<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">uprinmatus</journal-id><journal-title-group><journal-title xml:lang="ru">Известия Юго-Западного государственного университета. Серия: Управление, вычислительная техника, информатика. Медицинское приборостроение</journal-title><trans-title-group xml:lang="en"><trans-title>Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2223-1536</issn><publisher><publisher-name>Юго-Западный государственный университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21869/2223-1536-2026-16-4-122-149</article-id><article-id custom-type="elpub" pub-id-type="custom">uprinmatus-486</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>РАСПОЗНАВАНИЕ И ОБРАБОТКА ИЗОБРАЖЕНИЙ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>IMAGE RECOGNITION AND PROCESSING</subject></subj-group></article-categories><title-group><article-title>Двухконтурная валидация нейросетевой сегментации пневмоторакса в условиях дисбаланса классов</article-title><trans-title-group xml:lang="en"><trans-title>Two-loop validation of neural network-based pneumothorax segmentation under class imbalance</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0008-0426-5045</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Косинов</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Kosinov</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Косинов Александр Владимирович, аспирант кафедры биомедицинской инженерии</p><p>ул. 50 лет Октября, д. 94, г. Курск 305040</p></bio><bio xml:lang="en"><p>Aleksandr V. Kosinov, Postgraduate at the Department of Biomedical Engineering</p><p>50 Let Oktyabrya Str. 94, Kursk 305040</p></bio><email xlink:type="simple">skosinka@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-4951-8607</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Крупчатников</surname><given-names>Р. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Krupchatnikov</surname><given-names>R. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Крупчатников Роман Анатольевич, доктор технических наук, профессор, профессор кафедры биомедицинской инженерии</p><p>Scopus ID: 24471766700</p><p>ул. 50 лет Октября, д. 94, г. Курск 305040</p></bio><bio xml:lang="en"><p>Roman A. Krupchatnikov, Dr. Sci. (Engineering), Professor, Professor at the Department of Biomedical Engineering</p><p>Scopus ID: 24471766700</p><p>50 Let Oktyabrya Str. 94, Kursk 305040</p></bio><email xlink:type="simple">roman0406@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1923-3862</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Серебровский</surname><given-names>В. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Serebrovsky</surname><given-names>V. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Серебровский Вадим Владимирович, доктор технических наук, профессор, профессор кафедры программной инженерии</p><p>Researcher ID: О-8221-2015</p><p>ул. 50 лет Октября, д. 94, г. Курск 305040</p></bio><bio xml:lang="en"><p>Vadim V. Serebrovsky, Dr. of Sci. (Engineering), Professor, Professor of the Department of Software Engineering</p><p>Researcher ID: O-8221-2015</p><p>50 Let Oktyabrya Str. 94, Kursk 305040</p></bio><email xlink:type="simple">SV1111@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-2828-6261</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ефремов</surname><given-names>М. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Efremov</surname><given-names>M. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ефремов Михаил Александрович, кандидат технических наук, доцент кафедры информационной безопасности</p><p>Scopus ID: 58712948800</p><p>ул. 50 лет Октября, д. 94, г. Курск 305040</p></bio><bio xml:lang="en"><p>Mihail A. Efremov, Cand. Sci. (Engineering), Associate Professor at the Department of Information Security</p><p>Scopus ID: 58712948800</p><p>50 Let Oktyabrya Str. 94, Kursk 305040</p></bio><email xlink:type="simple">Efremov-ma@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-3925-4601</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кондрашов</surname><given-names>Д. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Kondrashov</surname><given-names>D. