<?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">dt</journal-id><journal-title-group><journal-title xml:lang="ru">Цифровая трансформация</journal-title><trans-title-group xml:lang="en"><trans-title>Digital Transformation</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2522-9613</issn><issn pub-type="epub">2524-2822</issn><publisher><publisher-name>Educational Establishment “Belarusian State University of Informatics and Radioelectronics”</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.35596/1729-7648-2025-31-4-55-64</article-id><article-id custom-type="elpub" pub-id-type="custom">dt-972</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>ТЕХНИЧЕСКИЕ НАУКИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>TECHNICAL SCIENCES</subject></subj-group></article-categories><title-group><article-title>Применение компьютерного зрения для автоматизированной обработки медицинских документов</article-title><trans-title-group xml:lang="en"><trans-title>Application of Computer Vision for Automated Processing of Medical Documents</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Курлюк</surname><given-names>Е. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Kurliuk</surname><given-names>Y. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Курлюк Евгений Александрович, оператор ПЭВМ науч.-исслед. лаб. ультразвуковых технологий и оборудования</p><p>220013, Минск, ул. П. Бровки, 6</p><p>Тел.: +379 29 794-86-00</p></bio><bio xml:lang="en"><p>Kurliuk Yauheni Aleksandrovich, PC Operator of the Research Laboratory of Ultrasound Technologies and Equipment</p><p>220013, Minsk, P. Brovki St., 6</p><p>Tel.: +379 29 794-86-00</p></bio><email xlink:type="simple">kurluke750@gmail.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>Ларченко</surname><given-names>Н. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Larchenko</surname><given-names>N. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ларченко Н. А., студент</p><p>Минск</p></bio><bio xml:lang="en"><p>Larchenko N. A., Student</p><p>Minsk</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>Давыдов</surname><given-names>М. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Davydov</surname><given-names>M. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Давыдов М. В., канд. техн. наук, доц., первый проректор</p><p>Минск</p></bio><bio xml:lang="en"><p>Davydov M. V., Сand. Sci. (Tech.), Associate Professor, First Vice-Rector</p><p>Minsk</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>Курлянская</surname><given-names>Е. К.</given-names></name><name name-style="western" xml:lang="en"><surname>Kurlyanskaya</surname><given-names>E. K.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Курлянская Е. К., д-р мед. наук, проф., зам. дир. по терапевтической помощи</p><p>Минск</p></bio><bio xml:lang="en"><p>Kurlyanskaya E. K., Dr. Sci. (Med.), Professor, Deputy Director for Therapeutic Care</p><p>Minsk</p></bio><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Белорусский государственный университет информатики и радиоэлектроники</institution></aff><aff xml:lang="en"><institution>Belarusian State University of Informatics and Radioelectronics</institution></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Республиканский научно-практический центр «Кардиология»</institution></aff><aff xml:lang="en"><institution>Scientific and Practical Centre “Cardiology”</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>23</day><month>12</month><year>2025</year></pub-date><volume>31</volume><issue>4</issue><fpage>55</fpage><lpage>64</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Курлюк Е.А., Ларченко Н.А., Давыдов М.В., Курлянская Е.К., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Курлюк Е.А., Ларченко Н.А., Давыдов М.В., Курлянская Е.К.</copyright-holder><copyright-holder xml:lang="en">Kurliuk Y.A., Larchenko N.A., Davydov M.V., Kurlyanskaya E.K.</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://dt.bsuir.by/jour/article/view/972">https://dt.bsuir.by/jour/article/view/972</self-uri><abstract><p>Рассмотрена задача автоматизации обработки медицинских изображений при диагностике артериальной гипертензии с применением методов искусственного интеллекта и технологий компьютерного зрения. Разработан программный компонент, обеспечивающий автоматическое извлечение и структурирование информации из визуальных представлений медицинских документов (включая результаты биохимического анализа, общего анализа крови и данных суточного мониторинга артериального давления), что позволяет минимизировать количество ошибок и ускорить процессы ввода и интерпретации медицинской информации. Созданы и апробованы алгоритмы предобработки изображений (увеличение разрешения изображения, устранение шумов, коррекция