Cargando…
BCR-UNet: Bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation
BACKGROUND: High precision segmentation of retinal blood vessels from retinal images is a significant step for doctors to diagnose many diseases such as glaucoma and cardiovascular diseases. However, at the peripheral region of vessels, previous U-Net-based segmentation methods failed to significant...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9722738/ https://www.ncbi.nlm.nih.gov/pubmed/36483248 http://dx.doi.org/10.3389/fpubh.2022.1056226 |
_version_ | 1784844020990607360 |
---|---|
author | Yi, Yugen Guo, Changlu Hu, Yangtao Zhou, Wei Wang, Wenle |
author_facet | Yi, Yugen Guo, Changlu Hu, Yangtao Zhou, Wei Wang, Wenle |
author_sort | Yi, Yugen |
collection | PubMed |
description | BACKGROUND: High precision segmentation of retinal blood vessels from retinal images is a significant step for doctors to diagnose many diseases such as glaucoma and cardiovascular diseases. However, at the peripheral region of vessels, previous U-Net-based segmentation methods failed to significantly preserve the low-contrast tiny vessels. METHODS: For solving this challenge, we propose a novel network model called Bi-directional ConvLSTM Residual U-Net (BCR-UNet), which takes full advantage of U-Net, Dropblock, Residual convolution and Bi-directional ConvLSTM (BConvLSTM). In this proposed BCR-UNet model, we propose a novel Structured Dropout Residual Block (SDRB) instead of using the original U-Net convolutional block, to construct our network skeleton for improving the robustness of the network. Furthermore, to improve the discriminative ability of the network and preserve more original semantic information of tiny vessels, we adopt BConvLSTM to integrate the feature maps captured from the first residual block and the last up-convolutional layer in a nonlinear manner. RESULTS AND DISCUSSION: We conduct experiments on four public retinal blood vessel datasets, and the results show that the proposed BCR-UNet can preserve more tiny blood vessels at the low-contrast peripheral regions, even outperforming previous state-of-the-art methods. |
format | Online Article Text |
id | pubmed-9722738 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-97227382022-12-07 BCR-UNet: Bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation Yi, Yugen Guo, Changlu Hu, Yangtao Zhou, Wei Wang, Wenle Front Public Health Public Health BACKGROUND: High precision segmentation of retinal blood vessels from retinal images is a significant step for doctors to diagnose many diseases such as glaucoma and cardiovascular diseases. However, at the peripheral region of vessels, previous U-Net-based segmentation methods failed to significantly preserve the low-contrast tiny vessels. METHODS: For solving this challenge, we propose a novel network model called Bi-directional ConvLSTM Residual U-Net (BCR-UNet), which takes full advantage of U-Net, Dropblock, Residual convolution and Bi-directional ConvLSTM (BConvLSTM). In this proposed BCR-UNet model, we propose a novel Structured Dropout Residual Block (SDRB) instead of using the original U-Net convolutional block, to construct our network skeleton for improving the robustness of the network. Furthermore, to improve the discriminative ability of the network and preserve more original semantic information of tiny vessels, we adopt BConvLSTM to integrate the feature maps captured from the first residual block and the last up-convolutional layer in a nonlinear manner. RESULTS AND DISCUSSION: We conduct experiments on four public retinal blood vessel datasets, and the results show that the proposed BCR-UNet can preserve more tiny blood vessels at the low-contrast peripheral regions, even outperforming previous state-of-the-art methods. Frontiers Media S.A. 2022-11-22 /pmc/articles/PMC9722738/ /pubmed/36483248 http://dx.doi.org/10.3389/fpubh.2022.1056226 Text en Copyright © 2022 Yi, Guo, Hu, Zhou and Wang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Public Health Yi, Yugen Guo, Changlu Hu, Yangtao Zhou, Wei Wang, Wenle BCR-UNet: Bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation |
title | BCR-UNet: Bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation |
title_full | BCR-UNet: Bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation |
title_fullStr | BCR-UNet: Bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation |
title_full_unstemmed | BCR-UNet: Bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation |
title_short | BCR-UNet: Bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation |
title_sort | bcr-unet: bi-directional convlstm residual u-net for retinal blood vessel segmentation |
topic | Public Health |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9722738/ https://www.ncbi.nlm.nih.gov/pubmed/36483248 http://dx.doi.org/10.3389/fpubh.2022.1056226 |
work_keys_str_mv | AT yiyugen bcrunetbidirectionalconvlstmresidualunetforretinalbloodvesselsegmentation AT guochanglu bcrunetbidirectionalconvlstmresidualunetforretinalbloodvesselsegmentation AT huyangtao bcrunetbidirectionalconvlstmresidualunetforretinalbloodvesselsegmentation AT zhouwei bcrunetbidirectionalconvlstmresidualunetforretinalbloodvesselsegmentation AT wangwenle bcrunetbidirectionalconvlstmresidualunetforretinalbloodvesselsegmentation |