<?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">rentrad</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник рентгенологии и радиологии</journal-title><trans-title-group xml:lang="en"><trans-title>Journal of radiology and nuclear medicine</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">0042-4676</issn><issn pub-type="epub">2619-0478</issn><publisher><publisher-name>Limited Liability Company "LUCHEVAYA DIAGNOSTIKA", Russian Association of Radiologists</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.20862/0042-4676-2024-105-1-20-28</article-id><article-id custom-type="elpub" pub-id-type="custom">rentrad-854</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 СТАТЬИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>ORIGINAL RESEARCH</subject></subj-group></article-categories><title-group><article-title>Оценка качества работы искусственного интеллекта в выявлении дегенеративных заболеваний пояснично-крестцового отдела позвоночника</article-title><trans-title-group xml:lang="en"><trans-title>Evaluation of Artificial Intelligence Effectiveness in Detection of Lumbosacral Spine Degenerative Diseases</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-5994-0468</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. В.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Нуднов Николай Васильевич, д. м. н., профессор, зам. директора по научной работе, заведующий научно-исследовательским отделом комплексной диагностики и радиотерапии</p><p>ул. Профсоюзная, 86, стр. 1, Москва, 117485</p></bio><bio xml:lang="en"><p>Nikolay В. Nudnov, Dr. Med. Sc., Professor, Deputy Director for Scientific Work, Head of Research Department of Complex Diagnostics and Radiotherapy</p><p>ul. Profsoyuznaya, 86, str. 1, Moscow, 117485</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Коробов</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Korobov</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Коробов Андрей Владимирович, директор</p><p>ул. Фридриха Энгельса, 58А, Воронеж, 394018</p></bio><bio xml:lang="en"><p>Andrey V. Korobov, Director</p><p>ul. Fridrikha Engelsa, 58А, Voronezh, 394018</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0002-6072-8143</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Скачков</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Skachkov</surname><given-names>А. А.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Скачков Артур Андреевич, специалист по машинному обучению</p><p>ул. Металлургов, вл. 1, лит. А, Липецк, 398017</p></bio><bio xml:lang="en"><p>Artur А. Skachkov, Machine Learning Specialist</p><p>ul. Metallurgov, 1, lit. А, Lipetsk, 398017</p></bio><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кульнева</surname><given-names>Т. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Kulneva</surname><given-names>T. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Кульнева Таисия Владимировна, зам. директора по экспертной работе в области медицинской визуализации</p><p>ул. Фридриха Энгельса, 58А, Воронеж, 394018</p></bio><bio xml:lang="en"><p>Taisia V. Kulneva, Deputy Director for Expert Work in Medical Imaging</p><p>ul. Fridrikha Engelsa, 58А, Voronezh, 394018</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Шерстобоев</surname><given-names>В. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Sherstoboev</surname><given-names>V. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Шерстобоев Владислав Васильевич, генеральный директор</p><p>ул. Металлургов, 1, Липецк, 398017</p></bio><bio xml:lang="en"><p>Vladislav V. Sherstoboev, Director General</p><p>ul. Metallurgov, 1, Lipetsk, 398017</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/0000-0002-8421-3411</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Титова</surname><given-names>Л. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Titova</surname><given-names>L. А.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Титова Лилия Александровна, д. м. н., доцент, заведующая кафедрой инструментальной диагностики</p><p>ул. Студенческая, 10, Воронеж, 394036</p></bio><bio xml:lang="en"><p>Lilia А. Titova, Dr. Med. Sc., Associate Professor, Chief of Chair of Instrumental Diagnostics</p><p>ul. Studencheskaya, 10, Voronezh, 394036</p></bio><xref ref-type="aff" rid="aff-5"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Русаков</surname><given-names>А. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Rusakov</surname><given-names>A. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Русаков Андрей Сергеевич, основатель и главный исполнительный директор</p><p>6 St Johns Ln, New York, NY 10013</p></bio><bio xml:lang="en"><p>Andrey S. Rusakov, Founder and Chief Executive Officer</p><p>6 St Johns Ln, New York, NY 10013</p></bio><xref ref-type="aff" rid="aff-6"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тумко</surname><given-names>В. