June 2020
Volume 61, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2020
Performance of a novel deep learning algorithm for Automatic Retinal Fluid Quantification in Home OCT Images
Author Affiliations & Notes
  • David Lally
    New England Retina Consultants, Springfield, Massachusetts, United States
    Surgery, University of Massachusetts Medical School-Baystate, Springfield, Massachusetts, United States
  • Judy E Kim
    Medical College of Wisconsin, Wisconsin, United States
  • Michael J Elman
    Elman Retina Group, Maryland, United States
  • Oren Tomkins-Netzer
    Bnai Zion Medical Center, Israel
  • Yael Alon
    Notal Vison, Israel
  • Elad Bergman
    Notal Vison, Israel
  • Anat Loewenstein
    Tel Aviv Medical Center, Israel
  • Footnotes
    Commercial Relationships   David Lally, Aldeyra Therapeutics (F), Alimera Sciences (R), Allergan (R), Apellis (F), Apellis (C), Apellis (R), ChengDu Kanghong Biotechnology Co, Ltd (F), Genentech (R), IVERIC Bio (F), Kodiak Sciences (F), Neurotech (F), Notal Vision (F), Notal Vision (R), Novartis (R), Novartis (F), Optos (F); Judy Kim, Adverum (C), Alimera Science (C), Allergan (C), Clearside (C), Gemini (C), Genentech (C), Kodiak (C), Notal Vision (F), Novartis (C), Optos (F); Michael Elman, Allergan Pharmaceutical (R), Apellis (F), Genentech Inc (C), Genentech Inc/F. Hoffman La Roche (F), Graybug Vision (F), JAEB Center (F), Lowy Medical Research Institute (F), National Institutes of Health (F), Notal Vision (F), Optos (F), YD Global Life Science (F); Oren Tomkins-Netzer, Allergan (C), Bayer (C), Notal Vision (F); Yael Alon, Notal Vision (E); Elad Bergman, Notal Vision (E); Anat Loewenstein, Allergan (F), Bayer (F), Beyeonics Surgical (C), KHB (C), Notal Vision (F), Novartis (F), Oculis (C), Oxurion (C), Pres-By (C), Roche (C), Syneos Health (C), WebMD (C), Xbran (C)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 2571. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      David Lally, Judy E Kim, Michael J Elman, Oren Tomkins-Netzer, Yael Alon, Elad Bergman, Anat Loewenstein; Performance of a novel deep learning algorithm for Automatic Retinal Fluid Quantification in Home OCT Images. Invest. Ophthalmol. Vis. Sci. 2020;61(7):2571.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To evaluate the performance of a deep learning algorithm in identifying and quantifying retinal fluid in output of a patient self-operated Notal Home OCT (NOCT) device

Methods : Data were collected from 5 clinics where AMD patients self-imaged the central 10° of their maculae with the NOCT V2.5. 355 eyes from 239 subjects were enrolled, mean age 78 years (range: 54-92). From each cube scan (88 B-scans), avg. of 10 B-scans were selected for manual segmentation. Each B-scan was labeled pixel-wise into 4 compartments: Vitreous/outer layers (V/O), Retina (R), subretinal fluid (SRF), intraretinal fluid (IRF). Eyes were randomly split into learning and validation sets (ratio 8/1). Quantifier was developed using semantic segmentation with convolutional neural network. 1)Fluid quantification was evaluated by correlating each B-scan’s fluid area segmented by human vs machine. 2)Pixel-wise fluid was compared withrecall / precision. 3)Presence of fluid in B-scans were compared for accuracy.

Results : 3428 B-scans were manually segmented (75% with fluid). The learning set included 2936 B-scans of 311 eyes.The validation set included 492 B-scans of 44 eyes.
The area of SRF and IRF from the automatic segmentation were compared to the human-defined segmented area: 1) Pearson correlation of fluid area was 0.98 (p<0.00001) for SRF and 0.90 for IRF (p<0.00001). 2) SRF Fluid pixel-wise recall was 0.72 and precision was 0.86; The IRF recall was 0.80 and the precision was 0.77. 3) Sensitivity for detecting presence of SRF in B-scans was 0.985 and specificity 0.98. Sensitivity for detecting IRF was 0.99 and specificity was 0.97.

Conclusions : This version of NOA performed comparably to human readers, utilizing deep learning for automatic fluid segmentation and quantification on self-obtained NOCT V2.5 images, as part of a home-based OCT fluid-evaluation system. By analyzing fluid status and its dynamics, and visualizing the locations of fluid, this system has the potential to accurately monitor AMD disease activity in a patient self-operated home-use environment.

This is a 2020 ARVO Annual Meeting abstract.

 

Figure 1, SegmentationResults: (a) Two B-scans from the validation set. (b,c) Manual and auto-segmentation of the B-scans. (d) Fluid thickness maps -fluid distribution for SRF and IRF extracted from the auto-segmentation. Blue arrow indicates the position of the displayed B-scans (a) in the map. Green circles with diameter of 1 and 3 mm.

Figure 1, SegmentationResults: (a) Two B-scans from the validation set. (b,c) Manual and auto-segmentation of the B-scans. (d) Fluid thickness maps -fluid distribution for SRF and IRF extracted from the auto-segmentation. Blue arrow indicates the position of the displayed B-scans (a) in the map. Green circles with diameter of 1 and 3 mm.

×
×

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.

×