<?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">medvis</journal-id><journal-title-group><journal-title xml:lang="ru">Медицинская визуализация</journal-title><trans-title-group xml:lang="en"><trans-title>Medical Visualization</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1607-0763</issn><issn pub-type="epub">2408-9516</issn><publisher><publisher-name>RDS-Media Ltd.</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.24835/1607-0763-1655</article-id><article-id custom-type="elpub" pub-id-type="custom">medvis-1655</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>Радиомика и технологии искусственного интеллекта</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Radiomics and artificial intelligence technologies</subject></subj-group></article-categories><title-group><article-title>Дифференциальная диагностика липом и атипичных липоматозных опухолей (ALT) конечностей: мультицентровое исследование с использованием моделей машинного обучения на основе радиомических и семиотических признаков бесконтрастной МРТ</article-title><trans-title-group xml:lang="en"><trans-title>Differential diagnosis of lipomas and atypical lipomatous tumors (ALT) of the extremities: a multicenter study using machine learning models based on radiomic and semiotic features of non-contrast MRI</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0004-8226-2449</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Уразов</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Urazov</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Уразов Александр Викторович – ассистент кафедры онкологии и рентгенорадиологии им. В.П. Харченко МИ ФГАОУ ВО “Российский университет дружбы народов имени Патриса Лумумбы” Минобрнауки России, Москваhttps://orcid.org/0009-0004-8226-2449</p></bio><bio xml:lang="en"><p>Aleksandr V. Urazov – Assistant Professor, Department of Oncology and Roentgenology named after V.P. Kharchenko, Peoples' Friendship University of Russia named after Patrice Lumumba (RUDN University), Moscow<ext-link xlink:href="https://orcid.org/0009-0004-8226-2449" ext-link-type="uri">https://orcid.org/0009-0004-8226-2449</ext-link></p></bio><email xlink:type="simple">urazoff1432@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/0000-0003-2552-5754</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Аксенова</surname><given-names>С. П.</given-names></name><name name-style="western" xml:lang="en"><surname>Aksenova</surname><given-names>S. P.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Аксенова Светлана Павловна – канд. мед. наук, научный сотрудник лаборатории рентгенорадиологии научно-исследовательского отдела комплексной диагностики заболеваний и радиотерапии ФГБУ “Российский научный центр рентгенорадиологии” Минздрава России; ассистент кафедры онкологии и рентгенорадиологии им. В.П. Харченко ФГАОУ ВО “Российский университет дружбы народов имени Патриса Лумумбы” Минобрнауки России, Москва<ext-link xlink:href="https://orcid.org/0000-0003-2552-5754" ext-link-type="uri">https://orcid.org/0000-0003-2552-5754</ext-link></p></bio><bio xml:lang="en"><p>Svetlana P. Aksenova – Cand. of Sci. (Med.), research fellow, Russian Scientific Center of Roentgenoradiology of the Ministry of Healthcare of the Russian Federation; Assistant Professor, Department of Oncology and Roentgenology named after V.P. Kharchenko, Peoples' Friendship University of Russia named after Patrice Lumumba (RUDN University), Moscow<ext-link xlink:href="https://orcid.org/0000-0003-2552-5754" ext-link-type="uri">https://orcid.org/0000-0003-2552-5754</ext-link>E-mail: fabella@mail.ru</p></bio><email xlink:type="simple">fabella@mail.ru</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-5994-0468</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Нуднов</surname><given-names>Н. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Nudnov</surname><given-names>N. