<?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">ojrdrt</journal-id><journal-title-group><journal-title xml:lang="ru">Онкологический журнал: лучевая диагностика, лучевая терапия</journal-title><trans-title-group xml:lang="en"><trans-title>Journal of oncology: diagnostic radiology and radiotherapy</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2587-7593</issn><issn pub-type="epub">2713-167X</issn><publisher><publisher-name>НЕКОММЕРЧЕСКОЕ ПАРТНЕРСТВО «ОБЩЕСТВО ИНТЕРВЕНЦИОННЫХ ОНКОРАДИОЛОГОВ»</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.37174/2587-7593-2026-9-1-43-52</article-id><article-id custom-type="elpub" pub-id-type="custom">ojrdrt-511</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>ЛУЧЕВАЯ ДИАГНОСТИКА</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>DIAGNOSTIC RADIOLOGY</subject></subj-group></article-categories><title-group><article-title>Оценка возможностей моделей машинного обучения и радиомического анализа для дифференциальной диагностики кистозных новообразований поджелудочной железы</article-title><trans-title-group xml:lang="en"><trans-title>Radiomics-Based Machine Learning Model for Differential Diagnosis of Pancreatic Cystic Neoplasms</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-0163-8335</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Карпов</surname><given-names>С. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Karpov</surname><given-names>S. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>123022, Москва, ул. Заморёнова, 27</p></bio><bio xml:lang="en"><p>27 Zamorenova St., Moscow 123022</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7070-3391</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кондратьев</surname><given-names>Е. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Kondratyev</surname><given-names>E. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>115093, Москва, ул. Большая Серпуховская, 27</p></bio><bio xml:lang="en"><p>27 Bolshaya Serpukhovskaya St., Moscow 115093</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-9267-8584</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Усталов</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Ustalov</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>115093, Москва, ул. Большая Серпуховская, 27</p></bio><bio xml:lang="en"><p>27 Bolshaya Serpukhovskaya St., Moscow 115093</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0007-5724-2763</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Шмелева</surname><given-names>С. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Shmeleva</surname><given-names>S. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>115093, Москва, ул. Большая Серпуховская, 27</p></bio><bio xml:lang="en"><p>27 Bolshaya Serpukhovskaya St., Moscow 115093</p></bio><email xlink:type="simple">sofiyaontonovna@gmail.com</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0003-9361-8538</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тарнопольский</surname><given-names>В. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Tarnopolsky</surname><given-names>V. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>115093, Москва, ул. Большая Серпуховская, 27</p></bio><bio xml:lang="en"><p>27 Bolshaya Serpukhovskaya St., Moscow 115093</p></bio><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Городская поликлиника № 220 Департамента здрравоохранения Москвы</institution><country>Россия</country></aff><aff xml:lang="en"><institution>City Polyclinic No. 220</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Национальный медицинский исследовательский центр хирургии им. А.В. Вишневского Минздрава России</institution><country>Россия</country></aff><aff xml:lang="en"><institution>A.V. Vishnevsky National Medical Research Center for Surgery</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>28</day><month>03</month><year>2026</year></pub-date><volume>9</volume><issue>1</issue><fpage>43</fpage><lpage>52</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Карпов С.С., Кондратьев Е.В., Усталов А.А., Шмелева С.А., Тарнопольский В.М., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Карпов С.С., Кондратьев Е.В., Усталов А.А., Шмелева С.А., Тарнопольский В.М.