June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
Ensemble and Majority-Vote Strategies for Deep-Learning Based Detection of Atrophy-Related Biomarkers in OCT Volumes
Author Affiliations & Notes
  • Davide Scandella
    ARTORG Center, Universitat Bern, Bern, Bern, Switzerland
  • Mathias Gallardo
    ARTORG Center, Universitat Bern, Bern, Bern, Switzerland
  • Raphael Sznitman
    ARTORG Center, Universitat Bern, Bern, Bern, Switzerland
  • Martin Sebastian Zinkernagel
    Department of Ophthalmology, Inselspital Universitatsspital Bern, Bern, Bern, Switzerland
  • Sebastian Wolf
    Department of Ophthalmology, Inselspital Universitatsspital Bern, Bern, Bern, Switzerland
  • Footnotes
    Commercial Relationships   Davide Scandella None; Mathias Gallardo None; Raphael Sznitman RetinAI Medical AG, Code I (Personal Financial Interest), RetinAI Medical AG, Code O (Owner); Martin Zinkernagel Bayer, Novartis, Roche, Zeiss, Code C (Consultant/Contractor), Bayer, Boehringer Ingelheim, Code F (Financial Support); Sebastian Wolf Bayer, Boehringer Ingelheim, EarlySigh, Novartis, Roche, Zeiss, Code C (Consultant/Contractor), Bayer, Novartis, Roche, Code F (Financial Support)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 1083. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Davide Scandella, Mathias Gallardo, Raphael Sznitman, Martin Sebastian Zinkernagel, Sebastian Wolf; Ensemble and Majority-Vote Strategies for Deep-Learning Based Detection of Atrophy-Related Biomarkers in OCT Volumes. Invest. Ophthalmol. Vis. Sci. 2023;64(8):1083.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Build a detection model for atrophy-related biomarkers in OCT Bscans of AMD patients and explore multiple training strategies using multi-grader annotations.

Methods : Retrospective cohort of 1738 OCT volumes from 1738 distinct eyes and 1471 patients. Those volumes were automatically selected based on inferred biomarkers and the pathology prediction suggested by our previous work. The target biomarkers are related to atrophy: Drusen, Reticular Drusen, Double Layer Sign, Drusenoid PED, cRORA, iRORA, Subretinal Fibrosis and three escape options (Healthy, Not in the list, and Cannot grade). The simultaneous presence of multiple biomarkers is possible. For training, 7690 Bscans from 1538 volumes were annotated, each Bscan by three randomly selected graders. For testing, 9800 Bscans from 200 volumes were annotated by all five graders. Bscans with no grader majority were discarded. Figure 1 shows the biomarker distributions on both sets. We considered two architectures: a model trained to simulate the grading majority vote and an ensemble model composed of 5 models, each trained to simulate one grader. For the ensemble architecture, we combined three outputting and two model selection strategies, as listed in Figure 2. All models use a Resnet50 pre-trained model. We evaluated all models using Cohen’s kappa and compared them to graders on a newly computed majority with the model output as an additional grader.

Results : All 7 trained models present similar solid performances, as shown in Figure 2. The majority model achieves the highest macro-averaged Cohen’s kappa K=0.71±0.18 and appears to be the best training strategy. On average, the proposed model outperforms all graders for the given task, achieving K=0.78 against K=0.75 of the best grader on the newly computed majority.

Conclusions : Deep learning can estimate the presence of atrophy-related biomarkers in AMD patients with solid performances. Such a detector can be of a great help to assist clinical practices and clinical development of new medications and therapies for atrophy development.

This abstract was presented at the 2023 ARVO Annual Meeting, held in New Orleans, LA, April 23-27, 2023.

 

Distribution of biomarkers annotated as present after majority vote for the training and testing sets.

Distribution of biomarkers annotated as present after majority vote for the training and testing sets.

 

Cohen’s Kappa score for the 7 compared detection models.

Cohen’s Kappa score for the 7 compared detection models.

×
×

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.

×