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
Selecting a well-performing approach for automated subretinal drusenoid deposits quantification
Author Affiliations & Notes
  • Simon Schürer-Waldheim
    Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medizinische Universitat Wien, Vienna, Austria
  • José Morano
    Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medizinische Universitat Wien, Vienna, Austria
  • Guilherme Moreira Aresta
    Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medizinische Universitat Wien, Vienna, Austria
  • Klaudia Kostolna
    Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medizinische Universitat Wien, Vienna, Austria
  • Gregor Sebastian Reiter
    Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medizinische Universitat Wien, Vienna, Austria
  • Ursula Schmidt-Erfurth
    Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medizinische Universitat Wien, Vienna, Austria
  • Hrvoje Bogunovic
    Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medizinische Universitat Wien, Vienna, Austria
  • Footnotes
    Commercial Relationships   Simon Schürer-Waldheim None; José Morano None; Guilherme Aresta None; Klaudia Kostolna None; Gregor Reiter None; Ursula Schmidt-Erfurth None; Hrvoje Bogunovic None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 2392. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Simon Schürer-Waldheim, José Morano, Guilherme Moreira Aresta, Klaudia Kostolna, Gregor Sebastian Reiter, Ursula Schmidt-Erfurth, Hrvoje Bogunovic; Selecting a well-performing approach for automated subretinal drusenoid deposits quantification. Invest. Ophthalmol. Vis. Sci. 2024;65(7):2392.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Subretinal drusenoid deposits (SDD) are an important risk factor for faster disease progression in age-related macular degeneration. As a result, automated detection and quantification of SDD in optical coherence tomography (OCT) scans is of particular interest. The purpose of this study is to develop a well-performing automated segmentation approach to quantify SDD in OCTs.

Methods : In total, the dataset consists of 1358 manual graded B-scans from 14 OCT volumes (Spectralis) and 14 subjects. Only SDD of stage 2 and stage 3 were annotated. The data was split on a patient-distinct basis into training (n=8), validation (n=2) and test set (n=4). Two state-of-the-art deep learning approaches were implemented: SwinUNETR and Mask R-CNN (R-50-FPN), treating the SDD detection as 3D segmentation and 2D instance segmentation task, respectively. For the instance segmentation method, a connected components analysis (connectivity=4) was performed to convert the pixel-wise annotation maps into separated objects. The Dice metric was used to assess the similarity between the algorithms and the annotations. Spearman’s rank correlation coefficients (ρ) were determined to evaluate the capability in quantifying the SDD volume amount and the number of SDD.

Results : Using expert manual annotations as a reference on the test set, the model segmentation based on Mask R-CNN (Figure 1) achieved a Dice of 0.579 (± 0.071) compared to 0.326 (± 0.035) achieved by SwinUNETR. The Mask R-CNN model reached a good correlation concerning the SDD volume amount (ρ=0.82, p=0.0003) and the number of SDD (ρ=0.76, p=0.0016). In contrast, the SwinUNETR model achieved a moderate correlation concerning the volume amount (ρ=0.70, p=0.0052) and a poor correlation concerning the SDD number (ρ=0.48, p=0.0814).

Conclusions : A Mask R-CNN model was shown successful in detecting and segmenting SDD in OCT, reaching good correlations with human gradings and outperforming another state-of-the-art deep learning approach (SwinUNETR) by a big margin.

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

 

Figure 1: Examples of the segmentation results of the selected deep learning approach (Mask R-CNN) compared to the expert manual annotations.

Figure 1: Examples of the segmentation results of the selected deep learning approach (Mask R-CNN) compared to the expert manual annotations.

×
×

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.

×