<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article 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" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="review-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Digital Diagnostics</journal-id><journal-title-group><journal-title xml:lang="en">Digital Diagnostics</journal-title><trans-title-group xml:lang="ru"><trans-title>Digital Diagnostics</trans-title></trans-title-group><trans-title-group xml:lang="zh"><trans-title>Digital Diagnostics</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2712-8490</issn><issn publication-format="electronic">2712-8962</issn><publisher><publisher-name xml:lang="en">Eco-Vector</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">697955</article-id><article-id pub-id-type="doi">10.17816/DD697955</article-id><article-id pub-id-type="edn">JCJTIP</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Reviews</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Научные обзоры</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="zh"><subject>科学评论</subject></subj-group><subj-group subj-group-type="article-type"><subject>Review Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Neural network analysis of histological images of non-neoplastic liver lesions: a review</article-title><trans-title-group xml:lang="ru"><trans-title>Нейросетевой анализ гистологических изображений при неопухолевых поражениях печени: обзор</trans-title></trans-title-group><trans-title-group xml:lang="zh"><trans-title>神经网络分析非肿瘤性肝脏病变的组织学图像：综述</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0003-6470-4891</contrib-id><contrib-id contrib-id-type="spin">8683-6870</contrib-id><name-alternatives><name xml:lang="en"><surname>Melikbekyan</surname><given-names>Ashot A.</given-names></name><name xml:lang="ru"><surname>Меликбекян</surname><given-names>Ашот Арсенович</given-names></name><name xml:lang="zh"><surname>Melikbekyan</surname><given-names>Ashot A.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><email>melikbekyan.ashot@yandex.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-9699-8375</contrib-id><contrib-id contrib-id-type="spin">8948-9169</contrib-id><name-alternatives><name xml:lang="en"><surname>Borbat</surname><given-names>Artyom M.</given-names></name><name xml:lang="ru"><surname>Борбат</surname><given-names>Артём Михайлович</given-names></name><name xml:lang="zh"><surname>Borbat</surname><given-names>Artyom M.</given-names></name></name-alternatives><address><country country="DE">Germany</country></address><email>aborbat@yandex.ru</email><xref ref-type="aff" rid="aff2"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1686-5629</contrib-id><contrib-id contrib-id-type="spin">9993-9645</contrib-id><name-alternatives><name xml:lang="en"><surname>Novikova</surname><given-names>Tatiana O.</given-names></name><name xml:lang="ru"><surname>Новикова</surname><given-names>Татьяна Олеговна</given-names></name><name xml:lang="zh"><surname>Novikova</surname><given-names>Tatiana O.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>MD, Cand. Sci. (Medicine)</p></bio><bio xml:lang="ru"><p>канд. мед. наук</p></bio><bio xml:lang="zh"><p>MD, Cand. Sci. (Medicine)</p></bio><email>tn.path1910@yandex.ru</email><xref ref-type="aff" rid="aff3"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Financial University under the Government of the Russian Federation</institution></aff><aff><institution xml:lang="ru">Финансовый университет при Правительстве Российской Федерации</institution></aff><aff><institution xml:lang="zh">Financial University under the Government of the Russian Federation</institution></aff></aff-alternatives><aff id="aff2"><institution>Pathologie Spandau</institution></aff><aff id="aff3"><institution>Laboratoires de