Affordable Access

deepdyve-link
Publisher Website

Detecting glaucoma based on spectral domain optical coherence tomography imaging of peripapillary retinal nerve fiber layer: a comparison study between hand-crafted features and deep learning model.

Authors
  • Zheng, Ce1, 2
  • Xie, Xiaolin2
  • Huang, Longtao3
  • Chen, Binyao2
  • Yang, Jianling2
  • Lu, Jiewei3
  • Qiao, Tong1
  • Fan, Zhun3
  • Zhang, Mingzhi4
  • 1 Department of Ophthalmology, Shanghai Children's Hospital, Shanghai Jiao Tong University, Shanghai, China. , (China)
  • 2 Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, 515000, Guangdong, China. , (China)
  • 3 Department of Electronic Engineering, Shantou University, Shantou, Guangdong, China. , (China)
  • 4 Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, 515000, Guangdong, China. [email protected] , (China)
Type
Published Article
Journal
Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie
Publication Date
Dec 07, 2019
Identifiers
DOI: 10.1007/s00417-019-04543-4
PMID: 31811363
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

To develop a deep learning (DL) model for automated detection of glaucoma and to compare diagnostic capability against hand-craft features (HCFs) based on spectral domain optical coherence tomography (SD-OCT) peripapillary retinal nerve fiber layer (pRNFL) images. A DL model with pre-trained convolutional neural network (CNN) based was trained using a retrospective training set of 1501 pRNFL OCT images, which included 690 images from 153 glaucoma patients and 811 images from 394 normal subjects. The DL model was further tested in an independent test set of 50 images from 50 glaucoma patients and 52 images from 52 normal subjects. A customized software was used to extract and measure HCFs including pRNFL thickness in average and four different sectors. Area under the receiver operator characteristics (AROC) curves was calculated to compare the diagnostic capability between DL model and hand-crafted pRNFL parameters. In this study, the DL model achieved an AROC of 0.99 [CI: 0.97 to 1.00] which was significantly larger than the AROC values of all other HCFs (AROCs 0.661 with 95% CI 0.549 to 0.772 for temporal sector, AROCs 0.696 with 95% CI 0.549 to 0.799 for nasal sector, AROCs 0.913 with 95% CI 0.855 to 0.970 for superior sector, AROCs 0.938 with 95% CI 0.894 to 0.982 for inferior sector, and AROCs 0.895 with 95% CI 0.832 to 0.957 for average). Our study demonstrated that DL models based on pre-trained CNN are capable of identifying glaucoma with high sensitivity and specificity based on SD-OCT pRNFL images.

Report this publication

Statistics

Seen <100 times