Diabetic retinopathy fundus image generation based on generative adversarial networks

Authors: Wan Cheng,  Zhou Peng,  Wu Luhui,  Wu Yiquan,  Shen Jianxin,  Ye Hui

DOI: 10.3760/cma.j.issn.2095-0160.2019.08.005
Published 2019-08-10
Cite as Chin J Exp Ophthalmol, 2019,37(8): 613-618.

Abstract

Objective

To generate various types of diabetic retinopathy (DR) fundus images automatically by computer vision algorithm.

Methods

A method based on deep learning to generate fundus images was proposed, which used the vascular vein of the fundus image and the text description of lesions as the constraint conditions to generate fundus image.The text description was encoded by using a long short-term memory (LSTM), and the vascular vein image was encoded by a convolutional neural network (CNN). Then the encoded information was combined and used to generate a fundus image by generative adversarial networks (GAN).

Results

The results showed that the algorithm can generate realistic fundus images.However, the image detail features were not obvious because the text-encoded recurrent neural network (RNN) loss function did not converge well.

Conclusions

Using the GAN can generate realistic DR fundus images, which has certain application value in expanding medical data.However, the generation of detail features in small areas still needs improvement.

Key words:

Generative adversarial networks; Fundus images; Image generation; Convolutional neural network

Contributor Information

Wan Cheng
College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Zhou Peng
College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Wu Luhui
College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Wu Yiquan
College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Shen Jianxin
College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Ye Hui
Department of Ophthalmology, Jiangsu Province Hospital, Nanjing 210029, China
(Read 115 times, 1 visits today)
Updated: September 25, 2019 — 10:40 am