Génie</institution></aff><pub-date date-type="preprint" iso-8601-date="2026-05-20" publication-format="electronic"><day>20</day><month>05</month><year>2026</year></pub-date><pub-date date-type="pub" iso-8601-date="2026-07-21" publication-format="electronic"><day>21</day><month>07</month><year>2026</year></pub-date><volume>7</volume><issue>2</issue><issue-title xml:lang="en"/><issue-title xml:lang="ru"/><issue-title xml:lang="zh"/><fpage>215</fpage><lpage>225</lpage><history><date date-type="received" iso-8601-date="2025-12-08"><day>08</day><month>12</month><year>2025</year></date><date date-type="accepted" iso-8601-date="2026-04-23"><day>23</day><month>04</month><year>2026</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2026, Eco-Vector</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2026, Эко-вектор</copyright-statement><copyright-statement xml:lang="zh">Copyright ©; 2026, Eco-Vector</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="en">Eco-Vector</copyright-holder><copyright-holder xml:lang="ru">Эко-вектор</copyright-holder><copyright-holder xml:lang="zh">Eco-Vector</copyright-holder><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/"/><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://creativecommons.org/licenses/by-nc-nd/4.0</ali:license_ref></license></permissions><self-uri xlink:href="https://jdigitaldiagnostics.com/DD/article/view/697955">https://jdigitaldiagnostics.com/DD/article/view/697955</self-uri><abstract xml:lang="en"><p>This review is devoted to the application of neural network models for the analysis of histological images in non-neoplastic liver diseases, with a focus on the technical aspects of model development and training. The relevance of this work is due to the growing interest in applying neural networks and computer vision for research and diagnostic tasks related to microscopic morphology. Although this disease group does not lose its clinical significance, and the importance of microscopic verification of morphological changes, the application of artificial intelligence in this field remains limited and fragmented.</p> <p>The review systematizes available annotated datasets of liver histological images, applied neural network architectures, image preprocessing approaches, and training strategies. It also examines the loss functions used and other key technical aspects of neural network development. It is shown that, although the contribution of such models to the automation and standardization of the morphological assessment appears promising, their practical implementation is constrained by the limited publicly available annotated data, the high labor intensity of annotation, and insufficient standardization of methodological approaches. It is noted that multimodal data, integrating histological images with clinical, biochemical, or radiological parameters, is of great clinical interest; however, it is currently rare.</p> <p>Most studies utilize universal neural network architectures, while models fine-tuned to work with microscopic features and liver morphology are applied much less commonly. The analysis of published studies has shown that weakly supervised learning can be sufficient for model development and, in combination with significantly lower annotation costs, offers substantial potential for further development. At the same time, a considerable proportion of studies describe methodologies with limited reproducibility.