<?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">sibmed</journal-id><journal-title-group><journal-title xml:lang="ru">Сибирский научный медицинский журнал</journal-title><trans-title-group xml:lang="en"><trans-title>Сибирский научный медицинский журнал</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2410-2512</issn><issn pub-type="epub">2410-2520</issn><publisher><publisher-name>ИЦиГ СО РАН</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.18699/SSMJ20240111</article-id><article-id custom-type="elpub" pub-id-type="custom">sibmed-1394</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>Статьи</subject></subj-group></article-categories><title-group><article-title>Применение алгоритма компьютерного зрения для определения очагов демиелинизации при рассеянном склерозе на МРТ-изображениях</article-title><trans-title-group xml:lang="en"><trans-title>Application of a computer vision algorithm to identify foci of demyelination in multiple sclerosis on MRI images</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-8931-9848</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тучинов</surname><given-names>Б. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Tuchinov</surname><given-names>B. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Тучинов Баир Николаевич </p><p>630090, г. Новосибирск, ул. Пирогова, 1;630090, г. Новосибирск, ул. Институтская, 3а</p></bio><bio xml:lang="en"><p>Bair N. Tuchinov </p><p>630090, Novosibirsk, Pirogova st., 1;630090, Novosibirsk, Institutskaya st., 3a</p></bio><email xlink:type="simple">bairts@nsu.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/0009-0007-1128-8053</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Суворов</surname><given-names>В.</given-names></name><name name-style="western" xml:lang="en"><surname>Suvorov</surname><given-names>V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Суворов Виктор </p><p>630090, г. Новосибирск, ул. Пирогова, 1;630090, г. Новосибирск, ул. Институтская, 3а</p></bio><bio xml:lang="en"><p>Victor Suvorov </p><p>630090, Novosibirsk, Pirogova st., 1;630090, Novosibirsk, Institutskaya st., 3a</p></bio><email xlink:type="simple">vic.suvorov@yahoo.com</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>Моторин</surname><given-names>К. О.</given-names></name><name name-style="western" xml:lang="en"><surname>Motorin</surname><given-names>K. O.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Моторин Кирилл Олегович </p><p>630090, г. Новосибирск, ул. Пирогова, 1</p></bio><bio xml:lang="en"><p>Kirill O. Motorin </p><p>630090, Novosibirsk, Pirogova st., 1</p></bio><email xlink:type="simple">k.motorin@g.nsu.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/0000-0001-6976-1885</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Павловский</surname><given-names>Е. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Pavlovsky</surname><given-names>E. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Павловский Евгений Николаевич, к.ф.-м.н.  </p><p>630090, г. Новосибирск, ул. Пирогова, 1;630090, г. Новосибирск, ул. Институтская, 3а</p></bio><bio xml:lang="en"><p>Evgeny N. Pavlovskiy, candidate of physical and mathematical sciences </p><p>630090, Novosibirsk, Pirogova st., 1;630090, Novosibirsk, Institutskaya st., 3a</p></bio><email xlink:type="simple">pavlovskiy@post.nsu.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-1838-8130</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Василькив</surname><given-names>Л. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Vasilkiv</surname><given-names>L. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Василькив Любовь Михайловна, к.м.н. </p><p>630090, г. Новосибирск, ул. Пирогова, 1;630090, г. Новосибирск, ул. Институтская, 3а</p></bio><bio xml:lang="en"><p>Liubov M. Vasilkiv, candidate of medical sciences </p><p>630090, Novosibirsk, Pirogova st., 1;630090, Novosibirsk, Institutskaya st., 3a</p></bio><email xlink:type="simple">vasilkiv@tomo.nsc.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/0000-0002-7959-5160</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Станкевич</surname><given-names>Ю. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Stankevich</surname><given-names>Yu. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Станкевич Юлия Александровна, к.м.н. </p><p>630090, г. Новосибирск, ул. Пирогова, 1;630090, г. Новосибирск, ул. Институтская, 3а</p></bio><bio xml:lang="en"><p>Yuliya A. Stankevich, candidate of medical sciences </p><p>630090, Novosibirsk, Pirogova st., 1;630090, Novosibirsk, Institutskaya st., 3a</p></bio><email xlink:type="simple">stankevich@tomo.nsc.