<?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">farmaec</journal-id><journal-title-group><journal-title xml:lang="en">FARMAKOEKONOMIKA. Modern Pharmacoeconomics and Pharmacoepidemiology</journal-title><trans-title-group xml:lang="ru"><trans-title>ФАРМАКОЭКОНОМИКА. Современная фармакоэкономика и фармакоэпидемиология</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2070-4909</issn><issn pub-type="epub">2070-4933</issn><publisher><publisher-name>IRBIS LLC</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17749/2070-4909/farmakoekonomika.2025.327</article-id><article-id custom-type="elpub" pub-id-type="custom">farmaec-1256</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>ORIGINAL ARTICLES</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ОРИГИНАЛЬНЫЕ ПУБЛИКАЦИИ</subject></subj-group></article-categories><title-group><article-title>Convolutional neural networks and transformers in skin tumor diagnostics: a comparative analysis of the efficiency of artificial intelligence models in computer vision programs</article-title><trans-title-group xml:lang="ru"><trans-title>Сверточные нейронные сети и визуальные трансформеры в диагностике опухолей кожи: сравнительный анализ эффективности моделей искусственного интеллекта в программах компьютерного зрения</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7930-6018</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ламоткин</surname><given-names>А. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Lamotkin</surname><given-names>A. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ламоткин Андрей Игоревич </p><p>2-я Брестская ул., д. 5, Москва 123056 </p><p>ул. Добролюбова, д. 11, Москва 127254 </p></bio><bio xml:lang="en"><p>Andrey I. Lamotkin </p><p>5 2nd Brestskaya Str., Moscow 123056 </p><p>11 Dobrolyubov Str., Moscow 127254 </p></bio><email xlink:type="simple">lamotkin.an@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/0000-0002-0459-0488</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Корабельников</surname><given-names>Д. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Korabelnikov</surname><given-names>D. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Корабельников Даниил Иванович, к.м.н., доцент</p><p>2-я Брестская ул., д. 5, Москва 123056  </p></bio><bio xml:lang="en"><p>Daniil I. Korabelnikov, PhD, Assoc. Prof. </p><p>5 2nd Brestskaya Str., Moscow 123056 </p></bio><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Автономная некоммерческая организация дополнительного профессионального образования «Московский медико-социальный институт им. Ф.П. Гааза»; Федеральное государственное бюджетное учреждение «Центральный научно-исследовательский институт организации и информатизации здравоохранения» Министерства здравоохранения Российской Федерации<country>Россия</country></aff><aff xml:lang="en">Moscow Haass Medical and Social Institute; Central Research Institute of Organization and Informatization of Healthcare<country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru">Автономная некоммерческая организация дополнительного профессионального образования «Московский медико-социальный институт им. Ф.П. Гааза»<country>Россия</country></aff><aff xml:lang="en">Moscow Haass Medical and Social Institute<country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>22</day><month>10</month><year>2025</year></pub-date><volume>18</volume><issue>3</issue><fpage>365</fpage><lpage>375</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Lamotkin A.I., Korabelnikov D.I., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Ламоткин А.И., Корабельников Д.И.</copyright-holder><copyright-holder xml:lang="en">Lamotkin A.I., Korabelnikov D.I.</copyright-holder><license 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.pharmacoeconomics.ru/jour/article/view/1256">https://www.pharmacoeconomics.ru/jour/article/view/1256</self-uri><abstract><sec><title>Background</title><p>Background. When applying computer vision programs in artificial intelligence (AI) models to diagnose skin tumors, melanoma in particular, even minimal classification errors are critical. Vision transformers (ViT), a new model architecture, have shown promising results in computer vision; however, their efficiency in classifying skin lesions has received insufficient research attention. This study is one of the first to directly compare convolutional neural networks (CNNs) and ViT on clinically relevant metrics, which is especially important for the implementation of AI in dermatological and oncological practice.