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Tumko</surname><given-names>V. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Тумко Владислав Владимирович, главный операционный директор</p><p>6 St Johns Ln, New York, NY 10013</p></bio><bio xml:lang="en"><p>Vladislav V. Tumko, Chief Operating Officer</p><p>6 St Johns Ln, New York, NY 10013</p></bio><xref ref-type="aff" rid="aff-6"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сарбаев</surname><given-names>Р. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Sarbaev</surname><given-names>R. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сарбаев Руслан Сергеевич, генеральный директор</p><p>ул. Декабристов, 33, Чебоксары, 428022, Чувашская Республика</p></bio><bio xml:lang="en"><p>Ruslan S. Sarbaev, Director General</p><p>ul. Dekabristov, 33, Cheboksary, 428022</p></bio><xref ref-type="aff" rid="aff-7"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Успенская</surname><given-names>Н. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Uspenskaya</surname><given-names>N. А.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Успенская Наталья Александровна, руководитель команды компьютерного зрения</p><p>6 St Johns Ln, New York, NY 10013</p></bio><bio xml:lang="en"><p>Natalia А. Uspenskaya, Head of Computer Vision Team</p><p>6 St Johns Ln, New York, NY 10013</p></bio><xref ref-type="aff" rid="aff-6"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Андриенко</surname><given-names>Е. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Andrienko</surname><given-names>E. А.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Андриенко Елизавета Андреевна, специалист общего отдела</p><p>ул. Фридриха Энгельса, 58А, Воронеж, 394018</p></bio><bio xml:lang="en"><p>Elizaveta А. Andrienko, Specialist, General Department</p><p>ul. Fridrikha Engelsa, 58А, Voronezh, 394018</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0007-0407-0953</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Иванников</surname><given-names>М. Е.</given-names></name><name name-style="western" xml:lang="en"><surname>Ivannikov</surname><given-names>M. Е.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Иванников Михаил Евгеньевич, клинический ординатор по специальности «рентгенология»</p><p>ул. Профсоюзная, 86, стр. 1, Москва, 117485</p></bio><bio xml:lang="en"><p>Mikhail Е. Ivannikov, Clinical Resident in Radiology</p><p>ul. Profsoyuznaya, 86, str. 1, Moscow, 117485</p></bio><email xlink:type="simple">ivannikovmichail@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><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</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>АНО ДПО «Институт Эксперт»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Expert Institute</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>ООО «Объединенное IT пространство»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>United IT Space LLC</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-4"><aff xml:lang="ru"><institution>Группа компаний «Эксперт»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>“Expert” Group of Companies</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-5"><aff xml:lang="ru"><institution>ФГБОУ ВО «Воронежский государственный медицинский университет им. Н.Н. Бурденко» Минздрава России</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Burdenko Voronezh State Medical University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-6"><aff xml:lang="ru"><institution>Remedy Logic</institution><country>Соединённые Штаты Америки</country></aff><aff xml:lang="en"><institution>Remedy Logic</institution><country>United States</country></aff></aff-alternatives><aff-alternatives id="aff-7"><aff xml:lang="ru"><institution>ООО «Системы поддержки принятий решений»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Decision Support Systems LLC</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>19</day><month>06</month><year>2024</year></pub-date><volume>105</volume><issue>1</issue><fpage>20</fpage><lpage>28</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Нуднов Н.В., Коробов А.В., Скачков А.А., Кульнева Т.В., Шерстобоев В.В., Титова Л.А., Русаков А.С., Тумко В.В., Сарбаев Р.С., Успенская Н.А., Андриенко Е.А., Иванников М.Е., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Нуднов Н.В., Коробов А.В., Скачков А.А., Кульнева Т.В., Шерстобоев В.В., Титова Л.А., Русаков А.С., Тумко В.В., Сарбаев Р.С., Успенская Н.А., Андриенко Е.А., Иванников М.Е.</copyright-holder><copyright-holder xml:lang="en">Nudnov N.В., Korobov A.V., Skachkov А.А., Kulneva T.V., Sherstoboev V.V., Titova L.