Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning

Abstract Background To diagnose key pathologies of age-related macular degeneration (AMD) and diabetic macular edema (DME) quickly and accurately, researchers attempted to develop effective artificial intelligence methods by using medical images. Results A convolutional neural network (CNN) with tra...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yao-Mei Chen, Wei-Tai Huang, Wen-Hsien Ho, Jinn-Tsong Tsai
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Convolutional neural network Transfer learning Hyperparameter Optical coherence tomography image Age-related macular degeneration Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/a01fd1b1d46344ebb6d02656c7e3979e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a01fd1b1d46344ebb6d02656c7e3979e
record_format	dspace
spelling	oai:doaj.org-article:a01fd1b1d46344ebb6d02656c7e3979e2021-11-14T12:13:01ZClassification of age-related macular degeneration using convolutional-neural-network-based transfer learning10.1186/s12859-021-04001-11471-2105https://doaj.org/article/a01fd1b1d46344ebb6d02656c7e3979e2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12859-021-04001-1https://doaj.org/toc/1471-2105Abstract Background To diagnose key pathologies of age-related macular degeneration (AMD) and diabetic macular edema (DME) quickly and accurately, researchers attempted to develop effective artificial intelligence methods by using medical images. Results A convolutional neural network (CNN) with transfer learning capability is proposed and appropriate hyperparameters are selected for classifying optical coherence tomography (OCT) images of AMD and DME. To perform transfer learning, a pre-trained CNN model is used as the starting point for a new CNN model for solving related problems. The hyperparameters (parameters that have set values before the learning process begins) in this study were algorithm hyperparameters that affect learning speed and quality. During training, different CNN-based models require different algorithm hyperparameters (e.g., optimizer, learning rate, and mini-batch size). Experiments showed that, after transfer learning, the CNN models (8-layer Alexnet, 22-layer Googlenet, 16-layer VGG, 19-layer VGG, 18-layer Resnet, 50-layer Resnet, and a 101-layer Resnet) successfully classified OCT images of AMD and DME. Conclusions The experimental results further showed that, after transfer learning, the VGG19, Resnet101, and Resnet50 models with appropriate algorithm hyperparameters had excellent capability and performance in classifying OCT images of AMD and DME.Yao-Mei ChenWei-Tai HuangWen-Hsien HoJinn-Tsong TsaiBMCarticleConvolutional neural networkTransfer learningHyperparameterOptical coherence tomography imageAge-related macular degenerationComputer applications to medicine. Medical informaticsR858-859.7Biology (General)QH301-705.5ENBMC Bioinformatics, Vol 22, Iss S5, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Convolutional neural network Transfer learning Hyperparameter Optical coherence tomography image Age-related macular degeneration Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
spellingShingle	Convolutional neural network Transfer learning Hyperparameter Optical coherence tomography image Age-related macular degeneration Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5 Yao-Mei Chen Wei-Tai Huang Wen-Hsien Ho Jinn-Tsong Tsai Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning
description	Abstract Background To diagnose key pathologies of age-related macular degeneration (AMD) and diabetic macular edema (DME) quickly and accurately, researchers attempted to develop effective artificial intelligence methods by using medical images. Results A convolutional neural network (CNN) with transfer learning capability is proposed and appropriate hyperparameters are selected for classifying optical coherence tomography (OCT) images of AMD and DME. To perform transfer learning, a pre-trained CNN model is used as the starting point for a new CNN model for solving related problems. The hyperparameters (parameters that have set values before the learning process begins) in this study were algorithm hyperparameters that affect learning speed and quality. During training, different CNN-based models require different algorithm hyperparameters (e.g., optimizer, learning rate, and mini-batch size). Experiments showed that, after transfer learning, the CNN models (8-layer Alexnet, 22-layer Googlenet, 16-layer VGG, 19-layer VGG, 18-layer Resnet, 50-layer Resnet, and a 101-layer Resnet) successfully classified OCT images of AMD and DME. Conclusions The experimental results further showed that, after transfer learning, the VGG19, Resnet101, and Resnet50 models with appropriate algorithm hyperparameters had excellent capability and performance in classifying OCT images of AMD and DME.
format	article
author	Yao-Mei Chen Wei-Tai Huang Wen-Hsien Ho Jinn-Tsong Tsai
author_facet	Yao-Mei Chen Wei-Tai Huang Wen-Hsien Ho Jinn-Tsong Tsai
author_sort	Yao-Mei Chen
title	Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning
title_short	Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning
title_full	Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning
title_fullStr	Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning
title_full_unstemmed	Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning
title_sort	classification of age-related macular degeneration using convolutional-neural-network-based transfer learning
publisher	BMC
publishDate	2021
url	https://doaj.org/article/a01fd1b1d46344ebb6d02656c7e3979e
work_keys_str_mv	AT yaomeichen classificationofagerelatedmaculardegenerationusingconvolutionalneuralnetworkbasedtransferlearning AT weitaihuang classificationofagerelatedmaculardegenerationusingconvolutionalneuralnetworkbasedtransferlearning AT wenhsienho classificationofagerelatedmaculardegenerationusingconvolutionalneuralnetworkbasedtransferlearning AT jinntsongtsai classificationofagerelatedmaculardegenerationusingconvolutionalneuralnetworkbasedtransferlearning
_version_	1718429364026081280

Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning

Ejemplares similares