August 2019
Volume 60, Issue 11
Open Access
ARVO Imaging in the Eye Conference Abstract  |   August 2019
An Artificial Intelligence Deep Learning System for Discriminating Ungradable Optical Coherence Tomography Three-Dimension Volumetric Scans
Author Affiliations & Notes
  • anran ran
    The Chinese University of Hong Kong, Hong Kong, China
  • Amanda, Kwan Yu NGAI
    The Chinese University of Hong Kong, Hong Kong, China
  • Vivian, Wai Yin CHAN
    The Chinese University of Hong Kong, Hong Kong, China
  • Jian Shi
    The Chinese University of Hong Kong, Hong Kong, China
  • Clement, Chee Yung THAM
    The Chinese University of Hong Kong, Hong Kong, China
  • Carol, Yim Lui CHEUNG
    The Chinese University of Hong Kong, Hong Kong, China
  • Footnotes
    Commercial Relationships   anran ran, None; Amanda, Kwan Yu NGAI, None; Vivian, Wai Yin CHAN, None; Jian Shi, None; Clement, Chee Yung THAM, None; Carol, Yim Lui CHEUNG, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science August 2019, Vol.60, PB097. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      anran ran, Amanda, Kwan Yu NGAI, Vivian, Wai Yin CHAN, Jian Shi, Clement, Chee Yung THAM, Carol, Yim Lui CHEUNG; An Artificial Intelligence Deep Learning System for Discriminating Ungradable Optical Coherence Tomography Three-Dimension Volumetric Scans. Invest. Ophthalmol. Vis. Sci. 2019;60(11):PB097.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : The image quality of optical coherence tomography (OCT) scans is crucial for the accurate and reliable interpretation of retinal structures. Traditionally, signal strength is used as an index to include or exclude OCT scans for further analysis. However, it is insufficient to assess other image quality issues which require specialized knowledge in OCT for such assessment. Our study aims to develop and evaluate a deep learning system (DLS) as an automated tool for filtering out ungradable OCT volumetric scans.

Methods : We proposed a two-stage method to improve the effectiveness of training and the generalization of DLS. In a total of 3205 optic disc OCT volumetric scans were extracted from Cirrus HD-OCT (Carl Zeiss Meditec, Inc., Dublin, CA, USA), in which contains 778 eyes collected from a tertiary eye hospital in Hong Kong for training (80%) and testing (20%). Each scan was labeled as gradable or ungradable by a trained grader and then by a senior grader to mitigate the dissonance. OCT volumes fulfilling either the criteria: 1) missing data, 2) motion artifacts, 3) blurry, 4) signal loss, or 5) poor centration were defined as ungradable. We developed a3D model based on RestNet18 structure to discriminate ungradable optic disc OCT scans from gradable ones. We further evaluated our system with two independent datasets of 1009 scans from 803 eyes collected from another two eye clinics. Receiver Operation Characteristics (ROC) curve, the area under the ROC curve (AUC), sensitivity and specificity were used to evaluate the performance.

Results : A total of 4214 volumes were used. In the internal validation, the DLS achieved an AUC of 0.918 (95%CI, 0.895 to 0.942). The optimal sensitivity, specificity, and accuracy were 0.876, 0.846, and 0.856, respectively. In the two external validation datasets, the AUC were 0.777 (95%CI, 0.738 to 0.816) and 0.806 (95%CI, 0.769 to 0.864), with sensitivity of 0.787 and 0.718, specificity of 0.699 and 0.815, accuracy of 0.727 and 0.782, respectively.

Conclusions : The presented DLS achieved a good performance to discriminate the ungradable from gradable OCT volumes in both internal and external validation.

This abstract was presented at the 2019 ARVO Imaging in the Eye Conference, held in Vancouver, Canada, April 26-27, 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.

×