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

doi:10.1167/tvst.9.2.29

	Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders
	Zheng, Ce 1; Xie, Xiaolin 4,5; Zhou, Kang2,3 ; Chen, Bang 2; Chen, Jili 6; Ye, Haiyun 1; Li, Wen 1; Qiao, Tong 1; Gao, Shenghua3 ; Yang, Jianlong 2; Liu, Jiang 2,7
	2020-01
发表期刊	TRANSLATIONAL VISION SCIENCE & TECHNOLOGY
ISSN	2164-2591
卷号	9 期号:2 页码:#VALUE!
DOI	10.1167/tvst.9.2.29
摘要	Purpose: To 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). Methods: The 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). Results: The 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. Conclusions: The GAN synthetic OCT images can be used by clinicians for educational purposes and for developing DL algorithms. Translational Relevance: The medical image synthesis based on GANs is promising in humans and machines to fulfill clinical tasks.
关键词	optical coherence tomography retinal disorders deep learning generative adversarial networks
URL	查看原文
收录类别	SCI ; SCIE
语种	英语
WOS研究方向	Ophthalmology
WOS类目	Ophthalmology
WOS记录号	WOS:000599489500015
出版者	ASSOC RESEARCH VISION OPHTHALMOLOGY INC
WOS关键词	DIABETIC-RETINOPATHY ; DEEP ; PREVALENCE ; VALIDATION ; DISEASES ; OCT
原始文献类型	Article
引用统计
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/126003
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_高盛华组信息科学与技术学院_博士生
通讯作者	Yang, Jianlong
作者单位	1.Shanghai Jiao Tong Univ, Shanghai Childrens Hosp, Dept Ophthalmol, Shanghai, Peoples R China; 2.Chinese Acad Sci, Cixi Inst Biomed Engn, Ningbo Inst Mat Technol & Engn, Ningbo, Zhejiang, Peoples R China; 3.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China; 4.Shantou Univ, Joint Shantou Int Eye Ctr, Shantou, Guangdong, Peoples R China; 5.Shantou Univ, Med Coll, Chinese Univ Hong Kong, Shantou, Guangdong, Peoples R China; 6.Shibei Hosp, Dept Ophthalmol, Shanghai, Peoples R China; 7.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Guangdong, Peoples R China
推荐引用方式 GB/T 7714	Zheng, Ce,Xie, Xiaolin,Zhou, Kang,et al. Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders[J]. TRANSLATIONAL VISION SCIENCE & TECHNOLOGY,2020,9(2):#VALUE!.
APA	Zheng, Ce.,Xie, Xiaolin.,Zhou, Kang.,Chen, Bang.,Chen, Jili.,...&Liu, Jiang.(2020).Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders.TRANSLATIONAL VISION SCIENCE & TECHNOLOGY,9(2),#VALUE!.
MLA	Zheng, Ce,et al."Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders".TRANSLATIONAL VISION SCIENCE & TECHNOLOGY 9.2(2020):#VALUE!.