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Нуднов Николай Васильевич – доктор мед. наук, профессор, заместитель директора по научной работе, заведующий научно-исследовательским отделом комплексной диагностики заболеваний и радиотерапии ФГБУ “Российский научный центр рентгенорадиологии” Минздрава России;профессор кафедры рентгенологии и радиологии ФГБОУ ДПО “Российская медицинская академия непрерывного профессионального образования” Минздрава России;профессор кафедры онкологии и рентгенорадиологии им. В.П. Харченко ФГАОУ ВО “Российский университет дружбы народов имени Патриса Лумумбы” Минобрнауки России, Москва<ext-link xlink:href="https://orcid.org/0000-0001-5994-0468." ext-link-type="uri">https://orcid.org/0000-0001-5994-0468</ext-link>E-mail: mailbox@rncrr.rssi.ru</p></bio><bio xml:lang="en"><p>Nikolay V. Nudnov – Doct. of Sci. (Med.),  Professor, Deputy Director for Scientific Work, Head of the Research Department for Complex Diagnostics of Diseases and Radiotherapy, Russian Scientific Center of Roentgenoradiology of the Ministry of Healthcare of the Russian Federation;</p><p>Professor, Department of Roentgenoradiology and Radiology, Russian Medical Academy of Continuous Professional Education of the Ministry of Healthcare of the Russian Federation;Professor, Department of Oncology and Radiology, Peoples' Friendship University of Russia named after Patrice Lumumba of the Ministry of Science and Higher Education of the Russian Federation, Moscow<ext-link xlink:href="https://orcid.org/0000-0001-5994-0468." ext-link-type="uri">https://orcid.org/0000-0001-5994-0468</ext-link>E-mail: mailbox@rncrr.rssi.ru</p></bio><email xlink:type="simple">mailbox@rncrr.rssi.ru</email><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-5352-492X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Харченко</surname><given-names>Н. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Kharchenko</surname><given-names>N. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Харченко Наталья Владимировна – доктор мед. наук, профессор, профессор кафедры онкологии и рентгенорадиологии им. В.П. Харченко ФГАОУ ВО “Российский университет дружбы народов имени Патриса Лумумбы” Минобрнауки России, Москва<ext-link xlink:href="https://orcid.org/0000-0002-5352-492X" ext-link-type="uri">https://orcid.org/0000-0002-5352-492X</ext-link></p></bio><bio xml:lang="en"><p>Natalia V. Kharchenko – Doct. of Sci. (Med.),  Professor, professor of the Department of Oncology and Roentgenology named after V.P. Kharchenko, Peoples' Friendship University of Russia named after Patrice Lumumba (RUDN University), Moscow<ext-link xlink:href="https://orcid.org/0000-0002-5352-492X" ext-link-type="uri">https://orcid.org/0000-0002-5352-492X</ext-link></p></bio><email xlink:type="simple">kharchenko-nv@rudn.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/0000-0003-4147-1928</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сергеев</surname><given-names>Н. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Sergeev</surname><given-names>N. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сергеев Николай Иванович – доктор мед. наук, заведующий лабораторией  рентгенорадиологии научно-исследовательского отдела комплексной диагностики заболеваний и радиотерапии ФГБУ “Российский научный центр рентгенорадиологии” Минздрава России, Москва<ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">https</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">://</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">orcid</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">.