July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Deep learning approach to improve the efficiency and effectiveness of optical coherence tomography (OCT) scans
Author Affiliations & Notes
  • Lingling Wang
    Carl Zeiss, Shanghai, China
  • Jianchun Zhao
    Vistel, China
  • Xuan Zou
    Peking Union Medical College Hospital, China
  • Xuan Chen
    Peking Union Medical College Hospital, China
  • Chunhui Jiang
    Eye & ENT Hospital of Fudan University, China
  • Xing Liu
    Zhongshan Ophthalmic Center, Sun Yat-Sen University, China
  • Hui Xiao
    Zhongshan Ophthalmic Center, Sun Yat-Sen University, China
  • Xiaoli Song
    Jiading Hospital of Traditional Chinese Medicine, China
  • Yao Zhang
    Northwestern Polytechnical University, China
  • Jun Wu
    Northwestern Polytechnical University, China
  • Jie Wang
    Renmin University of China, China
  • Dayong Ding
    Vistel, China
  • Junfeng Tan
    Carl Zeiss, Shanghai, China
  • Yuan Tian
    Carl Zeiss, Shanghai, China
  • Ningjiang Chen
    Carl Zeiss, Shanghai, China
  • Footnotes
    Commercial Relationships   Lingling Wang, Carl Zeiss (E); Jianchun Zhao, Vistel (E); Xuan Zou, None; Xuan Chen, None; Chunhui Jiang, None; Xing Liu, None; Hui Xiao, None; Xiaoli Song, None; Yao Zhang, Vistel (C); Jun Wu, Vistel (C); Jie Wang, Vistel (C); Dayong Ding, Vistel (E); Junfeng Tan, Carl Zeiss (E); Yuan Tian, Carl Zeiss (E); Ningjiang Chen, Carl Zeiss (E)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1514. doi:
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Lingling Wang, Jianchun Zhao, Xuan Zou, Xuan Chen, Chunhui Jiang, Xing Liu, Hui Xiao, Xiaoli Song, Yao Zhang, Jun Wu, Jie Wang, Dayong Ding, Junfeng Tan, Yuan Tian, Ningjiang Chen; Deep learning approach to improve the efficiency and effectiveness of optical coherence tomography (OCT) scans. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1514.

      Download citation file:

      © ARVO (1962-2015); The Authors (2016-present)

  • Supplements

Purpose : OCT macular exams routinely include a macular cube scan covering the whole macular region followed by high-resolution scans focusing on critical regions. However, accurately locating the critical pathological regions requires experience and is often time-consuming. This study aimed to develop a deep learning approach to automatically identify B-scans containing pathological anomalies in macular cube scans, such that technicians and ophthalmologists can efficiently find the critical information, and the subsequent high-resolution scans can be planned accordingly and automatically.

Methods : 599 cube scans (32 slices per scan) and 1,965 HD 5-line raster scans (5 slices per scan) centered on the macular were collected from a Primus OCT scanner (Carl Zeiss Meditec, Suzhou, China), yielding an OCT image set consisting of 28,993 B-scan slices. This OCT image set was split into a training set consisting of 23,500 B-scans and a test set consisting of 5,124 B-scans. Each of the B-scan slices in the training set was graded by one of three ophthalmologists with at least 5-year experience, to be 1) classified as no anomaly, 2) with visible anomaly in one of six sub-categories: overall deformation, fovea, above external limiting membrane (ELM), in or below ELM, sub-retinal area, and other, or 3) unable to determine. B-scan slices in the test set were cross-labeled by all three ophthalmologists. The training set was used to train a deep convolutional neural network with a customized loss function, and the trained model was evaluated on the test set. Sensitivity and specificity of the model to identify anomalies were computed.

Results : In the test set, 3,339 B-scans were labeled as no anomaly while 1,785 were labeled as with visible anomaly or unable to determine (combined as abnormal). The trained deep learning network correctly identified 3,032 normal and 1,617 abnormal B-scans, resulting in a sensitivity of 90.8% and specificity of 90.58%.

Conclusions : It is possible to detect pathological anomalies in OCT with high sensitivity and specificity using a deep learning approach. With this technique being integrated in OCT exam workflow, potential anomalies in a macular cube scan can be automatically identified, making the entire OCT exam workflow more effective and efficient.

This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.


This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.