<?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="en"><front><journal-meta><journal-id journal-id-type="publisher-id">sechenov</journal-id><journal-title-group><journal-title xml:lang="en">Sechenov Medical Journal</journal-title><trans-title-group xml:lang="ru"><trans-title>Сеченовский вестник</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2218-7332</issn><issn pub-type="epub">2658-3348</issn><publisher><publisher-name>Сеченовский Университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.47093/2218-7332.2020.11.3.4-14</article-id><article-id custom-type="elpub" pub-id-type="custom">sechenov-227</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="en"><subject>MODELING IN MEDICINE</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>МОДЕЛИРОВАНИЕ В МЕДИЦИНЕ</subject></subj-group></article-categories><title-group><article-title>Neural network-based segmentation model for breast cancer X-ray screening</article-title><trans-title-group xml:lang="ru"><trans-title>Сегментационная модель скрининга рака молочной железы на основе нейросетевого анализа рентгеновских изображений</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-0920-1549</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Рожкова</surname><given-names>Н. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Rozhkova</surname><given-names>N. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Рожкова Надежда Ивановна, д-р мед. наук, профессор, руководитель </p><p>ул. Погодинская, д. 6, г. Москва, 119121</p></bio><bio xml:lang="en"><p>Nadezhda I. Rozhkova, Dr. of Sci. (Medicine), Professor, Head </p><p>6, Pogodinskaya str., Moscow, 119121</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/0000-0002-9813-0385</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ройтберг</surname><given-names>П. Г.</given-names></name><name name-style="western" xml:lang="en"><surname>Roitberg</surname><given-names>P. G.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ройтберг Павел Григорьевич, канд. экон. наук, учредитель </p><p>2-й Тверской-Ямской пер., д. 10, г. Москва, 125047</p></bio><bio xml:lang="en"><p>Pavel G. Roitberg, Cand. of Sci. (Economy), founder</p><p>10, 2nd Tverskoy-Yamskoy Lane, Moscow, 125047</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/0000-0002-2038-2769</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Варфоломеева</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Varfolomeeva</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Варфоломеева Анна Андреевна, специалист по машинному обучению </p><p>2-й Тверской-Ямской пер., д. 10, г. Москва, 125047</p></bio><bio xml:lang="en"><p>Anna A. Varfolomeeva, Data Scientist</p><p>10, 2nd Tverskoy-Yamskoy Lane, Moscow, 125047</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/0000-0002-1313-6420</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Мазо</surname><given-names>М. Л.</given-names></name><name name-style="western" xml:lang="en"><surname>Mazo</surname><given-names>M. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Мазо Михаил Львович, канд. мед. наук, старший научный сотрудник </p><p>ул. Погодинская, д. 6, г. Москва, 119121</p></bio><bio xml:lang="en"><p>Mikhail L. Mazo, Cand. of Sci. (Medicine), Senior Researcher</p><p>6, Pogodinskaya str., Moscow, 119121</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/0000-0002-2452-914X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Добренький</surname><given-names>А. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Dobrenkii</surname><given-names>A. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Добренький Антон Николаевич, специалист по машинному обучению </p><p>2-й Тверской-Ямской пер., д. 10, г. Москва, 125047</p></bio><bio xml:lang="en"><p>Anton N. Dobrenkii, Data Scientist</p><p>10, 2nd Tverskoy-Yamskoy Lane, Moscow, 125047</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/0000-0002-8385-4356</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Блинов</surname><given-names>Д. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Blinov</surname><given-names>D. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Блинов Дмитрий Сергеевич, д-р мед. наук, руководитель отдела научных исследований и разработок</p><p>2-й Тверской-Ямской пер., д. 10, г. Москва, 125047</p><p>+7 (927) 197-14-22</p></bio><bio xml:lang="en"><p>Dmitry S. Blinov, Dr. of Sci. (Medicine), Head of Research and Development Department</p><p>10, 2nd Tverskoy-Yamskoy Lane, Moscow, 125047</p><p>+7 (927) 197-14-22 </p></bio><email xlink:type="simple">d.blinov@cmai.team</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-3508-7284</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сушков</surname><given-names>Е. