July 2018
Volume 59, Issue 9
Free
ARVO Annual Meeting Abstract  |   July 2018
Web based, fully automated, deep learning segmentation of oxygen induced retinopathy
Author Affiliations & Notes
  • Sa Xiao
    Ophthalmology, University of Washington School of Medicine, Kirkland, Washington, United States
  • Felicitas Bucher
    Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, United States
    Eye Center, Faculty of Medicine, University of Freiburg, Freiburg im Breisgau, Germany
  • yue wu
    Ophthalmology, University of Washington School of Medicine, Kirkland, Washington, United States
  • Ariel Rokem
    eScience Institute, University of Washington, Seattle, Washington, United States
  • Cecilia S Lee
    Ophthalmology, University of Washington School of Medicine, Kirkland, Washington, United States
  • Kyle V Marra
    Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, United States
    Department of Bioengineering, University of California, San Diego, San Diego, California, United States
  • Regis Fallon
    Lowy Medical Research Institute, La Jolla, California, United States
  • Sophia Diaz-Aguilar
    Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, United States
  • Edith Aguilar
    Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, United States
  • Martin Friedlander
    Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, United States
    Lowy Medical Research Institute, La Jolla, California, United States
  • Aaron Y. Lee
    Ophthalmology, University of Washington School of Medicine, Kirkland, Washington, United States
    eScience Institute, University of Washington, Seattle, Washington, United States
  • Footnotes
    Commercial Relationships   Sa Xiao, None; Felicitas Bucher, None; yue wu, None; Ariel Rokem, None; Cecilia Lee, None; Kyle Marra, University of California, San Diego Medical Scientist Training Program T32 GM007198-40 (F); Regis Fallon, None; Sophia Diaz-Aguilar, None; Edith Aguilar, None; Martin Friedlander, the Lowy Medical Research Institute (F), the NIH (EY11254) to MF (F); Aaron Lee, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2018, Vol.59, 1223. doi:https://doi.org/
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Sa Xiao, Felicitas Bucher, yue wu, Ariel Rokem, Cecilia S Lee, Kyle V Marra, Regis Fallon, Sophia Diaz-Aguilar, Edith Aguilar, Martin Friedlander, Aaron Y. Lee; Web based, fully automated, deep learning segmentation of oxygen induced retinopathy. Invest. Ophthalmol. Vis. Sci. 2018;59(9):1223. doi: https://doi.org/.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Oxygen-Induced Retinopathy (OIR) is a widely used rodent model of ischemic retinopathy. The percentages of retina with vaso-obliteration (VO) and neovascularization (NV) areas are the two primary parameters in this model. Currently, these areas are calculated using manual segmentation, a tedious and time consuming procedure. We have developed an automated pipeline and the purpose of our study was to extend the algorithm and create a fully deep learning, web-based workflow for VO and NV segmentation.

Methods : 1000 retina flatmount images of mice that went through the OIR procedure were obtained. Manual segmentation of VO and NV area were performed to serve as the ground truth for training. Two neural networks were trained separately for VO and NV. Due to the lack of manual segmentation of the total retina, we used kmeans to segment the 1000 images and manually picked the best 357 to use as the ground truth. Modified U-net architecture was utilized. The Dice coefficient was used to measure segmentation accuracy in the test set after training. A separate set of 37 images were manually segmented by four human experts. Each grader was set to the ground truth and the other 3 graders and the deep learning output were compared to the ground truth by Dice coefficients for the VO, NV and total retina regions. The percent of VO and NV regions were calculated and a linear correlation coefficient was calculated for each pairwise comparison.

Results : Our model achieved similar range of correlation coefficients (range 0.890 - 0.955) to expert inter-human correlation coefficients (range: 0.889 - 0.951) for the percent area of VO, and achieved a higher range of correlation coefficients (range: 0.940 - 0.988) compared to inter-expert correlation coefficients (range: 0.925 - 0.972) for the percent area of NV. Our new retina segmentation model was able to handle the cases that our previous kmeans model failed. In addition, we deployed our pipeline into an open access, user-friendly website.

Conclusions : We created a fully automated, fully deep-learning based model for OIR segmentation, and achieved similar performance as human experts.

This is an abstract that was submitted for the 2018 ARVO Annual Meeting, held in Honolulu, Hawaii, April 29 - May 3, 2018.

 

 

×
×

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.

×