</p></sec><sec><title>Objective</title><p>Objective: To compare the performance of CNNs and ViT in the tasks of binary classification of skin lesions: “melanoma/not melanoma” and “benign/malignant”.</p></sec><sec><title>Material and methods</title><p>Material and methods. The study used CNN (MobileNetV2, Xception) and ViT architectures. Testing was carried out on independent datasets (3000 and 4800 images, respectively) with assessment by the metrics of accuracy, sensitivity, specificity. Augmentation, class balancing, hyperparameter optimization, and data cleaning from artifacts were used.</p></sec><sec><title>Results</title><p>Results. ViT showed superiority over CNNs. Thus, in the “melanoma/non-melanoma” task, the accuracy was 92.93% versus 88% for Xception, and in the “benign/malignant” task – 91.35% versus 85%. Transformer model demonstrated better specificity (up to 95%).</p></sec><sec><title>Conclusion</title><p>Conclusion. ViT provides higher accuracy due to the analysis of global patterns, although requiring careful tuning and high-quality data. CNNs remain a stable solution with limited data. For clinical use, a combination of both architectures is recommended to improve the reliability of diagnostics.</p></sec></abstract><trans-abstract xml:lang="ru"><sec><title>Актуальность</title><p>Актуальность. При применении программ компьютерного зрения в моделях искусственного интеллекта (ИИ) для целей диагностики кожных опухолей, особенно меланомы, критически важны минимальные ошибки классификации. Новая архитектура моделей – визуальные трансформеры (англ. vision transformer, ViT) демонстрируют перспективные результаты, однако их эффективность для классификации кожных новообразований изучена недостаточно. Данное исследование является одним из первых, где проведено прямое сравнение сверточных нейронных сетей (англ. convolutional neural network, CNN) и ViT на клинически значимых метриках, что особенно важно для внедрения ИИ в дерматологическую и онкологическую практику.</p></sec><sec><title>Цель</title><p>Цель: сравнить эффективность CNN и ViT в задачах бинарной классификации опухолей кожи: «меланома / не меланома» и «доброкачественное/злокачественное».</p></sec><sec><title>Материал и методы</title><p>Материал и методы. В исследовании сравнивалась эффективность программ компьютерного зрения (приложения для смартфона) с использованием архитектуры CNN (MobileNetV2, Xception) и трансформера ViT. Тестирование проводилось на независимых наборах данных (3000 и 4800 изображений соответственно) с оценкой по метрикам точности, чувствительности, специфичности. Применялись методы аугментации, балансировки классов, оптимизации гиперпараметров и очистки данных от артефактов.</p></sec><sec><title>Результаты</title><p>Результаты. ViT показал превосходство над CNN: в задаче «меланома / не меланома» точность составила 92,93% против 88% у Xception, а в задаче «доброкачественное/злокачественное» – 91,35% против 85%. Модель трансформера продемонстрировала лучшую специфичность (до 95%).</p></sec><sec><title>Заключение</title><p>Заключение. ViT обеспечивает более высокую точность за счет анализа глобальных паттернов, но требует тщательной настройки и качественных данных. CNN остаются стабильным решением при ограниченных данных. Для клинического применения рекомендовано комбинирование обеих архитектур, позволяющее повысить эффективность диагностики.