<?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">sapi</journal-id><journal-title-group><journal-title xml:lang="ru">Системный анализ и прикладная информатика</journal-title><trans-title-group xml:lang="en"><trans-title>«System analysis and applied information science»</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2309-4923</issn><issn pub-type="epub">2414-0481</issn><publisher><publisher-name>Belarusian National Technical University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21122/2309-4923-2025-3-47-58</article-id><article-id custom-type="elpub" pub-id-type="custom">sapi-763</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>Обработка информации и принятие решений</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Data processing and decision–making</subject></subj-group></article-categories><title-group><article-title>Объективная оценка качества цифровых изображений сетчатки при скрининговом исследовании</article-title><trans-title-group xml:lang="en"><trans-title>Objective quality assessment of digital retinal images in screening study</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>Голуб</surname><given-names>Ю. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Golub</surname><given-names>Yu. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Голуб Юлия Игоревна – Кандидат технических наук, доцент, ведущий научный сотрудник.</p><p> г. Минск</p></bio><bio xml:lang="en"><p>Yuliya I. Golub – PhD, Associate Professor, Leading Researcher.</p><p>Minsk</p><p> </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>Старовойтов</surname><given-names>В. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Starovoitov</surname><given-names>V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Старовойтов Валерий Васильевич – Доктор технических наук, профессор, главный научный сотрудник.</p><p>г. Минск </p></bio><bio xml:lang="en"><p>Valery Starovoitov – Doctor of Science, Professor.</p><p>Minsk</p></bio><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Объединенный институт проблем информатики Национальной академии наук Беларуси</institution><country>Беларусь</country></aff><aff xml:lang="en"><institution>United Institute of Informatics Problems, National Academy of Sciences of Belarus</institution><country>Belarus</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>16</day><month>10</month><year>2025</year></pub-date><volume>0</volume><issue>3</issue><fpage>47</fpage><lpage>58</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Голуб Ю.И., Старовойтов В.В., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Голуб Ю.И., Старовойтов В.В.</copyright-holder><copyright-holder xml:lang="en">Golub Y.I., Starovoitov V.</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://sapi.bntu.by/jour/article/view/763">https://sapi.bntu.by/jour/article/view/763</self-uri><abstract><p>В статье представлен новый метод автоматизированной безэталонной количественной оценки качества цифровых изображений сетчатки для задач скрининга диабетической ретинопатии. Предложенный метод не требует локализации анатомических структур и основан на анализе центрального фрагмента изображения в зелёном спектральном канале с применением параметра масштаба распределения Вейбулла для интеграции локальных оценок качества. Проведён сравнительный анализ 36 безэталонных функций, выбраны две оценки, показавшие наиболее стабильные результаты. Экспериментально показано, что использование центрального фрагмента (crop) размером 50–67 % от исходных размеров снимка позволяет повысить точность оценки качества на 40 % по сравнению с анализом полного кадра. Масштабирование этого фрагмента до 512×512 пикселей сокращает время анализа снимка до 20 раз без потери точности. Эффективность метода подтверждена на трех тысячах изображениях из различных источников (базы Kaggle, DDR, белорусские клинические данные). Разработанный подход не требует эталонных данных и может быть интегрирован в системы массового скрининга изображений глазного дна, снижая нагрузку на специалистов, повышая доступность диагностики для пациентов при ограниченных вычислительных ресурсах.