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Sushkov</surname><given-names>E. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сушков Евгений Владимирович, заведующий отделением рентгенологии Центра амбулаторной онкологии</p><p>ул. Касаткина, д. 7, г. Москва, 129301</p></bio><bio xml:lang="en"><p>Evgenii V. Sushkov, Head of Radiology Unit, Oncology Department</p><p>7, Kasatkina str., Moscow, 129301</p></bio><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-8814-3369</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Дерябина</surname><given-names>О. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Deryabina</surname><given-names>O. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Дерябина Ольга Николаевна, канд. мед. наук, доцент кафедры онкологии Медицинского института </p><p>ул. Большевистская, д. 68, г. Саранск, 430005</p></bio><bio xml:lang="en"><p>Olga N. Deryabina, Cand. of Sci. (Medicine), Associate Professor, Oncology Department, Medical Institute</p><p>68, Bolshevistskaya str., Saransk, 430005</p></bio><xref ref-type="aff" rid="aff-4"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7515-2314</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Соколов</surname><given-names>А. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Sokolov</surname><given-names>A. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Соколов Алексей Ильясович, ассистент кафедры хирургии Медицинского института </p><p>ул. Красная, д. 40, г. Пенза, 440026</p></bio><bio xml:lang="en"><p>Aleksei I. Sokolov, Assistant Professor, Surgery Department, Medical Institute</p><p>40, Krasnaya str., Penza, 440026</p></bio><xref ref-type="aff" rid="aff-5"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Национальный центр онкологии репродуктивных органов Московского научного исследовательского онкологического института им. П.А. Герцена — филиала ФГБУ «Национальный медицинский исследовательский центр радиологии» Минздрава России</institution><country>Россия</country></aff><aff xml:lang="en"><institution>National Medical Research Radiological Center of the Ministry of Health of the Russian Federation</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>ООО «КэреМенторЭйАй», отдел научных исследований и разработок</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Care Mentor AI, Research and Development Department</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>ГБУЗ города Москвы «Городская клиническая больница № 40 Департамента здравоохранения города Москвы», Центр амбулаторной онкологии</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Moscow State Clinical Hospital No. 40, Department of Oncology</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-4"><aff xml:lang="ru"><institution>ФГБОУ ВО «Национальный исследовательский Мордовский государственный университет им. Н.П. Огарева»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Ogarev Mordovia State University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-5"><aff xml:lang="ru"><institution>ФГБОУ ВО «Пензенский государственный университет»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Penza State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2020</year></pub-date><pub-date pub-type="epub"><day>25</day><month>11</month><year>2020</year></pub-date><volume>11</volume><issue>3</issue><fpage>4</fpage><lpage>14</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Rozhkova N.I., Roitberg P.G., Varfolomeeva A.A., Mazo M.M., Dobrenkii A.N., Blinov D.S., Sushkov E.V., Deryabina O.N., Sokolov A.I., 2020</copyright-statement><copyright-year>2020</copyright-year><copyright-holder xml:lang="ru">Рожкова Н.И., Ройтберг П.Г., Варфоломеева А.А., Мазо М.Л., Добренький А.Н., Блинов Д.С., Сушков Е.В., Дерябина О.Н., Соколов А.И.</copyright-holder><copyright-holder xml:lang="en">Rozhkova N.I., Roitberg P.G., Varfolomeeva A.A., Mazo M.M., Dobrenkii A.N., Blinov D.S., Sushkov E.V., Deryabina O.N., Sokolov A.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://www.sechenovmedj.com/jour/article/view/227">https://www.sechenovmedj.com/jour/article/view/227</self-uri><abstract><p>Diagnostic efficiency of breast cancer screening remains one of the most important issues in oncology and radiology. Artificial intelligence technologies are widely used in clinical medicine to effectively solve a number of technological and diagnostic problems. The aim. To develop segmentation neural network model for breast plain radiographs analysis with subsequent study of its clinical effectiveness. Materials and methods. The artificial intelligence-based system was developed to analyze X-ray mammography, аnd included a segmentation neural network with the U-Net architecture, a classification neural architecture ResNet50 with outputting the result using gradient boosting. 