А., Rusakov A.S., Tumko V.V., Sarbaev R.S., Uspenskaya N.А., Andrienko E.А., Ivannikov M.Е.</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.russianradiology.ru/jour/article/view/854">https://www.russianradiology.ru/jour/article/view/854</self-uri><abstract><p>Цель: проведение сравнительной оценки выходных данных комплекса обученных моделей сверточных нейронных сетей (convolutional neural network, CNN) и интерпретации патологических изменений поясничного отдела позвоночника врачами-рентгенологами при проведении магнитно-резонансной томографии.Материал и методы. Собрано более 12 тыс. анонимизированных архивов для формирования обучающего и тестового наборов данных нейросети среди пациентов старше 18 лет. Каждый архив состоял из набора программ в двух плоскостях, содержащих последовательности Т2-TSE, Т1-TSE и Т2 с программой жироподавления. Далее на отобранных исследованиях выполняли разметку в два этапа, заключающуюся непосредственно в ручной разметке и ее проверке специалистами. Обучение CNN проводили отдельно для анализа нормы, качественного определения патологических изменений и количественного анализа. Проверку точности моделей путем сравнительного анализа протоколов пяти врачей-рентгенологов и выходных данных моделей CNN осуществляли в два этапа. На первом, промежуточном этапе оценивали точность работы нейросетей в выявлении выбуханий, протрузий и экструзий дисков, стеноза позвоночно- го канала, латеральных стенозов, фораминальных стенозов, спондилолистеза и артроза межпозвонковых суставов. На итоговом этапе помимо патологий, рассматриваемых на промежуточном этапе, проверяли точность выявления дегенеративных изменений замыкательных пластин, синовита межпозвонковых суставов, дегенерации дисков, остеофитов, переходных позвонков, гипертрофии желтых связок и грыжи Шморля. Эталонное значение для всех рассматриваемых в данной работе патологических изменений определено большинством голосов, и в случае разногласий решение принимал внешний рентгенолог. Затем интерпретации рентгенологов были сопоставлены с интерпретацией обученной модели.Результаты. Искусственный интеллект (ИИ) продемонстрировал сопоставимые значения чувствительности и специфичности в сравнении с эталонным результатом в группе опытных врачей-рентгенологов для бинарной классификации (наличие/отсутствие) наличия отдельных дегенеративных изменений пояснично-крестцового отдела позвоночника. Для экструзий чувствительность и специфичность результатов ИИ составили 0,88 и 0,97 соответственно, для протрузий – 0,81 и 0,94, для центрального стеноза – 0,87 и 0,98, для латерального стеноза – 0,83 и 0,85, для фораминального стеноза – 0,92 и 0,84, для артроза – 0,85 и 0,50, для дегенерации замыкательных пластин – 0,73 и 0,96, для синовита межпозвонковых суставов – 0,85 и 0,84, для дегенерации дисков – 0,91 и 0,88, для остеофитов – 0,93 и 0,72, для переходных позвонков – 1,0 и 1,0, для спондилолистезов – 0,8 и 1,0, для гипертрофии желтых связок – 0,67 и 0,99, для грыж Шморля – 0,75 и 1,0. Точность количественных характеристик размеров протрузий и экструзий пояснично-крестцового отдела позвоночника показала неудовлетворительные результаты, однако улучшение качества определения данных параметров планируется в последующих работах.Заключение. Модели ИИ продемонстрировали сопоставимые со специалистами-рентгенологами результаты в обнаружении дегенеративных изменений пояснично-крестцового отдела позвоночника. Последовательное улучшение моделей CNN на основе сравнительной оценки с результатами работы врачей-рентгенологов повышает чувствительность и специфичность выявления патологических изменений.</p></abstract><trans-abstract xml:lang="en"><p>Objective: comparative evaluation of output data of a set of trained convolutional neural network (CNN) models and interpretation of pathological changes in lumbar spine by radiologists during magnetic resonance imaging.Material and methods. More than 12,000 anonymized archives were collected to generate training and test neural network datasets from patients aged over 18 years. Each archive consisted of a set of programs in two planes containing T2-TSE, T1-TSE and T2 sequences with fat suppression program. Subsequently, the selected studies were tagged in two steps, directly consisting of manual tagging and its validation by experts. CNN training was performed separately for normal analysis, qualitative detection of individual pathological changes, and quantitative analysis. The accuracy of the models was verified by comparing the protocols of five radiologists and the output of CNN models in two steps. The first, intermediate stage evaluated the accuracy of the neural networks in detecting disc bulges, protrusions and extrusions, spinal canal stenosis, lateral stenosis, foraminal stenosis, spondylolisthesis and