</p></abstract><trans-abstract xml:lang="ru"><p>Настоящий обзор посвящён применению нейросетевых моделей для анализа гистологических изображений при неопухолевых заболеваниях печени с фокусом на технические аспекты разработки и обучения моделей. Актуальность работы обусловлена возрастающим интересом к использованию нейросетевых моделей и методов компьютерного зрения для решения исследовательских и диагностических задач применительно к микроскопической морфологии. Несмотря на сохраняющуюся клиническую значимость этой группы заболеваний, а также важную роль микроскопической верификации морфологических изменений, применение методов искусственного интеллекта в данной области остаётся ограниченным и фрагментарным.</p> <p>В обзоре систематизированы данные о доступных аннотированных наборах гистологических изображений печени, применяемых архитектурах нейросетевых моделей, подходах к предобработке изображений и стратегиям обучения, а также рассмотрены используемые функции потерь и другие ключевые технические аспекты разработки нейросетевых решений. Продемонстрировано, что, несмотря на высокий потенциальный вклад таких моделей в автоматизацию и стандартизацию морфологической оценки, их практическое внедрение сдерживается ограниченностью общедоступных размеченных данных, высокой трудоёмкостью аннотирования и недостаточной стандартизацией методологических подходов. Направление мультимодальных данных, объединяющих гистологические изображения с клиническими, биохимическими или радиологическими параметрами, представляет большой клинический интерес, однако в настоящее время встречается редко.</p> <p>В большинстве исследований преобладает использование универсальных архитектур нейросетей, тогда как специализированные модели, ориентированные на особенности микроскопических данных и морфологию печени, применяют значительно реже. На основе анализа опубликованных исследований установлено, что слабое обучение с учителем может быть достаточно эффективным для разработки моделей, а в сочетании с существенно меньшими затратами на аннотирование обладает значительным потенциалом для дальнейшего развития. Одновременно выявлено, что в значительной доле работ описание методологии представлено на уровне, недостаточном для воспроизведения научного эксперимента.</p></trans-abstract><trans-abstract xml:lang="zh"><p>本综述致力于应用神经网络模型分析非肿瘤性肝脏疾病的组织学图像，重点介绍了模型开发和训练的技术方面。本研究的现实意义在于人们对使用神经网络模型和计算机视觉方法解决显微形态学研究与诊断任务的兴趣日益增长。尽管这组疾病具有持续的临床意义，并且显微镜形态学验证发挥着重要作用，但人工智能方法在该领域的应用仍然有限且零散。</p> <p>综述系统化了关于可用带标注的肝脏组织学图像数据集、应用的神经网络模型架构、图像预处理方法和训练策略的数据，并考察了使用的损失函数和其他关键技术开发方面。研究表明，尽管这些模型在形态学评估自动化和标准化方面具有巨大潜力，但其实际应用受到公开可用标注数据的限制、标注的高劳动强度以及方法学途径标准化不足的制约。多模态数据方向（结合组织学图像与临床、生化或放射学参数）具有重要的临床意义，但目前仍较少见。</p> <p>大多数研究倾向于使用通用神经网络架构，而专门针对显微数据特点和肝脏形态学的专业模型应用显著较少。基于对已发表研究的分析确定，弱监督学习对于模型开发可能足够有效，并且结合显著减少的标注成本，具有巨大的进一步发展潜力。同时发现，在相当一部分工作中，方法学的描述水平不足以重现科学实验。</p></trans-abstract><kwd-group xml:lang="en"><kwd>non-neoplastic liver lesions</kwd><kwd>hepatocytes</kwd><kwd>artificial intelligence</kwd><kwd>neural network models</kwd><kwd>review</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>неопухолевые поражения печени</kwd><kwd>гепатоциты</kwd><kwd>искусственный интеллект</kwd><kwd>нейросетевые модели</kwd><kwd>обзор</kwd></kwd-group><kwd-group xml:lang="zh"><kwd>非肿瘤性肝脏病变</kwd><kwd>肝细胞</kwd><kwd>人工智能</kwd><kwd>神经网络模型</kwd><kwd>综述</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Ivashkin VT, Maevskaya MV, Zharkova MS, et al. Clinical practice guidelines of the Russian Scientific Liver Society, Russian Gastroenterological Association, Russian Association of Endocrinologists, Russian Association of Gerontologists and Geriatricians and National Society for Preventive Cardiology on diagnosis and treatment of non-alcoholic liver disease. Russian Journal of Gastroenterology, Hepatology, Coloproctology. 2022;32(4):104–140. doi: 10.22416/1382-4376-2022-32-4-104-140 EDN: EXTLXM</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>Ivashkin VT, Maevskaya MV, Zharkova MS, et al. Clinical recommendations of the Russian Scientific Liver Society and Russian Gastroenterological Association on diagnosis and treatment of liver fibrosis, cirrhosis and their complications. Russian Journal of Gastroenterology, Hepatology, Coloproctology. 