<?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="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Computational nanotechnology</journal-id><journal-title-group><journal-title xml:lang="en">Computational nanotechnology</journal-title><trans-title-group xml:lang="kk"><trans-title>Computational nanotechnology</trans-title></trans-title-group><trans-title-group xml:lang="pt"><trans-title>Computational nanotechnology</trans-title></trans-title-group><trans-title-group xml:lang="ru"><trans-title>Computational nanotechnology</trans-title></trans-title-group><trans-title-group xml:lang="zh"><trans-title>Computational nanotechnology</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2313-223X</issn><issn publication-format="electronic">2587-9693</issn><publisher><publisher-name xml:lang="en">YUR-VAK</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">678143</article-id><article-id pub-id-type="doi">10.33693/2313-223X-2025-12-2-109-118</article-id><article-id pub-id-type="edn">QYVOSN</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>INFORMATICS AND INFORMATION PROCESSING</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>ИНФОРМАТИКА И ИНФОРМАЦИОННЫЕ ПРОЦЕССЫ</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Post-processing of medical image segmentation results</article-title><trans-title-group xml:lang="ru"><trans-title>Постобработка результатов сегментации медицинских изображений</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0008-5159-0123</contrib-id><contrib-id contrib-id-type="spin">5931-1617</contrib-id><name-alternatives><name xml:lang="en"><surname>Ermolenko</surname><given-names>Sergey V.</given-names></name><name xml:lang="ru"><surname>Ермоленко</surname><given-names>Сергей Витальевич</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>postgraduate student</p></bio><bio xml:lang="ru"><p>аспирант</p></bio><email>ermolenko@math.vsu.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-8664-9817</contrib-id><contrib-id contrib-id-type="spin">1299-4820</contrib-id><name-alternatives><name xml:lang="en"><surname>Kashirina</surname><given-names>Irina L.</given-names></name><name xml:lang="ru"><surname>Каширина</surname><given-names>Ирина Леонидовна</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Professor, Department of Mathematical Methods of Operations Research; Dr. Sci. (Eng.); Professor, Department of Artificial Intelligence Technologies</p></bio><bio xml:lang="ru"><p>профессор, кафедра математических методов исследования операций; доктор технических наук; профессор, кафедра технологий искусственного интеллекта</p></bio><email>kash.irina@mail.ru</email><xref ref-type="aff" rid="aff1"/><xref ref-type="aff" rid="aff2"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="spin">3001-6791</contrib-id><name-alternatives><name xml:lang="en"><surname>Starichkova</surname><given-names>Yulia V.</given-names></name><name xml:lang="ru"><surname>Старичкова</surname><given-names>Юлия Викторовна</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Cand. Sci. (Eng.); Head, Department of Artificial Intelligence Technologies</p></bio><bio xml:lang="ru"><p>кандидат технических наук; заведующая, кафедра технологий искусственного интеллекта</p></bio><email>starichkova@mirea.ru</email><xref ref-type="aff" rid="aff2"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Voronezh State University</institution></aff><aff><institution xml:lang="ru">Воронежский государственный университет</institution></aff></aff-alternatives><aff-alternatives id="aff2"><aff><institution xml:lang="en">MIREA – Russian Technological University</institution></aff><aff><institution xml:lang="ru">МИРЭА – Российский технологический университет</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2025-08-19" publication-format="electronic"><day>19</day><month>08</month><year>2025</year></pub-date><volume>12</volume><issue>2</issue><issue-title xml:lang="en"/><issue-title xml:lang="ru"/><fpage>109</fpage><lpage>118</lpage><history><date date-type="received" iso-8601-date="2025-04-04"><day>04</day><month>04</month><year>2025</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2025, Yur-VAK</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2025, Юр-ВАК</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="en">Yur-VAK</copyright-holder><copyright-holder