June 2017
Volume 58, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2017
Deep-learning estimation of choroidal thickness from color fundus photographs
Author Affiliations & Notes
  • Hironobu Tampo
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Hidenori Takahashi
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Yasuo Yanagi
    Singapore Eye Research Institute, Singapore, Singapore
  • Shin-ichi Sakamoto
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Satoru Inoda
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Hidetoshi Kawashima
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Yuji Inoue
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Yusuke Arai
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Ryota Takahashi
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Megumi Soeta
    Ophthalmology, Jichi Medical University, Shimotsuke City, Japan
  • Footnotes
    Commercial Relationships   Hironobu Tampo, Bayer (R), Santen (R), Senju (R); Hidenori Takahashi, Bayer (R), DeepEyeVision LLC (I), Jichi Medical University (P), Kowa (R), Novartis (F), Santen (R); Yasuo Yanagi, Bayer (C), Novartis (C), Santen (C); Shin-ichi Sakamoto, None; Satoru Inoda, Bayer (R), Novartis (R); Hidetoshi Kawashima, Bayer (R), Kowa (R), Novartis (R), Santen (R), Senju (R); Yuji Inoue, Bayer (R), Novertis (R), Santen (R); Yusuke Arai, Bayer (R), Novartis (R); Ryota Takahashi, None; Megumi Soeta, None
  • Footnotes
    Support  Novartis Grant
Investigative Ophthalmology & Visual Science June 2017, Vol.58, 685. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Hironobu Tampo, Hidenori Takahashi, Yasuo Yanagi, Shin-ichi Sakamoto, Satoru Inoda, Hidetoshi Kawashima, Yuji Inoue, Yusuke Arai, Ryota Takahashi, Megumi Soeta; Deep-learning estimation of choroidal thickness from color fundus photographs. Invest. Ophthalmol. Vis. Sci. 2017;58(8):685.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : The accuracy of general image classification has drastically improved since the advent of automatic extraction by deep learning to identify characteristic points in images. In 2015, artificial intelligence by deep learning was reported to be more accurate than human beings for the first time. Few reports have considered the application of deep-learning analysis to fundus photographs. Here, we applied deep learning to automate estimation of choroidal thickness from color fundus photographs.

Methods : We used images from 597 subjects who underwent same-day optical coherence tomography examination (swept-source OCT) [DRI-OCT (TOPCON, TOKYO)] and color fundus photography using a fundus camera [VX-10 (KOWA, AICHI)] at the outpatient clinic of Jichi Medical University hospital. From these images, those showing any of age-related macular degeneration, central serous chorioretinopathy, and proliferative diabetes retinopathy were excluded. Central choroidal thickness (CCT) was measured manually with OCT. When more than 6 images were available of a single eye, 5 of those images were used for classifier training. Forty eyes had only 1 associated fundus photograph. Images of the 3 eyes with the highest variance in CCT (due to diurnal variance) were excluded. Of the fundus photographs, 546. were used for deep learning. The deep learning system was run on a workstation (graphical processing units: 4) for 51 h. The 51 excluded photographs were used for validation.

Results : The correlation coefficient for the 40 single-photograph eyes was 0.69. The same-eye correlation coefficients for the 3 eyes with highest CCT variance were 0.98, -0.96, and 0.45, in order of decreasing variance.

Conclusions : Artificial intelligence by deep learning estimated CCT from the color fundus photographs with good accuracy. However, single-eye diurnal CCT variation was not estimated well.

This is an abstract that was submitted for the 2017 ARVO Annual Meeting, held in Baltimore, MD, May 7-11, 2017.

×
×

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.

×