2021;31(6):56–102. doi: 10.22416/1382-4376-2021-31-6-56-102 EDN: GMKWTQ</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Kurbatsky SM. Does gastroenterology need artificial intelligence? Russian Journal of Gastroenterology, Hepatology, Coloproctology. 2022;31(6):103–105. doi: 10.22416/1382-4376-2021-31-6-103-105 EDN: YKECFX</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Pushkar DY, Khodyreva LA, Govorov AV, et al. Data Science – deep learning of neural networks and their application in healthcare. City Healthcare. 2021;2(2):109–115. doi: 10.47619/2713-2617.zm.2021.v2i2;109-115 EDN: SGWBPD</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Borbat AM. Neural networks for morphological diagnostics. Clinical and Experimental Morphology. 2020;9(2):11–15. doi: 10.31088/CEM2020.9.2.11-15 EDN: QNXGSR</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Shafi S, Parwani AV. Artificial intelligence in diagnostic pathology. Diagnostic Pathology. 2023;18(1):109. doi: 10.1186/s13000-023-01375-z EDN: WUSHTU</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>Roy M, Wang F, Vo H, et al. Deep-learning-based accurate hepatic steatosis quantification for histological assessment of liver biopsies. Laboratory Investigation. 2020;100(10):1367–1383. doi: 10.1038/s41374-020-0463-y EDN: JRLXIF</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Arjmand A, Angelis CT, Christou V, et al. Training of deep convolutional neural networks to identify critical liver alterations in histopathology image samples. Applied Sciences. 2019;10(1):42. doi: 10.3390/app10010042</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Cunningham RP, Porat-Shliom N. Liver zonation – revisiting old questions with new technologies. Frontiers in Physiology. 2021;12:732929. doi: 10.3389/fphys.2021.732929 EDN: NDTIPQ</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Ronquillo N, Garcia-Buitrago MT. Decoding liver biopsies: a pattern-based approach. Diagnostic Histopathology. 2025;31(6):325–339. doi: 10.1016/j.mpdhp.2025.03.010 EDN: CEVQTM</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Bedossa P, Poynard T. An algorithm for the grading of activity in chronic hepatitis C. Hepatology. 1996;24(2):289–293. doi: 10.1002/hep.510240201</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation>Kleiner DE, Brunt EM, Van Natta M, et al. Design and validation of a histological scoring system for nonalcoholic fatty liver disease. Hepatology. 2005;41(6):1313–1321. doi: 10.1002/hep.20701</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation>Krishna M. Histological grading and staging of chronic hepatitis. Clinical Liver Disease. 2021;17(4):222–226. doi: 10.1002/cld.1014 EDN: NEQGTM</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation>Kuznetsova A, Rom H, Alldrin N, et al. The Open Images Dataset V4. International Journal of Computer Vision. 2020;128(7):1956–1981. doi: 10.1007/s11263-020-01316-z EDN: WCGVFB</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation>Deng J, Dong W, Socher R, et al. ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE; 2009. P. 248–255. doi: 10.1109/cvpr.2009.5206848</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation>Ochi M, Komura D, Ishikawa S. Pathology foundation models. JMA Journal. 2025;8(1):121–130. doi: 10.31662/jmaj.2024-0206 EDN: SFXRQU</mixed-citation></ref><ref id="B17"><label>17.</label><mixed-citation>Kim YJ, Jang H, Lee K, et al. PAIP 2019: Liver cancer segmentation challenge. Medical Image Analysis. 2021;67:101854. doi: 10.1016/j.media.2020.101854 EDN: FHBYEK</mixed-citation></ref><ref id="B18"><label>18.