCESS.2025.3539550"},{"key":"ref-1680039","doi-asserted-by":"publisher","DOI":"10.2174\/0115734056342623241119061744"},{"key":"ref-1680040","doi-asserted-by":"crossref","unstructured":"Masood MK, Nava E, Otero P. A novel intensity-corrected blue channel compensation and edge-preserving contrast enhancement using laplace filter and sigmoid function for sand-dust image enhancement. IEEE Access 2025; 13: 43127-43144.","DOI":"10.1109\/ACCESS.2025.3548972"},{"key":"ref-1680041","unstructured":"Kaggle. Kaggle: Your home for data science. Available at: https:\/\/www.kaggle.com\/ (Accessed: 20.05.2025)."}],"container-title":["Polish Journal of Radiology"],"original-title":[],"link":[{"URL":"https:\/\/www.polradiol.com\/pdf-213688-136130","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.polradiol.com\/pdf-213688-136130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T08:48:32Z","timestamp":1772441312000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.polradiol.com\/An-automated-tuberculosis-detection-approach-using-deep-learning-and-machine-learning,213688,0,2.html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026]]}},"alternative-id":["213688"],"URL":"https:\/\/doi.org\/10.5114\/pjr\/213688","relation":{},"ISSN":["1899-0967"],"issn-type":[{"value":"1899-0967","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2,2]]}}}