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/0000-0002-1277-4113</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тулупов</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Tulupov</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Тулупов Андрей Александрович, д.м.н., проф., чл.-корр. РАН </p><p>630090, г. Новосибирск, ул. Пирогова, 1;630090, г. Новосибирск, ул. Институтская, 3а</p></bio><bio xml:lang="en"><p>Andrey A. Tulupov, doctor of medical sciences, professor, corresponding member of the RAS </p><p>630090, Novosibirsk, Pirogova st., 1;630090, Novosibirsk, Institutskaya st., 3a</p></bio><email xlink:type="simple">taa@tomo.nsc.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Новосибирский государственный университет;&#13;
Институт «Международный томографический центр» СО РАН</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Novosibirsk State University;&#13;
International Tomography Center of SB RAS</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Новосибирский государственный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Novosibirsk State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>07</day><month>03</month><year>2024</year></pub-date><volume>44</volume><issue>1</issue><fpage>107</fpage><lpage>115</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Тучинов Б.Н., Суворов В., Моторин К.О., Павловский Е.Н., Василькив Л.М., Станкевич Ю.А., Тулупов А.А., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Тучинов Б.Н., Суворов В., Моторин К.О., Павловский Е.Н., Василькив Л.М., Станкевич Ю.А., Тулупов А.А.</copyright-holder><copyright-holder xml:lang="en">Tuchinov B.N., Suvorov V., Motorin K.O., Pavlovsky E.N., Vasilkiv L.M., Stankevich Y.A., Tulupov A.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://sibmed.elpub.ru/jour/article/view/1394">https://sibmed.elpub.ru/jour/article/view/1394</self-uri><abstract><p>Исследование направлено на анализ современных алгоритмов для диагностики поражений при рассеянном склерозе на МРТ-изображениях. Рассеянный склероз, тяжелое заболевание центральной нервной системы, занимает первое место среди причин инвалидности у пациентов молодого трудоспособного возраста. В связи с развитием технологий компьютерного зрения и машинного обучения растет актуальность применения данных технологий для медицинской диагностики. Такие подходы необходимы для эффективной разработки и внедрения диагностических систем с использованием искусственного интеллекта. Материал и методы. В статье представлены особенности диагностики рассеянного склероза на МРТ-изображениях, существующие наборы данных: ISBI-2015, MSSEG-2016, MSSEG-2021; существующие алгоритмы и модели сегментации поражений: U-Net, nnU-Net, TransUnet, TransBTS, UNETR, Swin UNETR. Результаты и их обсуждение. Проведено обучение и сравнение архитектур и моделей nnU-Net, UNETR, Swin UNETR на ISBI-2015 c различными параметрами и функциями потерь, использованы четыре последовательности МРТ: Т2-взвешенное изображение, T2-FLAIR, PD, MPRAGE. Сегментация поражений одобрена тремя аттестованными опытными нейрорадиологами. Заключение. Описанные в статье подходы, включая процессы обработки данных, обучения моделей, анализ результатов, были сосредоточены на выборе и разработке высококачественных алгоритмов компьютерного зрения для определения поражений при рассеянном склерозе на МРТ-изображениях. Выявление и сегментация очагов демиелинизации является необходимым этапом для диагностики заболевания, а также для расчета и интерпретации более значимых показателей тяжести и прогрессирования заболевания.</p></abstract><trans-abstract xml:lang="en"><p>The research was aimed at analyzing modern algorithms for diagnosing lesions in multiple sclerosis on MRI images. Multiple sclerosis is a severe disease of the central nervous system and ranks first among the causes of disability in patients of young working age. In connection with the development of computer vision and machine learning technologies, the relevance of using these technologies for medical diagnostics is growing. Such approaches are necessary for the effective development and implementation of diagnostic systems using artificial intelligence. Modern algorithms and models for lesion segmentation were selected and implemented. Material and methods. The paper presents CV features of diagnosing multiple sclerosis on MRI images, existing data sets: ISBI-2015, MSSEG-2016, MSSEG-2021; existing algorithms and models for lesion segmentation: U-Net, nnU-Net, TransUnet, TransBTS, UNETR, Swin UNETR. Results and