</p></abstract><trans-abstract xml:lang="en"><p>The paper presents a new method for automated no-reference quantitative assessment of the quality of digital retinal images for diabetic retinopathy screening. The proposed method does not require localization of anatomical structures and is based on the analysis of the central fragment of the image in the green spectral channel using the Weibull distribution scale parameter for integrating local quality estimates. A comparative analysis of 36 no-reference functions was carried out, two evaluation measures that showed the best results were selected. It was experimentally shown that using a central fragment 50–67% of the original image size allows increasing the accuracy of image quality assessment by 40 % compared to full-image analysis. Scaling this fragment to 512×512 pixels reduces the image analysis time by up to 20 times without losing accuracy. The effectiveness of the method was confirmed on three thousand images from various sources: Kaggle and DDR databases, Belarusian clinical data. The developed approach does not require reference data and can be integrated into mass screening systems of fundus images, reducing the workload of specialists and increasing the availability of diagnostics for patients with limited computing resources.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>диабетическая ретинопатия</kwd><kwd>безэталонная оценка качества изображения</kwd><kwd>скрининг</kwd><kwd>обработка изображения сетчатки</kwd><kwd>масштабирование изображения</kwd><kwd>распределение Вейбулла</kwd><kwd>цифровая офтальмология</kwd></kwd-group><kwd-group xml:lang="en"><kwd>diabetic retinopathy</kwd><kwd>no-reference image quality assessment</kwd><kwd>screening</kwd><kwd>retinal image processing</kwd><kwd>image scaling</kwd><kwd>Weibull distribution</kwd><kwd>digital ophthalmology</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено в рамках проекта № Ф23ИНДГ-004.</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">Curran, K. Inclusion of diabetic retinopathy screening strategies in national-level diabetes care planning in low- and middle-income countries: a scoping review / K. Curran, P. Piyasena, N. Congdon [et al.] // Health Research Policy and Systems. 2023. Vol. 21, № 2. DOI: 10.1186/s12961-022-00940-0</mixed-citation><mixed-citation xml:lang="en">Curran K, Piyasena P, Congdon N, Duke L, Malanda B, Peto T. Inclusion of diabetic retinopathy screening strategies in national-level diabetes care planning in low- and middle-income countries: a scoping review. Health Research Policy and Systems. 2023;21(2). DOI: 10.1186/s12961-022-00940-0</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Nørgaard, M. F. Automated screening for diabetic retinopathy - A systematic review / M. F. Nørgaard, J. Grauslund // Ophthalmic research. 2018. Vol. 60, № 1. P. 9–17. DOI: 10.1159/000486284</mixed-citation><mixed-citation xml:lang="en">Nørgaard MF, Grauslund J. Automated screening for diabetic retinopathy - A systematic review. Ophthalmic research. 2018;60(1):9–17. DOI: 10.1159/000486284</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Павлов, В. Г. Современные тенденции скрининга диабетической ретинопатии / В. Г. Павлов, А. Л. Сидамонидзе, Д. В. Петрачков // Вестник офтальмологии. 2020. Т. 136, № 4. С. 300–309. DOI: 10.17116/oftalma2020136042300</mixed-citation><mixed-citation xml:lang="en">Pavlov VG, Sidamonidze AL, Petrachkov DV. Current trends in the screening for diabetic retinopathy. Russian Annals of Ophthalmology. 2020;136(4):300–309. (In Russ.). DOI: 10.17116/oftalma2020136042300</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Avidor, D. Cost-effectiveness of diabetic retinopathy screening programs using telemedicine: a systematic review / D. Avidor, A. Loewenstein, M. Waisbourd, A. Nutman // Cost Effectiveness and Resource Allocation. 2020. Vol. 18. P. 1–9. DOI: 10.1186/s12962-020-00211-1</mixed-citation><mixed-citation xml:lang="en">Avidor D. Loewenstein A, Waisbourd M, Nutman A. Cost-effectiveness of diabetic retinopathy screening programs using telemedicine: a systematic review. Cost Effectiveness and Resource Allocation. 2020;18:1–9. DOI: 10.1186/s12962-020-00211-1</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Tung, T. H. Economic evaluation of screening for diabetic retinopathy among Chinese type 2 diabetics: a community-based study in Kinmen / T. H. Tung [и др.] // Taiwan. J Epidemiol. 2008. Vol. 18, № 5. P. 225–33. DOI: 10.2188/jea.je2007439</mixed-citation><mixed-citation xml:lang="en">Tung T-H, Shih H-C, Chen S-J, Chou P, Liu C-M, Liu J-H. Economic evaluation of screening for diabetic retinopathy among Chinese type 2 diabetics: a community-based study in Kinmen, Taiwan. J Epidemiol. 2008;18(5):225–33. DOI: 10.2188/jea.je2007439</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Biswas, S. Which color channel is better for diagnosing retinal diseases automatically in color fundus photographs? / S. Biswas, Md. I. A. Khan, Md. T. Hossain, A. Biswas [et al.] // Life (Basel). 2022. Vol. 12, № 7. P. 973. DOI: 10.3390/life12070973</mixed-citation><mixed-citation xml:lang="en">Biswas S, Khan MdIA, Hossain MdT, Biswas A, Nakai T, Rohdin J. Which color channel is better for diagnosing retinal diseases automatically in color fundus photographs? Life (Basel). 