facet joint arthrosis. In the final stage, in addition to the pathologies considered in the intermediate one, the accuracy of detecting degenerative changes of the occlusive plates, synovitis of intervertebral joints, intervertebral discs degeneration, osteophytes, transitional vertebrae, hypertrophy of yellow ligaments and Schmorl’s hernia was tested. The reference value for all pathological changes considered in this paper was determined by majority vote and, in case of disagreement, by an external radiologist. The radiologists’ interpretations were then compared with those of the trained model.Results. The artificial intelligence (AI) showed comparable sensitivity and specificity values compared to the reference result in a group of experienced radiologists for binary classification (presence/absence) of individual lumbosacral spine degenerative changes. The sensitivity and specificity of AI results were 0.88 and 0.97 for extrusions, 0.81 and 0.94 for protrusions, 0.87 and 0.98 for central stenosis, 0.83 and 0.85 for lateral stenosis, 0.92 and 0.84 for foraminal stenosis, 0.85 and 0.5 for osteoarthritis, 0.73 and 0.96 for occlusive plates degeneration, 0.85 and 0.84 for intervertebral joint synovitis, 0.91 and 0.88 for osteophytes, 0.93 and 0.72 for intervertebral disc degeneration, 1.0 and 1.0 for transitional vertebrae, 0.8 and 1.0 for spondylolisthesis, 0.67 and 0.99 for yellow ligament hypertrophy, and 0.75 and 1.0 for Schmorl’s hernia, respectively. The accuracy of quantitative size characterization of lumbosacral spine protrusions and extrusions showed unsatisfactory results, but improvements in the quality of determination of these parameters are planned in future work.Conclusion. AI models showed comparable performance to expert radiologists in detecting lumbosacral spine degenerative changes. Consistent improvement of CNN models based on comparative evaluation with radiologists improves the sensitivity and specificity of pathologic change detection.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>магнитно-резонансная томография</kwd><kwd>искусственный интеллект</kwd><kwd>нейронная сеть</kwd><kwd>сверточная нейронная сеть</kwd><kwd>глубокое обучение</kwd><kwd>программное обеспечение в медицине</kwd></kwd-group><kwd-group xml:lang="en"><kwd>magnetic resonance imaging</kwd><kwd>artificial intelligence</kwd><kwd>neural network</kwd><kwd>convolutional neural network</kwd><kwd>deep learning</kwd><kwd>software in medicine</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">Li H, Luo H, Huan W, et al. Automatic lumbar spinal MRI image segmentation with a multi-scale attention network. Neural Comput Appl. 2021; 33(18): 11589–602. https://doi.org/10.1007/s00521-021-05856-4.</mixed-citation><mixed-citation xml:lang="en">Li H, Luo H, Huan W, et al. Automatic lumbar spinal MRI image segmentation with a multi-scale attention network. Neural Comput Appl. 2021; 33(18): 11589–602. https://doi.org/10.1007/s00521-021-05856-4.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Forsberg D, Sjöblom E, Sunshine JL. Detection and labeling of vertebrae in mr images using deep learning with clinical annotations as training data. J Digit Imaging. 2017; 30(4): 406–12. https://doi.org/10.1007/s10278-017-9945-x.</mixed-citation><mixed-citation xml:lang="en">Forsberg D, Sjöblom E, Sunshine JL. Detection and labeling of vertebrae in mr images using deep learning with clinical annotations as training data. J Digit Imaging. 2017; 30(4): 406–12. https://doi.org/10.1007/s10278-017-9945-x.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Zhou Y, Liu Y, Chen Q, et al. Automatic lumbar MRI detection and identification based on deep learning. J Digit Imaging. 2019; 32(3): 513–20. https://doi.org/10.1007/s10278-018-0130-7.</mixed-citation><mixed-citation xml:lang="en">Zhou Y, Liu Y, Chen Q, et al. Automatic lumbar MRI detection and identification based on deep learning. J Digit Imaging. 2019; 32(3): 513–20. https://doi.org/10.1007/s10278-018-0130-7.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Natalia F, Young JC, Afriliana N, et al. Automated selection of mid-height intervertebral disc slice in traverse lumbar spine MRI using a combination of deep learning feature and machine learning classifier. PLoS One. 2022; 17(1): e0261659. https://doi.org/10.1371/journal.pone.0261659.</mixed-citation><mixed-citation xml:lang="en">Natalia F, Young JC, Afriliana N, et al. Automated selection of mid-height intervertebral disc slice in traverse lumbar spine MRI using a combination of deep learning feature and machine learning classifier. PLoS One. 2022; 17(1): e0261659. https://doi.org/10.1371/journal.pone.0261659.