Cargando…
A Novel Elastomeric UNet for Medical Image Segmentation
Medical image segmentation is of important support for clinical medical applications. As most of the current medical image segmentation models are limited in the U-shaped structure, to some extent the deep convolutional neural network (CNN) structure design is hard to be accomplished. The design in...
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/PMC8961507/ https://www.ncbi.nlm.nih.gov/pubmed/35360219 http://dx.doi.org/10.3389/fnagi.2022.841297 |
_version_ | 1784677609720774656 |
---|---|
author | Cai, Sijing Wu, Yi Chen, Guannan |
author_facet | Cai, Sijing Wu, Yi Chen, Guannan |
author_sort | Cai, Sijing |
collection | PubMed |
description | Medical image segmentation is of important support for clinical medical applications. As most of the current medical image segmentation models are limited in the U-shaped structure, to some extent the deep convolutional neural network (CNN) structure design is hard to be accomplished. The design in this study mimics the way the wave is elastomeric propagating, extending the structure from both the horizontal and spatial dimensions for realizing the Elastomeric UNet (EUNet) structure. The EUNet can be divided into two types: horizontal EUNet and spatial EUNet, based on the propagation direction. The advantages of this design are threefold. First, the training structure can be deepened effectively. Second, the independence brought by each branch (a U-shaped design) makes the flexible design redundancy available. Finally, a horizontal and vertical series-parallel structure helps on feature accumulation and recursion. Researchers can adjust the design according to the requirements to achieve better segmentation performance for the independent structural design. The proposed networks were evaluated on two datasets: a self-built dataset (multi-photon microscopy, MPM) and publicly benchmark retinal datasets (DRIVE). The results of experiments demonstrated that the performance of EUNet outperformed the UNet and its variants. |
format | Online Article Text |
id | pubmed-8961507 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-89615072022-03-30 A Novel Elastomeric UNet for Medical Image Segmentation Cai, Sijing Wu, Yi Chen, Guannan Front Aging Neurosci Neuroscience Medical image segmentation is of important support for clinical medical applications. As most of the current medical image segmentation models are limited in the U-shaped structure, to some extent the deep convolutional neural network (CNN) structure design is hard to be accomplished. The design in this study mimics the way the wave is elastomeric propagating, extending the structure from both the horizontal and spatial dimensions for realizing the Elastomeric UNet (EUNet) structure. The EUNet can be divided into two types: horizontal EUNet and spatial EUNet, based on the propagation direction. The advantages of this design are threefold. First, the training structure can be deepened effectively. Second, the independence brought by each branch (a U-shaped design) makes the flexible design redundancy available. Finally, a horizontal and vertical series-parallel structure helps on feature accumulation and recursion. Researchers can adjust the design according to the requirements to achieve better segmentation performance for the independent structural design. The proposed networks were evaluated on two datasets: a self-built dataset (multi-photon microscopy, MPM) and publicly benchmark retinal datasets (DRIVE). The results of experiments demonstrated that the performance of EUNet outperformed the UNet and its variants. Frontiers Media S.A. 2022-03-10 /pmc/articles/PMC8961507/ /pubmed/35360219 http://dx.doi.org/10.3389/fnagi.2022.841297 Text en Copyright © 2022 Cai, Wu and Chen. 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 | Neuroscience Cai, Sijing Wu, Yi Chen, Guannan A Novel Elastomeric UNet for Medical Image Segmentation |
title | A Novel Elastomeric UNet for Medical Image Segmentation |
title_full | A Novel Elastomeric UNet for Medical Image Segmentation |
title_fullStr | A Novel Elastomeric UNet for Medical Image Segmentation |
title_full_unstemmed | A Novel Elastomeric UNet for Medical Image Segmentation |
title_short | A Novel Elastomeric UNet for Medical Image Segmentation |
title_sort | novel elastomeric unet for medical image segmentation |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8961507/ https://www.ncbi.nlm.nih.gov/pubmed/35360219 http://dx.doi.org/10.3389/fnagi.2022.841297 |
work_keys_str_mv | AT caisijing anovelelastomericunetformedicalimagesegmentation AT wuyi anovelelastomericunetformedicalimagesegmentation AT chenguannan anovelelastomericunetformedicalimagesegmentation AT caisijing novelelastomericunetformedicalimagesegmentation AT wuyi novelelastomericunetformedicalimagesegmentation AT chenguannan novelelastomericunetformedicalimagesegmentation |