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>искусственный интеллект</kwd><kwd>компьютерное зрение</kwd><kwd>сверточные нейронные сети</kwd><kwd>трансформеры</kwd><kwd>классификация изображений</kwd><kwd>меланома</kwd><kwd>доброкачественные опухоли</kwd><kwd>злокачественные опухоли</kwd><kwd>диагностика</kwd></kwd-group><kwd-group xml:lang="en"><kwd>artificial intelligence</kwd><kwd>computer vision</kwd><kwd>convolutional neural networks</kwd><kwd>visual transformers</kwd><kwd>image classification</kwd><kwd>melanoma</kwd><kwd>benign neoplasms</kwd><kwd>malignant neoplasms</kwd><kwd>diagnosis</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">Schaumburg F., Berli C. Challenges and proposed solutions for optical reading on point-of-need testing systems. Front Sensors. 2023; 4. https://doi.org/10.3389/fsens.2023.1327240.</mixed-citation><mixed-citation xml:lang="en">Schaumburg F., Berli C. Challenges and proposed solutions for optical reading on point-of-need testing systems. Front Sensors. 2023; 4. https://doi.org/10.3389/fsens.2023.1327240.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Visalini S., Kanagavalli R. A comprehensive survey of pneumonia diagnosis: image processing and deep learning advancements. In: 2023 3rd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA). https://doi.org/10.1109/ICIMIA60377.2023.10426403.</mixed-citation><mixed-citation xml:lang="en">Visalini S., Kanagavalli R. A comprehensive survey of pneumonia diagnosis: image processing and deep learning advancements. In: 2023 3rd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA). https://doi.org/10.1109/ICIMIA60377.2023.10426403.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Prabha S., Gupta S., Pandey S.P. Deep learning for medical image segmentation using convolutional neural networks. In: 2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC). https://doi.org/10.1109/ICOCWC60930.2024.10470841.</mixed-citation><mixed-citation xml:lang="en">Prabha S., Gupta S., Pandey S.P. Deep learning for medical image segmentation using convolutional neural networks. In: 2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC). https://doi.org/10.1109/ICOCWC60930.2024.10470841.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Das M., Sambodhi P.P., Khare A., Naik S.A. Challenges of medical text and image processing. In: 2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC). https://doi.org/10.1109/ASSIC55218.2022.10088402.</mixed-citation><mixed-citation xml:lang="en">Das M., Sambodhi P.P., Khare A., Naik S.A. Challenges of medical text and image processing. In: 2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC). https://doi.org/10.1109/ASSIC55218.2022.10088402.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Choudhury S., Gowri R., Babu Sena P., Dinh-Thuan D. (Eds) Intelligent Communication, Control and Devices Proceedings of ICICCD 2020: Proceedings of ICICCD 2020. https://doi.org/10.1007/978-981-16-1510-8.</mixed-citation><mixed-citation xml:lang="en">Choudhury S., Gowri R., Babu Sena P., Dinh-Thuan D. (Eds) Intelligent Communication, Control and Devices Proceedings of ICICCD 2020: Proceedings of ICICCD 2020. https://doi.org/10.1007/978-981-16-1510-8.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Ламоткин А.И., Корабельников Д.И., Ламоткин И.А. и др. Искусственный интеллект в здравоохранении и медицине: история ключевых событий, его значимость для врачей, уровень развития в разных странах. ФАРМАКОЭКОНОМИКА. Современная фармакоэкономика и фармакоэпидемиология. 2024; 17 (2): 243–50. https://doi.org/10.17749/2070-4909/farmakoekonomika.2024.254.</mixed-citation><mixed-citation xml:lang="en">Lamotkin A.I., Korabelnikov D.I., Lamotkin I.A., et al. Artificial intelligence in healthcare and medicine: the history of key events, its significance for doctors, the level of development in different countries. FARMAKOEKONOMIKA. Sovremennaya farmakoekonomika i farmakoepidemiologiya / FARMAKOEKONOMIKA. Modern Pharmacoeconomics and Pharmacoepidemiology. 2024; 17 (2): 243–50 (in Russ.). https://doi.org/10.17749/2070-4909/farmakoekonomika.2024.254.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Ламоткин А.И., Корабельников Д.И., Ламоткин И.А. и др. Точность предварительной диагностики злокачественных меланоцитарных опухолей кожи с помощью программы искусственного интеллекта Melanoma Check. Медицинский вестник Главного военного клинического госпиталя им. Н.Н. Бурденко. 