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
Robust deep learning for automated AMD screening and staging based on a retinal foundation model
Author Affiliations & Notes
  • Teresa Araújo
    Christian Doppler Lab for Artificial Intelligence in Retina, Medizinische Universitat Wien, Wien, Wien, Austria
  • Guilherme Moreira Aresta
    Christian Doppler Lab for Artificial Intelligence in Retina, Medizinische Universitat Wien, Wien, Wien, Austria
  • Ursula Schmidt-Erfurth
    Ophthalmology, Medizinische Universitat Wien, Wien, Wien, Austria
  • Hrvoje Bogunovic
    Christian Doppler Lab for Artificial Intelligence in Retina, Medizinische Universitat Wien, Wien, Wien, Austria
  • Footnotes
    Commercial Relationships   Teresa Araújo None; Guilherme Aresta None; Ursula Schmidt-Erfurth Apellis Pharmaceuticals, Bayer, EcoR1, AbbVie, Medscape, Johnson&Johnson, Allergan, Roche, Böhringer, Heidelberg, Novartis, Galimedix, Code C (Consultant/Contractor), Genentech, Heidelberg Engineering, Kodiak, Novartis, Roche, RetInSight, Apellis Pharmaceuticals, Code F (Financial Support), Apellis, Roche, AbbVie, Code R (Recipient); Hrvoje Bogunovic Heidelberg Engineering, Apellis, Code F (Financial Support)
  • Footnotes
    Support  Christian Doppler Research Organization
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 2833. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Teresa Araújo, Guilherme Moreira Aresta, Ursula Schmidt-Erfurth, Hrvoje Bogunovic; Robust deep learning for automated AMD screening and staging based on a retinal foundation model. Invest. Ophthalmol. Vis. Sci. 2024;65(7):2833.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Trustworthy Artificial Intelligence systems for retinal OCT classification must simultaneously maintain their performance for different acquisition settings and identify cases outside their expected repertoire (outliers). In this study we assess if a state-of-the-art retinal foundation model is better suited than a common model for robust Age-related macular degeneration (AMD) screening.

Methods : The public RETFound foundation model, pretrained with OCTs, was fine-tuned for AMD classification using Heidelberg Spectralis (HS) OCT central B-scans from a multi-center private dataset (1653 eyes) with target classes: healthy, intermediate AMD (iAMD), neovascular AMD (nAMD) and geographic atrophy (GA). The model was evaluated in: 1) a private dataset (1590 eyes), with the target classes and outliers: diabetic macular edema (DME), retinal vein occlusion (RVO), Stargardt disease and central serous chorioretinopathy (CSC), and in 2) OCTID, a public external dataset of 572 Cirrus images from classes: healthy, central serous retinopathy (CSR), diabetic retinopathy (DR) and macular hole (MH). The tested outlier scores were the Cosine and the Mahalanobis distances on the features of the penultimate layer. A ResNet-18 pretrained on ImageNet was fine-tuned for comparison. Each training was repeated 10 times to ensure result reliability.

Results : The balanced accuracy for AMD classification on the private dataset was 0.92±0.01 for RETFound and 0.91±0.01 for ResNet. On OCTID, RETFound distinguished healthy from AMD cases with 0.99±0.00 balanced accuracy vs 0.66±0.16 from ResNet. For outlier detection (Fig. 1), on the private dataset, the AUCs for RETFound were 0.82±0.07/0.74±0.06 and 0.57±0.05/0.82±0.01 for ResNet using Mahalanobis/Cosine scores, respectively. For OCTID these AUCs were 0.87±0.09/0.55±0.07 for RETFound, and only 0.30±0.10/0.66±0.08 for ResNet. RETFound with Mahalanobis was the best system when considering both AMD staging and outlier detection. The feature space (Fig. 2) also shows that RETFound is better at separating outliers from the target classes.

Conclusions : The RETFound model shows good generalization capability, successfully classifying OCTs and detecting unrelated pathologies in the context of AMD screening and staging. Retinal foundation models constitute promising and reliable approaches for trustworthy assisted diagnosis.

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.

×