July 2019
Volume 60, Issue 9
Free
ARVO Annual Meeting Abstract  |   July 2019
Machine Learning Based End-to-End Pipeline for Optical Coherence Tomography Angiography of Diabetic Retinopathy
Author Affiliations & Notes
  • Morgan Heisler
    School of Engineering Science, Simon Fraser University, Burnaby, British Columbia, Canada
  • Donghuan Lu
    School of Engineering Science, Simon Fraser University, Burnaby, British Columbia, Canada
  • Julian Lo
    School of Engineering Science, Simon Fraser University, Burnaby, British Columbia, Canada
  • Sonja Karst
    Department of Ophthalmology and Visual Sciences, University of British Columbia, Vancouver, British Columbia, Canada
  • Nathan Schuck
    Faculty of Medicine, University of British Columbia, Vancouver, British Columbia, Canada
  • MyeongJin Ju
    School of Engineering Science, Simon Fraser University, Burnaby, British Columbia, Canada
  • Ivana Zadro
    Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia
  • Sven Loncaric
    Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia
  • Simon Warner
    Department of Ophthalmology and Visual Sciences, University of British Columbia, Vancouver, British Columbia, Canada
  • David Maberley
    Department of Ophthalmology and Visual Sciences, University of British Columbia, Vancouver, British Columbia, Canada
  • Mirza Faisal Beg
    School of Engineering Science, Simon Fraser University, Burnaby, British Columbia, Canada
  • Eduardo Vitor Navajas
    Department of Ophthalmology and Visual Sciences, University of British Columbia, Vancouver, British Columbia, Canada
  • Marinko V Sarunic
    School of Engineering Science, Simon Fraser University, Burnaby, British Columbia, Canada
  • Footnotes
    Commercial Relationships   Morgan Heisler, None; Donghuan Lu, None; Julian Lo, None; Sonja Karst, None; Nathan Schuck, None; MyeongJin Ju, Seymour Vision Inc. (E); Ivana Zadro, None; Sven Loncaric, None; Simon Warner, None; David Maberley, None; Mirza Beg, None; Eduardo Navajas, None; Marinko Sarunic, Seymour Vision Inc. (I)
  • Footnotes
    Support  Natural Sciences and Engineering Research Council of Canada, Canadian Institutes of Health Research and National Health, Michael Smith Foundation for Health Research, Brain Canada
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 2204. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Morgan Heisler, Donghuan Lu, Julian Lo, Sonja Karst, Nathan Schuck, MyeongJin Ju, Ivana Zadro, Sven Loncaric, Simon Warner, David Maberley, Mirza Faisal Beg, Eduardo Vitor Navajas, Marinko V Sarunic; Machine Learning Based End-to-End Pipeline for Optical Coherence Tomography Angiography of Diabetic Retinopathy. Invest. Ophthalmol. Vis. Sci. 2019;60(9):2204.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Machine learning for binary classification of diabetic retinopathy (DR) in fundus images has achieved high validation accuracies, however classification results of multiple severity levels are generally less impressive. The use of optical coherence tomography angiography (OCTA) has potential to improve classification. We investigate an end-to-end machine learning based pipeline for the volumetric OCTA images consisting of cascaded Deep Neural Networks (DNNs) for the segmentation of five retinal layers, intraretinal fluid, microvasculature, the foveal avascular zone (FAZ), and DR severity grading.

Methods : 3x3mm volumetric scans centered on the fovea were used from two commercial OCTA systems: AngioPlex (Cirrus 5000 HD-OCT; Carl Zeiss Meditec), and PlexElite (Carl Zeiss Meditec). The first DNN, which segmented 5 retinal layers and intraretinal fluid, was trained on 14,700 OCT Bscans. The vessel and FAZ segmentation DNN was trained on 80 en face OCTA images. Both segmentation DNNs were modified UNET architectures. Seven FAZ metrics were calculated (area, perimeter, minimum and maximum diameter, axis ratio, eccentricity, acircularity index) along with four vascular parameters (density, skeleton density, fractal dimension, and average vessel diameter). Classification of DR severity (no DR, non-proliferative DR, proliferative DR) was performed separately.

Results : Figure 1 shows representative results from the stages of the pipeline. Figure 1 (a-b) is the en facesuperficial and deep OCTA, (c) a representative Bscan with the layer and fluid segmentations, (d-e) superficial and deep vessel segmentation maps with FAZ min (red) and max (green) diameter, and perimeter (yellow), (f) FAZ segmentation, (g) inner ring density, (h) central circle density, (i) en face fluid segmentation map.
The proposed layer and fluid segmentation DNN achieved a Dice index of 0.942 for RNFL, 0.970 for GCL, 0.957 for INL, 0.968 for OPL, 0.959 for the outer retina, and 0.786 for fluid. For the vessel and FAZ segmentation, the Dice index was 0.836 for the microvasculature and 0.957 for the FAZ. All segmentation performances were comparable to a second manual rater. The classification DNN achieved an accuracy of 88%.

Conclusions : Machine learning based segmentation enables reliable quantification of retinal OCTA scans. The results are encouraging for improving the classification towards a clinical severity scale.

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.

×