RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network

Diabetic retinopathy (DR) is a diabetic complication affecting the eyes, which is the main cause of blindness in young and middle-aged people. In order to speed up the diagnosis of DR, a mass of deep learning methods have been used for the detection of this disease, but they failed to attain excelle...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu Chen, Jun Long, Jifeng Guo
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/3116627a7b314e509e1d86800c1f3220
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3116627a7b314e509e1d86800c1f3220
record_format	dspace
spelling	oai:doaj.org-article:3116627a7b314e509e1d86800c1f32202021-11-22T01:10:09ZRF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network1687-527310.1155/2021/3812865https://doaj.org/article/3116627a7b314e509e1d86800c1f32202021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/3812865https://doaj.org/toc/1687-5273Diabetic retinopathy (DR) is a diabetic complication affecting the eyes, which is the main cause of blindness in young and middle-aged people. In order to speed up the diagnosis of DR, a mass of deep learning methods have been used for the detection of this disease, but they failed to attain excellent results due to unbalanced training data, i.e., the lack of DR fundus images. To address the problem of data imbalance, this paper proposes a method dubbed retinal fundus images generative adversarial networks (RF-GANs), which is based on generative adversarial network, to synthesize retinal fundus images. RF-GANs is composed of two generation models, RF-GAN1 and RF-GAN2. Firstly, RF-GAN1 is employed to translate retinal fundus images from source domain (the domain of semantic segmentation datasets) to target domain (the domain of EyePACS dataset connected to Kaggle (EyePACS)). Then, we train the semantic segmentation models with the translated images, and employ the trained models to extract the structural and lesion masks (hereafter, we refer to it as Masks) of EyePACS. Finally, we employ RF-GAN2 to synthesize retinal fundus images using the Masks and DR grading labels. This paper verifies the effectiveness of the method: RF-GAN1 can narrow down the domain gap between different datasets to improve the performance of the segmentation models. RF-GAN2 can synthesize realistic retinal fundus images. Adopting the synthesized images for data augmentation, the accuracy and quadratic weighted kappa of the state-of-the-art DR grading model on the testing set of EyePACS increase by 1.53% and 1.70%, respectively.Yu ChenJun LongJifeng GuoHindawi LimitedarticleComputer applications to medicine. Medical informaticsR858-859.7Neurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENComputational Intelligence and Neuroscience, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Yu Chen Jun Long Jifeng Guo RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network
description	Diabetic retinopathy (DR) is a diabetic complication affecting the eyes, which is the main cause of blindness in young and middle-aged people. In order to speed up the diagnosis of DR, a mass of deep learning methods have been used for the detection of this disease, but they failed to attain excellent results due to unbalanced training data, i.e., the lack of DR fundus images. To address the problem of data imbalance, this paper proposes a method dubbed retinal fundus images generative adversarial networks (RF-GANs), which is based on generative adversarial network, to synthesize retinal fundus images. RF-GANs is composed of two generation models, RF-GAN1 and RF-GAN2. Firstly, RF-GAN1 is employed to translate retinal fundus images from source domain (the domain of semantic segmentation datasets) to target domain (the domain of EyePACS dataset connected to Kaggle (EyePACS)). Then, we train the semantic segmentation models with the translated images, and employ the trained models to extract the structural and lesion masks (hereafter, we refer to it as Masks) of EyePACS. Finally, we employ RF-GAN2 to synthesize retinal fundus images using the Masks and DR grading labels. This paper verifies the effectiveness of the method: RF-GAN1 can narrow down the domain gap between different datasets to improve the performance of the segmentation models. RF-GAN2 can synthesize realistic retinal fundus images. Adopting the synthesized images for data augmentation, the accuracy and quadratic weighted kappa of the state-of-the-art DR grading model on the testing set of EyePACS increase by 1.53% and 1.70%, respectively.
format	article
author	Yu Chen Jun Long Jifeng Guo
author_facet	Yu Chen Jun Long Jifeng Guo
author_sort	Yu Chen
title	RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network
title_short	RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network
title_full	RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network
title_fullStr	RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network
title_full_unstemmed	RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network
title_sort	rf-gans: a method to synthesize retinal fundus images based on generative adversarial network
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/3116627a7b314e509e1d86800c1f3220
work_keys_str_mv	AT yuchen rfgansamethodtosynthesizeretinalfundusimagesbasedongenerativeadversarialnetwork AT junlong rfgansamethodtosynthesizeretinalfundusimagesbasedongenerativeadversarialnetwork AT jifengguo rfgansamethodtosynthesizeretinalfundusimagesbasedongenerativeadversarialnetwork
_version_	1718418390222110720

RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network

Ejemplares similares