15486 X-ray cases were used for training, estimation of diagnostic accuracy and validation of the developed segmental model. All cases were labeled in specially developed software environment LabelCMAITech. The segmentation accuracy was determined by Intersection over Union (IoU) similarity coefficient, the probability of malignancy was calculated using the binary classification metrics. Results. The developed system is represented by a segmentation model based on neural network architecture. The model allows, with high accuracy of 0.8176 and higher, at threshold values on the output neurons of the network of 0.1 and 0.15, to localize X-ray findings that have diagnostic value for determining the likelihood of the presence of breast cancer signs in an X-ray mammographic study — focus, architecture distortion, local asymmetry, calcifications. When comparing the results of machine segmentation and marking of images by a radiologist, it was found that the model is not inferior to the doctor in the accuracy of determining the formations, extra-focal calcifications and intraglandular lymph nodes. Conclusion. The results of this study allow considering the model as an intelligent assistant to a radiologist in the analysis of screening mammographic cases.</p></abstract><trans-abstract xml:lang="ru"><p>Повышение диагностической эффективности скрининга рака молочной железы (РМЖ) остается одной из наиболее актуальных проблем в онкологии и лучевой диагностике. Технологии искусственного интеллекта широко используются в клинической медицине для эффективного решения ряда технологических и диагностических задач.Цель. Разработать и изучить диагностическую эффективность сегментационной нейросетевой модели детекции патологических изменений молочных желез на цифровых рентгеновских снимках.Материалы и методы. Интеллектуальная система была разработана для описания маммографических исследований и включала в себя сегментационную нейронную сеть с архитектурой U-Net, классификационную нейронную архитектуру ResNet50 с выводом результата при помощи градиентного бустинга. Для обучения, определения диагностической точности и валидации разрабатываемой сегментационной диагностической модели использовали 15 486 рентгеновских исследований, размеченных в специально разработанной программной среде LabelCMAITech. Точность сегментации определяли по коэффициенту сходства, вероятность злокачественности находок вычисляли с помощью метрик бинарной классификации.Результаты. Разработана система, представленная сегментационной моделью на основе нейросетевой архитектуры. Модель позволяет с высокой точностью 0,8176 и выше при пороговых значениях на выходных нейронах сети 0,1 и 0,15 локализовать рентгенологические находки, имеющие диагностическое значение для определения вероятности наличия признаков РМЖ в рентгеновском маммографическом исследовании: образования, локальную перестройку структуры, локальную асимметрию, кальцинаты. При сравнении результатов машинной сегментации и разметки изображений рентгенологом установлено, что модель не уступает врачу в точности определения образований, внеочаговых кальцинатов и внутрижелезистых лимфатических узлов.Заключение. Результаты изучения эффективности работы системы позволяют рассматривать ее в качестве интеллектуального диагностического ассистента врача-рентгенолога при анализе скрининговых маммографических исследований.</p><p> </p></trans-abstract><kwd-group xml:lang="ru"><kwd>рак молочной железы</kwd><kwd>скрининг</kwd><kwd>искусственные нейронные сети</kwd><kwd>диагностические находки</kwd><kwd>сегментация</kwd></kwd-group><kwd-group xml:lang="en"><kwd>breast cancer</kwd><kwd>screening</kwd><kwd>artificial neural networks</kwd><kwd>diagnostic findings</kwd><kwd>segmentation</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">Siegel R.L., Miller K.D., Jemal A. Cancer statistics, 2019. CA A Cancer J Clin. 2019; 69: 7-34. https://doi.org/10.3322/caac.21551</mixed-citation><mixed-citation xml:lang="en">Siegel R.L., Miller K.D., Jemal A. Cancer statistics, 2019. CA A Cancer J Clin. 2019; 69: 7-34. https://doi.org/10.3322/caac.21551</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Breast cancer. [web resource] URL https://www.who.int/cancer/prevention/diagnosis-screening/breast-cancer/en/ free (accessed September 16, 2020).</mixed-citation><mixed-citation xml:lang="en">Breast cancer. [web resource] URL https://www.who.int/cancer/prevention/diagnosis-screening/breast-cancer/en/ free (accessed September 16, 2020).