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
All that glitters is not gold: are current retina foundation models able to efficiently detect hypertensive retinopathy?
Author Affiliations & Notes
  • Julio Silva-Rodríguez
    ETS Montreal, Quebec, Canada
  • Hadi Chakor
    Diagnos Inc., Quebec, Canada
  • Riadh Kobbi
    Diagnos Inc., Quebec, Canada
  • Balamurali Murugesan
    ETS Montreal, Quebec, Canada
  • Waziha Kabir
    Diagnos Inc., Quebec, Canada
  • Jihed Chelbi
    Diagnos Inc., Quebec, Canada
  • Marc-André Racine
    Diagnos Inc., Quebec, Canada
  • Jose Dolz
    ETS Montreal, Quebec, Canada
  • Ismail Ben Ayed
    ETS Montreal, Quebec, Canada
  • Footnotes
    Commercial Relationships   Julio Silva-Rodríguez None; Hadi Chakor None; Riadh Kobbi None; Balamurali Murugesan None; Waziha Kabir None; Jihed Chelbi None; Marc-André Racine None; Jose Dolz None; Ismail Ben Ayed None
  • Footnotes
    Support  Fonds de recherche du Québec (FRQ) and PROMPT Quebec
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 5660. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Julio Silva-Rodríguez, Hadi Chakor, Riadh Kobbi, Balamurali Murugesan, Waziha Kabir, Jihed Chelbi, Marc-André Racine, Jose Dolz, Ismail Ben Ayed; All that glitters is not gold: are current retina foundation models able to efficiently detect hypertensive retinopathy?. Invest. Ophthalmol. Vis. Sci. 2024;65(7):5660.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Early Hypertensive retinopathy (HR) detection is of great interest to avoid irreversible damage to the retinal microcirculation. Computer-aided systems are a promising solution for cost-effective disease screening using fundus images. A paradigm shift is currently emerging in AI for medical imaging with large-scale pre-trained foundation models (FMs), and their strong transferability capabilities. This study aims to elucidate if emerging FMs can effectively be adapted to the challenging task of HR detection.

Methods : We perform a efficient adaptation of FMs to HR detection by Linear Probing, i.e. adjusting a linear classifier over pre-trained features. Two data regimes are examined: a few-shot using 10 samples per class, and a large data regime using all training samples. Three FMs are considered. First, RETFound (Zhang et al., Nature 2023), a self-supervised autoencoder pre-trained on 800K fundus images, with a ViT-B/16 backbone. Second, FLAIR (Silva-Rodriguez et al., ArXiv 2023), a vision-language model encoding domain-specialized knowledge via text supervision, trained on 300K fundus images and 96 different retinal conditions using a RN50 (25M parameters). Finally, BioMedCLIP (Zhou et al., ArXiv 2023), a generalist ViT-B/16 transformer with 86M parameters pre-trained on 15M images from different domains (radiology, ophthalmology, etc.).

Results : We used the CGI-HR dataset following a 5-fold cross-evaluation. Our results show that generalist models such as BiomedCLIP fail to provide a meaningful classification (0.620 AUC). Although domain-specific data alleviates the performance drop using RETFound (0.679 AUC), still the performance is considerably lower than using FLAIR (0.786 AUC), which leverages expert’s knowledge in text supervision. Similar trends are observed in the low data regime, where FLAIR shows 5% improvements compared to other FMs.

Conclusions : This work studies the capability of recently released FMs for efficient HR detection. A careful selection of the FM used for adaptation is necessary. Larger model parameters or amounts of pre-training data are not necessarily preferable over domain-specific, expert-knowledge guided models. From a practical point of view, we must consider the potential for clinical application of this technique by doing so non-invasively, rapidly, safely and cost-effectively.

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.

×