discussion. The architectures and models of nnU-Net, UNETR, Swin UNETR were trained and compared at ISBI2015 with various parameters and loss functions. Four MRI sequences were used: T2-WI, T2-FLAIR, PD, MPRAGE. Lesion segmentation was approved by certified experienced neuroradiologists. Conclusions. The approaches described in the paper including data processing, model training, and results analysis, focused on the selection and development of high-quality computer vision algorithms for identifying multiple sclerosis lesions in MRI images. Identification and segmentation of demyelination foci is a necessary step for diagnosing the disease, as well as for calculating and interpreting more meaningful indicators of disease severity and progression.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>рассеянный склероз</kwd><kwd>компьютерное зрение</kwd><kwd>демиелинизация</kwd><kwd>сегментация изображений</kwd><kwd>МРТ</kwd><kwd>медицинская визуализация</kwd></kwd-group><kwd-group xml:lang="en"><kwd>multiple sclerosis</kwd><kwd>computer vision</kwd><kwd>demyelination</kwd><kwd>image segmentation</kwd><kwd>MRI</kwd><kwd>medical imaging</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование проведено в рамках проекта Российского научного фонда № 23-15-00377</funding-statement><funding-statement xml:lang="en">The research was supported by Russian Science Foundation № 23-15-00377</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">Кротенкова И.А., Брюхов В.В., Коновалов Р.Н., Захарова М.Н., Кротенкова М.В. Магнитнорезонансная томография в дифференциальной диагностике рассеянного склероза и других демиелинизирующих заболеваний. Вестн. рентгенол. и радиол. 2019;100(4):229–236. doi: 10.20862/0042-4676-2019-100-4-229-236</mixed-citation><mixed-citation xml:lang="en">Krotenkova I.A., Bryukhov V.V., Konovalov R.N., Zakharova M.N., Krotenkova M.V. Magnetic resonance imaging in the differential diagnosis of multiple sclerosis and other demyelinating diseases. Vestnik rentgenologii i radiologii = Bulletin of Roentgenology and Radiology. 2019;100(4):229–236. [In Russian]. doi: 10.20862/0042-4676-2019-100-4-229-236</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Thompson A.J., Banwell B.L., Barkhof F., Carroll W.M., Coetzee T., Comi G., Correale J., Fazekas F., Filippi M., Freedman M.S., … Cohen J.A. Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol. 2018;17(2):162–173. doi: 10.1016/S1474-4422(17)30470-2</mixed-citation><mixed-citation xml:lang="en">Thompson A.J., Banwell B.L., Barkhof F., Carroll W.M., Coetzee T., Comi G., Correale J., Fazekas F., Filippi M., Freedman M.S., … Cohen J.A. Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol. 2018;17(2):162–173. doi: 10.1016/S1474-4422(17)30470-2</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Zeng C., Gu L., Liu Z., Zhao S. Review of deep learning approaches for the segmentation of multiple sclerosis lesions on brain MRI. Front. Neuroinform. 2020;14:610967. doi: 10.3389/fninf.2020.610967</mixed-citation><mixed-citation xml:lang="en">Zeng C., Gu L., Liu Z., Zhao S. Review of deep learning approaches for the segmentation of multiple sclerosis lesions on brain MRI. Front. Neuroinform. 2020;14:610967. doi: 10.3389/fninf.2020.610967</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Carass A., Roy S., Jog A., Cuzzocreo J.L., Magrath E., Gherman A., Button J., Nguyen J., Prados F., Sudre C.H., ... Pham D.L. Longitudinal multiple sclerosis lesion segmentation: resource and challenge. Neuroimage. 2017;148:77–102. doi: 10.1016/j.neuroimage.2016.12.064</mixed-citation><mixed-citation xml:lang="en">Carass A., Roy S., Jog A., Cuzzocreo J.L., Magrath E., Gherman A., Button J., Nguyen J., Prados F., Sudre C.H., ... Pham D.L. Longitudinal multiple sclerosis lesion segmentation: resource and challenge. Neuroimage. 2017;148:77–102. doi: 10.1016/j.neuroimage.2016.12.064</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Commowick O., Istace A., Kain M., Laurent B., Leray F., Simon M., Pop S.C., Girard P., Améli R., Ferré J.C., ... Barillot C. Objective evaluation of multiple sclerosis lesion segmentation using a data management and processing infrastructure. Sci. Rep. 2018;8(1):13650. doi: 10.1038/s41598-018-31911-7</mixed-citation><mixed-citation xml:lang="en">Commowick O., Istace A., Kain M., Laurent B., Leray F., Simon M., Pop S.C., Girard P., Améli R., Ferré J.C., ... Barillot C. Objective evaluation of multiple sclerosis lesion segmentation using a data management and processing infrastructure. Sci. Rep. 2018;8(1):13650. doi: 10.1038/s41598-018-31911-7</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Commowick O., Cervenansky F., Cotton F., Dojat M. MSSEG-2 challenge proceedings: Multiple sclerosis new lesions segmentation challenge using a data management and processing infrastructure. 