Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Using AI Uncertainty for Image Quality Assessment and Gradability of Retinal Thickness in OCT
Author Affiliations & Notes
  • Hlynur Skulason
    RetInSight GmbH, Wien, Wien, Austria
  • Ariadne Whitby
    RetInSight GmbH, Wien, Wien, Austria
  • Oliver Leingang
    RetInSight GmbH, Wien, Wien, Austria
  • Wolf-Dieter Vogl
    RetInSight GmbH, Wien, Wien, Austria
  • Patrick Andre
    RetInSight GmbH, Wien, Wien, Austria
  • Taghleb Alzouni
    RetInSight GmbH, Wien, Wien, Austria
  • Ursula Schmidt-Erfurth
    RetInSight GmbH, Wien, Wien, Austria
    Medizinische Universitat Wien Universitatsklinik fur Augenheilkunde und Optometrie, Wien, Wien, Austria
  • Footnotes
    Commercial Relationships   Hlynur Skulason RetInSight GmbH, Code E (Employment); Ariadne Whitby RetInSight GmbH, Code E (Employment); Oliver Leingang RetInSight GmbH, Code E (Employment); Wolf-Dieter Vogl RetInSight GmbH, Code E (Employment); Patrick Andre RetInSight GmbH, Code E (Employment); Taghleb Alzouni RetInSight GmbH, Code E (Employment); Ursula Schmidt-Erfurth Genentech, Kodiak, Novartis, Apellis, RetInSight, Code C (Consultant/Contractor), RetInSight, Code F (Financial Support)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 5637. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Hlynur Skulason, Ariadne Whitby, Oliver Leingang, Wolf-Dieter Vogl, Patrick Andre, Taghleb Alzouni, Ursula Schmidt-Erfurth; Using AI Uncertainty for Image Quality Assessment and Gradability of Retinal Thickness in OCT. Invest. Ophthalmol. Vis. Sci. 2024;65(7):5637.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : AI-based measurements are becoming more common in clinical routine and clinical trial analysis. Poor image quality or obfuscation of features due to OCT-based artifacts can negatively impact the reliability of automated biomarker measurements. This study evaluates the efficacy of a novel deep learning (DL) algorithm in detecting image quality in OCT scans to measure retinal thickness. Our research aims to validate the potential of this DL model as a reliable tool for identifying scans with poor image quality, thereby enhancing the diagnostic accuracy and utility of OCT imaging.

Methods : The model (M) is designed to annotate retinal layers. It provides a segmentation of layer lines as well as the uncertainty of the prediction along A-scans. B-scan gradability is determined by a composite of the uncertainties (90th percentile, 3 lines) that exceeds a threshold. A real-world dataset was gathered from the macular clinic of the Vienna General Hospital between 2007 and 2018. From a registry of 128,000 scans acquired with a Cirrus (Carl Zeiss Meditec) scanner, 504 were randomly sampled by stratifying on acquisition year, with image quality varying. 2 experienced readers (R1, R2) independently assessed whether 816 B-scans were gradable for measuring retinal thickness, and if deemed ungradable, selected reason(s) why. Initial threshold was determined on a 504 B-scan training set and validated on a 200 B-scan test set. Finally, 112 were graded as a confirmation study on positively bad B-scans.

Results : The model achieved mean specificity of 0.99 on test set and agreement of 0.69 in confirmation study. Out of 191 test scans marked gradable by M, 173 (91%) were in accordance with R1+R2. Inter-reader gradability agreement was high across training and test sets (0.91/0.92) but dropped in confirmation study (0.80). Similarly, the agreement of M with R1+R2 was high across training and test sets (0.89/0.90) and reduced in confirmation study (0.59). 21 test scans with disagreement between M, R1, and R2 were qualitatively assessed. 17 were attributed to R1/R2 ambivalence, 4 as false positive cases.

Conclusions : A DL model was used to identify scans with insufficient quality for AI-based analysis using the uncertainty in layer predictions. Our findings show that these models can be used to efficiently identify problematic cases from large datasets and are suitable as a robust tool for OCT image quality assessment.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

 

×
×

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.

×