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Кондрашов Дмитрий Сергеевич, кандидат технических наук, преподаватель кафедры биомедицинской инженерии</p><p>Researcher ID: KFT-0791-2024</p><p>ул. 50 лет Октября, д. 94, г. Курск 305040</p></bio><bio xml:lang="en"><p>Dmitry S. Kondrashov, Cand. Sci. (Engineering), Lecturer at the Department of Biomedical Engineering</p><p>Researcher ID: KFT-0791-2024</p><p>50 Let Oktyabrya Str. 94, Kursk 305040</p></bio><email xlink:type="simple">kondrashov012@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Юго-Западный государственный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Southwest State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>07</day><month>08</month><year>2026</year></pub-date><volume>16</volume><issue>2</issue><fpage>122</fpage><lpage>149</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Косинов А.В., Крупчатников Р.А., Серебровский В.В., Ефремов М.А., Кондрашов Д.С., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Косинов А.В., Крупчатников Р.А., Серебровский В.В., Ефремов М.А., Кондрашов Д.С.</copyright-holder><copyright-holder xml:lang="en">Kosinov A.V., Krupchatnikov R.A., Serebrovsky V.V., Efremov M.A., Kondrashov D.S.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://uprinmatus.elpub.ru/jour/article/view/486">https://uprinmatus.elpub.ru/jour/article/view/486</self-uri><abstract><p>Целью исследования является разработка методики клинически ориентированного обучения, валидации и выбора нейросетевой модели сегментации пневмоторакса на рентгенограммах органов грудной клетки при выраженном дисбалансе классов и необходимости контролируемого ограничения ложных срабатываний в составе систем поддержки принятия решений.</p><sec><title>Методы</title><p>Методы. В работе предложена двухконтурная схема оценивания качества сегментации, включающая технический контур, служащий для контроля сходимости обучения по значениям функции потерь и сырым показателям, а также клинический контур для оценки бинаризованных масок после фиксированной постобработки результатов. Для каждой эпохи обучения выполняется перебор порога бинаризации; рабочая точка считается допустимой при выполнении клинических ограничений, после чего итоговая эпоха выбирается как максимизирующая индекс Дайса на положительных случаях среди допустимых решений. Сегментатор реализован на основе архитектуры U-Net++ и обучается по двухэтапной схеме с повышением пространственного разрешения с использованием гибридной функции потерь.</p></sec><sec><title>Результаты</title><p>Результаты. На клинически репрезентативном материале — наборе разработки SIIM-ACR — финальная конфигурация, выбранная по протоколу на 15-й эпохе, обеспечила индекс Дайса на положительных случаях = 0,753 (95% ДИ 0,734-0,771) при частоте ложноположительных срабатываний = 0,177 (95% AN 0,158-0,197) и чувствительности на уровне изображения = 0,948 и ощутимо превзошла базовую конфигурацию.</p></sec><sec><title>Заключение</title><p>Заключение. Предложенная методика двухконтурной валидации и критериального выбора эпохи в допустимой области обеспечивает воспроизводимый контроль компромисса между качеством сеементации на патологических снимках и частотой ложных тревог на снимках без патологии, снижая риск выбора субоптимальной модели при ориентировании только на минимум функции потерь. Полученные результаты подтверждают целесообразность использования разработанного протокола при проектировании сегментационных модулей для систем поддержки принятия решений в задачах лучевой диагностики.</p></sec></abstract><trans-abstract xml:lang="en"><p>The purpose of the research is to develop a clinically oriented methodology for training, validating, and selecting a neural network model for pneumothorax segmentation on chest radiographs under severe class imbalance and the need for controlled limitation of false positive alerts in clinical decision support systems.</p><sec><title>Methods</title><p>Methods. We propose a two-loop segmentation quality assessment framework comprising a technical loop for monitoring training convergence using the loss function values and raw metrics, and a clinical loop for evaluating binarized masks after a fixed post-processing pipeline. For each training epoch, a binarization threshold is swept; an operating point is deemed acceptable if predefined clinical constraints are satisfied. The final epoch is then selected as the one that maximizes Dice index on positive cases among all acceptable solutions. The segmenter is implemented using a UNet++ architecture and trained via a two-stage scheme with increasing spatial resolution, using a hybrid loss function.