наклона), сегментации и распознавания текстовых данных с помощью нейросетевых моделей Real-ESRGAN и EasyOCR. Особое внимание уделено улучшению качества распознавания текста при наличии характерных артефактов, возникающих при сканировании или фотографировании документов. Для оценки качества использовались метрики CER, WER, исследовалась эффективность работы модуля с применением суперразрешения и без него. Результаты исследования подтвердили эффективность предлагаемого подхода и показали, что интеграция технологии Real-ESRGAN позволяет повысить точность обработки медицинских изображений в условиях наличия значительных шумов и низкого разрешения исходных данных. Практическая значимость исследования заключается в упрощении и ускорении процесса диагностики гипертонии и создании основы для персонализированного подхода к лечению пациентов.</p></abstract><trans-abstract xml:lang="en"><p>This paper examines the automation of medical image processing for diagnosing arterial hypertension using artiﬁcial intelligence and computer vision technologies. A software component has been developed that automatically extracts and structures information from visual representations of medical documents (including biochemical analysis results, complete blood counts, and 24-hour blood pressure monitoring data), minimizing errors and accelerating the process of entering and interpreting medical information. Algorithms for image preprocessing (increasing image resolution, noise removal, and tilt correction), segmentation, and text recognition were developed and tested using the Real-ESRGAN and EasyOCR neural network models. Particular attention was paid to improving text recognition quality in the presence of characteristic artifacts that arise when scanning or photographing documents. CER and WER metrics were used to evaluate quality, and the module's performance was assessed with and without superresolution. The results of the study conﬁrmed the eﬀectiveness of the proposed approach and demonstrated that the integration of Real-ESRGAN technology improves the accuracy of medical image processing in the presence of signiﬁcant noise and low-resolution source data. The practical signiﬁcance of the study lies in simplifying and accelerating the process of diagnosing hypertension and creating the basis for a personalized approach to patient treatment.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>гипертония</kwd><kwd>машинное обучение</kwd><kwd>компьютерное зрение</kwd><kwd>оптическое распознавание текста</kwd><kwd>увеличение разрешения изображения</kwd><kwd>обработка медицинских данных</kwd><kwd>предобработка изображений</kwd></kwd-group><kwd-group xml:lang="en"><kwd>hypertension</kwd><kwd>machine learning</kwd><kwd>computer vision</kwd><kwd>optical character recognition</kwd><kwd>image super-resolution</kwd><kwd>medical data processing</kwd><kwd>image preprocessing</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">Kjeldsen, S. E. Hypertension and Cardiovascular Risk: General Aspects / S. E. Kjeldsen // Pharmacological Research. 2018. Vol. 129. P. 95–99.</mixed-citation><mixed-citation xml:lang="en">Kjeldsen S. E. (2018) Hypertension and Cardiovascular Risk: General Aspects. Pharmacological Research. 129, 95–99.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Hypertension Management in the High Cardiovascular Risk Population / I. Maraj [et al.] // International Journal of Hypertension. 2013. https://doi.org/10.1155/2013/382802.</mixed-citation><mixed-citation xml:lang="en">Maraj I., Makaryus J. N., Ashkar A., McFarlane S. I., Makaryus A. N. (2013) Hypertension Management in the High Cardiovascular Risk Population. International Journal of Hypertension. 2013. https://doi.org/10.1155/2013/382802.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Handler, J. Clinical Challenges in Diagnosing and Managing Adult Hypertension / J. Handler // Cleveland Clinic Journal of Medicine. 2015. Vol. 82, Iss. 2. P. S36–S41.</mixed-citation><mixed-citation xml:lang="en">Handler J. (2015) Clinical Challenges in Diagnosing and Managing Adult Hypertension. Cleveland Clinic Journal of Medicine. 82 (2), S36–S41.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Автоматизация обработки медицинских данных с использованием компьютерного зрения: подходы и перспективы внедрения в кардиологии / Е. А. Курлюк [и др.] // Средства медицинской электроники и новые медицинские технологии: матер. XIV Междунар. науч.-техн. конф. «Медэлектроника–2024», Минск, 5–6 дек. 2024 г. Минск: Белор. гос. ун-т информ. и радиоэлек., 2024. С. 254–259.