DOI 10.17586/0021-3454-2024-67-4-315-320
UDC 004.85
USING DEEP LEARNING IN PNEUMONIA DIAGNOSIS FROM X-RAYS PATTERNS
St. Petersburg State University of Aerospace Instrumentation, Department of Applied Informatics;
V. V. Bozhenko
St. Petersburg State University of Aerospace Instrumentation, Department of Applied Informatics; Senior Lecturer
M. T. Tatarnikova
Saint Petersburg State University of Aerospace Instrumentation; Professor
Reference for citation: Raskopina А. S., Bozhenko V. V., Tatarnikova T. M. Using deep learning in pneumonia diagnosis from x-rays patterns. Journal of Instrument Engineering. 2024. Vol. 67, N 4. P. 315—320 (in Russian). DOI: 10.17586/0021-3454-2024-67-4-315-320.
Abstract. With the development of neural networks, new effective solutions in the field of medical diagnosis are opening up. The level of accuracy and reliability achieved by neural networks reduces the risk of false positives and diagnostic errors. In the task of diagnosing pneumonia from X-ray images, various machine learning algorithms such as the support vector machine (SVM), K-nearest neighbors (KNN), convolutional neural networks (CNN) are compared. The advantages of these methods in the task of medical diagnostics are discussed. Machine learning algorithms are brought to software implementation, and for each of them training parameters are selected experimentally. To compare the methods, a standard metric, accuracy, was used, and the methods are also compared by training time. The corresponding experiments are conducted on real data from X-ray images of patients with pneumonia. The experimental results demonstrate better accuracy of deep neural networks compared to traditional machine learning methods, which confirms the effectiveness of their potential use for the diagnosis and treatment of this disease.
Abstract. With the development of neural networks, new effective solutions in the field of medical diagnosis are opening up. The level of accuracy and reliability achieved by neural networks reduces the risk of false positives and diagnostic errors. In the task of diagnosing pneumonia from X-ray images, various machine learning algorithms such as the support vector machine (SVM), K-nearest neighbors (KNN), convolutional neural networks (CNN) are compared. The advantages of these methods in the task of medical diagnostics are discussed. Machine learning algorithms are brought to software implementation, and for each of them training parameters are selected experimentally. To compare the methods, a standard metric, accuracy, was used, and the methods are also compared by training time. The corresponding experiments are conducted on real data from X-ray images of patients with pneumonia. The experimental results demonstrate better accuracy of deep neural networks compared to traditional machine learning methods, which confirms the effectiveness of their potential use for the diagnosis and treatment of this disease.
Keywords: neural networks, machine learning, diagnostics, support vector method, k-nearest neighbors, convolutional neural networks, deep learning
References:
References:
- Zhang Zh. Annals of Translational Medicine, 2016, no. 11(4), pp. 218–225, DOI: 10.21037/atm.2016.03.37.
- Bozhenko V.V. and Tatarnikova T.M. Wave Electronics and its Application in Information and Telecommunication Systems (WECONF), St. Petersburg, 2023, рр. 1–4, DOI: 10.1109/WECONF57201.2023.10148004.
- Razzak M.I., Imran M., Xu G. Neural Computing & Applications, 2020, vol. 32, рр. 4417–4451.
- Vasilchenko V.A., Burkovsky V.L., Danilov A.D. Computer optics, 2019, no. 2(43), pp. 296–303. (in Russ.)
- Maksimova E.I., Khaustov P.A. Fundamental research, 2016, no. 4–2, pp. 290–294. (in Russ.)
- Komkov A.A., Mazaev V.P., Ryazanova S.V., Samochatov D.N., Bazaeva E.V. Science review. Medical Sciences, 2020, no. 5, pp. 33–40, URL: https://science-medicine.ru/ru/article/view?id=1141. (in Russ.)
- Jaapar R.M.Q.R., Mansor M.A. Journal of Applied Sciences Research, 2018, no. 6(14), pp. 23–27, DOI: 10.22587/jasr.2018.14.6.5.
- Awad M., Khanna R. Efficient Learning Machines, 2015, рр. 39–66, DOI:10.1007/978-1-4302-5990-9_3.
- Tatarnikova T.M. and Mokretsov N.S. XXVI International Conference on Soft Computing and Measurements (SCM), St. Petersburg, 2023, рр. 240–243, DOI: 10.1109/SCM58628.2023.10159119.
- Paramasivam K., Sindha M.M.R., Balakrishnan S.B. Entropy, 2023, no. 844(25), pp. 1–15, DOI: 10.3390/e25060844.
- Alzubaidi L., Zhang J., Humaidi A.J., Al-Dujaili A., Duan Y., Al-Shamma O., Santamaría J., Fadhel M.A., Al-Amidie M., and Farhan L. Journal of Big Data, 2021, no. 53(8), pp. 1–74, DOI:10.1186/s40537-021-00444-8.
- LeCun Y., Bengio Y., Hinton G. Nature, 2015, no. 7553(521), pp. 436–444, DOI:10.1038/nature14539.
- Akcay S., Kundegorski M.E., Willcocks C.G., and Breckon T.P. IEEE Transactions on Information Forensics and Security, 2018, no. 9(13), pp. 2203–2215.