</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">org</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">/0000-0003-4147-1928</ext-link></p></bio><bio xml:lang="en"><p>Nikolay I. Sergeev – Doct. of Sci. (Med.), Head of the Laboratory of X-ray Radiology of the Research Department of Complex Diagnostics of Diseases and Radiotherapy of the Russian Scientific Center of Roentgenoradiology of the Ministry of Healthcare of the Russian Federation, Moscow<ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">https</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">://</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">orcid</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">.</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">org</ext-link><ext-link xlink:href="https://orcid.org/0000-0003-4147-1928" ext-link-type="uri">/0000-0003-4147-1928</ext-link></p></bio><email xlink:type="simple">sergeev_n@rncrr.ru</email><xref ref-type="aff" rid="aff-4"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ФГАОУ ВО “Российский университет дружбы народов имени Патриса Лумумбы” Минобрнауки России</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Peoples' Friendship University of Russia named after Patrice Lumumba (RUDN University)</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>ФГАОУ ВО “Российский университет дружбы народов имени Патриса Лумумбы” Минобрнауки России; &#13;
ФГБУ “Российский научный центр рентгенорадиологии” Минздрава России</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Peoples' Friendship University of Russia named after Patrice Lumumba (RUDN University); &#13;
Russian Scientific Center of Roentgenoradiology of the Ministry of Healthcare of the Russian Federation</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>ФГАОУ ВО “Российский университет дружбы народов имени Патриса Лумумбы” Минобрнауки России; &#13;
ФГБУ “Российский научный центр рентгенорадиологии” Минздрава России;&#13;
ФГБОУ ДПО “Российская медицинская академия непрерывного профессионального образования” Минздрава России</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Peoples' Friendship University of Russia named after Patrice Lumumba (RUDN University); &#13;
Russian Scientific Center of Roentgenoradiology of the Ministry of Healthcare of the Russian Federation;&#13;
Russian Medical Academy of Continuous Professional Education of the Ministry of Healthcare of the Russian Federation</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-4"><aff xml:lang="ru"><institution>ФГБУ “Российский научный центр рентгенорадиологии” Минздрава России</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Russian Scientific Center of Roentgenoradiology of the Ministry of Healthcare of the Russian Federation</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>01</day><month>10</month><year>2026</year></pub-date><volume>30</volume><issue>3</issue><fpage>124</fpage><lpage>135</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Уразов А.В., Аксенова С.П., Нуднов Н.В., Харченко Н.В., Сергеев Н.И., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Уразов А.В., Аксенова С.П., Нуднов Н.В., Харченко Н.В., Сергеев Н.И.</copyright-holder><copyright-holder xml:lang="en">Urazov A.V., Aksenova S.P., Nudnov N.V., Kharchenko N.V., Sergeev N.I.</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://medvis.rdsmedia.ru/jour/article/view/1655">https://medvis.rdsmedia.ru/jour/article/view/1655</self-uri><abstract><p>Дооперационная диагностика липом и атипичных липоматозных опухолей (ALT) конечностей остается актуальной клинической проблемой. При стандартной МРТ-оценке эти новообразования имеют сходные визуальные характеристики, что затрудняет постановку точного диагноза и может приводить к неправильной тактике лечения. В отличие от доброкачественных липом, ALT обладают потенциалом локального рецидивирования и требуют более радикального иссечения.</p><p>Современные подходы, основанные на радиомике и машинном обучении, позволяют извлекать из стандартных МР-последовательностей количественные признаки, отражающие микроструктурные особенности тканей, что открывает возможности для неинвазивной верификации диагноза.