AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography

Abstract Coronary Artery Disease (CAD) is commonly diagnosed using X-ray angiography, in which images are taken as radio-opaque dye is flushed through the coronary vessels to visualize the severity of vessel narrowing, or stenosis. Cardiologists typically use visual estimation to approximate the per...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kritika Iyer, Cyrus P. Najarian, Aya A. Fattah, Christopher J. Arthurs, S. M. Reza Soroushmehr, Vijayakumar Subban, Mullasari A. Sankardas, Raj R. Nadakuditi, Brahmajee K. Nallamothu, C. Alberto Figueroa
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/184594f6bad04a0e962b6c06d54dbbee
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:184594f6bad04a0e962b6c06d54dbbee
record_format	dspace
spelling	oai:doaj.org-article:184594f6bad04a0e962b6c06d54dbbee2021-12-02T14:58:48ZAngioNet: a convolutional neural network for vessel segmentation in X-ray angiography10.1038/s41598-021-97355-82045-2322https://doaj.org/article/184594f6bad04a0e962b6c06d54dbbee2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97355-8https://doaj.org/toc/2045-2322Abstract Coronary Artery Disease (CAD) is commonly diagnosed using X-ray angiography, in which images are taken as radio-opaque dye is flushed through the coronary vessels to visualize the severity of vessel narrowing, or stenosis. Cardiologists typically use visual estimation to approximate the percent diameter reduction of the stenosis, and this directs therapies like stent placement. A fully automatic method to segment the vessels would eliminate potential subjectivity and provide a quantitative and systematic measurement of diameter reduction. Here, we have designed a convolutional neural network, AngioNet, for vessel segmentation in X-ray angiography images. The main innovation in this network is the introduction of an Angiographic Processing Network (APN) which significantly improves segmentation performance on multiple network backbones, with the best performance using Deeplabv3+ (Dice score 0.864, pixel accuracy 0.983, sensitivity 0.918, specificity 0.987). The purpose of the APN is to create an end-to-end pipeline for image pre-processing and segmentation, learning the best possible pre-processing filters to improve segmentation. We have also demonstrated the interchangeability of our network in measuring vessel diameter with Quantitative Coronary Angiography. Our results indicate that AngioNet is a powerful tool for automatic angiographic vessel segmentation that could facilitate systematic anatomical assessment of coronary stenosis in the clinical workflow.Kritika IyerCyrus P. NajarianAya A. FattahChristopher J. ArthursS. M. Reza SoroushmehrVijayakumar SubbanMullasari A. SankardasRaj R. NadakuditiBrahmajee K. NallamothuC. Alberto FigueroaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Kritika Iyer Cyrus P. Najarian Aya A. Fattah Christopher J. Arthurs S. M. Reza Soroushmehr Vijayakumar Subban Mullasari A. Sankardas Raj R. Nadakuditi Brahmajee K. Nallamothu C. Alberto Figueroa AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography
description	Abstract Coronary Artery Disease (CAD) is commonly diagnosed using X-ray angiography, in which images are taken as radio-opaque dye is flushed through the coronary vessels to visualize the severity of vessel narrowing, or stenosis. Cardiologists typically use visual estimation to approximate the percent diameter reduction of the stenosis, and this directs therapies like stent placement. A fully automatic method to segment the vessels would eliminate potential subjectivity and provide a quantitative and systematic measurement of diameter reduction. Here, we have designed a convolutional neural network, AngioNet, for vessel segmentation in X-ray angiography images. The main innovation in this network is the introduction of an Angiographic Processing Network (APN) which significantly improves segmentation performance on multiple network backbones, with the best performance using Deeplabv3+ (Dice score 0.864, pixel accuracy 0.983, sensitivity 0.918, specificity 0.987). The purpose of the APN is to create an end-to-end pipeline for image pre-processing and segmentation, learning the best possible pre-processing filters to improve segmentation. We have also demonstrated the interchangeability of our network in measuring vessel diameter with Quantitative Coronary Angiography. Our results indicate that AngioNet is a powerful tool for automatic angiographic vessel segmentation that could facilitate systematic anatomical assessment of coronary stenosis in the clinical workflow.
format	article
author	Kritika Iyer Cyrus P. Najarian Aya A. Fattah Christopher J. Arthurs S. M. Reza Soroushmehr Vijayakumar Subban Mullasari A. Sankardas Raj R. Nadakuditi Brahmajee K. Nallamothu C. Alberto Figueroa
author_facet	Kritika Iyer Cyrus P. Najarian Aya A. Fattah Christopher J. Arthurs S. M. Reza Soroushmehr Vijayakumar Subban Mullasari A. Sankardas Raj R. Nadakuditi Brahmajee K. Nallamothu C. Alberto Figueroa
author_sort	Kritika Iyer
title	AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography
title_short	AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography
title_full	AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography
title_fullStr	AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography
title_full_unstemmed	AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography
title_sort	angionet: a convolutional neural network for vessel segmentation in x-ray angiography
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/184594f6bad04a0e962b6c06d54dbbee
work_keys_str_mv	AT kritikaiyer angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT cyruspnajarian angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT ayaafattah angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT christopherjarthurs angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT smrezasoroushmehr angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT vijayakumarsubban angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT mullasariasankardas angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT rajrnadakuditi angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT brahmajeeknallamothu angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography AT calbertofigueroa angionetaconvolutionalneuralnetworkforvesselsegmentationinxrayangiography
_version_	1718389248122421248

AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography

Ejemplares similares