June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Identification of initial events leading to outer retinal atrophy in age-related macular degeneration using deep learning quantifications
Author Affiliations & Notes
  • Gregor Sebastian Reiter
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Austria
  • Sophie Riedl
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Austria
  • Antoine Rivail
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Austria
  • Julia Mai
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Austria
  • Wolf-Dieter Vogl
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Austria
  • Christoph Grechenig
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Austria
  • Zhichao Wu
    Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Victoria, Australia
    Ophthalmology, Department of Surgery, The University of Melbourne, Victoria, Australia
  • Robyn H Guymer
    Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Victoria, Australia
    Ophthalmology, Department of Surgery, The University of Melbourne, Victoria, Australia
  • Hrvoje Bogunovic
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Austria
  • Ursula Schmidt-Erfurth
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Austria
  • Footnotes
    Commercial Relationships   Gregor Reiter, None; Sophie Riedl, None; Antoine Rivail, None; Julia Mai, None; Wolf-Dieter Vogl, None; Christoph Grechenig, None; Zhichao Wu, None; Robyn Guymer, Apellis (C), Bayer (C), Novartis (C), Roche Genentech (C); Hrvoje Bogunovic, None; Ursula Schmidt-Erfurth, Genentech (C), Heidelberg Engineering (C), Kodiak (C), Novartis (C), RetInSight (C), Roche (C)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 121. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Gregor Sebastian Reiter, Sophie Riedl, Antoine Rivail, Julia Mai, Wolf-Dieter Vogl, Christoph Grechenig, Zhichao Wu, Robyn H Guymer, Hrvoje Bogunovic, Ursula Schmidt-Erfurth; Identification of initial events leading to outer retinal atrophy in age-related macular degeneration using deep learning quantifications. Invest. Ophthalmol. Vis. Sci. 2021;62(8):121.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To investigate temporal changes of deep learning quantified imaging biomarkers in intermediate age-related macular degeneration (iAMD) in eyes developing initial outer retinal atrophy associated with incipient macular atrophy (iMA).

Methods : Eyes with iAMD from the sham treatment cohort of a prospective randomized clinical trial (LEAD study) were included. SD-OCT scans were acquired every 6 months for a follow up of 3 years. All eyes were re-graded for the development of iMA (choroidal hypertransmission (HT) > 125µm + evidence of RPE irregularities) on OCT in the absence of signs of exudation (IRF, SRF). Inner nuclear layer/outer plexiform layer (INL/OPL) subsidence (with at least subsidence of the INL-OPL and OPL-ONL junctions) was also annotated in all time-points for all iMA cases. Photoreceptor (PR) thickness, ONL thickness, drusen thickness (DT) and HT were measured using AI algorithms. Morphological changes before and after INL/OPL subsidence, as well as differences between areas of pathological and intact outer retina (subsidence/drusen/non-drusen area) were assessed using mixed effect models considering both eyes and multiple lesions per eye.

Results : Out of 280 eyes, 54 eyes developed iMA, of which 52 eyes presented with INL/OPL subsidence prior to iMA. Progressive PR thinning was present as the first sign of outer retinal changes with a mean thinning of -0.34 µm/month; 95% CI: -0.36,-0.33). ONL thinning was present after PR thinning (mean: -0.47 µm/months; 95% CI: -0.51,-0.44). DT decreased and HT appeared after the last visit before INL/OPL subsidence (Figure 1). A significant difference between INL/OPL subsidence area, drusen area and non-drusen area was identified for longitudinal PR thinning, ONL thinning, DT and HT (all p<0.001, except DT: p=0.047).

Conclusions : PR thinning on in-vivo OCT is an initiating sign of developing outer retinal atrophy in non-neovascular AMD. Subsequently, ONL thinning becomes apparent, DT declines and HT appears, leading to iMA in the vast majority of cases. Precise assessment of deep learning quantified retinal biomarkers using longitudinal in-vivo OCT volumes allows accurate identification and evaluation of early morphological alterations. These findings give new insight into the pathomechanism of atrophy development in AMD and provide novel possibilities in disease monitoring.

This is a 2021 ARVO Annual Meeting abstract.

 

×
×

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.

×