<?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">ketendo</journal-id><journal-title-group><journal-title xml:lang="ru">Клиническая и экспериментальная тиреоидология</journal-title><trans-title-group xml:lang="en"><trans-title>Clinical and experimental thyroidology</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1995-5472</issn><issn pub-type="epub">2310-3787</issn><publisher><publisher-name>Endocrinology Research Centre</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.14341/ket12757</article-id><article-id custom-type="elpub" pub-id-type="custom">ketendo-12757</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>Оригинальные исследования</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Original Studies</subject></subj-group></article-categories><title-group><article-title>Исследование применения нейросетевых моделей в классификации узлов щитовидной железы по категориям EU-TIRADS для персонализации ультразвуковой диагностики щитовидной железы</article-title><trans-title-group xml:lang="en"><trans-title>Investigation of neural network models application in EU-TIRADS thyroid nodules classification for personalization of thyroid gland ultrasound diagnostic</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0004-0764-8165</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Цыгулева</surname><given-names>К. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Tsyguleva</surname><given-names>K. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Цыгулева Ксения Владимировна </p><p>Москва</p></bio><bio xml:lang="en"><p>Kseniya V. Tsyguleva </p><p> </p></bio><email xlink:type="simple">k151201@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/0009-0005-8718-8468</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ложкин</surname><given-names>И. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Lozhkin</surname><given-names>I. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ложкин Илья Александрович </p><p>Москва</p></bio><bio xml:lang="en"><p> Ilya A. Lozhkin </p><p> Moscow </p></bio><email xlink:type="simple">ilya.lojckin@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/0009-0008-0952-2944</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Королев</surname><given-names>Д. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Korolev</surname><given-names>D. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Королев Денис Вячеславович </p><p>Москва</p></bio><bio xml:lang="en"><p>Denis V. Korolev </p><p> Moscow </p></bio><email xlink:type="simple">newmancu@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-0566-7379</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Зайцев</surname><given-names>К. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Zajcev</surname><given-names>K. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Зайцев Константин Сергеевич, д.т.н.</p><p>Москва</p></bio><bio xml:lang="en"><p>Konstantin S. Zajtsev, PhD </p><p> Moscow </p></bio><email xlink:type="simple">KSZajtsev@mephi.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Дунаев</surname><given-names>М. Е.</given-names></name><name name-style="western" xml:lang="en"><surname>Dunaev</surname><given-names>M. E.</given-names></name></name-alternatives><bio xml:lang="ru"><p> Дунаев Максим Евгеньевич </p><p>Москва</p></bio><bio xml:lang="en"><p>Maxim E. Dunaev </p><p>Moscow </p></bio><email xlink:type="simple">max.dunaev@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/0000-0002-1129-7220</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гармаш</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Garmash</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Гармаш Александр Александрович, к.т.н. </p><p>Москва</p></bio><bio xml:lang="en"><p>Alexandr A. Garmash, PhD </p><p> Moscow </p></bio><email xlink:type="simple">AAGarmash@mephi.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/0009-0003-8035-676X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Манаев</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Manaev</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Манаев Алмаз Вадимович </p><p>Москва</p></bio><bio xml:lang="en"><p> Almaz V. Manaev </p><p> Moscow </p></bio><email xlink:type="simple">a.manaew2016@yandex.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/0000-0001-6059-2827</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Захарова</surname><given-names>С. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Zaharova</surname><given-names>S. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Захарова Светлана Михайловна, к.м.н. </p><p>Москва</p></bio><bio xml:lang="en"><p>Svetlana M. Zakharova, MD, PhD </p><p> Moscow </p></bio><email xlink:type="simple">smzakharova@mail.