</label><mixed-citation>Heinemann F, Gross P, Zeveleva S, et al. Deep learning-based quantification of NAFLD/NASH progression in human liver biopsies. Scientific Reports. 2022;12(1):19236. doi: 10.1038/s41598-022-23905-3 EDN: MRKSDP</mixed-citation></ref><ref id="B19"><label>19.</label><mixed-citation>Heinemann F, Birk G, Stierstorfer B. Deep learning enables pathologist-like scoring of NASH models. Scientific Reports. 2019;9(1):1–10. doi: 10.1038/s41598-019-54904-6 EDN: EDWDDY</mixed-citation></ref><ref id="B20"><label>20.</label><mixed-citation>Igarashi Y, Nakatsu N, Yamashita T, et al. Open TG-GATEs: a large-scale toxicogenomics database. Nucleic Acids Research. 2014;43(D1):D921–D927. doi: 10.1093/nar/gku955</mixed-citation></ref><ref id="B21"><label>21.</label><mixed-citation>Bosch J, Chung C, Carrasco-Zevallos OM, et al. A machine learning approach to liver histological evaluation predicts clinically significant portal hypertension in NASH cirrhosis. Hepatology. 2021;74(6):3146–3160. doi: 10.1002/hep.32087 EDN: TBAWLW</mixed-citation></ref><ref id="B22"><label>22.</label><mixed-citation>Jana A, Qu H, Rattan P, et al. Deep learning based NAS score and fibrosis stage prediction from CT and pathology data. In: 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE). Cincinnati: IEEE; 2020. P. 981–986. doi: 10.1109/bibe50027.2020.00166</mixed-citation></ref><ref id="B23"><label>23.</label><mixed-citation>Puri M. Automated machine learning diagnostic support system as a computational biomarker for detecting drug-induced liver injury patterns in whole slide liver pathology images. ASSAY and Drug Development Technologies. 2020;18(1):1–10. doi: 10.1089/adt.2019.919 EDN: PZAYLW</mixed-citation></ref><ref id="B24"><label>24.</label><mixed-citation>Janowczyk A, Madabhushi A. Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases. Journal of Pathology Informatics. 2016;7(1):29. doi: 10.4103/2153-3539.186902 EDN: YFGJPV</mixed-citation></ref><ref id="B25"><label>25.</label><mixed-citation>Kandel I, Castelli M. The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset. ICT Express. 2020;6(4):312–315. doi: 10.1016/j.icte.2020.04.010 EDN: UENNRQ</mixed-citation></ref><ref id="B26"><label>26.</label><mixed-citation>Borbat AM, Lishchuk SV. The first Russian breast pathology histologic images data set. Medical Doctor and IT. 2020;(3):25–30. doi: 10.37690/1811-0193-2020-3-25-30 EDN: RBLTUN</mixed-citation></ref><ref id="B27"><label>27.</label><mixed-citation>Williams Jr DKA, Graifman G, Hussain N, et al. Digital pathology, deep learning, and cancer: a narrative review. Translational Cancer Research. 2024;13(5):2544–2560. doi: 10.21037/tcr-23-964 EDN: QFGVDF</mixed-citation></ref><ref id="B28"><label>28.</label><mixed-citation>Taylor-Weiner A, Pokkalla H, Han L, et al. A machine learning approach enables quantitative measurement of liver histology and disease monitoring in NASH. Hepatology. 2021;74(1):133–147. doi: 10.1002/hep.31750 EDN: JQEBBT</mixed-citation></ref><ref id="B29"><label>29.</label><mixed-citation>Baek EB, Hwang JH, Park H, et al. Artificial intelligence-assisted image analysis of acetaminophen-induced acute hepatic injury in sprague-dawley rats. Diagnostics. 2022;12(6):1478. doi: 10.3390/diagnostics12061478 EDN: NVUYFC</mixed-citation></ref><ref id="B30"><label>30.</label><mixed-citation>Naglah A, Khalifa F, El-Baz A, Gondim D. Conditional GANs based system for fibrosis detection and quantification in Hematoxylin and Eosin whole slide images. Medical Image Analysis. 2022;81:102537. doi: 10.1016/j.media.2022.102537 EDN: FTOHBE</mixed-citation></ref><ref id="B31"><label>31.</label><mixed-citation>Qu H, Minacapelli CD, Tait C, et al. Training of computational algorithms to predict NAFLD activity score and fibrosis stage from liver histopathology slides. Computer Methods and Programs in Biomedicine. 