</p></sec><sec><title>Results</title><p>Results. On clinically representative data SIIM-ACR development set, configuration selected by the protocol achieved Dice index on positive cases = 0,753 (95% CI 0,734–0,771) with false positive rate = 0,177 (95% CI 0,158– 0,197) and image-level sensitivity = 0,948, and substantially outperformed the baseline configuration.</p></sec><sec><title>Conclusion</title><p>Conclusion. The proposed two-loop validation methodology and constraint-based epoch selection within the admissible region provide reproducible control of the trade-off between segmentation quality on pathological images and the false alarm rate on non-pathological images, reducing the risk of selecting a suboptimal model when relying solely on minimum loss. The results support the use of the developed protocol in designing segmentation modules for decision support systems in radiological imaging tasks.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>сегментация медицинских изображений</kwd><kwd>пневмоторакс</kwd><kwd>рентгенография органов грудной клетки</kwd><kwd>клинический контур</kwd><kwd>валидация</kwd><kwd>системы поддержки принятия решений</kwd></kwd-group><kwd-group xml:lang="en"><kwd>medical image segmentation</kwd><kwd>pneumothorax</kwd><kwd>chest x-ray</kwd><kwd>clinical circuit</kwd><kwd>validation</kwd><kwd>decision support systems</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Работа выполнена в рамках реализации программы развития ФГБОУ ВО «Юго- Западный государственный университет» проекта «Приоритет-2030».</funding-statement><funding-statement xml:lang="en">The work was carried out within the framework of the Priority-2030 project development program of the Federal State Budgetary Educational Institution of Higher Education "Southwest State University."</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Lung imaging methods: indications, strengths and limitations / D. L. Tárnoki, K. Karlinger, C. A. Ridge, F. J. Kiss, T. Györke, E. M. Grabczak, Á. D. Tárnoki // Breathe (Sheff). 2024. Vol. 20, N 3. P. 230127. https://doi.org/10.1183/20734735.0127-2023.</mixed-citation><mixed-citation xml:lang="en">Tárnoki D.L., Karlinger K., Ridge C.A., Kiss F.J., Györke T., Grabczak E.M., Tárnoki Á.D. Lung imaging methods: indications, strengths and limitations. Breathe  (Sheff). 2024;20(3):230127. https://doi.org/10.1183/20734735.0127-2023.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Multidisciplinary Evaluation of an AI-Based Pneumothorax Detection Model: Clinical Comparison with Physicians in Edge and Cloud Environments / I. Dal, H. B. Kaya // J. Multidiscip. Healthc. 2025. Vol. 18. P. 4099–4111. https://doi.org/10.2147/JMDH.S535405.</mixed-citation><mixed-citation xml:lang="en">Dal I., Kaya H.B. Multidisciplinary Evaluation of an AI-Based Pneumothorax Detection Model: Clinical Comparison with Physicians in Edge and Cloud Environments. J. Multidiscip. Healthc. 2025;18:4099-4111. https://doi.org/10.2147/JMDH.S535405.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Clinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies / A. De Biase, N. M. Sijtsema, T. Janssen, C. Hurkmans, C. Brouwer, P. van Ooijen // BJR Artificial Intelligence. 2024. Vol. 1, N 1. P. ubae015. https://doi.org/10.1093/bjrai/ubae015.</mixed-citation><mixed-citation xml:lang="en">De Biase A., Sijtsema N.M., Janssen T., Hurkmans C., Brouwer C., van Ooijen P. Clinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies. BJR  Artificial  Intelligence. 2024;1(1):ubae015. https://doi.org/10.1093/bjrai/ubae015.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Metrics reloaded: recommendations for image analysis validation / L. Maier-Hein, A. Reinke, P. Godau [et al.] // Nat. Methods. 2024. Vol. 21, N 2. P. 195–212. https://doi.org/10.1038/s41592-023-02151-z.</mixed-citation><mixed-citation xml:lang="en">Maier-Hein L., Reinke A., Godau P., et al. Metrics reloaded: recommendations for image analysis validation. Nat.  Methods. 2024;21(2):195-212. https://doi.org/10.1038/s41592-023-02151-z.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Understanding metric-related pitfalls in image analysis validation / A. Reinke, M. D. Tizabi, M. Baumgartner [et al.] // Nat. Methods. 2024. Vol. 21, N 2. P. 182–194. https://doi.org/10.1038/s41592-023-02150-0.</mixed-citation><mixed-citation xml:lang="en">Reinke A., Tizabi M.D., Baumgartner M., et al. Understanding metric-related pitfalls in image analysis validation. Nat.  Methods. 2024;21(2):182-194. https://doi.org/10.1038/s41592-023-02150-0.