2025; 1: 42–51. https://doi.org/10.53652/2782-1730-2025-6-1-42-51.</mixed-citation><mixed-citation xml:lang="en">Lamotkin A.I., Korabelnikov D.I., Lamotkin I.A., et al. The accuracy of the preliminary diagnosis of malignant melanocytic skin tumors using the artificial intelligence program “Melanoma Check”. Medical Bulletin of the Main Military Clinical Hospital named after N.N. Burdenko. 2025; 1: 42–51 (in Russ.). https://doi.org/10.53652/2782-1730-2025-6-1-42-51.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Zhou Z., Jin Y., Ye H., et al. Classification, detection, and segmentation performance of image-based AI in intracranial aneurysm: a systematic review. BMC Med Imaging. 2024; 24 (1): 164. https://doi.org/10.1186/s12880-024-01347-9.</mixed-citation><mixed-citation xml:lang="en">Zhou Z., Jin Y., Ye H., et al. Classification, detection, and segmentation performance of image-based AI in intracranial aneurysm: a systematic review. BMC Med Imaging. 2024; 24 (1): 164. https://doi.org/10.1186/s12880-024-01347-9.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Корабельников Д.И., Ламоткин А.И. Эффективность применения искусственного интеллекта в клинической медицине. ФАРМАКОЭКОНОМИКА. Современная фармакоэкономика и фармакоэпидемиология. 2025; 18 (1): 114–24. https://doi.org/10.17749/2070-4909/farmakoekonomika.2025.287.</mixed-citation><mixed-citation xml:lang="en">Korabelnikov D.I., Lamotkin A.I. The effectiveness of using artificial intelligence in clinical medicine. FARMAKOEKONOMIKA. Sovremennaya farmakoekonomika i farmakoepidemiologiya / FARMAKOEKONOMIKA. Modern Pharmacoeconomics and Pharmacoepidemiology. 2025; 18 (1): 114–24 (in Russ.). https://doi.org/10.17749/2070-4909/farmakoekonomika.2025.287.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Alzubaidi L., Zhang J., Humaidi A.J., et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021; 8 (1): 53. https://doi.org/10.1186/s40537-021-00444-8.</mixed-citation><mixed-citation xml:lang="en">Alzubaidi L., Zhang J., Humaidi A.J., et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021; 8 (1): 53. https://doi.org/10.1186/s40537-021-00444-8.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">LeCun Y., Bengio Y., Hinton G. Deep learning. Nature. 2015; 521: 436–44. https://doi.org/10.1038/nature14539.</mixed-citation><mixed-citation xml:lang="en">LeCun Y., Bengio Y., Hinton G. Deep learning. Nature. 2015; 521: 436–44. https://doi.org/10.1038/nature14539.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Ламоткин А.И., Корабельников Д.И., Ламоткин И.А. Предварительная дифференциальная диагностика доброкачественных и злокачественных опухолей из эпидермальной ткани кожи с применением программы искусственного интеллекта «Derma Onko Check». Современные проблемы здравоохранения и медицинской статистики. 2025; 2: 223–42. https://doi.org/10.24412/2312-2935-2025-2-223-242.</mixed-citation><mixed-citation xml:lang="en">Lamotkin A.I., Korabelnikov D.I., Lamotkin I.A. Preliminary differential diagnosis of benign and malignant tumors from epidermal skin tissue using an artificial intelligence program "Derma Onko Check". Current Problems of Health Care and Medical Statistics. 2025; 2: 223–42 (in Russ.). https://doi.org/10.24412/2312-2935-2025-2-223-242.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Ламоткин А.И., Корабельников Д.И., Олисова О.Ю., Ламоткин И.А. Эффективность предварительной дифференциальной диагностики доброкачественных и злокачественных новообразований кожи с помощью программы искусственного интеллекта Derma Onko Check. ФАРМАКОЭКОНОМИКА. Современная фармакоэкономика и фармакоэпидемиология. 2025; 18 (2): 261–70. https://doi.org/10.17749/2070-4909/farmakoekonomika.2025.294.</mixed-citation><mixed-citation xml:lang="en">Lamotkin A.I., Korabelnikov D.I., Olisova O.Yu., Lamotkin I.A. Effectiveness of preliminary differential diagnosis of benign and malignant skin neoplasms using the Derma Onko Check artificial intelligence program. FARMAKOEKONOMIKA. Sovremennaya farmakoekonomika i farmakoepidemiologiya / FARMAKOEKONOMIKA. Modern Pharmacoeconomics and Pharmacoepidemiology. 