24th International Conference on Medical Image Computing and Computer Assisted Intervention: proc. conf., Strasbourg, France, Sep 2021. P. 1–118.</mixed-citation><mixed-citation xml:lang="en">Commowick O., Cervenansky F., Cotton F., Dojat M. MSSEG-2 challenge proceedings: Multiple sclerosis new lesions segmentation challenge using a data management and processing infrastructure. 24th International Conference on Medical Image Computing and Computer Assisted Intervention: proc. conf., Strasbourg, France, Sep 2021. P. 1–118.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Ronneberger O., Fischer P., Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: proc. conf., Munich, Germany, October 5–9, 2015. Part III 18. Springer International Publishing, 2015. doi: 10.48550/arXiv.1505.04597</mixed-citation><mixed-citation xml:lang="en">Ronneberger O., Fischer P., Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: proc. conf., Munich, Germany, October 5–9, 2015. Part III 18. Springer International Publishing, 2015. doi: 10.48550/arXiv.1505.04597</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang H., Valcarcel A.M., Bakshi R., Chu R., Bagnato F., Shinohara R.T., Hett K., Oguz I. Multiple sclerosis lesion segmentation with tiramisu and 2.5D stacked slices. Med. Image Comput. Comput. Assist. Interv. 2019;11766:338–346. doi: 10.1007/978-3-030-32248-9_38</mixed-citation><mixed-citation xml:lang="en">Zhang H., Valcarcel A.M., Bakshi R., Chu R., Bagnato F., Shinohara R.T., Hett K., Oguz I. Multiple sclerosis lesion segmentation with tiramisu and 2.5D stacked slices. Med. Image Comput. Comput. Assist. Interv. 2019;11766:338–346. doi: 10.1007/978-3-030-32248-9_38</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Isensee F., Jaeger P.F., Kohl S.A., Petersen J., Maier-Hein K.H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods. 2021;18(2):203–211. doi: 10.1038/s41592-020-01008-z</mixed-citation><mixed-citation xml:lang="en">Isensee F., Jaeger P.F., Kohl S.A., Petersen J., Maier-Hein K.H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods. 2021;18(2):203–211. doi: 10.1038/s41592-020-01008-z</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Dosovitskiy A., Beyer L., Kolesnikov A., Weissenborn D., Zhai X., Unterthiner T., Dehghani M., Minderer M., Heigold G., Gelly S., Uszkoreit J., Houlsby N. (2020). An image is worth 16×16 words: Transformers for image recognition at scale. arXiv preprint arXiv. 2010.11929.</mixed-citation><mixed-citation xml:lang="en">Dosovitskiy A., Beyer L., Kolesnikov A., Weissenborn D., Zhai X., Unterthiner T., Dehghani M., Minderer M., Heigold G., Gelly S., Uszkoreit J., Houlsby N. (2020). An image is worth 16×16 words: Transformers for image recognition at scale. arXiv preprint arXiv. 2010.11929.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Hatamizadeh A., Tang Y., Nath V., Yang D., Myronenko A., Landman B., Roth H., Xu D. UNETR: Transformers for 3D medical image segmentation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2022. P. 574–584</mixed-citation><mixed-citation xml:lang="en">Hatamizadeh A., Tang Y., Nath V., Yang D., Myronenko A., Landman B., Roth H., Xu D. UNETR: Transformers for 3D medical image segmentation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2022. P. 574–584</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Hatamizadeh A., Nath V., Tang Y., Yang D., Roth H.R., Xu D. Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images. In: International MICCAI Brainlesion Workshop. Cham: Springer International Publishing, 2021. P. 272–284. doi: 10.48550/arXiv.2201.01266</mixed-citation><mixed-citation xml:lang="en">Hatamizadeh A., Nath V., Tang Y., Yang D., Roth H.R., Xu D. Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images. In: International MICCAI Brainlesion Workshop. Cham: Springer International Publishing, 2021. P. 272–284. doi: 10.48550/arXiv.2201.01266</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Lin T.Y., Goyal P., Girshick R., He K., Dollár P. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. 2017. P. 2980–2988. doi:10.1109/ICCV.2017.324</mixed-citation><mixed-citation xml:lang="en">Lin T.Y., Goyal P., Girshick R., He K., Dollár P. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. 2017. P. 2980–2988. doi:10.1109/ICCV.2017.324</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>
