Literature DB >> 33610832

Deep Learning Approach for Automated Detection of Myopic Maculopathy and Pathologic Myopia in Fundus Images.

Ran Du1, Shiqi Xie1, Yuxin Fang1, Tae Igarashi-Yokoi1, Muka Moriyama1, Satoko Ogata1, Tatsuhiko Tsunoda2, Takashi Kamatani3, Shinji Yamamoto4, Ching-Yu Cheng5, Seang-Mei Saw5, Daniel Ting5, Tien Y Wong5, Kyoko Ohno-Matsui6.   

Abstract

PURPOSE: To determine whether eyes with pathologic myopia can be identified and whether each type of myopic maculopathy lesion on fundus photographs can be diagnosed by deep learning (DL) algorithms.
DESIGN: A DL algorithm was developed to recognize myopic maculopathy features and to categorize the myopic maculopathy automatically. PARTICIPANTS: We examined 7020 fundus images from 4432 highly myopic eyes obtained from the Advanced Clinical Center for Myopia.
METHODS: Deep learning (DL) algorithms were developed to recognize the key features of myopic maculopathy with 5176 fundus images. These algorithms were also used to develop a Meta-analysis for Pathologic Myopia (META-PM) study categorizing system (CS) by adding a specific processing layer. Models and the system were evaluated by 1844 fundus image. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to determine the performance of each DL algorithm. The rate of correct predictions was used to determine the performance of the META-PM study CS. MAIN OUTCOME MEASURES: Four trained DL models were able to recognize the lesions of myopic maculopathy accurately with high sensitivity and specificity. The META-PM study CS also showed a high accuracy and was qualified to be used in a semiautomated way during screening for myopic maculopathy in highly myopic eyes.
RESULTS: The sensitivity of the DL models was 84.44% for diffuse atrophy, 87.22% for patchy atrophy, 85.10% for macular atrophy, and 37.07% for choroidal neovascularization, and the AUC values were 0.970, 0.978, 0.982, and 0.881, respectively. The rate of total correct predictions from the META-PM study CS was 87.53%, with rates of 90.18%, 95.28%, 97.50%, and 91.14%, respectively, for each type of lesion. The META-PM study CS showed an overall rate of 92.08% in detecting pathologic myopia correctly, which was defined as having myopic maculopathy equal to or more serious than diffuse atrophy.
CONCLUSIONS: The novel DL models and system can achieve high sensitivity and specificity in identifying the different types of lesions of myopic maculopathy. These results will assist in the screening for pathologic myopia and subsequent protection of patients against low vision and blindness caused by myopic maculopathy.
Copyright © 2021 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Deep learning; Fundus image; META-PM categorizing system; Pathologic myopia

Mesh:

Year:  2021        PMID: 33610832     DOI: 10.1016/j.oret.2021.02.006

Source DB:  PubMed          Journal:  Ophthalmol Retina        ISSN: 2468-6530


  7 in total

Review 1.  Novel Uses and Challenges of Artificial Intelligence in Diagnosing and Managing Eyes with High Myopia and Pathologic Myopia.

Authors:  Ran Du; Kyoko Ohno-Matsui
Journal:  Diagnostics (Basel)       Date:  2022-05-12

2.  Development of deep learning-based detecting systems for pathologic myopia using retinal fundus images.

Authors:  Li Lu; Enliang Zhou; Wangshu Yu; Bin Chen; Peifang Ren; Qianyi Lu; Dian Qin; Lixian Lu; Qin He; Xuyuan Tang; Miaomiao Zhu; Li Wang; Wei Han
Journal:  Commun Biol       Date:  2021-10-26

Review 3.  Applications of Artificial Intelligence in Myopia: Current and Future Directions.

Authors:  Chenchen Zhang; Jing Zhao; Zhe Zhu; Yanxia Li; Ke Li; Yuanping Wang; Yajuan Zheng
Journal:  Front Med (Lausanne)       Date:  2022-03-11

4.  Automated detection of myopic maculopathy from color fundus photographs using deep convolutional neural networks.

Authors:  Jun Li; Lilong Wang; Yan Gao; Qianqian Liang; Lingzhi Chen; Xiaolei Sun; Huaqiang Yang; Zhongfang Zhao; Lina Meng; Shuyue Xue; Qing Du; Zhichun Zhang; Chuanfeng Lv; Haifeng Xu; Zhen Guo; Guotong Xie; Lixin Xie
Journal:  Eye Vis (Lond)       Date:  2022-04-01

5.  A Multicenter Clinical Study of the Automated Fundus Screening Algorithm.

Authors:  Fei Li; Jianying Pan; Dalu Yang; Junde Wu; Yiling Ou; Huiting Li; Jiamin Huang; Huirui Xie; Dongmei Ou; Xiaoyi Wu; Binghong Wu; Qinpei Sun; Huihui Fang; Yehui Yang; Yanwu Xu; Yan Luo; Xiulan Zhang
Journal:  Transl Vis Sci Technol       Date:  2022-07-08       Impact factor: 3.048

6.  A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration.

Authors:  Giovana A Benvenuto; Marilaine Colnago; Maurício A Dias; Rogério G Negri; Erivaldo A Silva; Wallace Casaca
Journal:  Bioengineering (Basel)       Date:  2022-08-05

7.  Deep Learning Model Based on 3D Optical Coherence Tomography Images for the Automated Detection of Pathologic Myopia.

Authors:  So-Jin Park; Taehoon Ko; Chan-Kee Park; Yong-Chan Kim; In-Young Choi
Journal:  Diagnostics (Basel)       Date:  2022-03-18
  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.