VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification

From diagnosing cardiovascular diseases to analyzing the progression of diabetic retinopathy, accurate retinal artery/vein (A/V) classification is critical. Promising approaches for A/V classification, ranging from conventional graph based methods to recent convolutional neural network (CNN) based m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Suraj Mishra, Ya Xing Wang, Chuan Chuan Wei, Danny Z. Chen, X. Sharon Hu
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	retinal images artery/vein classification vessel topology convolutional neural networks graph convolutional networks Medicine (General) R5-920
Acceso en línea:	https://doaj.org/article/dcf8bea666134b4785802bcac8619162
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dcf8bea666134b4785802bcac8619162
record_format	dspace
spelling	oai:doaj.org-article:dcf8bea666134b4785802bcac86191622021-11-08T05:35:51ZVTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification2296-858X10.3389/fmed.2021.750396https://doaj.org/article/dcf8bea666134b4785802bcac86191622021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fmed.2021.750396/fullhttps://doaj.org/toc/2296-858XFrom diagnosing cardiovascular diseases to analyzing the progression of diabetic retinopathy, accurate retinal artery/vein (A/V) classification is critical. Promising approaches for A/V classification, ranging from conventional graph based methods to recent convolutional neural network (CNN) based models, have been known. However, the inability of traditional graph based methods to utilize deep hierarchical features extracted by CNNs and the limitations of current CNN based methods to incorporate vessel topology information hinder their effectiveness. In this paper, we propose a new CNN based framework, VTG-Net (vessel topology graph network), for retinal A/V classification by incorporating vessel topology information. VTG-Net exploits retinal vessel topology along with CNN features to improve A/V classification accuracy. Specifically, we transform vessel features extracted by CNN in the image domain into a graph representation preserving the vessel topology. Then by exploiting a graph convolutional network (GCN), we enable our model to learn both CNN features and vessel topological features simultaneously. The final predication is attained by fusing the CNN and GCN outputs. Using a publicly available AV-DRIVE dataset and an in-house dataset, we verify the high performance of our VTG-Net for retinal A/V classification over state-of-the-art methods (with ~2% improvement in accuracy on the AV-DRIVE dataset).Suraj MishraYa Xing WangChuan Chuan WeiDanny Z. ChenX. Sharon HuFrontiers Media S.A.articleretinal imagesartery/vein classificationvessel topologyconvolutional neural networksgraph convolutional networksMedicine (General)R5-920ENFrontiers in Medicine, Vol 8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	retinal images artery/vein classification vessel topology convolutional neural networks graph convolutional networks Medicine (General) R5-920
spellingShingle	retinal images artery/vein classification vessel topology convolutional neural networks graph convolutional networks Medicine (General) R5-920 Suraj Mishra Ya Xing Wang Chuan Chuan Wei Danny Z. Chen X. Sharon Hu VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification
description	From diagnosing cardiovascular diseases to analyzing the progression of diabetic retinopathy, accurate retinal artery/vein (A/V) classification is critical. Promising approaches for A/V classification, ranging from conventional graph based methods to recent convolutional neural network (CNN) based models, have been known. However, the inability of traditional graph based methods to utilize deep hierarchical features extracted by CNNs and the limitations of current CNN based methods to incorporate vessel topology information hinder their effectiveness. In this paper, we propose a new CNN based framework, VTG-Net (vessel topology graph network), for retinal A/V classification by incorporating vessel topology information. VTG-Net exploits retinal vessel topology along with CNN features to improve A/V classification accuracy. Specifically, we transform vessel features extracted by CNN in the image domain into a graph representation preserving the vessel topology. Then by exploiting a graph convolutional network (GCN), we enable our model to learn both CNN features and vessel topological features simultaneously. The final predication is attained by fusing the CNN and GCN outputs. Using a publicly available AV-DRIVE dataset and an in-house dataset, we verify the high performance of our VTG-Net for retinal A/V classification over state-of-the-art methods (with ~2% improvement in accuracy on the AV-DRIVE dataset).
format	article
author	Suraj Mishra Ya Xing Wang Chuan Chuan Wei Danny Z. Chen X. Sharon Hu
author_facet	Suraj Mishra Ya Xing Wang Chuan Chuan Wei Danny Z. Chen X. Sharon Hu
author_sort	Suraj Mishra
title	VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification
title_short	VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification
title_full	VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification
title_fullStr	VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification
title_full_unstemmed	VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification
title_sort	vtg-net: a cnn based vessel topology graph network for retinal artery/vein classification
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/dcf8bea666134b4785802bcac8619162
work_keys_str_mv	AT surajmishra vtgnetacnnbasedvesseltopologygraphnetworkforretinalarteryveinclassification AT yaxingwang vtgnetacnnbasedvesseltopologygraphnetworkforretinalarteryveinclassification AT chuanchuanwei vtgnetacnnbasedvesseltopologygraphnetworkforretinalarteryveinclassification AT dannyzchen vtgnetacnnbasedvesseltopologygraphnetworkforretinalarteryveinclassification AT xsharonhu vtgnetacnnbasedvesseltopologygraphnetworkforretinalarteryveinclassification
_version_	1718442954340696064

VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification

Ejemplares similares