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Mohammadi M., Mollazade K., Behroozi-Khazaei N. Under- and over-segmentation: new metrics for image segmentation accuracy measurement // Array. 2025. Vol. 28. P. 100624. https://doi.org/10.1016/j.array.2025.100624.</mixed-citation><mixed-citation xml:lang="en">Mohammadi M., Mollazade K., Behroozi-Khazaei N. Under- and over-segmentation: new metrics for image segmentation accuracy measurement. Array. 2025;28:100624. https://doi.org/10.1016/j.array.2025.100624.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Association Between False-Positive Results and Return to Screening Mammography in the Breast Cancer Surveillance Consortium Cohort / D. L. Miglioretti, L. Abraham, B. L. Sprague [et al.] // Ann. Intern. Med. 2024. Vol. 177, N 10. P. 1297–1307. https://doi.org/10.7326/M24-0123.</mixed-citation><mixed-citation xml:lang="en">Miglioretti D.L., Abraham L., Sprague B.L., et al. Association Between False-Positive Results and Return to Screening Mammography in the Breast Cancer Surveillance Consortium Cohort. Ann. Intern. Med. 2024;177(10):1297-1307. https://doi.org/10.7326/M24-0123.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Conquering class imbalances in deep learning-based segmentation of dental radiographs with different loss functions / M. Büttner, L. Schneider, A. Krasowski [et al.] // J. Dent. 2024. Vol. 148. P. 105063. https://doi.org/10.1016/j.jdent.2024.105063.</mixed-citation><mixed-citation xml:lang="en">Büttner M., Schneider L., Krasowski A., et al. Conquering class imbalances in deep learning-based segmentation of dental radiographs with different loss functions. J.  Dent. 2024;148:105063. https://doi.org/10.1016/j.jdent.2024.105063.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Cabezas M., Diez Y. An Analysis of Loss Functions for Heavily Imbalanced Lesion Segmentation // Sensors. 2024. Vol. 24, N 6. P. 1981. https://doi.org/10.3390/s24061981.</mixed-citation><mixed-citation xml:lang="en">Cabezas M., Diez Y. An Analysis of Loss Functions for Heavily Imbalanced Lesion Segmentation. Sensors. 2024;24(6):1981. https://doi.org/10.3390/s24061981.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Reinke A., Tizabi M. D., Maier-Hein L. Advancing standards in biomedical image analysis validation: A perspective on Metrics Reloaded // Clin. Transl. Med. 2025. Vol. 15, N 9. P. e70237. https://doi.org/10.1002/ctm2.70237.</mixed-citation><mixed-citation xml:lang="en">Reinke A., Tizabi M. D., Maier-Hein L. Advancing standards in biomedical image analysis validation: A perspective on Metrics Reloaded. Clin. Transl. Med. 2025;15(9):e70237. https://doi.org/10.1002/ctm2.70237.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Малютина И. А., Кузьмин А. А., Шаталова О. В. Методы и алгоритмы анализа рентгенограмм грудной клетки, использующие локальные окна в задачах обнаружения патологий // Прикаспийский журнал: управление и высокие технологии. 2017. № 3 (39). С. 131-138.</mixed-citation><mixed-citation xml:lang="en">Malyutina I.A., Kuz’min A.A., Shatalova O.V. Methods and algorithms for analyzing chest radiographs using local windows in pathology detection tasks. Prikaspiiskii zhurnal: upravlenie  i vysokie tekhnologii = Caspian Journal: Management and High Technologies. 2017;(3):131-138. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Моделирование морфологических образований на рентгенограммах грудной клетки в интеллектуальных диагностических системах медицинского назначения / П. С. Кудрявцев, А. А. Кузьмин, Д. Ю. Савинов, С. А. Филист, О. В. Шаталова // Прикаспийский журнал: управление и высокие технологии. 2017. № 3 (39). С. 109-120.</mixed-citation><mixed-citation xml:lang="en">Kudryavtsev P.S., Kuz’min A.A., Savinov D.Yu., Filist S.A., Shatalova O.V. Modeling of morphological formations on chest radiographs in intelligent medical diagnostic systems. Prikaspiiskii  zhurnal: upravlenie  i  vysokie  tekhnologii  = Caspian Journal: Management and High Technologies. 2017;(3):109-120. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Математические модели для интеллектуальных систем классификации рентгенограмм грудной клетки / М. В. Дюдин, П. С. Кудрявцев, K. В. Подмастерьев, С. А. Филист, О. В. Шаталова // Известия Юго-Западного государственного университета. Серия: Управление, вычислительная техника, информатика. Медицинское приборостроение. 2016. № 2 (19). С. 94-107.