</p><sec><title>Цель исследования</title><p>Цель исследования: создать и провести сравнительный анализ диагностической эффективности моделей машинного обучения (LASSO и Random Forest), построенных на основе клинико-семиотических и радиомических признаков бесконтрастной МРТ (Т1- и Т2-ВИ), для дифференциальной диагностики липом и атипичных липоматозных опухолей (ALT) конечностей.</p></sec><sec><title>Материал и методы</title><p>Материал и методы. Исследование является мультицентровым и ретроспективным. Включены данные 61 пациента с гистологически верифицированными липомами и атипичными липоматозными опухолями (ALT) конечностей. Проведена сегментация образований на бесконтрастных Т1- и Т2-ВИ с извлечением радиомических признаков (n = 221) и оценкой клинико-семиотических параметров. Набор данных разделен на обучающую (80%) и тестовую (20%) выборки. Построены прогностические модели с использованием LASSO-логистической регрессии (кросс-валидация по 10 фолдам) и случайного леса (Random Forest, подбор гиперпараметров сеточным поиском). Эффективность моделей оценена по Accuracy, ROC-AUC, чувствительности, специфичности, Precision и F1-мере. Сравнение выполнено с применением теста Макнемара, теста Делонга и бутстрап-анализа (1000 итераций). Статистически значимыми считали различия при p &lt; 0,05.</p></sec><sec><title>Результаты</title><p>Результаты. На тестовой выборке LASSO-логистическая регрессия достигла ROC-AUC 0,889 (95% ДИ 0,694–1,000) и точности 0,692 (95% ДИ 0,434–0,950); чувствительность составила 0,250, специфичность – 0,889, F1-мера (F1-Score) – 0,333. Случайный лес показал ROC-AUC 0,833 (95% ДИ 0,533–1,000) при точности 0,692 (95% ДИ 0,440–0,944); чувствительность и F1-мера (F1-Score) составили 0,000 при специфичности 1,000.</p><p>При сравнении моделей с помощью теста Макнемара статистически значимых различий не выявлено (p = 1,000). Согласно тесту Делонга, различия в значениях ROC-AUC также не достигли статистической значимости (p = 0,771). Бутстрап-анализ (1000 итераций) подтвердил стабильность показателей: для LASSO средняя ROC-AUC составила 0,892 ± 0,101, точность – 0,691 ± 0,131, для случайного леса – 0,832 ± 0,153 и 0,685 ± 0,125 соответственно.</p><p>LASSO-регрессия отобрала 12 наиболее значимых признаков, включающих семиотические характеристики (“гиперинтенсивный сигнал с FS”, “расположение относительно компартментов”, “форма”, “количество перегородок”, “наличие солидной ткани”, “толщина перегородок”) и радиомические параметры (Coarseness, Maximum2DDiameterColumn, VoxelVolume, ShortRunLowGrayLevelEmphasis.1, MeshVolume, Maximum2DDiameterColumn.1).</p></sec><sec><title>Заключение</title><p>Заключение. В данном исследовании LASSO-логистическая регрессия и случайный лес, построенные на основе клинико-семиотических и радиомических признаков бесконтрастной МРТ (Т1-ВИ и Т2-ВИ), продемонстрировали сопоставимую эффективность в дифференциальной диагностике липом и атипичных липоматозных опухолей конечностей (ROC-AUC 0,889 и 0,833 соответственно; p &gt; 0,05).</p><p>Разработанные прогностические модели в перспективе могут служить инструментом поддержки принятия клинических решений, способствуя повышению точности дооперационной диагностики и стандартизации оценки липоматозных образований мягких тканей. Для подтверждения полученных результатов требуется дальнейшее тестирование на расширенных выборках с проведением внешней валидации.</p></sec></abstract><trans-abstract xml:lang="en"><p>Preoperative differentiation of lipomas from atypical lipomatous tumors (ALT) of the extremities remains a relevant clinical challenge. On standard MRI assessment, these neoplasms demonstrate overlapping imaging characteristics, which complicates accurate diagnosis and may lead to suboptimal treatment strategies. Unlike benign lipomas, ALTs carry a potential for local recurrence and require wider surgical excision.