xml:lang="ru">Юр-ВАК</copyright-holder><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/" start_date="2026-08-19"/><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://journals.eco-vector.com/2313-223X/about/editorialPolicies</ali:license_ref></license></permissions><self-uri xlink:href="https://journals.eco-vector.com/2313-223X/article/view/678143">https://journals.eco-vector.com/2313-223X/article/view/678143</self-uri><abstract xml:lang="en"><p>In modern medical diagnostics, computer vision and deep learning play an increasingly important role, especially in the analysis of complex 3D medical images. A significant obstacle to the implementation of modern deep learning algorithms in clinical practice are artifacts and inaccuracies of the primary classification by neural networks. In this paper, we systematized the main post-processing methods used in medical image segmentation tasks and reviewed related works on this topic. The aim of the study is to develop post-processing methods to eliminate segmentation errors associated with spatial incoherence and incorrect classification of 3D image voxels. In this paper, we propose a post-processing module for CT image segmentation results that effectively solves the problems of intersecting and nested pathologies. Three algorithms have been developed and implemented to eliminate fragments of false positive responses of the neural network. Experimental verification has shown that the proposed algorithms successfully provide unified coherent pathologies, which improves the quality of segmentation and simplifies subsequent analysis. The developed post-processing module can be integrated with the existing neural network framework for segmentation of medical images nnU-Net, which will contribute to improving the quality of diagnostics. The results of the study open up prospects for further development of post-processing methods in the field of medical imaging and can find wide application in systems for supporting medical decision-making.</p></abstract><trans-abstract xml:lang="ru"><p>В современной медицинской диагностике компьютерное зрение и глубокое обучение играют все более значимую роль, особенно при анализе сложных трехмерных медицинских изображений. Существенным препятствием для внедрения современных алгоритмов глубокого обучения в клиническую практику являются артефакты и неточности первичной классификации нейронными сетями. В данной работе были систематизированы основные методы постобработки, применяемые в задачах сегментации медицинских изображений, и проведен обзор связанных работ на эту тему. Целью исследования является разработка методов постобработки для устранения ошибок сегментации, связанных с пространственной несвязностью и некорректной классификацией вокселей 3D-снимков. В работе предложен модуль постобработки результатов сегментации КТ-изображений, эффективно решающий проблемы пересекающихся и вложенных патологий. Разработаны и реализованы 3 алгоритма, позволяющие устранять фрагменты ложноположительных ответов нейронной сети. Экспериментальная проверка показала, что предложенные алгоритмы успешно обеспечивают получение единых связных патологий, что повышает качество сегментации и упрощает последующий анализ. Разработанный модуль постобработки может быть интегрирован c существующим нейросетевым фреймворком для сегментации медицинских изображений nnU-Net, что поспособствует улучшению качества диагностики. Результаты исследования открывают перспективы для дальнейшего развития методов постобработки в области медицинской визуализации и могут найти широкое применение в системах поддержки принятия врачебных решений.</p></trans-abstract><kwd-group xml:lang="en"><kwd>post-processing</kwd><kwd>computer vision</kwd><kwd>deep learning</kwd><kwd>image segmentation</kwd><kwd>medical diagnostics</kwd><kwd>probability maps</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>постобработка</kwd><kwd>компьютерное зрение</kwd><kwd>глубокое обучение</kwd><kwd>сегментация изображений</kwd><kwd>медицинская диагностика</kwd><kwd>карты вероятностей</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><citation-alternatives><mixed-citation xml:lang="en">Salvi M., Acharya U.R., Molinari F., Meiburger K.M. The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis. Computers in Biology and Medicine. 2021. Vol. 128. P. 104129.