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">DeSantis C.E., Ma J., Gaudet M.M., Newman L.A., Miller K.D., Goding Sauer A., Jemal A., Siegel, R.L. Breast cancer statistics, 2019. CA A Cancer J Clin. 2019; 69: 438-451. https://doi.org/10.3322/caac.21583</mixed-citation><mixed-citation xml:lang="en">DeSantis C.E., Ma J., Gaudet M.M., Newman L.A., Miller K.D., Goding Sauer A., Jemal A., Siegel, R.L. Breast cancer statistics, 2019. CA A Cancer J Clin. 2019; 69: 438-451. https://doi.org/10.3322/caac.21583</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Li Y., Chen H., Cao L., Ma J. A survey of computer-aided detection of breast cancer with mammography. J Health Med Inf. 2016; 4: 238. https://doi.org/10.4172/2157-7420.1000238</mixed-citation><mixed-citation xml:lang="en">Li Y., Chen H., Cao L., Ma J. A survey of computer-aided detection of breast cancer with mammography. J Health Med Inf. 2016; 4: 238. https://doi.org/10.4172/2157-7420.1000238</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Welch H.G., Passow H.J. Quantifying the benefits and harms of screening mammography. JAMA Intern Med. 2014; 3: 448-454. https://doi.org/10.1001/jamainternmed.2013.13635</mixed-citation><mixed-citation xml:lang="en">Welch H.G., Passow H.J. Quantifying the benefits and harms of screening mammography. JAMA Intern Med. 2014; 3: 448-454. https://doi.org/10.1001/jamainternmed.2013.13635</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Curtis C., Frayne R., Fear E. Using X-Ray Mammograms to Assist in Microwave Breast Image Interpretation. Int. J. Biomed. Imag. 2012; 2012: 235380. https://doi.org/10.1155/2012/235380</mixed-citation><mixed-citation xml:lang="en">Curtis C., Frayne R., Fear E.  Using X-Ray Mammograms to Assist in Microwave Breast Image Interpretation. Int. J. Biomed. Imag. 2012; 2012: 235380. https://doi.org/10.1155/2012/235380</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Abdelhafiz D., Yang C., Ammar R. et al. Deep convolutional neural networks for mammography: advances, challenges and applications. BMC Bioinformatics. 2019; 20: 281 https://doi.org/10.1186/s12859-019-2823-4</mixed-citation><mixed-citation xml:lang="en">Abdelhafiz D., Yang C., Ammar R. et al. Deep convolutional neural networks for mammography: advances, challenges and applications. BMC Bioinformatics. 2019; 20: 281 https://doi.org/10.1186/s12859-019-2823-4</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">American College of Radiology. The ACR breast imaging reporting and data system (BI-RADS) [web resource]. November 11, 2003. URL: http://www.Acr. org/departments/stand_accred/birads/contents.html. free (accessed February 27, 2020).</mixed-citation><mixed-citation xml:lang="en">American  College  of  Radiology.  The  ACR  breast  imaging   reporting   and   data   system   (BI-RADS)   [web   resource].  November  11,  2003.  URL:  http://www.Acr. org/departments/stand_accred/birads/contents.html. free (accessed February 27, 2020).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Arxiv. Lib. 2015; 15: 1-8. https://doi.org/10.1007/978-3-319-24574-4_28</mixed-citation><mixed-citation xml:lang="en">Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Arxiv. Lib. 2015; 15: 1-8. https://doi.org/10.1007/978-3-319-24574-4_28</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">He K., Zhang X., Ren S. Deep Residual Learning for Image Recognition. IEEE Comput. Vis. Pattern. Recognit. 2016; 10: 1-4. https://doi.org/10.1109/cvpr.2016.90</mixed-citation><mixed-citation xml:lang="en">He K., Zhang X., Ren S. Deep Residual Learning for Image Recognition. IEEE Comput. Vis. Pattern. Recognit. 2016; 10: 1-4. https://doi.org/10.1109/cvpr.2016.90</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Natekin A., Knoll A. Gradient Boosting Machines, A Tutorial. Frontiers in Neurorobotics. 2013; 7: 21. https://doi.org/10.3389/fnbot.2013.00021</mixed-citation><mixed-citation xml:lang="en">Natekin A., Knoll A. Gradient Boosting Machines, A Tutorial. Frontiers in Neurorobotics. 2013; 7: 21. https://doi.org/10.3389/fnbot.2013.00021</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Wu J., Mahfouz M. R. Robust X-ray image segmentation by spectral clustering and active shape model. J Med. Imag. 2016; 3: 034005. https://doi.org/10.1117/1.jmi.3.3.034005</mixed-citation><mixed-citation xml:lang="en">Wu J., Mahfouz M. R. Robust X-ray image segmentation by spectral clustering and active shape model. J Med. Imag. 2016; 3: 034005. https://doi.org/10.1117/1.jmi.3.3.034005</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>