2025; 18 (2): 261–70 (in Russ.). https://doi.org/10.17749/2070-4909/farmakoekonomika.2025.294.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Milletari F., Ahmadi S.A., Kroll C., et al. Hough-CNN: deep learning for segmentation of deep brain regions in MRI and ultrasound. Computer Vision Image Underst. 2017; 164: 92–102. https://doi.org/10.48550/arXiv.1601.07014.</mixed-citation><mixed-citation xml:lang="en">Milletari F., Ahmadi S.A., Kroll C., et al. Hough-CNN: deep learning for segmentation of deep brain regions in MRI and ultrasound. Computer Vision Image Underst. 2017; 164: 92–102. https://doi.org/10.48550/arXiv.1601.07014.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Yamada M., Saito Y., Imaoka H., et al. Development of a real-time endoscopic image diagnosis support system using deep learning technology in colonoscopy. Sci Rep. 2019; 9 (1): 14465. https://doi.org/10.1038/s41598-019-50567-5.</mixed-citation><mixed-citation xml:lang="en">Yamada M., Saito Y., Imaoka H., et al. Development of a real-time endoscopic image diagnosis support system using deep learning technology in colonoscopy. Sci Rep. 2019; 9 (1): 14465. https://doi.org/10.1038/s41598-019-50567-5.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Yadav D., Rathor S. Bone fracture detection and classification using deep learning approach. In: 2020 International Conference on Power Electronics &amp; IoT Applications in Renewable Energy and its Control (PARC). https://doi.org/10.1109/PARC49193.2020.236611.</mixed-citation><mixed-citation xml:lang="en">Yadav D., Rathor S. Bone fracture detection and classification using deep learning approach. In: 2020 International Conference on Power Electronics &amp; IoT Applications in Renewable Energy and its Control (PARC). https://doi.org/10.1109/PARC49193.2020.236611.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Rahman T., Chowdhury M.E., Khandakar A., et al. Transfer learning with deep convolutional neural network (CNN) for pneumonia detection using chest X-ray. Appl Sci. 2020; 10 (9): 3233. https://doi.org/10.3390/app10093233.</mixed-citation><mixed-citation xml:lang="en">Rahman T., Chowdhury M.E., Khandakar A., et al. Transfer learning with deep convolutional neural network (CNN) for pneumonia detection using chest X-ray. Appl Sci. 2020; 10 (9): 3233. https://doi.org/10.3390/app10093233.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Hamamoto R., Suvarna K., Yamada M., et al. Application of artificial intelligence technology in oncology: towards the establishment of precision medicine. Cancers. 2020; 12 (12): 3532. https://doi.org/10.3390/cancers12123532.</mixed-citation><mixed-citation xml:lang="en">Hamamoto R., Suvarna K., Yamada M., et al. Application of artificial intelligence technology in oncology: towards the establishment of precision medicine. Cancers. 2020; 12 (12): 3532. https://doi.org/10.3390/cancers12123532.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Asada K., Kobayashi K., Joutard S., et al. Uncovering prognosisrelated genes and pathways by multi-omics analysis in lung cancer. Biomolecules. 2020; 10: 524. https://doi.org/10.3390/biom10040524.</mixed-citation><mixed-citation xml:lang="en">Asada K., Kobayashi K., Joutard S., et al. Uncovering prognosisrelated genes and pathways by multi-omics analysis in lung cancer. Biomolecules. 2020; 10: 524. https://doi.org/10.3390/biom10040524.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Kobayashi K., Bolatkan A., Shiina S., Hamamoto R. Fully-connected neural networks with reduced parameterization for predicting histological types of lung cancer from somatic mutations. Biomolecules. 2020; 10 (9): 1249. https://doi.org/10.3390/biom10091249.</mixed-citation><mixed-citation xml:lang="en">Kobayashi K., Bolatkan A., Shiina S., Hamamoto R. Fully-connected neural networks with reduced parameterization for predicting histological types of lung cancer from somatic mutations. Biomolecules. 2020; 10 (9): 1249. https://doi.org/10.3390/biom10091249.</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Takahashi S., Asada K., Takasawa K., et al. Predicting deep learning based multi-omics parallel integration survival subtypes in lung cancer using reverse phase protein array data. Biomolecules. 