2022;12(7):973. DOI: 10.3390/life12070973</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Guo, T. Refined image quality assessment for color fundus photography based on deep learning / T. Guo, K. Liu, H. Zou [et al.] // Digital Health. 2024. Vol. 10. P. 1–13. DOI: 10.1177/20552076231207582</mixed-citation><mixed-citation xml:lang="en">Guo T, Liu K, Zou H, Xu X, Yang J, Yu Q. Refined image quality assessment for color fundus photography based on deep learning. Digital Health. 2024;10:1–13. DOI: 10.1177/20552076231207582</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">1000 Fundus images with 39 categories. URL: https://www.kaggle.com/datasets/linchundan/fundusimage1000/data (дата обращения: 19.05.2025).</mixed-citation><mixed-citation xml:lang="en">1000 Fundus images with 39 categories. URL: https://www.kaggle.com/datasets/linchundan/fundusimage1000/data (date of access: 19.05.2025).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Li T. Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening / Tao Li, Yingqi Gao, Kai Wang [et al.] // Information Sciences. 2019. Vol. 501. P. 511–522. DOI: 10.1016/j.ins.2019.06.011</mixed-citation><mixed-citation xml:lang="en">Li T, Gao Y, Wang K, Guo S, Liu H, Kang H. Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening. Information Sciences. 2019;501:511–522. DOI: 10.1016/j.ins.2019.06.011</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Lundström C. Technical report: Measuring digital image quality. 2006. 15 p.</mixed-citation><mixed-citation xml:lang="en">Lundström C. Technical report: Measuring digital image quality. 2006. 15 p.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Keelan B. Handbook of image quality: characterization and prediction / by Brian Keelan. CRC Press, 2002. 544 p. DOI: 10.1201/9780203910825.</mixed-citation><mixed-citation xml:lang="en">Keelan B. Handbook of image quality: characterization and prediction. CRC Press; 2002. 544 p. DOI: 10.1201/9780203910825</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Голуб Ю. И., Старовойтов В. В. Оценка качества цифровых изображений. Минск : ОИПИ НАН Беларуси, 2023. 252 с.</mixed-citation><mixed-citation xml:lang="en">Golub YI, Starovoitov VV. Image quality assessment. Minsk: OIPI NAN Belarus; 2023. 252 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Amin, J. A. Review on recent developments for detection of diabetic retinopathy / J. Amin, M. Sharif, M. Yasmin // Scientifica (Cairo). 2016. Vol. 2016 (6838976). DOI: 10.1155/2016/6838976</mixed-citation><mixed-citation xml:lang="en">Amin J, Sharif M, Yasmin M. Review on recent developments for detection of diabetic retinopathy. Scientifica (Cairo). 2016;2016:6838976. DOI: 10.1155/2016/6838976</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Raja, D. S. S. Performance analysis of retinal image blood vessel segmentation / D. S. S. Raja, S. Vasuki, D. R. Kumar // Advanced Computing: An international journal. 2014. Vol. 5, № 2/3. P. 17–23. DOI: 10.5121/acij.2014.5302</mixed-citation><mixed-citation xml:lang="en">Raja D.S.S. Vasuki S, Kumar DR. Performance analysis of retinal image blood vessel segmentation. Advanced Computing: An international journal. 2014;5(2/3):17–23. DOI: 10.5121/acij.2014.5302</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Long, S. Microaneurysms detection in color fundus images using machine learning based on directional local contrast / S. Long, J. Chen, A. Hu [et al.] // Biomedical engineering online. 2020. Vol. 19(21). DOI: 10.1186/s12938-020-00766-3</mixed-citation><mixed-citation xml:lang="en">Long S, Chen J, Hu A, Liu H, Chen Z, Zheng D. Microaneurysms detection in color fundus images using machine learning based on directional local contrast. Biomedical engineering online. 2020;19(21). DOI: 10.1186/s12938-020-00766-3</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Старовойтов, В. В. Оценка качества цифровых изображений сетчатки / В. В. Старовойтов, Ю. И. Голуб, М. М. Лукашевич // Системный анализ и прикладная информатика. 2021. № 4. С. 25–38.</mixed-citation><mixed-citation xml:lang="en">Starovoitov VV, Golub YuI, Lukashevich ММ. Digital fundus image quality assessment. System analysis and applied information science. 2021;4:25–38. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Starovoitov, V. A universal retinal image template for automated screening of diabetic retinopathy / V. V. Starovoitov, Yu. I. Golub, M. V. Lukashevich // Pattern Recognition and Image Analysis. 2022. Vol 32. P. 322–331. 10.1134/S1054661822020195</mixed-citation><mixed-citation xml:lang="en">Starovoitov VV, Golub YuI, Lukashevich ММ. A universal retinal image template for automated screening of diabetic retinopathy. Pattern Recognition and Image Analysis. 2022;32:322–331. DOI: 10.1134/S1054661822020195</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>