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/0000-0001-5592-4727</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Трухин</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Trukhin</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Трухин Алексей Андреевич, к.т.н.</p><p>117036 Москва, ул. Дм. Ульянова, д. 11, к. 2</p></bio><bio xml:lang="en"><p>Alexey A. Trukhin, PhD </p><p>11 bld 2, Dm. Ulyanova street, 117036 Moscow, Russia </p></bio><email xlink:type="simple">Alexey.trukhin12@gmail.com</email><xref ref-type="aff" rid="aff-4"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-8520-8702</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Трошина</surname><given-names>Е. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Troshina</surname><given-names>E. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Трошина Екатерина Анатольевна, д.м.н., профессор, член-корр. РАН </p><p>Москва</p></bio><bio xml:lang="en"><p>Ekaterina A. Troshina, MD, PhD, Professor </p><p> Moscow </p></bio><email xlink:type="simple">troshina@inbox.ru</email><xref ref-type="aff" rid="aff-3"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Национальный исследовательский ядерный университет «МИФИ»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>National Research Nuclear University «MEPhI» (Moscow Engineering Physics Institute)</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Национальный исследовательский ядерный университет «МИФИ»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>National Research Nuclear University «MEPhI» (Moscow Engineering Physics Institute);&#13;
Endocrinology Research Centre</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>Национальный медицинский исследовательский центр эндокринологии</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Endocrinology Research Centre</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-4"><aff xml:lang="ru"><institution>Национальный исследовательский ядерный университет «МИФИ»;&#13;
Национальный медицинский исследовательский центр эндокринологии</institution><country>Россия</country></aff><aff xml:lang="en"><institution>National Research Nuclear University «MEPhI» (Moscow Engineering Physics Institute);&#13;
Endocrinology Research Centre</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2023</year></pub-date><pub-date pub-type="epub"><day>12</day><month>09</month><year>2023</year></pub-date><volume>19</volume><issue>1</issue><fpage>4</fpage><lpage>11</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Цыгулева К.В., Ложкин И.А., Королев Д.В., Зайцев К.С., Дунаев М.Е., Гармаш А.А., Манаев А.В., Захарова С.М., Трухин А.А., Трошина Е.А., 2023</copyright-statement><copyright-year>2023</copyright-year><copyright-holder xml:lang="ru">Цыгулева К.В., Ложкин И.А., Королев Д.В., Зайцев К.С., Дунаев М.Е., Гармаш А.А., Манаев А.В., Захарова С.М., Трухин А.А., Трошина Е.А.</copyright-holder><copyright-holder xml:lang="en">Tsyguleva K.V., Lozhkin I.A., Korolev D.V., Zajcev K.S., Dunaev M.E., Garmash A.A., Manaev A.V., Zaharova S.M., Trukhin A.A., Troshina E.A.</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.cet-endojournals.ru/jour/article/view/12757">https://www.cet-endojournals.ru/jour/article/view/12757</self-uri><abstract><p>ОБОСНОВАНИЕ. Известно, что около 69% всех узлов щитовидной железы, подвергшихся хирургическому лечению, представляют собой доброкачественные образования, а до 75% пациентов с промежуточным цитологическим заключением подвергаются ненужному хирургическому вмешательству. Это позволяет предположить, что повышение качества дифференциальной диагностики узловых образований позволит избежать избыточных экономических затрат для системы здравоохранения. В связи с этим встал вопрос о привлечении технологий искусственного интеллекта в диагностические алгоритмы классификации узловых образований щитовидной железы.ЦЕЛЬ. Повышение эффективности автоматической классификации узловых образований щитовидной железы на ультразвуковых изображениях за счет использования набора нейросетевых моделей.МАТЕРИАЛЫ И МЕТОДЫ. В работе использовались ультразвуковые изображения узловых образований щитовидной железы, доступные в открытых источниках и полученные при помощи 3 ультразвуковых аппаратов ГНЦ РФ ФГБУ «НМИЦ эндокринологии» Минздрава России в рамках реализации проекта №22-15-00135 гранта Российского научного фонда. В работе исследована гипотеза о том, что объем обучающей выборки не может быть увеличен за счет повторения схожих изображений из ультразвуковой кинопетли одного пациента, а только благодаря расширению датасета новыми уникальными экземплярами других пациентов и/или данными процесса аугментации.