2020; 10 (10): 1460. https://doi.org/10.3390/biom10101460.</mixed-citation><mixed-citation xml:lang="en">Takahashi S., Asada K., Takasawa K., et al. Predicting deep learning based multi-omics parallel integration survival subtypes in lung cancer using reverse phase protein array data. Biomolecules. 2020; 10 (10): 1460. https://doi.org/10.3390/biom10101460.</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Takahashi S., Sakaguchi Y., Kouno N., et al. Comparison of vision transformers and convolutional neural networks in medical image analysis: a systematic review. J Med Syst. 2024; 48 (1): 84. https://doi.org/10.1007/s10916-024-02105-8.</mixed-citation><mixed-citation xml:lang="en">Takahashi S., Sakaguchi Y., Kouno N., et al. Comparison of vision transformers and convolutional neural networks in medical image analysis: a systematic review. J Med Syst. 2024; 48 (1): 84. https://doi.org/10.1007/s10916-024-02105-8.</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Selvaraju R.R., Cogswell M., Das A., et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In: 2017 Proceedings of the IEEE international conference on computer vision. https://doi.org/10.48550/arXiv.1610.02391.</mixed-citation><mixed-citation xml:lang="en">Selvaraju R.R., Cogswell M., Das A., et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In: 2017 Proceedings of the IEEE international conference on computer vision. https://doi.org/10.48550/arXiv.1610.02391.</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Takahashi S., Takahashi M., Kinoshita M., et al. Fine-tuning approach for segmentation of gliomas in brain magnetic resonance images with a machine learning method to normalize image differences among facilities. Cancers. 2021; 13: 1415. https://doi.org/10.3390/cancers13061415.</mixed-citation><mixed-citation xml:lang="en">Takahashi S., Takahashi M., Kinoshita M., et al. Fine-tuning approach for segmentation of gliomas in brain magnetic resonance images with a machine learning method to normalize image differences among facilities. Cancers. 2021; 13: 1415. https://doi.org/10.3390/cancers13061415.</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Nam H., Lee H., Park J., et al. Reducing domain gap by reducing style bias. In: 2021 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://doi.org/10.48550/arXiv.1910.11645.</mixed-citation><mixed-citation xml:lang="en">Nam H., Lee H., Park J., et al. Reducing domain gap by reducing style bias. In: 2021 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://doi.org/10.48550/arXiv.1910.11645.</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Yan W., Wang Y., Gu S., et al. The domain shift problem of medical image segmentation and vendor-adaptation by Unet-GAN. In: Medical Image Computing and Computer Assisted Intervention– MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II. https://doi.org/10.48550/arXiv.1910.13681.</mixed-citation><mixed-citation xml:lang="en">Yan W., Wang Y., Gu S., et al. The domain shift problem of medical image segmentation and vendor-adaptation by Unet-GAN. In: Medical Image Computing and Computer Assisted Intervention– MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II. https://doi.org/10.48550/arXiv.1910.13681.</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">Barzekar H., Patel Y., Tong L., Yu Z. MultiNet with transformers: a model for cancer diagnosis using images. arXiv:230109007. https://doi.org/10.48550/arXiv.2301.09007.</mixed-citation><mixed-citation xml:lang="en">Barzekar H., Patel Y., Tong L., Yu Z. MultiNet with transformers: a model for cancer diagnosis using images. arXiv:230109007. https://doi.org/10.48550/arXiv.2301.09007.</mixed-citation></citation-alternatives></ref><ref id="cit28"><label>28</label><citation-alternatives><mixed-citation xml:lang="ru">Vaswani A., Shazeer N., Parmar N., et al. Attention is all you need. In: Advances in Neural Information Processing Systems 30 (NIPS 2017). https://doi.org/10.48550/arXiv.1706.03762.