Problems of Social Hygiene, Public Health and History of MedicineProblems of Social Hygiene, Public Health and History of Medicine0869-866X2412-2106Joint-Stock Company Chicot237910.32687/0869-866X-2025-33-5-1203-1209Научная статьяThe Development of Algorithm of Intellectual System of Supporting Decision-Making in Mammographic Diagnostics of Breast Cancer Based on Convolutional Neuronic NetworkOsmanovE. M.TuktamyshevaL. M.ManyakovR. R.PivovarovaK. V.GaraevaA. S.KorkmazovaL. H.DrepinV. V.ZubayraevaYa. S.The Federal State Autonomous Educational Institution of Higher Education “The I. M. Sechenov First Moscow State Medical University” of the Minzdrav of Russia (Sechenov University), 119991, Moscow, RussiaThe State Budget Institution “The Tambov Oblast Children Clinical Hospital”, 392000, Tambov, RussiaThe Federal State Budget Educational Institution of Higher Education “The Orenburg State University”, 460000, Orenburg, RussiaThe Federal State Budget Educational Institution of Higher Education “The I. F. Bunin Elets State University”, 399770, Elets, Russia081120253351203120912112025Copyright © 2025,2025The article considers issues of training models of convolutional neuronic network (CNN) for automated identification of point functions of visualization to discern mammography pictures belonging to negative, false benign and malignant cases, targeting to improve interpretation of results of mammographic examination. On the basis of automated deep training (application of CNN) the approach is proposed, that permits to detect small differences in mammographic pictures to diagnose true positive and false positive results. The information base for training CNN is represented by digital base (open resource for methods of intellectual studying of analysis of mammographic pictures) of data of mammography screening of the Massachusetts General Hospital and the Winston-Salem Medical College, the USA. The share of false positive results according trained model in the total number of examined patients from different age groups made up from 22% to 32%. To compare, share of false positive results based on decoding of mammographic picture by medical specialist varied from 34% to 53%. The trained model based on the CNN can be used for mammographic pictures of any database. The predictive accuracy of model depends, among other things, on volume of training sample. Therefore, formation of open database of results of mammographic examinations with accurately established diagnosis will permit later on to broadly apply possibilities of deep training in medical practice. The study has great potential to incorporate deep training of CNN into clinical practice of screening of breast cancer and to improve interpretation of mammographic pictures.convolutional neuronic networkmammographybreast cancer, artificial intelligenceмаммографиярак молочной железыискусственный интеллект[Аминодова И. П., Васильев М. Д., Перминова Е. В. Комплексный подход к обследованию пациенток при диагностике доброкачественных заболеваний и рака молочной железы. Проблемы социальной гигиены, здравоохранения и истории медицины. 2020;(6):1349—54. doi: 10.32687/0869-866X-2020-28-6-1349-1354][Морозов С. П., Ветшева Н. Н., Овсянников А. Г. Московский скрининг: организация маммографического скрининга как способ повысить выявляемость рака молочной железы на ранних стадиях. Проблемы социальной гигиены, здравоохранения и истории медицины. 2019;27:623—9. doi: 10.32687/0869-866X-2019-27-si1-623-629][Tabar L., Fagerberg G., Chen H. H. Efficacy of breast cancer screening by age: New results from the Swedish Two-County Trial. Cancer. 