bsuirДоклады БГУИРDoklady BGUIR1729-76482708-0382БГУИР10.35596/1729-7648-2024-22-3-84-92bsuir-3937Research ArticleСтатьиЭффективный алгоритм сегментации биомедицинских изображенийEffective Algorithm for Biomedical Image SegmentationДиДжаоDiZhao

Postgraduate at the Department of Information Technologies in Automated Systems

220013, Minsk, Brovki St., 6

Postgraduate at the Department of Information Technologies in Automated Systems

220013, Minsk, Brovki St., 6

ИТанYiTang

Master’s Student at the Department of Information Technologies in Automated Systems

220013, Minsk, Brovki St., 6

Master’s Student at the Department of Information Technologies in Automated Systems

220013, Minsk, Brovki St., 6

ГуриновичА. Б.GourinovitchA. B.

Gourinovitch Alevtina Borisovna, Assistant Professor at the Department of Information Technologies in Automated Systems

220013, Minsk, Brovki St., 6

Tel.: +375 29 622-69-34

Gourinovitch Alevtina Borisovna, Assistant Professor at the Department of Information Technologies in Automated Systems

220013, Minsk, Brovki St., 6

Tel.: +375 29 622-69-34

gurinovich@bsuir.byБелорусский государственный университет информатики и радиоэлектроникиBelarusian State University of Informatics and Radioelectronics2024240620242238492Copyright © Ди Д., И Т., Гуринович А.Б., 20242024Ди Д., И Т., Гуринович А.Б.Di Z., Yi T., Gourinovitch A.B.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://doklady.bsuir.by/jour/article/view/3937

Сегментация биомедицинских изображений играет важную роль в количественном анализе, клинической диагностике и медицинских манипуляциях. Объекты на медицинских изображениях имеют различный масштаб, тип, сложный фон и схожий внешний вид тканей, что усложняет извлечение информации. Для решения данной проблемы предлагается модуль, учитывающий особенности изображений, что позволит усовершенствовать биомедицинскую сеть сегментации изображений FE-Net. Неотъемлемая часть алгоритма FE-Net – механизм пропуска соединений, обеспечивающий соединение и объединение карт признаков из различных слоев в кодере и декодере. Признаки на уровне кодера комбинируются с  высокоуровневыми семантическими знаниями на уровне декодера. Алгоритм устанавливает связи между картами признаков, что используется в медицине для обработки изображений. Предлагаемый метод протестирован на трех общедоступных наборах данных: Kvasir-SEG, CVC-ClinicDB и 2018 Data Science Bowl. По результатам исследования установлено, что FE-Net демонстрирует лучшую производительность по сравнению с другими методами по показателям Intersection over Union и F1-оценки. Рассматриваемая сеть эффективнее справляется с деталями сегментации и границами объектов, сохраняя при этом высокую точность. Исследование проведено совместно с отделением магнитно-резонансной томографии Национального онкологического центра имени Н. Н. Александрова. Доступ к исходному коду алгоритма и дополнительным техническим деталям размещен по ссылке https://github.com/tyjcbzd/FE-Net.

Biomedical image segmentation plays an important role in quantitative analysis, clinical diagnosis, and  medical manipulation. Objects in medical images have different scales, types, complex backgrounds, and similar tissue appearances, making information extraction challenging. To solve this problem, a module is proposed that takes into account the features of images, which will improve the biomedical image segmentation network FE-Net. An integral part of the FE-Net algorithm is the connection skipping mechanism, which ensures the connection and fusion of feature maps from different layers in the encoder and decoder. Features at the encoder level are combined with high-level semantic knowledge at the decoder level. The algorithm establishes connections between feature maps, which is used in medicine for image processing. The proposed method is tested on three public datasets: Kvasir-SEG, CVC-ClinicDB and 2018 Data Science Bowl. Based on the results of the study, it  was found that FE-Net demonstrates better performance compared to other methods in terms of Intersection over Union and F1-score. The network under consideration copes more effectively with segmentation details and object boundaries, while maintaining high accuracy. The study was conducted jointly with the Department of Magnetic Resonance Imaging of the N. N. Alexandrov National Oncology Center. Access to the source code of the algorithm and additional technical details is available at https://github.com/tyjcbzd/FE-Net.