</mixed-citation><mixed-citation xml:lang="en">Dyudin M.V., Kudryavtsev P.S., Podmaster’ev K.V., Filist S.A., Shatalova O.V. Mathematical models for intelligent systems of chest radiograph classification. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Serija: Upravlenie, vychislitel'naja tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineer- ing. 2016;2(19):94-107. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Анализ биомедицинских изображений различными методами сегментации, основанными на операторах вычисления градиента / С. А. Филист, Е. А. Шашкова, О. В. Шаталова, Р. А. Томакова // Перспективы развития информационных технологий. 2011. № 3-1. С. 146-150.</mixed-citation><mixed-citation xml:lang="en">Filist S.A., Shashkova E.A., Shatalova O.V., Tomakova R.A. Analysis of biomedical images by various segmentation methods based on gradient operators. Perspektivy razvitiya informatsionnykh tekhnologii = Prospects  for  the Development of  Information Technology. 2011;(3-1):146-150. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">An Automated System for Classification of Radiographs of the Breast / A. R. Dabagov, V. A. Gorbunov, S. A. Filist [et al.] // Biomedical Engineering. 2020. Vol. 53, N 6. P. 425–428. https://doi.org/10.1007/s10527-020-09957-7.</mixed-citation><mixed-citation xml:lang="en">Dabagov A.R., Gorbunov V.A., Filist S.A., et al. An Automated System for Classification of Radiographs of the Breast. Biomedical  Engineering. 2020;53(6):425-428. https://doi.org/10.1007/s10527-020-09957-7.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Hybrid neural networks with virtual flows in medical risk classifiers / K. Khatatneh, S. Filist, O. Shatalova [et al.] // Journal of Intelligent and Fuzzy Systems. 2022. Vol. 43, N 1. P. 1621–1632. https://doi.org/10.3233/JIFS-212617.</mixed-citation><mixed-citation xml:lang="en">Khatatneh K., Filist S., Shatalova O., et al. Hybrid neural networks with virtual flows in medical risk classifiers. Journal of Intelligent and Fuzzy Systems. 2022;43(1):1621– 1632. https://doi.org/10.3233/JIFS-212617.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Коровин Е. H., Шаталова О. B., Жилин В. В. Применение гибридной нейронной сети с макрослоями для классификации сердечно-сосудистых заболеваний // Биомедицинская радиоэлектроника. 2014. № 9. С. 32-37.</mixed-citation><mixed-citation xml:lang="en">Korovin E.N., Shatalova O.V., Zhilin V.V. Application of a hybrid neural network with macrolayers for the classification of cardiovascular diseases. Biomeditsinskaya radioelektronika = Biomedical Radioelectronics. 2014;(9):32-37. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Biotechnical neural network system for predicting cardiovascular health state using processing оf bio-signals / S. Filist, В. Т. Al-Kasasbeh, О. V. Shatalova [et al.] // International Journal оf Medical Engineering and Informatics. 2024. Vol. 16, N 4. P. 324-349. https://doi.org/10.1504/ITME1.2024.139884.</mixed-citation><mixed-citation xml:lang="en">Filist S., Al-Kasasbeh R.T., Shatalova O.V., et al. Biotechnical neural network system for predicting cardiovascular health state using processing of bio-signals. International Journal  of  Medical  Engineering  and  Informatics. 2024;16(4):324-349. https://doi.org/10.1504/IJMEI.2024.139884.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Сверточная нейронная сеть для моделей классификаторов медицинского риска с синергетическими каналами / Р. А. Крупчатников, Д. А. Медников, 3. У. Протасова [и др.] // Известия Юго-Западного государственного университета. Серия: Управление, вычислительная техника, информатика. Медицинское приборостроение. 2021. Т. 11, Ne 2. С. 25—50.</mixed-citation><mixed-citation xml:lang="en">Krupchatnikov R.A., Mednikov D.A., Protasova Z.U., et al. Convolutional neural network for medical risk classifier models with synergetic channels. Izvestiya  Yugo- Zapadnogo gosudarstvennogo universiteta. Serija: Upravlenie, vychislitel'naja tekhnika, informatika. Meditsinskoe  priborostroenie  = Proceedings  of  the  Southwest  State  University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2021;11(2):25–50. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Multimodal neural network classifier оf the functional state of the respiratory system / S. А. Filist, М. В. Myasnyankin, R. 1. Safronov, А. A Kuzmin // Journal оf Physics: Conference Series. 2021. Vol. 2094. P. 032064. https://doi.org/10.1088/1742-6596/2094/3/032064.