</mixed-citation><mixed-citation xml:lang="en">Vaswani A., Shazeer N., Parmar N., et al. Attention is all you need. In: Advances in Neural Information Processing Systems 30 (NIPS 2017). https://doi.org/10.48550/arXiv.1706.03762.</mixed-citation></citation-alternatives></ref><ref id="cit29"><label>29</label><citation-alternatives><mixed-citation xml:lang="ru">Dosovitskiy A., Beyer L., Kolesnikov A., et al. An image is worth 16×16 words: transformers for image recognition at scale. arXiv:201011929. https://doi.org/10.48550/arXiv.2010.11929.</mixed-citation><mixed-citation xml:lang="en">Dosovitskiy A., Beyer L., Kolesnikov A., et al. An image is worth 16×16 words: transformers for image recognition at scale. arXiv:201011929. https://doi.org/10.48550/arXiv.2010.11929.</mixed-citation></citation-alternatives></ref><ref id="cit30"><label>30</label><citation-alternatives><mixed-citation xml:lang="ru">Liu Y., Wu Y.H., Sun G., et al. Vision transformers with hierarchical attention. arXiv:210603180. https://doi.org/10.48550/arXiv.2106.03180.</mixed-citation><mixed-citation xml:lang="en">Liu Y., Wu Y.H., Sun G., et al. Vision transformers with hierarchical attention. arXiv:210603180. https://doi.org/10.48550/arXiv.2106.03180.</mixed-citation></citation-alternatives></ref><ref id="cit31"><label>31</label><citation-alternatives><mixed-citation xml:lang="ru">Han K., Wang Y., Chen H., et al. A survey on vision transformer. arXiv:2012.12556. https://doi.org/10.48550/arXiv.2012.12556.</mixed-citation><mixed-citation xml:lang="en">Han K., Wang Y., Chen H., et al. A survey on vision transformer. arXiv:2012.12556. https://doi.org/10.48550/arXiv.2012.12556.</mixed-citation></citation-alternatives></ref><ref id="cit32"><label>32</label><citation-alternatives><mixed-citation xml:lang="ru">Hatamizadeh A., Yin H., Heinrich G., et al. In: 2023 Global context vision transformers. arXiv:2206.09959. https://doi.org/10.48550/arXiv.2206.09959.</mixed-citation><mixed-citation xml:lang="en">Hatamizadeh A., Yin H., Heinrich G., et al. In: 2023 Global context vision transformers. arXiv:2206.09959. https://doi.org/10.48550/arXiv.2206.09959.</mixed-citation></citation-alternatives></ref><ref id="cit33"><label>33</label><citation-alternatives><mixed-citation xml:lang="ru">He K., Gan C., Li Z., et al. Transformers in medical image analysis. Intel Med. 2023; 3 (1): 59–78. https://doi.org/10.1016/j.imed.2022.07.002.</mixed-citation><mixed-citation xml:lang="en">He K., Gan C., Li Z., et al. Transformers in medical image analysis. Intel Med. 2023; 3 (1): 59–78. https://doi.org/10.1016/j.imed.2022.07.002.</mixed-citation></citation-alternatives></ref><ref id="cit34"><label>34</label><citation-alternatives><mixed-citation xml:lang="ru">Stassin S., Corduant V., Mahmoudi S.A., Siebert X. Explainability and evaluation of vision transformers: an in-depth experimental study. Electronics. 2023; 13 (1): 175. https://doi.org/10.3390/electronics13010175.</mixed-citation><mixed-citation xml:lang="en">Stassin S., Corduant V., Mahmoudi S.A., Siebert X. Explainability and evaluation of vision transformers: an in-depth experimental study. Electronics. 2023; 13 (1): 175. https://doi.org/10.3390/electronics13010175.</mixed-citation></citation-alternatives></ref><ref id="cit35"><label>35</label><citation-alternatives><mixed-citation xml:lang="ru">Chetoui M., Akhloufi M.A. Explainable vision transformers and radiomics for COVID-19 detection in chest X-rays. J Clin Med. 2022; 11 (11): 3013. https://doi.org/10.3390/jcm11113013.</mixed-citation><mixed-citation xml:lang="en">Chetoui M., Akhloufi M.A. Explainable vision transformers and radiomics for COVID-19 detection in chest X-rays. J Clin Med. 2022; 11 (11): 3013. https://doi.org/10.3390/jcm11113013.</mixed-citation></citation-alternatives></ref><ref id="cit36"><label>36</label><citation-alternatives><mixed-citation xml:lang="ru">Dipto S.M., Reza M.T., Rahman M.N.J., et al. An XAI integrated identification system of white blood cell type using variants of vision transformer. In: Proceedings of the Second International Conference on Innovations in Computing Research (ICR’23). https://doi.org/10.1007/978-3-031-35308-6_26.