</p><p>Contemporary approaches based on radiomics and machine learning enable the extraction of quantitative features from standard MRI sequences that reflect the microstructural properties of tissues, thereby offering opportunities for non-invasive diagnostic verification.</p><sec><title>Objective</title><p>Objective. To develop and comparatively evaluate the diagnostic performance of machine learning models (LASSO logistic regression and Random Forest) built upon clinical-semiotic and radiomic features derived from non-contrast MRI (T1-WI and T2-WI) for the differential diagnosis of lipomas and atypical lipomatous tumors (ALT) of the extremities.</p></sec><sec><title>Materials and Methods</title><p>Materials and Methods. This multicenter, retrospective study included data from 61 patients with histologically verified lipomas and atypical lipomatous tumors (ALT) of the extremities. Tumor segmentation was performed on non-contrast T1-WI and T2-WI sequences, followed by extraction of radiomic features (n = 221) and assessment of clinical-semiotic parameters. The dataset was split into training (80%) and test (20%) subsets. Predictive models were constructed using LASSO logistic regression (10-fold cross-validation) and Random Forest (hyperparameter tuning via grid search). Model performance was evaluated by Accuracy, ROC-AUC, sensitivity, specificity, Precision, and F1-score. Comparison was performed using McNemar's test, DeLong's test, and bootstrap analysis (1,000 iterations). Differences were considered statistically significant at p &lt; 0.05.</p></sec><sec><title>Results</title><p>Results. On the test subset, LASSO logistic regression achieved an ROC-AUC of 0.889 (95% CI 0.694-1.000) and an accuracy of 0.692 (95% CI 0.434-0.950); sensitivity was 0.250, specificity 0.889, and F1-score 0.333. The Random Forest model yielded an ROC-AUC of 0.833 (95% CI 0.533-1.000) with an accuracy of 0.692 (95% CI 0.440-0.944); sensitivity and F1-score were 0.000 at a specificity of 1.000.</p><p>McNemar's test revealed no statistically significant difference between the models (p = 1.000). DeLong's test likewise showed no significant difference in ROC-AUC values (p = 0.771). Bootstrap analysis (1,000 iterations) confirmed the stability of the metrics: for LASSO, the mean ROC-AUC was 0.892 ± 0.101 and accuracy 0.691 ± 0.131; for Random Forest, 0.832 ± 0.153 and 0.685 ± 0.125, respectively.</p><p>LASSO regression selected 12 features of highest importance, comprising semiotic characteristics (“Hyperintense signal on FS”, “intra-/extra compartmental location”, “Shape”, “Number of septa”, “Presence of solid tissue”, “Septal thickness”) and radiomic parameters (Coarseness, Maximum2DDiameterColumn, VoxelVolume, ShortRunLowGrayLevelEmphasis.1, MeshVolume, Maximum2DDiameterColumn.1).</p></sec><sec><title>Conclusion</title><p>Conclusion. In this study, LASSO logistic regression and Random Forest models constructed from clinical-semiotic and radiomic features of non-contrast MRI (T1-WI and T2-WI) demonstrated comparable diagnostic performance in the differential diagnosis of lipomas and atypical lipomatous tumors of the extremities (ROC-AUC 0.889 and 0.833, respectively; p &gt; 0.05).</p><p>The developed predictive models may prospectively serve as clinical decision-support tools, contributing to improved preoperative diagnostic accuracy and standardization of soft tissue lipomatous lesion assessment. Further validation on larger cohorts with external validation is required to confirm these findings.