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Wang X, Zhai S, Niu Y. Automatic vertebrae localization and identification by combining deep SSAE contextual features and structured regression forest. J Digit Imaging. 2019; 32(2): 336–48. https://doi.org/10.1007/s10278-018-0140-5.</mixed-citation><mixed-citation xml:lang="en">Wang X, Zhai S, Niu Y. Automatic vertebrae localization and identification by combining deep SSAE contextual features and structured regression forest. J Digit Imaging. 2019; 32(2): 336–48. https://doi.org/10.1007/s10278-018-0140-5.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Lewandrowski KU, Muraleedharan N, Eddy SA, et al. Feasibility of deep learning algorithms for reporting in routine spine magnetic resonance imaging. Int J Spine Surg. 2020; 14(s3): S86–97. https://doi.org/10.14444/7131.</mixed-citation><mixed-citation xml:lang="en">Lewandrowski KU, Muraleedharan N, Eddy SA, et al. Feasibility of deep learning algorithms for reporting in routine spine magnetic resonance imaging. Int J Spine Surg. 2020; 14(s3): S86–97. https://doi.org/10.14444/7131.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Hallinan JTPD, Zhu L, Yang K, et al. Deep learning model for automated detection and classification of central canal, lateral recess, and neural foraminal stenosis at lumbar spine MRI. Radiology. 2021; 300(1): 130–8. https://doi.org/10.1148/radiol.2021204289.</mixed-citation><mixed-citation xml:lang="en">Hallinan JTPD, Zhu L, Yang K, et al. Deep learning model for automated detection and classification of central canal, lateral recess, and neural foraminal stenosis at lumbar spine MRI. Radiology. 2021; 300(1): 130–8. https://doi.org/10.1148/radiol.2021204289.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Jamaludin A, Lootus M, Kadir T, et al. ISSLS Prize in Bioengineering Science 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist. Eur Spine J. 2017; 26(5): 1374–83. https://doi.org/10.1007/s00586-017-4956-3.</mixed-citation><mixed-citation xml:lang="en">Jamaludin A, Lootus M, Kadir T, et al. ISSLS Prize in Bioengineering Science 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist. Eur Spine J. 2017; 26(5): 1374–83. https://doi.org/10.1007/s00586-017-4956-3.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Lehnen NC, Haase R, Faber J, et al. Detection of degenerative changes on mr images of the lumbar spine with a convolutional neural network: a feasibility study. Diagnostics. 2021; 11(5): 902. https://doi.org/10.3390/diagnostics11050902.</mixed-citation><mixed-citation xml:lang="en">Lehnen NC, Haase R, Faber J, et al. Detection of degenerative changes on mr images of the lumbar spine with a convolutional neural network: a feasibility study. Diagnostics. 2021; 11(5): 902. https://doi.org/10.3390/diagnostics11050902.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Tsai JY, Hung IYJ, Guo YL, et al. Lumbar disc herniation automatic detection in magnetic resonance imaging based on deep learning. Front Bioeng Biotechnol. 2021; 9: 708137. https://doi.org/10.3389/fbioe.2021.708137.</mixed-citation><mixed-citation xml:lang="en">Tsai JY, Hung IYJ, Guo YL, et al. Lumbar disc herniation automatic detection in magnetic resonance imaging based on deep learning. Front Bioeng Biotechnol. 2021; 9: 708137. https://doi.org/10.3389/fbioe.2021.708137.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Han Z, Wei B, Leung S, et al. Automated pathogenesis-based diagnosis of lumbar neural foraminal stenosis via deep multiscale multitask learning. Neuroinformatics. 2018; 16(3-4): 325–37. https://doi.org/10.1007/s12021-018-9365-1.</mixed-citation><mixed-citation xml:lang="en">Han Z, Wei B, Leung S, et al. Automated pathogenesis-based diagnosis of lumbar neural foraminal stenosis via deep multiscale multitask learning. Neuroinformatics. 2018; 16(3-4): 325–37. https://doi.org/10.1007/s12021-018-9365-1.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Galbusera F, Casaroli G, Bassani T. Artificial intelligence and machine learning in spine research. JOR Spine. 2019; 2(1): e1044. https://doi.org/10.1002/jsp2.1044.</mixed-citation><mixed-citation xml:lang="en">Galbusera F, Casaroli G, Bassani T. Artificial intelligence and machine learning in spine research. JOR Spine. 2019; 2(1): e1044. https://doi.org/10.1002/jsp2.1044.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Azimi P, Yazdanian T, Benzel EC, et al. A review on the use of artificial intelligence in spinal diseases. Asian Spine J. 2020; 14(4): 543–71. https://doi.org/10.31616/asj.2020.0147.</mixed-citation><mixed-citation xml:lang="en">Azimi P, Yazdanian T, Benzel EC, et al. A review on the use of artificial intelligence in spinal diseases. Asian Spine J. 2020; 14(4): 543–71. https://doi.org/10.31616/asj.2020.0147.</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>