</mixed-citation><mixed-citation xml:lang="en">Dipto S.M., Reza M.T., Rahman M.N.J., et al. An XAI integrated identification system of white blood cell type using variants of vision transformer. In: Proceedings of the Second International Conference on Innovations in Computing Research (ICR’23). https://doi.org/10.1007/978-3-031-35308-6_26.</mixed-citation></citation-alternatives></ref><ref id="cit37"><label>37</label><citation-alternatives><mixed-citation xml:lang="ru">Cao Y.H., Yu H., Wu J. Training vision transformers with only 2040 images. arXiv:2201.10728. https://doi.org/10.48550/arXiv.2201.10728.</mixed-citation><mixed-citation xml:lang="en">Cao Y.H., Yu H., Wu J. Training vision transformers with only 2040 images. arXiv:2201.10728. https://doi.org/10.48550/arXiv.2201.10728.</mixed-citation></citation-alternatives></ref><ref id="cit38"><label>38</label><citation-alternatives><mixed-citation xml:lang="ru">Lee S.H., Lee S., Song B.C. Vision transformer for small-size datasets. arXiv:211213492. https://doi.org/10.48550/arXiv.2112.13492.</mixed-citation><mixed-citation xml:lang="en">Lee S.H., Lee S., Song B.C. Vision transformer for small-size datasets. arXiv:211213492. https://doi.org/10.48550/arXiv.2112.13492.</mixed-citation></citation-alternatives></ref><ref id="cit39"><label>39</label><citation-alternatives><mixed-citation xml:lang="ru">Liu Y., Sangineto E., Bi W., et al. Efficient training of visual transformers with small datasets. arXiv:2106.03746. https://doi.org/10.48550/arXiv.2106.03746.</mixed-citation><mixed-citation xml:lang="en">Liu Y., Sangineto E., Bi W., et al. Efficient training of visual transformers with small datasets. arXiv:2106.03746. https://doi.org/10.48550/arXiv.2106.03746.</mixed-citation></citation-alternatives></ref><ref id="cit40"><label>40</label><citation-alternatives><mixed-citation xml:lang="ru">Fukushima K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybernetics. 1980; 36 (4): 193–202. https://doi.org/10.1007/BF00344251.</mixed-citation><mixed-citation xml:lang="en">Fukushima K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybernetics. 1980; 36 (4): 193–202. https://doi.org/10.1007/BF00344251.</mixed-citation></citation-alternatives></ref><ref id="cit41"><label>41</label><citation-alternatives><mixed-citation xml:lang="ru">LeCun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proceedings IEEE. 1998; 86 (11): 2278–324. https://doi.org/10.1109/5.726791.</mixed-citation><mixed-citation xml:lang="en">LeCun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proceedings IEEE. 1998; 86 (11): 2278–324. https://doi.org/10.1109/5.726791.</mixed-citation></citation-alternatives></ref><ref id="cit42"><label>42</label><citation-alternatives><mixed-citation xml:lang="ru">Hamamoto R., Komatsu M., Takasawa K., et al. Epigenetics analysis and integrated analysis of multiomics data, including epigenetic data, using artificial intelligence in the era of precision medicine. Biomolecules. 2020; 10 (1): 62. https://doi.org/10.3390/biom10010062.</mixed-citation><mixed-citation xml:lang="en">Hamamoto R., Komatsu M., Takasawa K., et al. Epigenetics analysis and integrated analysis of multiomics data, including epigenetic data, using artificial intelligence in the era of precision medicine. Biomolecules. 2020; 10 (1): 62. https://doi.org/10.3390/biom10010062.</mixed-citation></citation-alternatives></ref><ref id="cit43"><label>43</label><citation-alternatives><mixed-citation xml:lang="ru">Himel G.M.S., Islam M.M., Al-Aff K.A., et al. Skin cancer segmentation and classification using vision transformer for automatic analysis in dermatoscopy-based noninvasive digital system. Int J Biomed Imaging. 2024; 2024: 3022192. https://doi.org/10.1155/2024/3022192.</mixed-citation><mixed-citation xml:lang="en">Himel G.M.S., Islam M.M., Al-Aff K.A., et al. Skin cancer segmentation and classification using vision transformer for automatic analysis in dermatoscopy-based noninvasive digital system. Int J Biomed Imaging. 2024; 2024: 3022192. https://doi.org/10.1155/2024/3022192.</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>