2021;207:106153. doi: 10.1016/j.cmpb.2021.106153 EDN: VZIOAF</mixed-citation></ref><ref id="B32"><label>32.</label><mixed-citation>Sulyok M, Luibrand J, Strohäker J, et al. Implementing deep learning models for the classification of Echinococcus multilocularis infection in human liver tissue. Parasites &amp; Vectors. 2023;16(1):29. doi: 10.1186/s13071-022-05640-w EDN: SUNVTS</mixed-citation></ref><ref id="B33"><label>33.</label><mixed-citation>Ramot Y, Deshpande A, Morello V, et al. Microscope-based automated quantification of liver fibrosis in mice using a deep learning algorithm. Toxicologic Pathology. 2021;49(5):1126–1133. doi: 10.1177/01926233211003866 EDN: ORWPSE</mixed-citation></ref><ref id="B34"><label>34.</label><mixed-citation>Hwang JH, Kim HJ, Park H, et al. Implementation and practice of deep learning-based instance segmentation algorithm for quantification of hepatic fibrosis at whole slide level in sprague-dawley rats. Toxicologic Pathology. 2021;50(2):186–196. doi: 10.1177/01926233211057128 EDN: UVMNUH</mixed-citation></ref><ref id="B35"><label>35.</label><mixed-citation>Baek EB, Lee J, Hwang JH, et al. Application of multiple-finding segmentation utilizing Mask R-CNN-based deep learning in a rat model of drug-induced liver injury. Scientific Reports. 2023;13(1):17555. doi: 10.1038/s41598-023-44897-8 EDN: OBHXFO</mixed-citation></ref><ref id="B36"><label>36.</label><mixed-citation>Hwang JH, Lim M, Han G, et al. Segmentation algorithm can be used for detecting hepatic fibrosis in SD rat. Laboratory Animal Research. 2023;39(1):16. doi: 10.1186/s42826-023-00167-2 EDN: GZLDOM</mixed-citation></ref><ref id="B37"><label>37.</label><mixed-citation>Yu Y, Wang J, Ng CW, et al. Deep learning enables automated scoring of liver fibrosis stages. Scientific Reports. 2018;8(1):1–10. doi: 10.1038/s41598-018-34300-2 EDN: PWYNUB</mixed-citation></ref><ref id="B38"><label>38.</label><mixed-citation>Zingman I, Stierstorfer B, Lempp C, Heinemann F. Learning image representations for anomaly detection: Application to discovery of histological alterations in drug development. Medical Image Analysis. 2024;92:103067. doi: 10.1016/j.media.2023.103067 EDN: UDLPMJ</mixed-citation></ref><ref id="B39"><label>39.</label><mixed-citation>Gerussi A, Saldanha OL, Cazzaniga G et al. Deep learning helps discriminate between autoimmune hepatitis and primary biliary cholangitis. JHEP Reports: Innovation in Hepatology. 2024;7(2):101198. doi: 10.1016/j.jhepr.2024.101198 EDN: RESQRS</mixed-citation></ref><ref id="B40"><label>40.</label><mixed-citation>Ko SM, Shin J, Hong Y, et al. Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitis. Frontiers in Medicine. 2025;12:1629036. doi: 10.3389/fmed.2025.1629036 EDN: GHFZOA</mixed-citation></ref><ref id="B41"><label>41.</label><mixed-citation>Shabanian M, Taylor Z, Woods C, et al. Liver fibrosis classification on trichrome histology slides using weakly supervised learning in children and young adults. Journal of Pathology Informatics. 2025;16:100416. doi: 10.1016/j.jpi.2024.100416 EDN: EAZVWE</mixed-citation></ref><ref id="B42"><label>42.</label><mixed-citation>Nakatsuka T, Tateishi R, Sato M, et al. Deep learning and digital pathology powers prediction of HCC development in steatotic liver disease. Hepatology. 2024;81(3):976–989. doi: 10.1097/HEP.0000000000000904 EDN: STZUDU</mixed-citation></ref><ref id="B43"><label>43.</label><mixed-citation>Cazzaniga G, L’Imperio V, Bonoldi E, et al. Automating liver biopsy segmentation with a robust, open-source tool for pathology research: the HOTSPoT model. NPJ Digital Medicine. 2025;8(1):455. doi: 10.1038/s41746-025-01870-1 EDN: EYTRNG</mixed-citation></ref><ref id="B44"><label>44.