</copyright-holder><copyright-holder xml:lang="en">Karpov S.S., Kondratyev E.V., Ustalov A.A., Shmeleva S.A., Tarnopolsky V.M.</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://www.oncoradjournal.ru/jour/article/view/511">https://www.oncoradjournal.ru/jour/article/view/511</self-uri><abstract><p>Актуальность: Дифференциальная диагностика кистозных образований поджелудочной железы имеет решающее значение для выбора оптимальной тактики лечения и предотвращения прогрессирования заболевания. В связи с этим актуальной задачей современной лучевой диагностики является разработка и внедрение новых методов, которые могут повысить точность диагностики и снизить зависимость от субъективной интерпретации данных. Цель: Исследование возможностей МРТ и радиомического анализа МРТ-изображений в дифференциальной диагностике кистозных новообразований поджелудочной железы, а также разработка радиомических моделей на основе машинного    обучения для определения злокачественного потенциала кистозных образований поджелудочной железы. Материалы и методы: Ретроспективно были проанализированы МРТ-изображения 67 пациентов с верифицированными (по результатам оперативного вмешательства) кистозными новообразованиями поджелудочной железы. Разметку и извлечение радиомических признаков исследований проводил врач-рентгенолог с опытом абдоминальной визуализации и выполнения разметки патологий поджелудочной железы. Образования были разделены для бинарной задачи классификации. Было использовано 7 моделей машинного обучения. Эффективность моделей оценивалась с помощью различных метрик (ROC-AUC, PR-AUC, точность, чувствительность, специфичность, F1). Наилучшая модель была определена по результатам ROC-AUC. Результаты: Наилучшие результаты показали алгоритмы Random Forest с ROC-AUC = 0.83, и LightGBM с ROC-AUC = 0.77. Анализ SHAP выявил ключевые радиомические признаки.    Выводы: Полученные результаты демонстрируют перспективность данного подхода и служат основанием для проведения дальнейших исследований, направленных на повышение точности и обобщаемости моделей.</p></abstract><trans-abstract xml:lang="en"><p>Introduction: Accurate differential diagnosis of pancreatic cystic lesions is crucial for selecting the optimal management strategy and for timely identification of lesions with malignant potential. A key objective of radiology is the development and implementation of quantitative imaging approaches that can improve diagnostic performance and reduce reliance on subjective image interpretation. Purpose: To evaluate the value of magnetic resonance imaging (MRI) and MRI-based radiomic analysis for the differential diagnosis of pancreatic cystic neoplasms, and to develop machine-learning radiomic models for predicting the malignant potential of pancreatic cystic lesions. Materials and methods: In this retrospective study, MRI examinations of 67 patients with surgically and pathologically confirmed pancreatic cystic neoplasms were analyzed. Lesion segmentation and radiomic feature extraction were performed by a radiologist experienced in abdominal imaging. Seven supervised machine-learning models were trained. Model performance was assessed using area under the receiver operating characteristic curve (ROC-AUC), precision–recall AUC (PR-AUC), accuracy, sensitivity, specificity, and F1-score. The best-performing model was selected based on ROC-AUC. Model interpretability was evaluated using SHapley Additive exPlanations (SHAP). Results: The Random Forest classifier showed the best performance (ROC-AUC = 0.83), followed by LightGBM (ROC-AUC = 0.77). SHAP analysis highlighted the radiomic features with the greatest impact on the model outputs. Conclusion: MRI-based radiomics may support risk stratification of pancreatic cystic lesions. Further studies with larger cohorts are needed to confirm these findings and improve model generalizability.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>кистозные новообразования поджелудочной железы</kwd><kwd>дифференциальная диагностика</kwd><kwd>МРТ</kwd><kwd>радиомика</kwd><kwd>машинное обучение</kwd><kwd>радиомический анализ</kwd></kwd-group><kwd-group xml:lang="en"><kwd>pancreatic cystic neoplasms</kwd><kwd>differential diagnosis</kwd><kwd>MRI</kwd><kwd>radiomics</kwd><kwd>machine learning</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Скульский СК, Ратников ВА, Лубашев ЯА, и др. Магнитно-резонансная томография в лучевой диагностике кистозных неоплазий поджелудочной железы на этапах медицинского обследования. Врач. 2022;33(11):40-47.