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>дифференциальная диагностика</kwd><kwd>липома</kwd><kwd>атипичная липоматозная опухоль (ALT)</kwd><kwd>магнитно-резонансная томография (МРТ)</kwd><kwd>радиомика</kwd><kwd>машинное обучение</kwd><kwd>LASSO</kwd><kwd>случайный лес</kwd><kwd>мультицентровое исследование</kwd></kwd-group><kwd-group xml:lang="en"><kwd>differential diagnosis</kwd><kwd>lipoma</kwd><kwd>atypical lipomatous tumor (ALT)</kwd><kwd>magnetic resonance imaging (MRI)</kwd><kwd>radiomics</kwd><kwd>machine learning</kwd><kwd>LASSO</kwd><kwd>random forest</kwd><kwd>multicenter study</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">Zhao J., Du W., Tao X. et al. Survival and prognostic factors among different types of liposarcomas based on SEER database. Sci. Rep. 2025; 15 (1): 1790. https://doi.org/10.1038/s41598-025-85937-9</mixed-citation><mixed-citation xml:lang="en">Zhao J., Du W., Tao X. et al. Survival and prognostic factors among different types of liposarcomas based on SEER database. Sci. Rep. 2025; 15 (1): 1790. https://doi.org/10.1038/s41598-025-85937-9</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Knebel C., Lenze U., Pohlig F. et al. Prognostic factors and outcome of Liposarcoma patients: a retrospective evaluation over 15 years. BMC Cancer. 2017; 17 (1): 410. https://doi.org/10.1186/s12885-017-3398-y</mixed-citation><mixed-citation xml:lang="en">Knebel C., Lenze U., Pohlig F. et al. Prognostic factors and outcome of Liposarcoma patients: a retrospective evaluation over 15 years. BMC Cancer. 2017; 17 (1): 410. https://doi.org/10.1186/s12885-017-3398-y</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Jonczak E., Grossman J., Alessandrino F. et al. Liposarcoma: A Journey into a Rare Tumor's Epidemiology, Diagnosis, Pathophysiology, and Limitations of Current Therapies. Cancers. 2024; 16 (22): 3858. https://doi.org/10.3390/cancers16223858</mixed-citation><mixed-citation xml:lang="en">Jonczak E., Grossman J., Alessandrino F. et al. Liposarcoma: A Journey into a Rare Tumor's Epidemiology, Diagnosis, Pathophysiology, and Limitations of Current Therapies. Cancers. 2024; 16 (22): 3858. https://doi.org/10.3390/cancers16223858</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Noebauer-Huhmann I.M., Vanhoenacker F.M., Vilanova J.C. et al. Soft tissue tumor imaging in adults: European Society of Musculoskeletal Radiology Guidelines 2023 – overview, and primary local imaging: how and where? Eur. Radiol. 2024; 34 (7): 4427–4437. https://doi.org/10.1007/s00330-023-10425-5</mixed-citation><mixed-citation xml:lang="en">Noebauer-Huhmann I.M., Vanhoenacker F.M., Vilanova J.C. et al. Soft tissue tumor imaging in adults: European Society of Musculoskeletal Radiology Guidelines 2023 – overview, and primary local imaging: how and where? Eur. Radiol. 2024; 34 (7): 4427–4437. https://doi.org/10.1007/s00330-023-10425-5</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Состояние онкологической помощи населению России в 2024 году / Под ред. А.Д. Каприна, В.В. Старинского, А.О. Шахзадовой. М.: МНИОИ им. П.А. Герцена - филиал ФГБУ ”НМИЦ радиологии“ Минздрава России, 2025. 275 с. ISBN 978-5-85502-309-1</mixed-citation><mixed-citation xml:lang="en">Kaprin A.D., Starinskiy V.V., Shakhzadova A.O. (eds). Sostoyanie onkologicheskoy pomoshchi naseleniyu Rossii v 2024 godu [The State of Oncological Care for the Population of Russia in 2024]. Moscow: P.A. Herzen Moscow Oncology Research Institute – Branch of the FSBI “National Medical Research Radiological Centre” of the Ministry of Health of Russia, 2025. 275 p. ISBN 978-5-85502-309-1 (In Russian)</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Клинические рекомендации. Саркомы мягких тканей. 2025. URL: https://cr.minzdrav.gov.ru/preview-cr/515_3 (дата обращения: 02.04.2026).</mixed-citation><mixed-citation xml:lang="en">Ministerstvo zdravookhraneniya Rossiyskoy Federatsii. Klinicheskiye rekomendatsii. Sarkomy myagkikh tkaney [Clinical Guidelines. Soft Tissue Sarcomas]. 