<?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">bsuir</journal-id><journal-title-group><journal-title xml:lang="ru">Доклады БГУИР</journal-title><trans-title-group xml:lang="en"><trans-title>Doklady BGUIR</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1729-7648</issn><issn pub-type="epub">2708-0382</issn><publisher><publisher-name>БГУИР</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.35596/1729-7648-2023-21-1-98-103</article-id><article-id custom-type="elpub" pub-id-type="custom">bsuir-3571</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>КРАТКИЕ СООБЩЕНИЯ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>SHORT NOTES</subject></subj-group></article-categories><title-group><article-title>Система поддержки принятия решений для диагностики патологий сердечно-сосудистой системы по рентгеновским изображениям грудной клетки</article-title><trans-title-group xml:lang="en"><trans-title>Decision Making Support System for the Diagnostics of the Cardiovascular System Pathologies by the X-ray Images of the Chest</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Раджабов</surname><given-names>А. Г.</given-names></name><name name-style="western" xml:lang="en"><surname>Radzhabov</surname><given-names>A. G.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Раджабов Ахмедхан Гаджимаммяевич, аспирант, младший научный сотрудник</p><p>220141,г. Минск, ул. Руссиянова, 50</p><p>+375 33 385-23-20</p></bio><bio xml:lang="en"><p>Radzhabov Ahmedkhan Gadgimammyaevich, Postgraduate, Junior Researcher </p><p>220141, Russiyanova St., 50</p><p>+375 33 385-23-20</p></bio><email xlink:type="simple">axmegxah@outlook.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Объединенный институт проблем информатики Национальной академии наук Беларуси</institution></aff><aff xml:lang="en"><institution>The United Institute of Informatics Problems of the National Academy of Sciences of Belarus</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2023</year></pub-date><pub-date pub-type="epub"><day>02</day><month>03</month><year>2023</year></pub-date><volume>21</volume><issue>1</issue><fpage>98</fpage><lpage>103</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Раджабов А.Г., 2023</copyright-statement><copyright-year>2023</copyright-year><copyright-holder xml:lang="ru">Раджабов А.Г.</copyright-holder><copyright-holder xml:lang="en">Radzhabov A.G.</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://doklady.bsuir.by/jour/article/view/3571">https://doklady.bsuir.by/jour/article/view/3571</self-uri><abstract><p>Отсутствие универсальных (генерализированных) наборов данных и недостаток аннотированных данных делают необходимым исследование возможностей нейросетевых подходов для конкретных наборов данных. Важность построения алгоритмов для обнаружения внелёгочных патологий на рентгеновских изображениях грудной клетки продиктована социальной значимостью заболеваний данной группы (например, сердечно-сосудистых), условиями доступности таких изображений ввиду широкого распространения малоинвазивных и относительно дешевых рентгенологических методов диагностики. Одна из важных проблем при решении задач автоматизации классификации медицинских изображений – подготовка данных. В результате работы над базой изображений удалось повысить производительность итогового алгоритма с 75 до 95 %. Для медицинских учреждений обработка всего объема получаемых изображений и проведение их диагностики по широкому списку патологий затруднены ограниченностью ресурсов. В связи с чем целесообразно использовать автоматизацию процессов сегментации и распознавания, что уже на первых этапах ее применения дает возможность врачам перераспределить внимание на потенциально патологические случаи и обратить повторно внимание на те, которые ошибочно были идентифицированы как непатологические.</p></abstract><trans-abstract xml:lang="en"><p>The lack of universal (generalized) data sets, as well as the lack of annotated data, creates the need to study the possibilities of neural network approaches for specific data sets. The importance of building algorithms for detecting extrapulmonary pathologies on chest X-ray images is dictated by the great social significance of many diseases of this group (for example, cardiovascular diseases), given the availability of such images, due to the widespread use of minimally invasive and relatively cheap X-ray diagnostic methods. One of the most impor tant issues in solving the problems of automating the classification of medical images is data preparation. As a result of work on the image base, the performance of the final algorithm has been increased from 75 to 95 %. The processing of the entire volume of the obtained images and their diagnostics for a wide list of pathologies are difficult for medical institutions because of the limited resources. In this regard, it is advisable to use the automation of segmentation and recognition processes, which even at the first stages of development of the technology makes it possible to redistribute the attention of doctors, focusing on potentially pathological cases and returning attention to cases mistakenly identified as non-pathological.