Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm

This paper exploits the extreme learning machine (ELM) approach to address diabetic retinopathy (DR), a medical condition in which impairment occurs to the retina caused by diabetes. DR, a leading cause of blindness worldwide, is a sort of swelling leakage due to excessive blood sugar in the retina...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Md. Nahiduzzaman, Md. Robiul Islam, S. M. Riazul Islam, Md. Omaer Faruq Goni, Md. Shamim Anower, Kyung-Sup Kwak
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Ben Graham’s pre-processing contrast limited adaptive histogram equalization (CLAHE) convolutional neural network-singular value decomposition (CNN-SVD) diabetic retinopathy (DR) extreme learning machine (ELM) Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/bd326b8c15104142953d12d645ba0f7f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bd326b8c15104142953d12d645ba0f7f
record_format	dspace
spelling	oai:doaj.org-article:bd326b8c15104142953d12d645ba0f7f2021-11-20T00:00:46ZHybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm2169-353610.1109/ACCESS.2021.3125791https://doaj.org/article/bd326b8c15104142953d12d645ba0f7f2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9605633/https://doaj.org/toc/2169-3536This paper exploits the extreme learning machine (ELM) approach to address diabetic retinopathy (DR), a medical condition in which impairment occurs to the retina caused by diabetes. DR, a leading cause of blindness worldwide, is a sort of swelling leakage due to excessive blood sugar in the retina vessels. An early-stage diagnosis is therefore beneficial to prevent diabetes patients from losing their sight. This study introduced a novel method to detect DR for binary class and multiclass classification based on the APTOS-2019 blindness detection and Messidor-2 datasets. First, DR images have been pre-processed using Ben Graham’s approach. After that, contrast limited adaptive histogram equalization (CLAHE) has been used to get contrast-enhanced images with lower noise and more distinguishing features. Then a novel hybrid convolutional neural network-singular value decomposition model has been developed to reduce input features for classifiers. Finally, the proposed method uses an ELM algorithm as the classifier that minimizes the training time cost. The experiments focus on accuracy, precision, recall, and F1-score and demonstrate the feasibility of adopting the proposed scheme for DR diagnosis. The method outperforms the existing techniques and shows an optimistic accuracy and recall of 99.73% and 100%, respectively, for binary class. For five stages of DR classification, the proposed model achieved an accuracy of 98.09% and 96.26% for APTOS-2019 and Messidor-2 datasets, respectively, which outperformed the existing state-of-art models.Md. NahiduzzamanMd. Robiul IslamS. M. Riazul IslamMd. Omaer Faruq GoniMd. Shamim AnowerKyung-Sup KwakIEEEarticleBen Graham’s pre-processingcontrast limited adaptive histogram equalization (CLAHE)convolutional neural network-singular value decomposition (CNN-SVD)diabetic retinopathy (DR)extreme learning machine (ELM)Electrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152261-152274 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Ben Graham’s pre-processing contrast limited adaptive histogram equalization (CLAHE) convolutional neural network-singular value decomposition (CNN-SVD) diabetic retinopathy (DR) extreme learning machine (ELM) Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Ben Graham’s pre-processing contrast limited adaptive histogram equalization (CLAHE) convolutional neural network-singular value decomposition (CNN-SVD) diabetic retinopathy (DR) extreme learning machine (ELM) Electrical engineering. Electronics. Nuclear engineering TK1-9971 Md. Nahiduzzaman Md. Robiul Islam S. M. Riazul Islam Md. Omaer Faruq Goni Md. Shamim Anower Kyung-Sup Kwak Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm
description	This paper exploits the extreme learning machine (ELM) approach to address diabetic retinopathy (DR), a medical condition in which impairment occurs to the retina caused by diabetes. DR, a leading cause of blindness worldwide, is a sort of swelling leakage due to excessive blood sugar in the retina vessels. An early-stage diagnosis is therefore beneficial to prevent diabetes patients from losing their sight. This study introduced a novel method to detect DR for binary class and multiclass classification based on the APTOS-2019 blindness detection and Messidor-2 datasets. First, DR images have been pre-processed using Ben Graham’s approach. After that, contrast limited adaptive histogram equalization (CLAHE) has been used to get contrast-enhanced images with lower noise and more distinguishing features. Then a novel hybrid convolutional neural network-singular value decomposition model has been developed to reduce input features for classifiers. Finally, the proposed method uses an ELM algorithm as the classifier that minimizes the training time cost. The experiments focus on accuracy, precision, recall, and F1-score and demonstrate the feasibility of adopting the proposed scheme for DR diagnosis. The method outperforms the existing techniques and shows an optimistic accuracy and recall of 99.73% and 100%, respectively, for binary class. For five stages of DR classification, the proposed model achieved an accuracy of 98.09% and 96.26% for APTOS-2019 and Messidor-2 datasets, respectively, which outperformed the existing state-of-art models.
format	article
author	Md. Nahiduzzaman Md. Robiul Islam S. M. Riazul Islam Md. Omaer Faruq Goni Md. Shamim Anower Kyung-Sup Kwak
author_facet	Md. Nahiduzzaman Md. Robiul Islam S. M. Riazul Islam Md. Omaer Faruq Goni Md. Shamim Anower Kyung-Sup Kwak
author_sort	Md. Nahiduzzaman
title	Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm
title_short	Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm
title_full	Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm
title_fullStr	Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm
title_full_unstemmed	Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm
title_sort	hybrid cnn-svd based prominent feature extraction and selection for grading diabetic retinopathy using extreme learning machine algorithm
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/bd326b8c15104142953d12d645ba0f7f
work_keys_str_mv	AT mdnahiduzzaman hybridcnnsvdbasedprominentfeatureextractionandselectionforgradingdiabeticretinopathyusingextremelearningmachinealgorithm AT mdrobiulislam hybridcnnsvdbasedprominentfeatureextractionandselectionforgradingdiabeticretinopathyusingextremelearningmachinealgorithm AT smriazulislam hybridcnnsvdbasedprominentfeatureextractionandselectionforgradingdiabeticretinopathyusingextremelearningmachinealgorithm AT mdomaerfaruqgoni hybridcnnsvdbasedprominentfeatureextractionandselectionforgradingdiabeticretinopathyusingextremelearningmachinealgorithm AT mdshamimanower hybridcnnsvdbasedprominentfeatureextractionandselectionforgradingdiabeticretinopathyusingextremelearningmachinealgorithm AT kyungsupkwak hybridcnnsvdbasedprominentfeatureextractionandselectionforgradingdiabeticretinopathyusingextremelearningmachinealgorithm
_version_	1718419861033451520

Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm

Ejemplares similares