1995;75(10):2507—17. doi: 10.1002/1097-0142(19950515)75:10<2507::aid-cncr2820751017>3.0.co;2-h][Siu A. L.; U. S. Preventive Services Task Force. Screening for Breast Cancer: U. S. Preventive Services Task Force Recommendation Statement [published correction appears in Ann Intern Med. 2016 Mar 15;164(6):448]. Ann. Intern. Med. 2016;164(4):279—96. doi: 10.7326/M15-2886][Coldman A., Phillips N., Wilson C. Pan-Canadian study of mammography screening and mortality from breast cancer [published correction appears in J Natl Cancer Inst. 2015 Jan;107(1):dju404 doi:10.1093/jnci/dju404]. J. Natl. Cancer Inst. 2014;106(11):dju261. doi: 10.1093/jnci/dju261][Lehman D., Arao R. F., Sprague B. L. National Performance Benchmarks for Modern Screening Digital Mammography: Update from the Breast Cancer Surveillance Consortium Constance. Radiology. 2017;283(1):49—58. doi: 10.1148/radiol.2016161174][Silverstein M. J., Lagios M. D., Recht A. Image-detected breast cancer: state of the art diagnosis and treatment. J. Am. Coll. Surg. 2005;201(4):586—97. doi: 10.1016/j.jamcollsurg.2005.05.032][Wu N., Geras K. J., Shen Y., Su J., Kim S. G., Kim E., Wolfson S., Moy L., Cho K. Breast Density Classification with Deep Convolutional Neural Networks. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Press; 2018. P. 6682—6. doi: 10.1109/ICASSP.2018.8462671][Ручай А. Н., Кобер В. И., Дорофеев К. А. Классификация патологий молочной железы с использованием глубокой сверточной нейронной сети и трансферного обучения. Информационные процессы. 2020;(4):357—65.][Wang X., Liang G., Zhang Y., Blanton H., Bessinger Z., Jacobs N. Inconsistent Performance of Deep Learning Models on Mammogram Classification. J. Am. Coll. Radiol. 2020;17(6):796—803. doi: 10.1016/j.jacr.2020.01.006][Tsochatzidis L., Costaridou L., Pratikakis I. Deep Learning for Breast Cancer Diagnosis from Mammograms — A Comparative Study. J. Imaging. 2019;5(3):37. doi: 10.3390/jimaging5030037][Kim J., Sangjun O., Kim Y., Lee M. Convolutional Neural Network with Biologically Inspired Retinal Structure. Procedia Computer Science. 2016;88:145—54. doi: 10.1016/j.procs.2016.07.418][Matsugu M., Mori K., Mitari Y., Kaneda Y. Subject independent facial expression recognition with robust face detection using a convolutional neural network. Neural Netw. 2003;16(5-6):555—9. doi: 10.1016/S0893-6080(03)00115-1][Abdelhafiz D., Yang C., Ammar R., Nabavi S. Deep convolutional neural networks for mammography: Advances, challenges and applications. BMC Bioinformatics. 2019;20:281. doi: 10.1186/s12859-019-2823-4][Heath M., Bowyer K., Kopans D., Moore R., Kegelmeyer P. Jr. The digital database for screening mammography. Режим доступа: http://www.eng.usf.edu/cvprg/Mammography/software/HeathEtAlIWDM_2000.pdf (дата обращения 12.02.2021).][Heath M., Bowyer K., Kopans D., Moore R., Kegelmeyer P. Jr., Moore R., Chang K., Munishkumaran S. Digital database for screening mammography: 1998. Режим доступа: http://www.eng.usf.edu/cvprg/Mammography/software/HeathEtAlIWDM_1998.pdf (дата обращения 12.02.2021).][Бермишева М. А., Богданова Н. В., Гилязова И. Р. Этнические особенности формирования генетической предрасположенности к развитию рака молочной железы. Генетика. 2018;(2):233—42 doi: 10.7868/S0016675818020042][Inuzuka M., Watanabe T., Yotsumoto J. Analysis of clinical characteristics in breast cancer patients with the Japanese founder mutation of BRCA1 L63X. J. Clin. Oncol. 2015;33(28_suppl):22. doi: 10.1200/jco.2015.33.28_suppl.22][Loizidou M. A., Hadjisavvas A., Pirpa P. BRCA1 and BRCA2 mutation testing in Cyprus; a population based study. Clin. Genet. 2017;91(4):611—5. doi: 10.1111/cge.12886][Абдураимов А. Б., Михайлова З. Ф., Лесько К. А. Выбор стратегии скрининга рака молочной железы у женщин старших возрастных групп. Клиническая геронтология. 2018;1—2(24):8—15. doi: 10.26347/1607-2499201801-02008-015]