РЕЗУЛЬТАТЫ. В результате предложена нейросетевая модель EfficientNet-B6 для решения задачи классификации по EU-TIRADS узловых образований щитовидной железы по ее ультразвуковым изображениям.ЗАКЛЮЧЕНИЕ. Полученные результаты позволяют продвинуться в вопросах использования методов искусственного интеллекта для персонализированной медицины при заболеваниях щитовидной железы.</p></abstract><trans-abstract xml:lang="en"><p>SUBSTANTIATION. It is known that about 69% of all thyroid nodules undergoing surgical treatment are benign formations, and up to 75% of patients with an intermediate cytological conclusion undergo unnecessary surgical intervention. This suggests that improving the quality of differential diagnosis of nodular formations will avoid excessive economic costs for the healthcare system. In this regard, AI technologies in diagnostic algorithms for the classification of thyroid nodules were involved.AIM. Improving the efficiency of automatic classification of thyroid nodules on ultrasound images by using a set of neural network models.MATERIALS AND METHODS. We used ultrasound images of thyroid nodules available in open sources and obtained with the help of 3 ultrasound devices of Endocrinology Research Centre as part of Project № 22-15-00135 of the grant of the Russian Science Foundation. This article check the hypothesis that the size of the training set cannot be increased by repeating similar images from the ultrasound cine loop of one patient, but only by expanding the dataset with new unique specimens of other patients and/or data from the augmentation process.RESULTS. As a result, a neural network model EfficientNet-B6 was proposed to solve the problem of EU-TIRADS classification of thyroid nodules based on ultrasound images of the thyroid gland.CONCLUSION. The results obtained allow us to advance in the use of artificial intelligence methods for personalized medicine in thyroid diseases.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>персонализированная медицина</kwd><kwd>щитовидная железа</kwd><kwd>ультразвуковая визуализация</kwd><kwd>обнаружение</kwd><kwd>сегментация</kwd><kwd>классификация EU-TIRADS</kwd><kwd>нейронные сети</kwd><kwd>машинное обучение</kwd></kwd-group><kwd-group xml:lang="en"><kwd>personalized medicine</kwd><kwd>thyroid gland</kwd><kwd>ultrasound examination</kwd><kwd>detection</kwd><kwd>segmentation</kwd><kwd>EU-TIRADS classification</kwd><kwd>neural networks</kwd><kwd>machine learning</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Материал подготовлен по гранту Российского научного фонда в рамках реализации проекта №22-15-00135 «Научное обоснование, разработка и внедрение новых технологий диагностики коморбидных йододефицитных и аутоиммунных заболеваний щитовидной железы с использованием возможностей искусственного интеллекта».</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">Brockwell PJ, Davis RA. Introduction to time series and forecasting. New York: Springer; 2016.</mixed-citation><mixed-citation xml:lang="en">Brockwell PJ, Davis RA. Introduction to time series and forecasting. New York: Springer; 2016.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Aldweesh A, Derhab A, Emam AZ. Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues. Knowledge-Based Syst. 2020;(189):105124. doi: https://doi.org/10.1016/j.knosys.2019.105124</mixed-citation><mixed-citation xml:lang="en">Aldweesh A, Derhab A, Emam AZ. Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues. Knowledge-Based Syst. 2020;(189):105124. doi: https://doi.org/10.1016/j.knosys.2019.105124</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Chen J, You H, Li K. A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images. Comput Methods Programs Biomed. 2020;(185):105329. doi: https://doi.org/10.1016/j.cmpb.2020.105329</mixed-citation><mixed-citation xml:lang="en">Chen J, You H, Li K. A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images. Comput Methods Programs Biomed. 2020;(185):105329. doi: https://doi.org/10.1016/j.cmpb.2020.105329</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Deng P, Han X, Wei X, Chang L. Automatic classification of thyroid nodules in ultrasound images using a multi-task attention network guided by clinical knowledge. Comput Biol Med. 2022;(150):106172. doi: https://doi.org/10.1016/j.compbiomed.2022.106172</mixed-citation><mixed-citation xml:lang="en">Deng P, Han X, Wei X, Chang L. Automatic classification of thyroid nodules in ultrasound images using a multi-task attention network guided by clinical knowledge. Comput Biol Med. 2022;(150):106172. doi: https://doi.org/10.1016/j.compbiomed.2022.106172</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang X, Lee VC, Rong J, et al. Deep convolutional neural networks in thyroid disease detection: A multi-classification comparison by ultrasonography and computed tomography. Comput Methods Programs Biomed. 