</mixed-citation><mixed-citation xml:lang="ru">Salvi M., Acharya U.R., Molinari F., Meiburger K.M. The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis // Computers in Biology and Medicine. 2021. Vol. 128. P. 104129.</mixed-citation></citation-alternatives></ref><ref id="B2"><label>2.</label><citation-alternatives><mixed-citation xml:lang="en">Camara G., Assunçao R., Carvalho A.X. et al. Bayesian inference for post-processing of remote-sensing image classification. Remote Sensing. 2024. Vol. 16. P. 4572.</mixed-citation><mixed-citation xml:lang="ru">Camara G., Assunçao R., Carvalho A.X. et al. Bayesian inference for post-processing of remote-sensing image classification // Remote Sensing. 2024. Vol. 16. P. 4572.</mixed-citation></citation-alternatives></ref><ref id="B3"><label>3.</label><citation-alternatives><mixed-citation xml:lang="en">Linkon A.H.M., Labib M.M., Hasan T. et al. Deep learning in prostate cancer diagnosis and Gleason grading in histopathology images: An extensive study. Informatics in Medicine Unlocked. 2021. Vol. 24. P. 100582.</mixed-citation><mixed-citation xml:lang="ru">Linkon A.H.M., Labib M.M., Hasan T. et al. Deep learning in prostate cancer diagnosis and Gleason grading in histopathology images: An extensive study // Informatics in Medicine Unlocked. 2021. Vol. 24. P. 100582.</mixed-citation></citation-alternatives></ref><ref id="B4"><label>4.</label><citation-alternatives><mixed-citation xml:lang="en">Karimi D., Nir G., Fazli L. et al. Deep learning-based gleason grading of prostate cancer from histopathology images – role of multiscale decision aggregation and data augmentation. IEEE J. Biomed. Heal. Informatics. 2019. Vol. 24. Pp. 1413–1426.</mixed-citation><mixed-citation xml:lang="ru">Karimi D., Nir G., Fazli L. et al. Deep learning-based gleason grading of prostate cancer from histopathology images – role of multiscale decision aggregation and data augmentation // IEEE J. Biomed. Heal. Informatics. 2019. Vol. 24. Pp. 1413–1426.</mixed-citation></citation-alternatives></ref><ref id="B5"><label>5.</label><citation-alternatives><mixed-citation xml:lang="en">Cipollari S., Guarrasi V., Pecoraro M. et al. Convolutional neural networks for automated classification of prostate multiparametric magnetic resonance imaging based on image quality. J. Magn. Reson. Imaging. 2022. Vol. 55. № 2. Pp. 480–490.</mixed-citation><mixed-citation xml:lang="ru">Cipollari S., Guarrasi V., Pecoraro M. et al. Convolutional neural networks for automated classification of prostate multiparametric magnetic resonance imaging based on image quality // J. Magn. Reson. Imaging. 2022. Vol. 55. № 2. Pp. 480–490.</mixed-citation></citation-alternatives></ref><ref id="B6"><label>6.</label><citation-alternatives><mixed-citation xml:lang="en">Le H., Gupta R., Hou L. et al. Utilizing automated breast cancer detection to identify spatial distributions of tumor infiltrating lymphocytes in invasive breast cancer. Am. J. Pathol. 2020. Vol. 190. No. 7.</mixed-citation><mixed-citation xml:lang="ru">Le H., Gupta R., Hou L. et al. Utilizing automated breast cancer detection to identify spatial distributions of tumor infiltrating lymphocytes in invasive breast cancer // Am. J. Pathol. 2020. Vol. 190. No. 7.</mixed-citation></citation-alternatives></ref><ref id="B7"><label>7.</label><citation-alternatives><mixed-citation xml:lang="en">Yan R., Ren F., Wang Z. et al. Breast cancer histopathological image classification using a hybrid deep neural network. Methods. 2020. Vol. 173. Pp. 52–60.</mixed-citation><mixed-citation xml:lang="ru">Yan R., Ren F., Wang Z. et al. Breast cancer histopathological image classification using a hybrid deep neural network // Methods. 2020. Vol. 173. Pp. 52–60.</mixed-citation></citation-alternatives></ref><ref id="B8"><label>8.</label><citation-alternatives><mixed-citation xml:lang="en">Li Y., Huang X., Wang Y. et al. U-net ensemble model for segmentation in histopathology images. In: MICCAI 2019 Workshop COMPAY. 2019.</mixed-citation><mixed-citation xml:lang="ru">Li Y., Huang X., Wang Y. et al. U-net ensemble model for segmentation in histopathology images // MICCAI 2019 Workshop COMPAY. 2019.</mixed-citation></citation-alternatives></ref><ref id="B9"><label>9.</label><citation-alternatives><mixed-citation xml:lang="en">Wei J.W., Tafe L.J., Linnik Y.A. et al. Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks. Sci. Rep. 2019. Vol. 9. Pp. 1–8.