0 111

Cited 0 times in

Automated detection of crystalline retinopathy via fundus photography using multistage generative adversarial networks

Authors
 Eun Young Choi  ;  Seung Hoon Han  ;  Ik Hee Ryu  ;  Jin Kuk Kim  ;  In Sik Lee  ;  Eoksoo Han  ;  Hyungsu Kim  ;  Joon Yul Choi  ;  Tae Keun Yoo 
Citation
 BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, Vol.43(4) : 725-735, 2023-10 
Journal Title
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
Issue Date
2023-10
Keywords
Crystalline retinopathy ; Multistage GAN ; CutMix ; Deep learning ; Fundus photography
Abstract
Purpose : Crystalline retinopathy is characterized by reflective crystal deposits in the macula and is caused by various systemic conditions including hereditary, toxic, and embolic etiologies. Herein, we introduce a novel application of deep learning with a multistage generative adversarial network (GAN) to detect crystalline retinopathy using fundus photography.

Methods : The dataset comprised major classes (healthy retina, diabetic retinopathy, exudative age-related macular degeneration, and drusen) and a crystalline retinopathy class (minor set). To overcome the limited data on crystalline retinopathy, we proposed a novel multistage GAN framework. The GAN was retrained after CutMix combination by inputting the GAN-generated synthetic data as new inputs to the original training data. After the multistage CycleGAN augmented the data for crystalline retinopathy, we built a deep-learning classifier model for detection.

Results : Using the multistage CycleGAN facilitated realistic fundus photography synthesis with the characteristic features of retinal crystalline deposits. The proposed method outperformed typical transfer learning, prototypical networks, and knowledge distillation for both multiclass and binary classifications. The final model achieved an area under the curve of the receiver operating characteristics of 0.962 for internal validation and 0.987 for external validation for the detection of crystalline retinopathy.

Conclusion : We introduced a deep learning approach for detecting crystalline retinopathy, a potential biomarker of underlying systemic pathological conditions. Our approach enables realistic pathological image synthesis and more accurate prediction of crystalline retinopathy, an essential but minor retinal condition.
Full Text
https://www.sciencedirect.com/science/article/pii/S0208521623000591
DOI
10.1016/j.bbe.2023.10.005
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Ophthalmology (안과학교실) > 1. Journal Papers
Yonsei Authors
Choi, Eun Young(최은영) ORCID logo https://orcid.org/0000-0002-1668-6452
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/196858
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links