Cargando…

MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation

Segmentation of retinal vessels is important for doctors to diagnose some diseases. The segmentation accuracy of retinal vessels can be effectively improved by using deep learning methods. However, most of the existing methods are incomplete for shallow feature extraction, and some superficial featu...

Descripción completa

Detalles Bibliográficos
Autores principales: Jiang, Yun, Wu, Chao, Wang, Ge, Yao, Hui-Xia, Liu, Wen-Huan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8274903/
https://www.ncbi.nlm.nih.gov/pubmed/34252111
http://dx.doi.org/10.1371/journal.pone.0253056
_version_ 1783721624225185792
author Jiang, Yun
Wu, Chao
Wang, Ge
Yao, Hui-Xia
Liu, Wen-Huan
author_facet Jiang, Yun
Wu, Chao
Wang, Ge
Yao, Hui-Xia
Liu, Wen-Huan
author_sort Jiang, Yun
collection PubMed
description Segmentation of retinal vessels is important for doctors to diagnose some diseases. The segmentation accuracy of retinal vessels can be effectively improved by using deep learning methods. However, most of the existing methods are incomplete for shallow feature extraction, and some superficial features are lost, resulting in blurred vessel boundaries and inaccurate segmentation of capillaries in the segmentation results. At the same time, the “layer-by-layer” information fusion between encoder and decoder makes the feature information extracted from the shallow layer of the network cannot be smoothly transferred to the deep layer of the network, resulting in noise in the segmentation features. In this paper, we propose the MFI-Net (Multi-resolution fusion input network) network model to alleviate the above problem to a certain extent. The multi-resolution input module in MFI-Net avoids the loss of coarse-grained feature information in the shallow layer by extracting local and global feature information in different resolutions. We have reconsidered the information fusion method between the encoder and the decoder, and used the information aggregation method to alleviate the information isolation between the shallow and deep layers of the network. MFI-Net is verified on three datasets, DRIVE, CHASE_DB1 and STARE. The experimental results show that our network is at a high level in several metrics, with F1 higher than U-Net by 2.42%, 2.46% and 1.61%, higher than R2U-Net by 1.47%, 2.22% and 0.08%, respectively. Finally, this paper proves the robustness of MFI-Net through experiments and discussions on the stability and generalization ability of MFI-Net.
format Online
Article
Text
id pubmed-8274903
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-82749032021-07-27 MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation Jiang, Yun Wu, Chao Wang, Ge Yao, Hui-Xia Liu, Wen-Huan PLoS One Research Article Segmentation of retinal vessels is important for doctors to diagnose some diseases. The segmentation accuracy of retinal vessels can be effectively improved by using deep learning methods. However, most of the existing methods are incomplete for shallow feature extraction, and some superficial features are lost, resulting in blurred vessel boundaries and inaccurate segmentation of capillaries in the segmentation results. At the same time, the “layer-by-layer” information fusion between encoder and decoder makes the feature information extracted from the shallow layer of the network cannot be smoothly transferred to the deep layer of the network, resulting in noise in the segmentation features. In this paper, we propose the MFI-Net (Multi-resolution fusion input network) network model to alleviate the above problem to a certain extent. The multi-resolution input module in MFI-Net avoids the loss of coarse-grained feature information in the shallow layer by extracting local and global feature information in different resolutions. We have reconsidered the information fusion method between the encoder and the decoder, and used the information aggregation method to alleviate the information isolation between the shallow and deep layers of the network. MFI-Net is verified on three datasets, DRIVE, CHASE_DB1 and STARE. The experimental results show that our network is at a high level in several metrics, with F1 higher than U-Net by 2.42%, 2.46% and 1.61%, higher than R2U-Net by 1.47%, 2.22% and 0.08%, respectively. Finally, this paper proves the robustness of MFI-Net through experiments and discussions on the stability and generalization ability of MFI-Net. Public Library of Science 2021-07-12 /pmc/articles/PMC8274903/ /pubmed/34252111 http://dx.doi.org/10.1371/journal.pone.0253056 Text en © 2021 Jiang et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Jiang, Yun
Wu, Chao
Wang, Ge
Yao, Hui-Xia
Liu, Wen-Huan
MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation
title MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation
title_full MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation
title_fullStr MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation
title_full_unstemmed MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation
title_short MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation
title_sort mfi-net: a multi-resolution fusion input network for retinal vessel segmentation
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8274903/
https://www.ncbi.nlm.nih.gov/pubmed/34252111
http://dx.doi.org/10.1371/journal.pone.0253056
work_keys_str_mv AT jiangyun mfinetamultiresolutionfusioninputnetworkforretinalvesselsegmentation
AT wuchao mfinetamultiresolutionfusioninputnetworkforretinalvesselsegmentation
AT wangge mfinetamultiresolutionfusioninputnetworkforretinalvesselsegmentation
AT yaohuixia mfinetamultiresolutionfusioninputnetworkforretinalvesselsegmentation
AT liuwenhuan mfinetamultiresolutionfusioninputnetworkforretinalvesselsegmentation