Literature DB >> 36048435

Evaluation of Generative Adversarial Networks for High-Resolution Synthetic Image Generation of Circumpapillary Optical Coherence Tomography Images for Glaucoma.

Ashish Jith Sreejith Kumar1,2,3, Rachel S Chong4, Jonathan G Crowston1,4, Jacqueline Chua1,4, Inna Bujor5, Rahat Husain1,4, Eranga N Vithana1,4, Michaël J A Girard1,4,6, Daniel S W Ting1,4, Ching-Yu Cheng1,4,6, Tin Aung1,4,7, Alina Popa-Cherecheanu5,8, Leopold Schmetterer1,4,2,6,9,10,11,12, Damon Wong1,2,10.   

Abstract

Importance: Deep learning (DL) networks require large data sets for training, which can be challenging to collect clinically. Generative models could be used to generate large numbers of synthetic optical coherence tomography (OCT) images to train such DL networks for glaucoma detection. Objective: To assess whether generative models can synthesize circumpapillary optic nerve head OCT images of normal and glaucomatous eyes and determine the usability of synthetic images for training DL models for glaucoma detection. Design, Setting, and Participants: Progressively growing generative adversarial network models were trained to generate circumpapillary OCT scans. Image gradeability and authenticity were evaluated on a clinical set of 100 real and 100 synthetic images by 2 clinical experts. DL networks for glaucoma detection were trained with real or synthetic images and evaluated on independent internal and external test data sets of 140 and 300 real images, respectively. Main Outcomes and Measures: Evaluations of the clinical set between the experts were compared. Glaucoma detection performance of the DL networks was assessed using area under the curve (AUC) analysis. Class activation maps provided visualizations of the regions contributing to the respective classifications.
Results: A total of 990 normal and 862 glaucomatous eyes were analyzed. Evaluations of the clinical set were similar for gradeability (expert 1: 92.0%; expert 2: 93.0%) and authenticity (expert 1: 51.8%; expert 2: 51.3%). The best-performing DL network trained on synthetic images had AUC scores of 0.97 (95% CI, 0.95-0.99) on the internal test data set and 0.90 (95% CI, 0.87-0.93) on the external test data set, compared with AUCs of 0.96 (95% CI, 0.94-0.99) on the internal test data set and 0.84 (95% CI, 0.80-0.87) on the external test data set for the network trained with real images. An increase in the AUC for the synthetic DL network was observed with the use of larger synthetic data set sizes. Class activation maps showed that the regions of the synthetic images contributing to glaucoma detection were generally similar to that of real images. Conclusions and Relevance: DL networks trained with synthetic OCT images for glaucoma detection were comparable with networks trained with real images. These results suggest potential use of generative models in the training of DL networks and as a means of data sharing across institutions without patient information confidentiality issues.

Entities:  

Mesh:

Year:  2022        PMID: 36048435      PMCID: PMC9437828          DOI: 10.1001/jamaophthalmol.2022.3375

Source DB:  PubMed          Journal:  JAMA Ophthalmol        ISSN: 2168-6165            Impact factor:   8.253


  37 in total

1.  Methodology of the Singapore Indian Chinese Cohort (SICC) eye study: quantifying ethnic variations in the epidemiology of eye diseases in Asians.

Authors:  Raghavan Lavanya; V Swetha E Jeganathan; Yingfeng Zheng; Prema Raju; Ning Cheung; E Shyong Tai; Jie Jin Wang; Ecosse Lamoureux; Paul Mitchell; Terri L Young; Howard Cajucom-Uy; Paul J Foster; Tin Aung; Seang Mei Saw; Tien Y Wong
Journal:  Ophthalmic Epidemiol       Date:  2009 Nov-Dec       Impact factor: 1.648

2.  Simultaneous denoising and super-resolution of optical coherence tomography images based on generative adversarial network.

Authors:  Yongqiang Huang; Zexin Lu; Zhimin Shao; Maosong Ran; Jiliu Zhou; Leyuan Fang; Yi Zhang
Journal:  Opt Express       Date:  2019-04-29       Impact factor: 3.894

3.  OCT Signal Enhancement with Deep Learning.

Authors:  Georgios Lazaridis; Marco Lorenzi; Jibran Mohamed-Noriega; Soledad Aguilar-Munoa; Katsuyoshi Suzuki; Hiroki Nomoto; Sebastien Ourselin; David F Garway-Heath
Journal:  Ophthalmol Glaucoma       Date:  2020-10-15

4.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.

Authors:  Varun Gulshan; Lily Peng; Marc Coram; Martin C Stumpe; Derek Wu; Arunachalam Narayanaswamy; Subhashini Venugopalan; Kasumi Widner; Tom Madams; Jorge Cuadros; Ramasamy Kim; Rajiv Raman; Philip C Nelson; Jessica L Mega; Dale R Webster
Journal:  JAMA       Date:  2016-12-13       Impact factor: 56.272

5.  Low-Shot Deep Learning of Diabetic Retinopathy With Potential Applications to Address Artificial Intelligence Bias in Retinal Diagnostics and Rare Ophthalmic Diseases.

Authors:  Philippe Burlina; William Paul; Philip Mathew; Neil Joshi; Katia D Pacheco; Neil M Bressler
Journal:  JAMA Ophthalmol       Date:  2020-10-01       Impact factor: 7.389

6.  Patch-Based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation.

Authors:  Shujun Wang; Lequan Yu; Xin Yang; Chi-Wing Fu; Pheng-Ann Heng
Journal:  IEEE Trans Med Imaging       Date:  2019-02-18       Impact factor: 10.048

Review 7.  The pathophysiology and treatment of glaucoma: a review.

Authors:  Robert N Weinreb; Tin Aung; Felipe A Medeiros
Journal:  JAMA       Date:  2014-05-14       Impact factor: 56.272

Review 8.  Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis.

Authors:  Yih-Chung Tham; Xiang Li; Tien Y Wong; Harry A Quigley; Tin Aung; Ching-Yu Cheng
Journal:  Ophthalmology       Date:  2014-06-26       Impact factor: 12.079

9.  Artificial intelligence for the detection of age-related macular degeneration in color fundus photographs: A systematic review and meta-analysis.

Authors:  Li Dong; Qiong Yang; Rui Heng Zhang; Wen Bin Wei
Journal:  EClinicalMedicine       Date:  2021-05-08

Review 10.  Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey.

Authors:  Aram You; Jin Kuk Kim; Ik Hee Ryu; Tae Keun Yoo
Journal:  Eye Vis (Lond)       Date:  2022-02-02
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.