2022;(220):106823. doi: https://doi.org/10.1016/j.cmpb.2022.106823</mixed-citation><mixed-citation xml:lang="en">Zhang X, Lee VC, Rong J, et al. Deep convolutional neural networks in thyroid disease detection: A multi-classification comparison by ultrasonography and computed tomography. Comput Methods Programs Biomed. 2022;(220):106823. doi: https://doi.org/10.1016/j.cmpb.2022.106823</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Sharifi Y, Bakhshali MA, Dehghani T, et al. Deep learning on ultrasound images of thyroid nodules. Biocybern Biomed Eng. 2021;41(2):636-655. doi: https://doi.org/10.1016/j.bbe.2021.02.008</mixed-citation><mixed-citation xml:lang="en">Sharifi Y, Bakhshali MA, Dehghani T, et al. Deep learning on ultrasound images of thyroid nodules. Biocybern Biomed Eng. 2021;41(2):636-655. doi: https://doi.org/10.1016/j.bbe.2021.02.008</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Tessler FN, Middleton WD, Grant EG. Thyroid Imaging Reporting and Data System (TI-RADS): A user’s guide. Radiology. 2018;287(1):29-36. doi: https://doi.org/10.1148/radiol.2017171240</mixed-citation><mixed-citation xml:lang="en">Tessler FN, Middleton WD, Grant EG. Thyroid Imaging Reporting and Data System (TI-RADS): A user’s guide. Radiology. 2018;287(1):29-36. doi: https://doi.org/10.1148/radiol.2017171240</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Redmon J, Divvala S, Girshick R, et al. You only look once: unified, realtime object detection. Nucl Instruments Methods Phys Res Sect A Accel Spectrometers, Detect Assoc Equip. 2015 [cited 15.08.2023]. Available from: http://arxiv.org/abs/1506.02640</mixed-citation><mixed-citation xml:lang="en">Redmon J, Divvala S, Girshick R, et al. You only look once: unified, realtime object detection. Nucl Instruments Methods Phys Res Sect A Accel Spectrometers, Detect Assoc Equip. 2015 [cited 15.08.2023]. Available from: http://arxiv.org/abs/1506.02640</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Chen LC, Papandreou G, Kokkinos I, et al. Rethinking Atrous Convolution for Semantic Image Segmentation Liang-Chieh. IEEE Trans Pattern Anal Mach Intell. 2018 [cited 15.08.2023]. Available from: http://arxiv.org/abs/1706.05587</mixed-citation><mixed-citation xml:lang="en">Chen LC, Papandreou G, Kokkinos I, et al. Rethinking Atrous Convolution for Semantic Image Segmentation Liang-Chieh. IEEE Trans Pattern Anal Mach Intell. 2018 [cited 15.08.2023]. Available from: http://arxiv.org/abs/1706.05587</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Maharana K, Mondal S, Nemade B. A review: Data pre-processing and data augmentation techniques. Glob Transitions Proc. 2022;3(1):91-99. doi: https://doi.org/10.1016/j.gltp.2022.04.020</mixed-citation><mixed-citation xml:lang="en">Maharana K, Mondal S, Nemade B. A review: Data pre-processing and data augmentation techniques. Glob Transitions Proc. 2022;3(1):91-99. doi: https://doi.org/10.1016/j.gltp.2022.04.020</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Nalepa J, Marcinkiewicz M, Kawulok M. Data augmentation for braintumor segmentation: A review. Front Comput Neurosci. 2019;(13). doi: https://doi.org/10.3389/fncom.2019.00083</mixed-citation><mixed-citation xml:lang="en">Nalepa J, Marcinkiewicz M, Kawulok M. Data augmentation for braintumor segmentation: A review. Front Comput Neurosci. 2019;(13). doi: https://doi.org/10.3389/fncom.2019.00083</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Chlap P, Min H, Vandenberg N, et al. A review of medical image data augmentation techniques for deep learning applications. J Med Imaging Radiat Oncol. 2021;65(5):545-563. doi: https://doi.org/10.1111/1754-9485.13261</mixed-citation><mixed-citation xml:lang="en">Chlap P, Min H, Vandenberg N, et al. A review of medical image data augmentation techniques for deep learning applications. J Med Imaging Radiat Oncol. 2021;65(5):545-563. doi: https://doi.org/10.1111/1754-9485.13261</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Hoar D, Lee PQ, Guida A, et al. Combined transfer learning and testtime augmentation improves convolutional neural network-based semantic segmentation of prostate cancer from multi-parametric MR images. Comput Methods Programs Biomed. 2021;(210):106375. doi: https://doi.org/10.1016/j.cmpb.2021.106375</mixed-citation><mixed-citation xml:lang="en">Hoar D, Lee PQ, Guida A, et al. Combined transfer learning and testtime augmentation improves convolutional neural network-based semantic segmentation of prostate cancer from multi-parametric MR images. Comput Methods Programs Biomed. 