Literature DB >> 33538890

Development of a deep-learning system for detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus images: a pilot study.

Chenxi Zhang1, Feng He1, Bing Li1, Hao Wang2, Xixi He2, Xirong Li3,4, Weihong Yu5, Youxin Chen6.   

Abstract

PURPOSE: To investigate the detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus imaging system (Optos) with convolutional neural network technology.
METHODS: This study included 1500 Optos color images for tessellated fundus confirmation and peripheral retinal lesion (lattice degeneration, retinal breaks, and retinal detachment) assessment. Three retinal specialists evaluated all images and proposed the reference standard when an agreement was achieved. Then, 722 images were used to train and verify a combined deep-learning system of 3 optimal binary classification models trained using seResNext50 algorithm with 2 preprocessing methods (original resizing and cropping), and a test set of 189 images were applied to verify the performance compared to the reference standard.
RESULTS: With optimal preprocessing approach (original resizing method for lattice degeneration and retinal detachment, cropping method for retinal breaks), the combined deep-learning system exhibited an area under curve of 0.888, 0.953, and 1.000 for detection of lattice degeneration, retinal breaks, and retinal detachment respectively in tessellated eyes. The referral accuracy of this system was 79.8% compared to the reference standard.
CONCLUSION: A deep-learning system is feasible to detect lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field images. And this system may be considered for screening and telemedicine.
© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.

Entities:  

Keywords:  Deep learning; Lattice degeneration; Retinal breaks; Retinal detachment; Tessellated fundus; Ultra-wide-field fundus imaging

Year:  2021        PMID: 33538890     DOI: 10.1007/s00417-021-05105-3

Source DB:  PubMed          Journal:  Graefes Arch Clin Exp Ophthalmol        ISSN: 0721-832X            Impact factor:   3.117


  2 in total

1.  Pathologic changes in highly myopic eyes of young males in Singapore.

Authors:  Victor Tc Koh; Gerard Km Nah; Lan Chang; Adeline H X Yang; Sheng Tong Lin; Kyoko Ohno-Matsui; Tien Yin Wong; Seang Mei Saw
Journal:  Ann Acad Med Singapore       Date:  2013-05       Impact factor: 2.473

2.  Tessellated fundus appearance and its association with myopic refractive error.

Authors:  Divya Jagadeesh; Krupa Philip; Thomas J Naduvilath; Cathleen Fedtke; Monica Jong; Haidong Zou; Padmaja Sankaridurg
Journal:  Clin Exp Optom       Date:  2018-08-09       Impact factor: 2.742

  2 in total
  3 in total

1.  Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images.

Authors:  Xinyu Zhao; Lihui Meng; Hao Su; Bin Lv; Chuanfeng Lv; Guotong Xie; Youxin Chen
Journal:  Front Cell Dev Biol       Date:  2022-05-19

2.  Automated detection of retinal exudates and drusen in ultra-widefield fundus images based on deep learning.

Authors:  Zhongwen Li; Chong Guo; Danyao Nie; Duoru Lin; Tingxin Cui; Yi Zhu; Chuan Chen; Lanqin Zhao; Xulin Zhang; Meimei Dongye; Dongni Wang; Fabao Xu; Chenjin Jin; Ping Zhang; Yu Han; Pisong Yan; Haotian Lin
Journal:  Eye (Lond)       Date:  2021-08-03       Impact factor: 4.456

3.  A cascade eye diseases screening system with interpretability and expandability in ultra-wide field fundus images: A multicentre diagnostic accuracy study.

Authors:  Jing Cao; Kun You; Jingxin Zhou; Mingyu Xu; Peifang Xu; Lei Wen; Shengzhan Wang; Kai Jin; Lixia Lou; Yao Wang; Juan Ye
Journal:  EClinicalMedicine       Date:  2022-09-05
  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.