Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples

Diabetic retinopathy (DR) is a worldwide problem associated with the human retina. It leads to minor and major blindness and is more prevalent among adults. Automated screening saves time of medical care specialists. In this work, we have used different deep learning (DL) based 3D convolutional neur...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ahsan Bin Tufail, Inam Ullah, Wali Ullah Khan, Muhammad Asif, Ijaz Ahmad, Yong-Kui Ma, Rahim Khan, null Kalimullah, Md. Sadek Ali
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi-Wiley 2021
Materias:	Technology T Telecommunication TK5101-6720
Acceso en línea:	https://doaj.org/article/df2ea26b23a24a01b75398c1f3de9f83
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:df2ea26b23a24a01b75398c1f3de9f83
record_format	dspace
spelling	oai:doaj.org-article:df2ea26b23a24a01b75398c1f3de9f832021-11-29T00:56:01ZDiagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples1530-867710.1155/2021/6013448https://doaj.org/article/df2ea26b23a24a01b75398c1f3de9f832021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/6013448https://doaj.org/toc/1530-8677Diabetic retinopathy (DR) is a worldwide problem associated with the human retina. It leads to minor and major blindness and is more prevalent among adults. Automated screening saves time of medical care specialists. In this work, we have used different deep learning (DL) based 3D convolutional neural network (3D-CNN) architectures for binary and multiclass (5 classes) classification of DR. We have considered mild, moderate, no, proliferate, and severe DR categories. We have deployed two artificial data augmentation/enhancement methods: random weak Gaussian blurring and random shift along with their combination to accomplish these tasks in the spatial domain. In the binary classification case, we have found the performance of 3D-CNN architecture trained by deploying combined augmentation methods to be the best, while in the multiclass case, the performance of model trained without augmentation is the best. It is observed that the DL algorithms working with large volumes of data may achieve better performances as compared to the methods working with small volumes of data.Ahsan Bin TufailInam UllahWali Ullah KhanMuhammad AsifIjaz AhmadYong-Kui MaRahim Khannull KalimullahMd. Sadek AliHindawi-WileyarticleTechnologyTTelecommunicationTK5101-6720ENWireless Communications and Mobile Computing, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Technology T Telecommunication TK5101-6720
spellingShingle	Technology T Telecommunication TK5101-6720 Ahsan Bin Tufail Inam Ullah Wali Ullah Khan Muhammad Asif Ijaz Ahmad Yong-Kui Ma Rahim Khan null Kalimullah Md. Sadek Ali Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples
description	Diabetic retinopathy (DR) is a worldwide problem associated with the human retina. It leads to minor and major blindness and is more prevalent among adults. Automated screening saves time of medical care specialists. In this work, we have used different deep learning (DL) based 3D convolutional neural network (3D-CNN) architectures for binary and multiclass (5 classes) classification of DR. We have considered mild, moderate, no, proliferate, and severe DR categories. We have deployed two artificial data augmentation/enhancement methods: random weak Gaussian blurring and random shift along with their combination to accomplish these tasks in the spatial domain. In the binary classification case, we have found the performance of 3D-CNN architecture trained by deploying combined augmentation methods to be the best, while in the multiclass case, the performance of model trained without augmentation is the best. It is observed that the DL algorithms working with large volumes of data may achieve better performances as compared to the methods working with small volumes of data.
format	article
author	Ahsan Bin Tufail Inam Ullah Wali Ullah Khan Muhammad Asif Ijaz Ahmad Yong-Kui Ma Rahim Khan null Kalimullah Md. Sadek Ali
author_facet	Ahsan Bin Tufail Inam Ullah Wali Ullah Khan Muhammad Asif Ijaz Ahmad Yong-Kui Ma Rahim Khan null Kalimullah Md. Sadek Ali
author_sort	Ahsan Bin Tufail
title	Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples
title_short	Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples
title_full	Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples
title_fullStr	Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples
title_full_unstemmed	Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples
title_sort	diagnosis of diabetic retinopathy through retinal fundus images and 3d convolutional neural networks with limited number of samples
publisher	Hindawi-Wiley
publishDate	2021
url	https://doaj.org/article/df2ea26b23a24a01b75398c1f3de9f83
work_keys_str_mv	AT ahsanbintufail diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples AT inamullah diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples AT waliullahkhan diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples AT muhammadasif diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples AT ijazahmad diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples AT yongkuima diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples AT rahimkhan diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples AT nullkalimullah diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples AT mdsadekali diagnosisofdiabeticretinopathythroughretinalfundusimagesand3dconvolutionalneuralnetworkswithlimitednumberofsamples
_version_	1718407739635400704

Diagnosis of Diabetic Retinopathy through Retinal Fundus Images and 3D Convolutional Neural Networks with Limited Number of Samples

Ejemplares similares