Cargando…

Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation

Left ventricular segmentation is a vital and necessary procedure for assessing cardiac systolic and diastolic function, while echocardiography is an indispensable diagnostic technique that enables cardiac functionality assessment. However, manually labeling the left ventricular region on echocardiog...

Descripción completa

Detalles Bibliográficos
Autores principales: Ye, Zi, Kumar, Yogan Jaya, Song, Fengyan, Li, Guanxi, Zhang, Suyu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10144960/
https://www.ncbi.nlm.nih.gov/pubmed/37109569
http://dx.doi.org/10.3390/life13041040
_version_ 1785034219106336768
author Ye, Zi
Kumar, Yogan Jaya
Song, Fengyan
Li, Guanxi
Zhang, Suyu
author_facet Ye, Zi
Kumar, Yogan Jaya
Song, Fengyan
Li, Guanxi
Zhang, Suyu
author_sort Ye, Zi
collection PubMed
description Left ventricular segmentation is a vital and necessary procedure for assessing cardiac systolic and diastolic function, while echocardiography is an indispensable diagnostic technique that enables cardiac functionality assessment. However, manually labeling the left ventricular region on echocardiography images is time consuming and leads to observer bias. Recent research has demonstrated that deep learning has the capability to employ the segmentation process automatically. However, on the downside, it still ignores the contribution of all semantic information through the segmentation process. This study proposes a deep neural network architecture based on BiSeNet, named Bi-DCNet. This model comprises a spatial path and a context path, with the former responsible for spatial feature (low-level) acquisition and the latter responsible for contextual semantic feature (high-level) exploitation. Moreover, it incorporates feature extraction through the integration of dilated convolutions to achieve a larger receptive field to capture multi-scale information. The EchoNet-Dynamic dataset was utilized to assess the proposed model, and this is the first bilateral-structured network implemented on this large clinical video dataset for accomplishing the segmentation of the left ventricle. As demonstrated by the experimental outcomes, our method obtained 0.9228 and 0.8576 in DSC and IoU, respectively, proving the structure’s effectiveness.
format Online
Article
Text
id pubmed-10144960
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-101449602023-04-29 Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation Ye, Zi Kumar, Yogan Jaya Song, Fengyan Li, Guanxi Zhang, Suyu Life (Basel) Article Left ventricular segmentation is a vital and necessary procedure for assessing cardiac systolic and diastolic function, while echocardiography is an indispensable diagnostic technique that enables cardiac functionality assessment. However, manually labeling the left ventricular region on echocardiography images is time consuming and leads to observer bias. Recent research has demonstrated that deep learning has the capability to employ the segmentation process automatically. However, on the downside, it still ignores the contribution of all semantic information through the segmentation process. This study proposes a deep neural network architecture based on BiSeNet, named Bi-DCNet. This model comprises a spatial path and a context path, with the former responsible for spatial feature (low-level) acquisition and the latter responsible for contextual semantic feature (high-level) exploitation. Moreover, it incorporates feature extraction through the integration of dilated convolutions to achieve a larger receptive field to capture multi-scale information. The EchoNet-Dynamic dataset was utilized to assess the proposed model, and this is the first bilateral-structured network implemented on this large clinical video dataset for accomplishing the segmentation of the left ventricle. As demonstrated by the experimental outcomes, our method obtained 0.9228 and 0.8576 in DSC and IoU, respectively, proving the structure’s effectiveness. MDPI 2023-04-18 /pmc/articles/PMC10144960/ /pubmed/37109569 http://dx.doi.org/10.3390/life13041040 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ye, Zi
Kumar, Yogan Jaya
Song, Fengyan
Li, Guanxi
Zhang, Suyu
Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation
title Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation
title_full Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation
title_fullStr Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation
title_full_unstemmed Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation
title_short Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation
title_sort bi-dcnet: bilateral network with dilated convolutions for left ventricle segmentation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10144960/
https://www.ncbi.nlm.nih.gov/pubmed/37109569
http://dx.doi.org/10.3390/life13041040
work_keys_str_mv AT yezi bidcnetbilateralnetworkwithdilatedconvolutionsforleftventriclesegmentation
AT kumaryoganjaya bidcnetbilateralnetworkwithdilatedconvolutionsforleftventriclesegmentation
AT songfengyan bidcnetbilateralnetworkwithdilatedconvolutionsforleftventriclesegmentation
AT liguanxi bidcnetbilateralnetworkwithdilatedconvolutionsforleftventriclesegmentation
AT zhangsuyu bidcnetbilateralnetworkwithdilatedconvolutionsforleftventriclesegmentation