</mixed-citation><mixed-citation xml:lang="en">Skulskiy SK, Ratnikov VA, Lubashev YA, et al. MRI diagnosis pancreas cystics neoplasms at the stages of a medical examination. Vrach. 2022;33(11):40-47. (In Russ.) https://doi.org/10.29296/25877305-2022-11-07</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Ardeshna DR, Cao T, Rodgers B, et al. Recent advances in the diagnostic evaluation of pancreatic cystic lesions. World J Gastroenterol. 2022;28(6):624-34. https://doi.org/10.3748/wjg.v28.i6.624</mixed-citation><mixed-citation xml:lang="en">Ardeshna DR, Cao T, Rodgers B, et al. Recent advances in the diagnostic evaluation of pancreatic cystic lesions. World J Gastroenterol. 2022;28(6):624-34. https://doi.org/10.3748/wjg.v28.i6.624</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Rogowska J, Semeradt J, Durko Ł, Małecka-Wojciesko E. Diagnostics and Management of Pancreatic Cystic Lesions-New Techniques and Guidelines. J Clin Med. 2024 Aug 8;13(16):4644. https://doi.org/10.3390/jcm13164644</mixed-citation><mixed-citation xml:lang="en">Rogowska J, Semeradt J, Durko Ł, Małecka-Wojciesko E. Diagnostics and Management of Pancreatic Cystic Lesions-New Techniques and Guidelines. J Clin Med. 2024 Aug 8;13(16):4644. https://doi.org/10.3390/jcm13164644</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Кондратьев ЕВ, Шмелева СА, Усталов АА и др. Теоретические основы текстурного анализа КТ-изображений образований органов брюшной полости: обзор. Лучевая диагностика и терапия. 2025;16(1):33-46.</mixed-citation><mixed-citation xml:lang="en">Kondratyev EV, Shmeleva SA, Ustalov AA, et al. Theoretical basics of abdominal CT radiomics: a review. Diagnostic Radiology and Radiotherapy. 2025;16(1):33-46. (In Russ.). https://doi.org/10.22328/2079-5343-2025-16-1-33-46</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Ștefan PA, Lupean RA, Lebovici A, et al. Quantitative MRI of Pancreatic Cystic Lesions: A New Diagnostic Approach. Healthcare (Basel). 2022;10(6):1039. https://doi.org/10.3390/healthcare10061039</mixed-citation><mixed-citation xml:lang="en">Ștefan PA, Lupean RA, Lebovici A, et al. Quantitative MRI of Pancreatic Cystic Lesions: A New Diagnostic Approach. Healthcare (Basel). 2022;10(6):1039. https://doi.org/10.3390/healthcare10061039</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Yao L, Zhang Z, Demir U, et al. Radiomics Boosts Deep Learning Model for IPMN Classification. Mach Learn Med Imaging. 2023;14349:134 143. https://doi.org/10.1007/978-3-031-45676-3_14</mixed-citation><mixed-citation xml:lang="en">Yao L, Zhang Z, Demir U, et al. Radiomics Boosts Deep Learning Model for IPMN Classification. Mach Learn Med Imaging. 2023;14349:134 143. https://doi.org/10.1007/978-3-031-45676-3_14</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Zwanenburg A, Vallières M, Abdalah MA, et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020;295(2):328-338. https://doi.org/10.1148/radiol.2020191145</mixed-citation><mixed-citation xml:lang="en">Zwanenburg A, Vallières M, Abdalah MA, et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020;295(2):328-338. https://doi.org/10.1148/radiol.2020191145</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Lambin P, Woodruff HC, Mali SA, et al. Radiomics Quality Score 2.0: towards radiomics readiness levels and clinical translation for personalized medicine. Nat Rev Clin Oncol. 2025;22(11):831-846. https://doi.org/10.1038/s41571-025-01067-1</mixed-citation><mixed-citation xml:lang="en">Lambin P, Woodruff HC, Mali SA, et al. Radiomics Quality Score 2.0: towards radiomics readiness levels and clinical translation for personalized medicine. Nat Rev Clin Oncol. 2025;22(11):831-846. https://doi.org/10.1038/s41571-025-01067-1</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru"></mixed-citation><mixed-citation xml:lang="en"></mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru"></mixed-citation><mixed-citation xml:lang="en"></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>