2025. Available at: https://cr.minzdrav.gov.ru/preview-cr/515_3 (accessed: 02.04.2026). (In Russian)</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Морозов А.К., Завадовская В.Д., Алексеева О.Г. и др. Лучевая диагностика заболеваний костей и суставов: национальное руководство. 2-е изд., перераб. и доп. М.: ГЭОТАР-Медиа, 2026: 615–625. ISBN 978-5-9704-8867-6. https://doi.org/10.33029/9704-8867-6-DKS-2026-1-664. EDN: NPVDLH</mixed-citation><mixed-citation xml:lang="en">Morozov A.K., Zavadovskaya V.D., Alekseeva O.G. et al. Luchevaya diagnostika zabolevaniy kostey i sustavov: natsionalnoye rukovodstvo [Radiation Diagnosis of Bone and Joint Diseases: National Guidelines]. 2nd ed., revised and expanded. Moscow: GEOTAR-Media; 2026: 615–625. ISBN 978-5-9704-8867-6. https://doi.org/10.33029/9704-8867-6-DKS-2026-1-664. EDN: NPVDLH. (In Russian)</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Natella R., Varriano G., Brunese M.C. et al. Increasing differential diagnosis between lipoma and liposarcoma through radiomics: a narrative review. Explor. Targeted Anti-tum. Ther. 2023; 4 (3): 498–510. https://doi.org/10.37349/etat.2023.00147</mixed-citation><mixed-citation xml:lang="en">Natella R., Varriano G., Brunese M.C. et al. Increasing differential diagnosis between lipoma and liposarcoma through radiomics: a narrative review. Explor. Targeted Anti-tum. Ther. 2023; 4 (3): 498–510. https://doi.org/10.37349/etat.2023.00147</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Burt A.M., Huang B.K. Imaging review of lipomatous musculoskeletal lesions. SICOT J. 2017; 3: 34. https://doi.org/10.1051/sicotj/2017015</mixed-citation><mixed-citation xml:lang="en">Burt A.M., Huang B.K. Imaging review of lipomatous musculoskeletal lesions. SICOT J. 2017; 3: 34. https://doi.org/10.1051/sicotj/2017015</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Kransdorf M.J., Bancroft L.W., Peterson J.J. et al. Imaging of fatty tumors: distinction of lipoma and well-differentiated liposarcoma. Radiology. 2002; 224 (1): 99–104. https://doi.org/10.1148/radiol.2241011113</mixed-citation><mixed-citation xml:lang="en">Kransdorf M.J., Bancroft L.W., Peterson J.J. et al. Imaging of fatty tumors: distinction of lipoma and well-differentiated liposarcoma. Radiology. 2002; 224 (1): 99–104. https://doi.org/10.1148/radiol.2241011113</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Zhou X.P., Xing J.P., Sun L.B. et al. Molecular characteristics and systemic treatment options of liposarcoma: A systematic review. Biomed. &amp; Pharmacother. 2024; 178: 117204. https://doi.org/10.1016/j.biopha.2024.117204</mixed-citation><mixed-citation xml:lang="en">Zhou X.P., Xing J.P., Sun L.B. et al. Molecular characteristics and systemic treatment options of liposarcoma: A systematic review. Biomed. &amp; Pharmacother. 2024; 178: 117204. https://doi.org/10.1016/j.biopha.2024.117204</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Dwianingsih E.K., Bawono R.G., Saputri A. et al. Histomorphological and molecular characteristics of liposarcoma (Review). Oncol. Lett. 2025; 30 (4): 454. https://doi.org/10.3892/ol.2025.15200</mixed-citation><mixed-citation xml:lang="en">Dwianingsih E.K., Bawono R.G., Saputri A. et al. Histomorphological and molecular characteristics of liposarcoma (Review). Oncol. Lett. 2025; 30 (4): 454. https://doi.org/10.3892/ol.2025.15200</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Lee A.T.J., Thway K., Huang P.H., Jones R.L. Clinical and molecular spectrum of liposarcoma. J. Clin. Oncol. 2018; 36 (2): 151–159. https://doi.org/10.1200/JCO.2017.74.9598</mixed-citation><mixed-citation xml:lang="en">Lee A.T.J., Thway K., Huang P.H., Jones R.L. Clinical and molecular spectrum of liposarcoma. J. Clin. Oncol. 2018; 36 (2): 151–159. https://doi.org/10.1200/JCO.2017.74.9598</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Malinauskaite I., Hofmeister J., Burgermeister S. et al. Radiomics and Machine Learning Differentiate Soft-Tissue Lipoma and Liposarcoma Better than Musculoskeletal Radiologists. Sarcoma. 