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>глубокое обучение</kwd><kwd>внелёгочные патологии</kwd><kwd>подготовка данных</kwd><kwd>предобученные нейронные сети</kwd><kwd>классификация</kwd></kwd-group><kwd-group xml:lang="en"><kwd>deep learning</kwd><kwd>extrapulmonary pathologies</kwd><kwd>data preparation</kwd><kwd>pretrained neural networks</kwd><kwd>classification</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">Канюков, В. Н. Компьютерные технологии в медико-биологических исследованиях / В. Н. Канюков, Р. Р. Григорьев, А. Д. Стрекаловская. Оренбург: Оренб. госуд. ун-т, 2009. Ч. 1. 109 с.</mixed-citation><mixed-citation xml:lang="en">Kanyukov V. N. (2009) Computer Technologies in Biomedical Research. Ch. 1. Orenburg, GOU ORG. 109. (in Russian).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Shortliffe, E. H. Computer-based Medical Consultations: MYCIN / Е. Н. Shorliffe. New York: Elsevier Computer Science Library, 1976. 286 p.</mixed-citation><mixed-citation xml:lang="en">Shortiffe E. H. (1976) Computer-Based Medical Consultations: MYCIN. New York, Elsevier Computer Science Publi. Comp. 286.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Пеккер, Я. С. Компьютерные технологии в медико-биологических исследованиях. Сигналы био ло гического происхождения и медицинские изображения / Я. С. Пеккер, К. С. Бразовский. Томск: Изд-во Томск. политех. ун-та, 2002. 240 с.</mixed-citation><mixed-citation xml:lang="en">Pekker Ya. S. (2002) Computer Technologies in Biomedical Research. Biological Signals and Medical Imaging. Tomsk, Tomsk Polytechnic University Publ. 240 (in Russian).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Гудфеллоу, Я. Д. Глубокое обучение / Я. Д. Гудфеллоу. СПб.: ДМК, 2017. 652 с.</mixed-citation><mixed-citation xml:lang="en">Gudfellou Ya. D. (2017) Deep Learning. Saint Petersburg, DMK. 652.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">PadChest: a Large Chest X-ray Image Dataset with Multi-label Annotated Reports / А. Bustos [et al.] // Medical Image Analysis. 2020. Vol. 66.</mixed-citation><mixed-citation xml:lang="en">Bustos A., Pertusa A., Salinas J.-M., de la Iglesia-Vayá M. (2020) PadChest: a Large Chest X-ray Image Dataset with Multi-label Annotated Reports. Medical Image Analysis. 66.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Han, Y. Cross-Modal Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics Using a Feedback Loop / Y. Han, B. Glicksberg // arXiv. 2021. https://arxiv.org/pdf/2104.04968.pdf. Date of access: 25.11.2021.</mixed-citation><mixed-citation xml:lang="en">Han Y., Glicksberg B. (2021) Cross-Modal Contrastive Learning for Abnormality Classification and Localization in Chest X-Rays with Radiomics Using a Feedback Loop. arXiv. https://arxiv.org/pdf/2104.04968.pdf (Accessed 25 November 2021).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models / H. Sowrirajan [et al.] // arXiv. 2021. https://arxiv.org/pdf/2010.05352.pdf. Date of access: 25.11.2021.</mixed-citation><mixed-citation xml:lang="en">Sowrirajan H., Yang J., Ng A. Y., Rajpurkar P. (2021) MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-Ray Models. arXiv. https://arxiv.org/pdf/2010.05352.pdf (Accessed 25 November 2021).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Chen, X. Deep Mask for X-Ray Based Heart Disease Classification / Х. Chen, B. Shi // arXiv. 2018. https:// arxiv.org/abs/1808.08277. Date of access: 25.11.2021.</mixed-citation><mixed-citation xml:lang="en">Chen X., Shi B. (2018) Deep Mask for X-Ray Based Heart Disease Classification. arXiv. https://arxiv.org/abs/1808.08277 (Accessed 25 November 2021).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Radzhabov, A. Performance Analysis of Deep Learning Models for Heart Segmentation in Chest X-ray Images on a Small Dataset / А. Radzhabov, V. Kovalev // International Conference on Pattern Recognition and Information Processing. 2021.</mixed-citation><mixed-citation xml:lang="en">Radzhabov A., Kovalev V. (2021) Performance Analysis of Deep Learning Models for Heart Segmentation in Chest X-ray Images on a Small Dataset. International Conference on Pattern Recognition and Information Processing.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Tan, M. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks / М. Tan, Q. V. Le // arXiv. 2020. https://arxiv.org/pdf/1905.11946.pdf. Date of access: 25.11.2021.</mixed-citation><mixed-citation xml:lang="en">Tan M., Le Q. V. (2020) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv. https://arxiv.org/pdf/1905.11946.pdf (Accessed 25 November 2021).</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>