2021;(210):106375. doi: https://doi.org/10.1016/j.cmpb.2021.106375</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Image Test Time Augmentation with PyTorch [Internet]. TTAch [cited 01.03.2023]. Available from: https://github.com/qubvel/ttach</mixed-citation><mixed-citation xml:lang="en">Image Test Time Augmentation with PyTorch [Internet]. TTAch [cited 01.03.2023]. Available from: https://github.com/qubvel/ttach</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Documentation of the imgaug library for image augmentation [Internet] [cited 01.03.2023]. Available from: https://imgaug.readthedocs.io/en/latest/, free</mixed-citation><mixed-citation xml:lang="en">Documentation of the imgaug library for image augmentation [Internet] [cited 01.03.2023]. Available from: https://imgaug.readthedocs.io/en/latest/, free</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Hussain Z, Gimenez F, Yi D, Rubin D. Differential data augmentation techniques for medical imaging classification tasks. AMIA . Annu Symp proceedings AMIA Symp. 2017. P. 979-984.</mixed-citation><mixed-citation xml:lang="en">Hussain Z, Gimenez F, Yi D, Rubin D. Differential data augmentation techniques for medical imaging classification tasks. AMIA . Annu Symp proceedings AMIA Symp. 2017. P. 979-984.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Chen Y, Yang X-H, Wei Z, et al. Generative Adversarial Networks in Medical Image augmentation: A review. Comput Biol Med. 2022;144:105382. doi: https://doi.org/10.1016/j.compbiomed.2022.105382</mixed-citation><mixed-citation xml:lang="en">Chen Y, Yang X-H, Wei Z, et al. Generative Adversarial Networks in Medical Image augmentation: A review. Comput Biol Med. 2022;144:105382. doi: https://doi.org/10.1016/j.compbiomed.2022.105382</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Shi G, Wang J, Qiang Y, et al. Knowledge-guided synthetic medical image adversarial augmentation for ultrasonography thyroid nodule classification. Comput Methods Programs Biomed. 2020;(196):105611. doi: https://doi.org/10.1016/j.cmpb.2020.105611</mixed-citation><mixed-citation xml:lang="en">Shi G, Wang J, Qiang Y, et al. Knowledge-guided synthetic medical image adversarial augmentation for ultrasonography thyroid nodule classification. Comput Methods Programs Biomed. 2020;(196):105611. doi: https://doi.org/10.1016/j.cmpb.2020.105611</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Neurohive [Internet]. ResNet (34, 50, 101): «остаточные» CNN для классификации изображений. Доступно по: https://neurohive.io/ru/vidy-nejrosetej/resnet-34-50-101/. Ссылка активна на 01.03.2023.</mixed-citation><mixed-citation xml:lang="en">Neurohive [Internet]. ResNet (34, 50, 101): «остаточные» CNN для классификации изображений. Доступно по: https://neurohive.io/ru/vidy-nejrosetej/resnet-34-50-101/. Ссылка активна на 01.03.2023.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">ResNet [Internet]. PyTorch Documentation [cited 01.03.2023]. Available from: https://pytorch.org/vision/stable/models/resnet.html</mixed-citation><mixed-citation xml:lang="en">ResNet [Internet]. PyTorch Documentation [cited 01.03.2023]. Available from: https://pytorch.org/vision/stable/models/resnet.html</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Tan M, Le Q V. EfficientNet: Rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning, ICML 2019; 2019.</mixed-citation><mixed-citation xml:lang="en">Tan M, Le Q V. EfficientNet: Rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning, ICML 2019; 2019.</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">EfficientNet [Internet]. PyTorch Documentation [cited 01.03.2023]. Available from: https://pytorch.org/vision/stable/models/efficientnet.html</mixed-citation><mixed-citation xml:lang="en">EfficientNet [Internet]. PyTorch Documentation [cited 01.03.2023]. Available from: https://pytorch.org/vision/stable/models/efficientnet.html</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Ludwig M, Ludwig B, Mikuła A, et al. The use of artificial intelligence in the diagnosis and classification of thyroid nodules: An update. Cancers (Basel). 2023;15(3):708. doi: https://doi.org/10.3390/cancers15030708</mixed-citation><mixed-citation xml:lang="en">Ludwig M, Ludwig B, Mikuła A, et al. The use of artificial intelligence in the diagnosis and classification of thyroid nodules: An update. Cancers (Basel). 2023;15(3):708. doi: https://doi.org/10.3390/cancers15030708</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>