</mixed-citation><mixed-citation xml:lang="ru">Wei J.W., Tafe L.J., Linnik Y.A. et al. Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks // Sci. Rep. 2019. Vol. 9. Pp. 1–8.</mixed-citation></citation-alternatives></ref><ref id="B10"><label>10.</label><citation-alternatives><mixed-citation xml:lang="en">Leo M., Carcagnì P., Signore L. et al. Convolutional Neural Networks in the Diagnosis of Colon Adenocarcinoma. AI. 2024. Vol. 5. No. 1. Pp. 324–341.</mixed-citation><mixed-citation xml:lang="ru">Leo M., Carcagnì P., Signore L. et al. Convolutional Neural Networks in the Diagnosis of Colon Adenocarcinoma // AI. 2024. Vol. 5. No. 1. Pp. 324–341.</mixed-citation></citation-alternatives></ref><ref id="B11"><label>11.</label><citation-alternatives><mixed-citation xml:lang="en">Saeedi S., Rezayi S., Keshavarz H. et al. MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques. BMC Med. Inform. Decis. Mak. 2023. Vol. 23. P. 16.</mixed-citation><mixed-citation xml:lang="ru">Saeedi S., Rezayi S., Keshavarz H. et al. MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques // BMC Med. Inform. Decis. Mak. 2023. Vol. 23. P. 16.</mixed-citation></citation-alternatives></ref><ref id="B12"><label>12.</label><citation-alternatives><mixed-citation xml:lang="en">Zeng Z., Xie W., Zhang Y., Lu Y. RIC-UNet: An improved neural network based on UNet for nuclei segmentation in histology images. IEEE Access. 2019. Vol. 7. Pp. 21420–21428.</mixed-citation><mixed-citation xml:lang="ru">Zeng Z., Xie W., Zhang Y., Lu Y. RIC-UNet: An improved neural network based on UNet for nuclei segmentation in histology images // IEEE Access. 2019. Vol. 7. Pp. 21420–21428.</mixed-citation></citation-alternatives></ref><ref id="B13"><label>13.</label><citation-alternatives><mixed-citation xml:lang="en">Survarachakan S., Prasad P.J.R., Naseem R. et al. Deep learning for image-based liver analysis – A comprehensive review focusing on malignant lesions. Artificial Intelligence in Medicine. 2022. Vol. 130. P. 102331.</mixed-citation><mixed-citation xml:lang="ru">Survarachakan S., Prasad P.J.R., Naseem R. et al. Deep learning for image-based liver analysis – A comprehensive review focusing on malignant lesions // Artificial Intelligence in Medicine. 2022. Vol. 130. P. 102331.</mixed-citation></citation-alternatives></ref><ref id="B14"><label>14.</label><citation-alternatives><mixed-citation xml:lang="en">Bilic P., Christ P. et al. The Liver Tumor Segmentation Benchmark (LiTS). Medical Image Analysis. 2023. Vol. 84. P. 102680.</mixed-citation><mixed-citation xml:lang="ru">Bilic P., Christ P. et al. The Liver Tumor Segmentation Benchmark (LiTS) // Medical Image Analysis. 2023. Vol. 84. P. 102680.</mixed-citation></citation-alternatives></ref><ref id="B15"><label>15.</label><citation-alternatives><mixed-citation xml:lang="en">Virtanen P., Gommers R., Oliphant T.E. et al. SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nature Methods. 2020. Vol. 17. No. 3. Pp. 261–272.</mixed-citation><mixed-citation xml:lang="ru">Virtanen P., Gommers R., Oliphant T.E. et al. SciPy 1.0: Fundamental algorithms for scientific computing in Python // Nature Methods. 2020. Vol. 17. No. 3. Pp. 261–272.</mixed-citation></citation-alternatives></ref><ref id="B16"><label>16.</label><citation-alternatives><mixed-citation xml:lang="en">Kulikov A.A., Kashirina I.L., Savkina E.F. Segmentation of liver volumetric lesions in multiphase CT images using the nnU-Net framework. Modeling, Optimization and Information Technology. 2025. Vol. 13. No. 1 (48). (In Rus.)</mixed-citation><mixed-citation xml:lang="ru">Куликов А.А., Каширина И.Л., Савкина Е.Ф. Сегментация объемных образований печени на мультифазных КТ-изображениях с использованием фреймворка nnU-Net // Моделирование, оптимизация и информационные технологии. 2025. Т. 13. № 1 (48).</mixed-citation></citation-alternatives></ref><ref id="B17"><label>17.</label><citation-alternatives><mixed-citation xml:lang="en">Isensee F., Jaeger P.F., Kohl S.A. et al. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nature Methods. 2021. Vol. 18. No. 2. Pp. 203–211.</mixed-citation><mixed-citation xml:lang="ru">Isensee F., Jaeger P.F., Kohl S.A. et al. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation // Nature Methods. 2021. Vol. 18. No. 2. Pp. 203–211.</mixed-citation></citation-alternatives></ref></ref-list></back></article>
