A combined convolutional and recurrent neural network for enhanced glaucoma detection

Abstract Glaucoma, a leading cause of blindness, is a multifaceted disease with several patho-physiological features manifesting in single fundus images (e.g., optic nerve cupping) as well as fundus videos (e.g., vascular pulsatility index). Current convolutional neural networks (CNNs) developed to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Soheila Gheisari, Sahar Shariflou, Jack Phu, Paul J. Kennedy, Ashish Agar, Michael Kalloniatis, S. Mojtaba Golzan
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/7c2228465968407c9872f6dbb79a31c4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7c2228465968407c9872f6dbb79a31c4
record_format	dspace
spelling	oai:doaj.org-article:7c2228465968407c9872f6dbb79a31c42021-12-02T13:48:42ZA combined convolutional and recurrent neural network for enhanced glaucoma detection10.1038/s41598-021-81554-42045-2322https://doaj.org/article/7c2228465968407c9872f6dbb79a31c42021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81554-4https://doaj.org/toc/2045-2322Abstract Glaucoma, a leading cause of blindness, is a multifaceted disease with several patho-physiological features manifesting in single fundus images (e.g., optic nerve cupping) as well as fundus videos (e.g., vascular pulsatility index). Current convolutional neural networks (CNNs) developed to detect glaucoma are all based on spatial features embedded in an image. We developed a combined CNN and recurrent neural network (RNN) that not only extracts the spatial features in a fundus image but also the temporal features embedded in a fundus video (i.e., sequential images). A total of 1810 fundus images and 295 fundus videos were used to train a CNN and a combined CNN and Long Short-Term Memory RNN. The combined CNN/RNN model reached an average F-measure of 96.2% in separating glaucoma from healthy eyes. In contrast, the base CNN model reached an average F-measure of only 79.2%. This proof-of-concept study demonstrates that extracting spatial and temporal features from fundus videos using a combined CNN and RNN, can markedly enhance the accuracy of glaucoma detection.Soheila GheisariSahar ShariflouJack PhuPaul J. KennedyAshish AgarMichael KalloniatisS. Mojtaba GolzanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Soheila Gheisari Sahar Shariflou Jack Phu Paul J. Kennedy Ashish Agar Michael Kalloniatis S. Mojtaba Golzan A combined convolutional and recurrent neural network for enhanced glaucoma detection
description	Abstract Glaucoma, a leading cause of blindness, is a multifaceted disease with several patho-physiological features manifesting in single fundus images (e.g., optic nerve cupping) as well as fundus videos (e.g., vascular pulsatility index). Current convolutional neural networks (CNNs) developed to detect glaucoma are all based on spatial features embedded in an image. We developed a combined CNN and recurrent neural network (RNN) that not only extracts the spatial features in a fundus image but also the temporal features embedded in a fundus video (i.e., sequential images). A total of 1810 fundus images and 295 fundus videos were used to train a CNN and a combined CNN and Long Short-Term Memory RNN. The combined CNN/RNN model reached an average F-measure of 96.2% in separating glaucoma from healthy eyes. In contrast, the base CNN model reached an average F-measure of only 79.2%. This proof-of-concept study demonstrates that extracting spatial and temporal features from fundus videos using a combined CNN and RNN, can markedly enhance the accuracy of glaucoma detection.
format	article
author	Soheila Gheisari Sahar Shariflou Jack Phu Paul J. Kennedy Ashish Agar Michael Kalloniatis S. Mojtaba Golzan
author_facet	Soheila Gheisari Sahar Shariflou Jack Phu Paul J. Kennedy Ashish Agar Michael Kalloniatis S. Mojtaba Golzan
author_sort	Soheila Gheisari
title	A combined convolutional and recurrent neural network for enhanced glaucoma detection
title_short	A combined convolutional and recurrent neural network for enhanced glaucoma detection
title_full	A combined convolutional and recurrent neural network for enhanced glaucoma detection
title_fullStr	A combined convolutional and recurrent neural network for enhanced glaucoma detection
title_full_unstemmed	A combined convolutional and recurrent neural network for enhanced glaucoma detection
title_sort	combined convolutional and recurrent neural network for enhanced glaucoma detection
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/7c2228465968407c9872f6dbb79a31c4
work_keys_str_mv	AT soheilagheisari acombinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT saharshariflou acombinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT jackphu acombinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT pauljkennedy acombinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT ashishagar acombinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT michaelkalloniatis acombinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT smojtabagolzan acombinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT soheilagheisari combinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT saharshariflou combinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT jackphu combinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT pauljkennedy combinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT ashishagar combinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT michaelkalloniatis combinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection AT smojtabagolzan combinedconvolutionalandrecurrentneuralnetworkforenhancedglaucomadetection
_version_	1718392446853840896

A combined convolutional and recurrent neural network for enhanced glaucoma detection

Ejemplares similares