2020:7163453. https://doi.org/10.1155/2020/7163453</mixed-citation><mixed-citation xml:lang="en">Malinauskaite I., Hofmeister J., Burgermeister S. et al. Radiomics and Machine Learning Differentiate Soft-Tissue Lipoma and Liposarcoma Better than Musculoskeletal Radiologists. Sarcoma. 2020:7163453. https://doi.org/10.1155/2020/7163453</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Нуднов Н.В., Харченко Н.В., Аксенова С.П. и др. Магнитно-резонансная томография в дифференциальной диагностике липом и липосарком мягких тканей. Медицинская визуализация. 2025; 29 (2): 72–87 https://doi.org/10.24835/1607-0763-1533</mixed-citation><mixed-citation xml:lang="en">Nudnov N.V., Kharchenko N.V., Aksenova S.P. et al. Magnetic resonance imaging in the differential diagnosis of soft tissue lipomas and liposarcomas. Medical Visualization. 2025; 29 (2): 72–87. https://doi.org/10.24835/1607-0763-1533. (In Russian)</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Foreman S.C., Llorián-Salvador O., David D.E. et al. Development and Evaluation of MR-Based Radiogenomic Models to Differentiate Atypical Lipomatous Tumors from Lipomas. Cancers. 2023; 15 (7): 2150. https://doi.org/10.3390/cancers15072150</mixed-citation><mixed-citation xml:lang="en">Foreman S.C., Llorián-Salvador O., David D.E. et al. Development and Evaluation of MR-Based Radiogenomic Models to Differentiate Atypical Lipomatous Tumors from Lipomas. Cancers. 2023; 15 (7): 2150. https://doi.org/10.3390/cancers15072150</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Gitto S., Interlenghi M., Cuocolo R. et al. MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor of the extremities. La Radiologia Medica. 2023; 128: 989–998. https://doi.org/10.1007/s11547-023-01657-y</mixed-citation><mixed-citation xml:lang="en">Gitto S., Interlenghi M., Cuocolo R. et al. MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor of the extremities. La Radiologia Medica. 2023; 128: 989–998. https://doi.org/10.1007/s11547-023-01657-y</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Tang Y., Cui J., Zhu J., Fan G. Differentiation Between Lipomas and Atypical Lipomatous Tumors of the Extremities Using Radiomics. J. Magn. Res. Imaging. 2022; 56 (6): 1746–1754. https://doi.org/10.1002/jmri.28167</mixed-citation><mixed-citation xml:lang="en">Tang Y., Cui J., Zhu J., Fan G. Differentiation Between Lipomas and Atypical Lipomatous Tumors of the Extremities Using Radiomics. J. Magn. Res. Imaging. 2022; 56 (6): 1746–1754. https://doi.org/10.1002/jmri.28167</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Cay N., Mendi B.A.R., Batur H. et al. Discrimination of lipoma from atypical lipomatous tumor/well-differentiated liposarcoma using magnetic resonance imaging radiomics combined with machine learning. Japanese J. Radiol. 2022; 40 (9): 951–960. https://doi.org/10.1007/s11604-022-01278-x</mixed-citation><mixed-citation xml:lang="en">Cay N., Mendi B.A.R., Batur H. et al. Discrimination of lipoma from atypical lipomatous tumor/well-differentiated liposarcoma using magnetic resonance imaging radiomics combined with machine learning. Japanese J. Radiol. 2022; 40 (9): 951–960. https://doi.org/10.1007/s11604-022-01278-x</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Vos M., Starmans M.P.A., Timbergen M.J.M. et al. Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI. Br. J. Surg. 2019; 106 (13): 1800–1809. https://doi.org/10.1002/bjs.11410</mixed-citation><mixed-citation xml:lang="en">Vos M., Starmans M.P.A., Timbergen M.J.M. et al. Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI. Br. J. Surg. 2019; 106 (13): 1800–1809. https://doi.org/10.1002/bjs.11410</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>