сегментация биомедицинских изображенийсвёрточная нейронная сетьмодуль распознавания признаковмеханизм вниманиясеть с U-образной архитектуройbiomedical image segmentationconvolution neural networkfeature aware moduleattention mechanismU-shaped networkРабота поддерживается Китайским стипендиальным советом.This work is funded by the China Scholarship Council.ReferencesLi tjens G., Kooi T., Bejnordi B. E., Adiyoso Setio А. А., Ciompi F., Ghafoorian M., et al. (2017) A Survey on Deep Learning in Medical Image Analysis. Medical Image Analysis. 60–88.Li tjens G., Kooi T., Bejnordi B. E., Adiyoso Setio А. А., Ciompi F., Ghafoorian M., et al. (2017) A Survey on Deep Learning in Medical Image Analysis. Medical Image Analysis. 60–88.Ronneberger O., Fischer P., Brox T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 18th International Conference . 234–241.Ronneberger O., Fischer P., Brox T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 18th International Conference . 234–241.Zhou Z., Rahman Siddiquee M. M., Tajbakhsh N., Liang J. (2018) Unet++: A Nested U-Net Architecture for Medical Image Segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 4th International Workshop DLMIA 2018, and 8th International Workshop ML-CDS 2018 . 3–11.Zhou Z., Rahman Siddiquee M. M., Tajbakhsh N., Liang J. (2018) Unet++: A Nested U-Net Architecture for Medical Image Segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 4th International Workshop DLMIA 2018, and 8th International Workshop ML-CDS 2018 . 3–11.Jha D., Smedsrud P. H., Riegler M. A., Johansen D. (2019) Resunet++: An Advanced Architecture for Medical Image Segmentation. In 2019 IEEE International Symposium on Multimedia . 225–255.Jha D., Smedsrud P. H., Riegler M. A., Johansen D. (2019) Resunet++: An Advanced Architecture for Medical Image Segmentation. In 2019 IEEE International Symposium on Multimedia . 225–255.Long J., Shelhamer E., Darrell T. (2015) Fully Convolutional Networks for Semantic Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3431–3440.Long J., Shelhamer E., Darrell T. (2015) Fully Convolutional Networks for Semantic Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3431–3440.Seo H., Huang C., Bassenne M., Xiao R., Xing L. (2019) Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images. IEEE Transactions on Medical Imaging . 39 (5), 1316–1325.Seo H., Huang C., Bassenne M., Xiao R., Xing L. (2019) Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images. IEEE Transactions on Medical Imaging . 39 (5), 1316–1325.He K., Zhang X., Ren S., Sun J. (2016) Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.He K., Zhang X., Ren S., Sun J. (2016) Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.Hu J., Shen L., Sun G. (2018) Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 7132–7141.Hu J., Shen L., Sun G. (2018) Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 7132–7141.Zhang Z., Liu Q., Wang Y. (2018) Road Extraction by Deep Residual U-Net. IEEE Geoscience and Remote Sensing Letters. 15 (5), 749–753.Zhang Z., Liu Q., Wang Y. (2018) Road Extraction by Deep Residual U-Net. IEEE Geoscience and Remote Sensing Letters. 15 (5), 749–753.Tomar N. K., Jha D., Riegler M. A., Johansen H. D., Johansen D., Rittscher J., et al. (2022) Fanet: A Feedback Attention Network for Improved Biomedical Image Segmentation. IEEE Transactions on Neural Networks and Learning Systems .Tomar N. K., Jha D., Riegler M. A., Johansen H. D., Johansen D., Rittscher J., et al. (2022) Fanet: A Feedback Attention Network for Improved Biomedical Image Segmentation. IEEE Transactions on Neural Networks and Learning Systems .Yang C., Guo X., Zhu M., Ibragimov B., Yuan Y. (2021) Mutual-Prototype Adaptation for Cross-Domain Polyp Segmentation. IEEE Journal of Biomedical and Health Informatics . 25 (10), 3886–3897. DOI: 10.1109/JBHI.2021.3077271.Yang C., Guo X., Zhu M., Ibragimov B., Yuan Y. (2021) Mutual-Prototype Adaptation for Cross-Domain Polyp Segmentation. IEEE Journal of Biomedical and Health Informatics . 25 (10), 3886–3897. DOI: 10.1109/JBHI.2021.3077271.Chlap P., Min H., Vandenberg N., Dowling J., Holloway L., Haworth A. (2021) A Review of Medical Image Data Augmentation Techniques for Deep Learning Applications. Journal of Medical Imaging and Radiation Oncology . 65 (5), 545–563. DOI: 10.1111/1754-9485.13261.Chlap P., Min H., Vandenberg N., Dowling J., Holloway L., Haworth A. (2021) A Review of Medical Image Data Augmentation Techniques for Deep Learning Applications. Journal of Medical Imaging and Radiation Oncology . 65 (5), 545–563. DOI: 10.1111/1754-9485.13261.Oktay O., Schlemper J., Folgoc L. L., Lee M., Heinrich M., Misawa K., et al. (2018) Attention U-Net: Learning Where to Look for the Pancreas. 1st Conference on Medical Imaging with Deep Learning (MIDL 2018), Amsterdam, the Netherlands.Oktay O., Schlemper J., Folgoc L. L., Lee M., Heinrich M., Misawa K., et al. (2018) Attention U-Net: Learning Where to Look for the Pancreas. 1st Conference on Medical Imaging with Deep Learning (MIDL 2018), Amsterdam, the Netherlands.Jha D., Riegler M. A., Johansen D., Halvorsen P., Johansen H. D. (2020) Doubleu-Net: A Deep Convolutional Neural Network for Medical Image Segmentation. In 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems. 558–564.Jha D., Riegler M. A., Johansen D., Halvorsen P., Johansen H. D. (2020) Doubleu-Net: A Deep Convolutional Neural Network for Medical Image Segmentation. In 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems. 558–564.Iqbal A., Sharif M., Khan M. A., Nisar W., Alhaisoni M. (2022) FF-UNet: A U-Shaped Deep Convolutional Neural Network for Multimodal Biomedical Image Segmentation. Cognitive Computation. 14 (4), 1287–1302.Iqbal A., Sharif M., Khan M. A., Nisar W., Alhaisoni M. (2022) FF-UNet: A U-Shaped Deep Convolutional Neural Network for Multimodal Biomedical Image Segmentation. Cognitive Computation. 14 (4), 1287–1302.

The authors declare that there are no conflicts of interest present.