</mixed-citation><mixed-citation xml:lang="en">Kurlyuk E. A., Larchenko N. A., Davydov M. V., Kurlyanskaya E. K. (2024) Automation of Medical Data Processing Using Computer Vision: Approaches and Implementation Prospects in Cardiology. Proceedings of the XIV International Scientiﬁc and Technical Conference “Medelectronics–2024”, Minsk, Dec. 5–6. Minsk, Belarusian State University of Informatics and Radioelectronics. 254–259 (in Russian).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Применение искусственного интеллекта в кардиологии и перспективы его дальнейшего внедрения / Н. А. Ларченко [и др.] // Средства медицинской электроники и новые медицинские технологии: матер. XIV Междунар. науч.-техн. конф. «Медэлектроника–2024», Минск, 5–6 дек. 2024 г. Минск: Белор. гос. ун-т информ. и радиоэлек., 2024. С. 12–16.</mixed-citation><mixed-citation xml:lang="en">Larchenko N. A., Kurlyuk E. A., Davydov M. V., Kurlyanskaya E. K. (2024) Application of Artiﬁcial Intelligence in Cardiology and Prospects for Its Implementation. Proceedings of the XIV International Scientiﬁc and Technical Conference “Medelectronics–2024”, Minsk, Dec. 5–6. Minsk, Belarusian State University of Informatics and Radioelectronics. 12–16 (in Russian).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Cardiac Imaging: Working Towards Fully-Automated Machine Analysis &amp; Interpretation / P. J. Slomka [et al.] // Expert Review of Medical Devices. 2017. Vol. 14, No 3. P. 197–212.</mixed-citation><mixed-citation xml:lang="en">Slomka P. J., Dey D., Sitek A., Motwani M., Berman D. S., Germano G. (2017) Cardiac Imaging: Working Towards Fully-Automated Machine Analysis &amp; Interpretation. Expert Review of Medical Devices. 14 (3), 197–212.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Artiﬁcial Intelligence as a Business Partner in Cardiovascular Precision Medicine: An Emerging Approach for Disease Detection and Treatment Optimization / V. Visco [et al.] // Current Medicinal Chemistry. 2021. Vol. 28. P. 6569–6590.</mixed-citation><mixed-citation xml:lang="en">Visco V., Ferruzzi G. J., Nicastro F., Virtuoso N., Carrizzo A., Galasso G., et al. (2021) Artiﬁcial Intelligence as a Business Partner in Cardiovascular Precision Medicine: An Emerging Approach for Disease Detection and Treatment Optimization. Current Medicinal Chemistry. 28, 6569–6590.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Highly Precise Risk Prediction Model for New-Onset Hypertension Using Artiﬁcial Intelligence Techniques / H. Kanegae [et al.] // The Journal of Clinical Hypertension. 2020. Vol. 22. P. 445–450.</mixed-citation><mixed-citation xml:lang="en">Kanegae H., Suzuki K., Fukatani K., Ito T., Harada N., Kario K. (2020) Highly Precise Risk Prediction Model for New-Onset Hypertension Using Artiﬁcial Intelligence Techniques. The Journal of Clinical Hypertension. 22, 445–450.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">An Application of Machine Learning to Etiological Diagnosis of Secondary Hypertension: Retrospective Study Using Electronic Medical Records / X. Diao [et al.] // JMIR Medical Informatics. 2021. Vol. 9. https://doi.org/10.2196/19739.</mixed-citation><mixed-citation xml:lang="en">Diao X., Huo Y., Zhanzheng Y., Wang H., Yuan J., Wang Y., et al. (2021) An Application of Machine Learning to Etiological Diagnosis of Secondary Hypertension: Retrospective Study Using Electronic Medical Records. JMIR Medical Informatics. 9. https://doi.org/10.2196/19739.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Li, Y. Improving Tabular Data Extraction in Scanned Laboratory Reports Using Deep Learning Models / Y. Li, Q. Wei // Journal of Biomedical Informatics. 2024. Vol. 159. P. 1–13.</mixed-citation><mixed-citation xml:lang="en">Li Y., Wei Q. (2024) Improving Tabular Data Extraction in Scanned Laboratory Reports Using Deep Learning Models. Journal of Biomedical Informatics. 159, 1–13.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">IRE: Improved Image Super-Resolution Based on Real-ESRGAN / Z. Zhu [et al.] // IEEE Access. 2023. Vol. 11. P. 45334–45348.</mixed-citation><mixed-citation xml:lang="en">Zhu Z., Lei Y., Qin Y., Zhu C., Zhu Y. (2023) IRE: Improved Image Super-Resolution Based on Real-ESRGAN. IEEE Access. 11, 45334–45348.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">De-Las-Heras, G. Advanced Driver Assistance Systems (ADAS) Based on Machine Learning Techniques for the Detection and Transcription of Variable Message Signs on Roads / G. De-Las-Heras, J. Sánchez-Soriano, E. Puertas // Sensors. 2021. Vol. 21, No 17. https://doi.org/10.3390/s21175866.</mixed-citation><mixed-citation xml:lang="en">De-Las-Heras G., Sánchez-Soriano J., Puertas E. (2021) Advanced Driver Assistance Systems (ADAS) Based on Machine Learning Techniques for the Detection and Transcription of Variable Message Signs on Roads. Sensors. 21 (17). https://doi.org/10.3390/s21175866.</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>
