Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders.

Ce Zheng,Xiaolin Xie,Shenghua Gao,Jili Chen,Jianlong Yang,Kang Zhou,Jiang Liu,Tong Qiao,Wen Li,Haiyun Ye,Bang Chen

doi:10.1167/tvst.9.2.29

Abstract

PurposeTo assess whether a generative adversarial network (GAN) could synthesize realistic optical coherence tomography (OCT) images that satisfactorily serve as the educational images for retinal specialists, and the training datasets for the classification of various retinal disorders using deep learning (DL).MethodsThe GANs architecture was adopted to synthesize high-resolution OCT images trained on a publicly available OCT dataset, including urgent referrals (37,206 OCT images from eyes with choroidal neovascularization, and 11,349 OCT images from eyes with diabetic macular edema) and nonurgent referrals (8617 OCT images from eyes with drusen, and 51,140 OCT images from normal eyes). Four hundred real and synthetic OCT images were evaluated by two retinal specialists (with over 10 years of clinical retinal experience) to assess image quality. We further trained two DL models on either real or synthetic datasets and compared the performance of urgent versus nonurgent referrals diagnosis tested on a local (1000 images from the public dataset) and clinical validation dataset (278 images from Shanghai Shibei Hospital).ResultsThe image quality of real versus synthetic OCT images was similar as assessed by two retinal specialists. The accuracy of discrimination of real versus synthetic OCT images was 59.50% for retinal specialist 1 and 53.67% for retinal specialist 2. For the local dataset, the DL model trained on real (DL_Model_R) and synthetic OCT images (DL_Model_S) had an area under the curve (AUC) of 0.99, and 0.98, respectively. For the clinical dataset, the AUC was 0.94 for DL_Model_R and 0.90 for DL_Model_S.ConclusionsThe GAN synthetic OCT images can be used by clinicians for educational purposes and for developing DL algorithms.Translational RelevanceThe medical image synthesis based on GANs is promising in humans and machines to fulfill clinical tasks.

Highlights

Optical coherence tomography (OCT), which uses laser to capture high-resolution retina images in vivo [1], is a standard of care for guiding the diagnosis and treatment of some of the leading causes of blindness worldwide, including age-related macular degeneration (AMD) and diabetic macular edema (DME) [2,3]
The image quality of real vs synthetic OCT images was similar as assessed by 2 retinal specialists
The generative adversarial network (GAN)-synthetic OCT images can be used by clinicians for educational purposes and developing deep learning (DL) algorithms

Summary

Introduction

Optical coherence tomography (OCT), which uses laser to capture high-resolution retina images in vivo [1], is a standard of care for guiding the diagnosis and treatment of some of the leading causes of blindness worldwide, including age-related macular degeneration (AMD) and diabetic macular edema (DME) [2,3]. Recently demonstrated highly accurate DL algorithms for OCT imaging classification and performance is comparable to that of human experts [7]. Despite these promising results, DL algorithm require large, diverse, and well-balanced image training data sets with labels defining structures [8]. Kermany et al, trained a DL algorithm using a training dataset with totally 108,312 images by sharing data from different centers [7]. Adding large amounts of unbalanced data, like images from healthy subjects, will most likely not improve performance

Objectives

Methods

Results

Conclusion