T.M. Magrupov1, B.J. Tashev2, Sh.Sh. Zubaydullaev3

1–3 Tashkent State Technical University n.a. Islam Karimov (Tashkent, Republic Uzbekistan)
1 talatmt@rambler.ru, 2 bekjigittashev@gmail.com, 3 mirametovali@gmail.com3

The organization of disease prevention and diagnosis processes in medicine requires great accuracy and speed. Neural networks and especially deep learning technologies open up new possibilities for the diagnosis and prediction of lung diseases based on the processing and analysis of biomedical images of the lungs.

The work purpose – development of a convolutional neural network model for analyzing, processing, and classifying biomedical lung images to determine the type of disease.

The methodological and algorithmic foundations of the processing and analysis of biomedical images of lung diseases are investigated. Methods, learning algorithms, and architecture of convolutional neural networks for classifying lung images have been developed. Databases of biomedical images of lung diseases with their subsequent processing have been formed. A method for digitizing images and clinical data is proposed to obtain data for models in a form that is convenient and ready for analysis.

The proposed algorithms of convolutional neural networks provide automatic extraction and analysis of key features in images that are difficult to detect with an unarmed eye, and provides highly accurate diagnostics, helping doctors.

Magrupov T.M., Tashev B.J., Zubaydullaev Sh.Sh. Development of a model for processing and analyzing lung diseases based on convolutional neural networks. Biomedicine Radioengineering. 2025. V. 28. № 5. P. 120–124. DOI: https:// doi.org/10.18127/j15604136-202505-24 (In Russian)

1. Levitan R., Stephen J. The Importance of Lung Sound Analysis in Medical Diagnosis. Journal of Pulmonary Medicine. 2020. V. 23. № 5. P. 345–357.
2. Wang Y., Chen X. IEEE Learning Applications in Medical Diagnosis: A Comprehensive Review. International Journal of Medical Informatics. 2019. V. 112. P. 66–77.
3. Lee K.S. Neural Networks for Automated Respiratory Sound Analysis. Biomedical Signal Processing and Control. 2019. V. 51. P. 79–85.
4. Singh P., Kumar A. Challenges in Respiratory Sound Data Collection for Disease Classification. Respiratory Medicine and Research. 2021. V. 42. № 2. P. 103–110.
5. Ghorbani M., Amir H.M. Assessment of Acoustic Features in Respiratory Sound Analysis. IEEE Transactions on Biomedical Engineering. 2020. V. 67. № 9. P. 2895–2903.
6. He Q.-H., Yu B., Hong X., Lv B., Liu T., Ran J., Bi Y.-T. An improved lung sound de-noising method by wavelet packet transform with PSO-based threshold selection. Intell. Autom. Soft Comput. 2018. V. 24(2). P. 223–230.
7. Magrupov T.M., Nazirov R.M., Abdullaev I.N. Formation of a database of lung disease sound signals. Science and Innovation. International scientific journal. September 2024. V. 3. Is. 9. P. 90–96.