</mixed-citation><mixed-citation xml:lang="en">Filist S.A., Myasnyankin M.B., Safronov R.I., Kuzmin A.A. Multimodal neural network classifier of the functional state of the respiratory system. Journal of Physics: Confer- ence Series. 2021;2094:032064. https://doi.org/10.1088/1742-6596/2094/3/032064.</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">A multitask approach for automated detection and segmentation of thyroid nodules in ultrasound images / А. Radhachandran, А. Kinzel, J. Chen, V. Sant, M. Patel, R. Masamed, C. W. Amold, W. Speier / Comput. Biol. Med. 2024. Vol. 170. P. 107974. https://doi.org/10.1016/j.compbiomed.2024.107974.</mixed-citation><mixed-citation xml:lang="en">Radhachandran A., Kinzel A., Chen J., Sant V., Patel M., Masamed R., Arnold C.W., Speier W. A multitask approach for automated detection and segmentation of thyroid nodules in ultrasound images. Comput.  Biol.  Med. 2024;170:107974. https://doi.org/10.1016/j.compbiomed.2024.107974.</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">UNet++: A Nested U-Net Architecture for Medical Image Segmentation / Z. Zhou, M. M. R. Siddiquee, М. Tajbakhsh, J. Liang // Deep Learn Med Image Anal Multimodal Learn Clin Decis Support. 2018. Vol. 11045. P. 3-11. https://doi.org/10.1007/978-3-030- 00889-5_1.</mixed-citation><mixed-citation xml:lang="en">Zhou Z., Siddiquee M.M.R., Tajbakhsh N., Liang J. UNet++: A Nested U-Net Architecture for Medical Image Segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support. 2018;11045:3–11. https://doi.org/10.1007/978-3-030-00889-5_1.</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Deeply-Supervised Nets / C. Y. Lee, S. Xie, P. Gallagher, Z. Zhang, Z. Tu // arXiv. URL: https://arxiv.org/abs/1409.5185 (дата обращения: 16.03.2026).</mixed-citation><mixed-citation xml:lang="en">Lee C.Y., Xie S., Gallagher P., Zhang Z., Tu Z. Deeply-Supervised Nets. Available at: https://arxiv.org/abs/1409.5185 (accessed 16.03.2026).</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Effect of image resolution on automated classification of chest X-rays / M. I. U. Haque, A. K. Dubey, I. Danciu, A. C. Justice, O. S. Ovchinnikova, J. D. Hinkle // J. Med. Imaging (Bellingham). 2023. Vol. 10, N 4. $. 044503. https://doi.org/10.1117/1.JMI.10.4.044503.</mixed-citation><mixed-citation xml:lang="en">Haque M.I.U., Dubey A.K., Danciu I., Justice A.C., Ovchinnikova O.S., Hinkle J.D. Effect of image resolution on automated classification of chest X-rays. J. Med. Imaging (Bel- lingham). 2023;10(4):044503. https://doi.org/10.1117/1.JMI.10.4.044503.</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">CACSNet for automatic robust classification and segmentation of carotid artery calcification on panoramic radiographs using a cascaded deep learning network / S. W. Yoo, S. Yang, J. E. Kim [et al.] // Sci. Rep. 2024. Vol. 14. P. 13894. https://doi.org/10.1038/s41598- 024-64265-4.</mixed-citation><mixed-citation xml:lang="en">Yoo S.W., Yang S., Kim J.E., et al. CACSNet for automatic robust classification and segmentation of carotid artery calcification on panoramic radiographs using a cascaded deep learning network. Sci. Rep. 2024;14:13894. https://doi.org/10.1038/s41598-024-64265-4.</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">How threshold customisation affects the performance of a multiclass X-ray AI model for primary care triage: a retrospective study / J. Z. T. Sim, J. Lin, Q. W. Fong, A. Y. Q. Soon, L. W. Khin, S. Balakrishnan, T. Lin, S. Wong, C. H. Tan // BMJ Open. 2026. Vol. 16, N 2. P. e111127. https://doi.org/10.1136/bmjopen-2025-111127.</mixed-citation><mixed-citation xml:lang="en">Sim J.Z.T., Lin J., Fong Q.W., Soon A.Y.Q., Khin L.W., Balakrishnan S., Lin T., Wong S., Tan C.H. How threshold customisation affects the performance of a multiclass X-ray AI model for primary care triage: a retrospective study. BMJ  Open. 2026;16(2):e111127. https://doi.org/10.1136/bmjopen-2025-111127.</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">Tabassum M., Di Ieva A., Liu S. Meta transfer learning for brain tumor segmentation using nnUNet in meningioma and metastasis cases // Sci. Rep. 2025. Vol. 15. P. 37599. https://doi.org/10.1038/s41598-025-20957-z.</mixed-citation><mixed-citation xml:lang="en">Tabassum M., Di Ieva A., Liu S. Meta transfer learning for brain tumor segmentation using nnUNet in meningioma and metastasis cases. Sci.  Rep. 2025;15:37599. https://doi.org/10.1038/s41598-025-20957-z.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
