Real-time coronary artery stenosis detection based on modern neural networks

Abstract Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Viacheslav V. Danilov, Kirill Yu. Klyshnikov, Olga M. Gerget, Anton G. Kutikhin, Vladimir I. Ganyukov, Alejandro F. Frangi, Evgeny A. Ovcharenko
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/af0e99a2f2bf46a59aad110982b117f1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:af0e99a2f2bf46a59aad110982b117f1
record_format	dspace
spelling	oai:doaj.org-article:af0e99a2f2bf46a59aad110982b117f12021-12-02T18:15:25ZReal-time coronary artery stenosis detection based on modern neural networks10.1038/s41598-021-87174-22045-2322https://doaj.org/article/af0e99a2f2bf46a59aad110982b117f12021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87174-2https://doaj.org/toc/2045-2322Abstract Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.95, F1-score 0.96 and the slowest prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with a low mAP of 0.83, F1-score of 0.80 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, F1-score 0.96 while the prediction speed is 10 fps. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings.Viacheslav V. DanilovKirill Yu. KlyshnikovOlga M. GergetAnton G. KutikhinVladimir I. GanyukovAlejandro F. FrangiEvgeny A. OvcharenkoNature 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 Viacheslav V. Danilov Kirill Yu. Klyshnikov Olga M. Gerget Anton G. Kutikhin Vladimir I. Ganyukov Alejandro F. Frangi Evgeny A. Ovcharenko Real-time coronary artery stenosis detection based on modern neural networks
description	Abstract Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.95, F1-score 0.96 and the slowest prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with a low mAP of 0.83, F1-score of 0.80 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, F1-score 0.96 while the prediction speed is 10 fps. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings.
format	article
author	Viacheslav V. Danilov Kirill Yu. Klyshnikov Olga M. Gerget Anton G. Kutikhin Vladimir I. Ganyukov Alejandro F. Frangi Evgeny A. Ovcharenko
author_facet	Viacheslav V. Danilov Kirill Yu. Klyshnikov Olga M. Gerget Anton G. Kutikhin Vladimir I. Ganyukov Alejandro F. Frangi Evgeny A. Ovcharenko
author_sort	Viacheslav V. Danilov
title	Real-time coronary artery stenosis detection based on modern neural networks
title_short	Real-time coronary artery stenosis detection based on modern neural networks
title_full	Real-time coronary artery stenosis detection based on modern neural networks
title_fullStr	Real-time coronary artery stenosis detection based on modern neural networks
title_full_unstemmed	Real-time coronary artery stenosis detection based on modern neural networks
title_sort	real-time coronary artery stenosis detection based on modern neural networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/af0e99a2f2bf46a59aad110982b117f1
work_keys_str_mv	AT viacheslavvdanilov realtimecoronaryarterystenosisdetectionbasedonmodernneuralnetworks AT kirillyuklyshnikov realtimecoronaryarterystenosisdetectionbasedonmodernneuralnetworks AT olgamgerget realtimecoronaryarterystenosisdetectionbasedonmodernneuralnetworks AT antongkutikhin realtimecoronaryarterystenosisdetectionbasedonmodernneuralnetworks AT vladimiriganyukov realtimecoronaryarterystenosisdetectionbasedonmodernneuralnetworks AT alejandroffrangi realtimecoronaryarterystenosisdetectionbasedonmodernneuralnetworks AT evgenyaovcharenko realtimecoronaryarterystenosisdetectionbasedonmodernneuralnetworks
_version_	1718378414391427072

Real-time coronary artery stenosis detection based on modern neural networks

Ejemplares similares