HDC-Net: A hierarchical dilation convolutional network for retinal vessel segmentation.
The cardinal symptoms of some ophthalmic diseases observed through exceptional retinal blood vessels, such as retinal vein occlusion, diabetic retinopathy, etc. The advanced deep learning models used to obtain morphological and structural information of blood vessels automatically are conducive to t...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Public Library of Science (PLoS)
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/47022759f5ce458893b6ad4174ac7120 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:47022759f5ce458893b6ad4174ac7120 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:47022759f5ce458893b6ad4174ac71202021-12-02T20:08:27ZHDC-Net: A hierarchical dilation convolutional network for retinal vessel segmentation.1932-620310.1371/journal.pone.0257013https://doaj.org/article/47022759f5ce458893b6ad4174ac71202021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0257013https://doaj.org/toc/1932-6203The cardinal symptoms of some ophthalmic diseases observed through exceptional retinal blood vessels, such as retinal vein occlusion, diabetic retinopathy, etc. The advanced deep learning models used to obtain morphological and structural information of blood vessels automatically are conducive to the early treatment and initiative prevention of ophthalmic diseases. In our work, we propose a hierarchical dilation convolutional network (HDC-Net) to extract retinal vessels in a pixel-to-pixel manner. It utilizes the hierarchical dilation convolution (HDC) module to capture the fragile retinal blood vessels usually neglected by other methods. An improved residual dual efficient channel attention (RDECA) module can infer more delicate channel information to reinforce the discriminative capability of the model. The structured Dropblock can help our HDC-Net model to solve the network overfitting effectively. From a holistic perspective, the segmentation results obtained by HDC-Net are superior to other deep learning methods on three acknowledged datasets (DRIVE, CHASE-DB1, STARE), the sensitivity, specificity, accuracy, f1-score and AUC score are {0.8252, 0.9829, 0.9692, 0.8239, 0.9871}, {0.8227, 0.9853, 0.9745, 0.8113, 0.9884}, and {0.8369, 0.9866, 0.9751, 0.8385, 0.9913}, respectively. It surpasses most other advanced retinal vessel segmentation models. Qualitative and quantitative analysis demonstrates that HDC-Net can fulfill the task of retinal vessel segmentation efficiently and accurately.Xiaolong HuLiejun WangShuli ChengYongming LiPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 9, p e0257013 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Xiaolong Hu Liejun Wang Shuli Cheng Yongming Li HDC-Net: A hierarchical dilation convolutional network for retinal vessel segmentation. |
description |
The cardinal symptoms of some ophthalmic diseases observed through exceptional retinal blood vessels, such as retinal vein occlusion, diabetic retinopathy, etc. The advanced deep learning models used to obtain morphological and structural information of blood vessels automatically are conducive to the early treatment and initiative prevention of ophthalmic diseases. In our work, we propose a hierarchical dilation convolutional network (HDC-Net) to extract retinal vessels in a pixel-to-pixel manner. It utilizes the hierarchical dilation convolution (HDC) module to capture the fragile retinal blood vessels usually neglected by other methods. An improved residual dual efficient channel attention (RDECA) module can infer more delicate channel information to reinforce the discriminative capability of the model. The structured Dropblock can help our HDC-Net model to solve the network overfitting effectively. From a holistic perspective, the segmentation results obtained by HDC-Net are superior to other deep learning methods on three acknowledged datasets (DRIVE, CHASE-DB1, STARE), the sensitivity, specificity, accuracy, f1-score and AUC score are {0.8252, 0.9829, 0.9692, 0.8239, 0.9871}, {0.8227, 0.9853, 0.9745, 0.8113, 0.9884}, and {0.8369, 0.9866, 0.9751, 0.8385, 0.9913}, respectively. It surpasses most other advanced retinal vessel segmentation models. Qualitative and quantitative analysis demonstrates that HDC-Net can fulfill the task of retinal vessel segmentation efficiently and accurately. |
format |
article |
author |
Xiaolong Hu Liejun Wang Shuli Cheng Yongming Li |
author_facet |
Xiaolong Hu Liejun Wang Shuli Cheng Yongming Li |
author_sort |
Xiaolong Hu |
title |
HDC-Net: A hierarchical dilation convolutional network for retinal vessel segmentation. |
title_short |
HDC-Net: A hierarchical dilation convolutional network for retinal vessel segmentation. |
title_full |
HDC-Net: A hierarchical dilation convolutional network for retinal vessel segmentation. |
title_fullStr |
HDC-Net: A hierarchical dilation convolutional network for retinal vessel segmentation. |
title_full_unstemmed |
HDC-Net: A hierarchical dilation convolutional network for retinal vessel segmentation. |
title_sort |
hdc-net: a hierarchical dilation convolutional network for retinal vessel segmentation. |
publisher |
Public Library of Science (PLoS) |
publishDate |
2021 |
url |
https://doaj.org/article/47022759f5ce458893b6ad4174ac7120 |
work_keys_str_mv |
AT xiaolonghu hdcnetahierarchicaldilationconvolutionalnetworkforretinalvesselsegmentation AT liejunwang hdcnetahierarchicaldilationconvolutionalnetworkforretinalvesselsegmentation AT shulicheng hdcnetahierarchicaldilationconvolutionalnetworkforretinalvesselsegmentation AT yongmingli hdcnetahierarchicaldilationconvolutionalnetworkforretinalvesselsegmentation |
_version_ |
1718375176814460928 |