</label><mixed-citation>Li B, He Q, Chang J, et al. Toward efficient slide-level grading of liver biopsy via explainable deep learning framework. Medical &amp; Biological Engineering &amp; Computing. 2025;63(5):1435–1449. doi: 10.1007/s11517-024-03266-x EDN: TCKEQZ</mixed-citation></ref><ref id="B45"><label>45.</label><mixed-citation>Aatresh AA, Alabhya K, Lal S, et al. LiverNet: efficient and robust deep learning model for automatic diagnosis of sub-types of liver hepatocellular carcinoma cancer from H&amp;E stained liver histopathology images. International Journal of Computer Assisted Radiology and Surgery. 2021;16(9):1549–1563. doi: 10.1007/s11548-021-02410-4 EDN: OJMODY</mixed-citation></ref><ref id="B46"><label>46.</label><mixed-citation>Hwang JH, Lim M, Han G, et al. Preparing pathological data to develop an artificial intelligence model in the nonclinical study. Scientific Reports. 2023;13(1):3896. doi: 10.1038/s41598-023-30944-x EDN: TACKEA</mixed-citation></ref><ref id="B47"><label>47.</label><mixed-citation>Pischon H, Mason D, Lawrenz B, et al. Artificial intelligence in toxicologic pathology: quantitative evaluation of compound-induced hepatocellular hypertrophy in rats. Toxicologic Pathology. 2021;49(4):928–937. doi: 10.1177/0192623320983244 EDN: HXOFII</mixed-citation></ref><ref id="B48"><label>48.</label><mixed-citation>Sjöblom N, Boyd S, Manninen A, et al. Chronic cholestasis detection by a novel tool: automated analysis of cytokeratin 7-stained liver specimens. Diagnostic Pathology. 2021;16(1):1–12. doi: 10.1186/s13000-021-01102-6 EDN: YGONZK</mixed-citation></ref><ref id="B49"><label>49.</label><mixed-citation>Ercan C, Kordy K, Knuuttila A, et al. A deep-learning-based model for assessment of autoimmune hepatitis from histology: AI(H). Virchows Archiv. 2024;485(6):1095–1105. doi: 10.1007/s00428-024-03841-5 EDN: TLAMKC</mixed-citation></ref><ref id="B50"><label>50.</label><mixed-citation>Preechathammawong N, Charoenpitakchai M, Wongsason N, et al. Development of a diagnostic support system for the fibrosis of nonalcoholic fatty liver disease using artificial intelligence and deep learning. The Kaohsiung Journal of Medical Sciences. 2024;40(8):757–765. doi: 10.1002/kjm2.12850 EDN: LXBSFF</mixed-citation></ref><ref id="B51"><label>51.</label><mixed-citation>Pérez-Sanz F, Riquelme-Pérez M, Martínez-Barba E, et al. Efficiency of machine learning algorithms for the determination of macrovesicular steatosis in frozen sections stained with sudan to evaluate the quality of the graft in liver transplantation. Sensors. 2021;21(6):1993. doi: 10.3390/s21061993 EDN: TWYHID</mixed-citation></ref><ref id="B52"><label>52.</label><mixed-citation>Sjöblom N, Boyd S, Manninen A, et al. Automated image analysis of keratin 7 staining can predict disease outcome in primary sclerosing cholangitis. Hepatology Research. 2022;53(4):322–333. doi: 10.1111/hepr.13867 EDN: YBGSRL</mixed-citation></ref><ref id="B53"><label>53.</label><mixed-citation>Jadon S. A survey of loss functions for semantic segmentation. In: 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). Via del Mar: IEEE; 2020. P. 1–7. doi: 10.1109/cibcb48159.2020.9277638</mixed-citation></ref><ref id="B54"><label>54.</label><mixed-citation>Ashour AS, Hawas AR, Guo Y. Comparative study of multiclass classification methods on light microscopic images for hepatic schistosomiasis fibrosis diagnosis. Health Information Science and Systems. 2018;6(1):1–12. doi: 10.1007/s13755-018-0047-z EDN: AUEQQI</mixed-citation></ref><ref id="B55"><label>55.</label><mixed-citation>Arjmand A, Tsipouras MG, Tzallas AT, et al. Quantification of liver fibrosis — a comparative study. Applied Sciences. 2020;10(2):447. doi: 10.3390/app10020447 EDN: UOWQGU</mixed-citation></ref></ref-list></back></article>
