June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Automated region of interest selection improves the deep learning based segmentation of hyper-reflective foci in optical coherence tomography images
Author Affiliations & Notes
  • Minhaj Nur Alam
    Biomedical Data Science, Stanford University, Stanford, California, United States
  • Maximilian Pfau
    Rheinische Friedrich-Wilhelms-Universitat Bonn, Bonn, Nordrhein-Westfalen, Germany
    Ophthalmic Genetics and Visual Function Branch, National Eye Institute, Bethesda, Maryland, United States
  • Darvin Yi
    Illinois Eye and Ear Infirmary, Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, Illinois, United States
  • Daniel L Rubin
    Biomedical Data Science, Stanford University, Stanford, California, United States
    Radiology, Stanford University, Stanford, California, United States
  • Joelle Hallak
    Illinois Eye and Ear Infirmary, Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, Illinois, United States
  • Footnotes
    Commercial Relationships   Minhaj Nur Alam, None; Maximilian Pfau, None; Darvin Yi, None; Daniel Rubin, None; Joelle Hallak, None
  • Footnotes
    Support  BrightFocus Foundation Grant, NEI P30 Core grant (P30 EY001792) and unrestricted grant support from the RPB
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 2449. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Minhaj Nur Alam, Maximilian Pfau, Darvin Yi, Daniel L Rubin, Joelle Hallak; Automated region of interest selection improves the deep learning based segmentation of hyper-reflective foci in optical coherence tomography images. Invest. Ophthalmol. Vis. Sci. 2021;62(8):2449.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Hyper-reflective foci(HRFs) are associated with age-related macular degeneration(AMD), and with visual outcomes in diabetic retinopathy. Automating the HRF segmentation in retinal tissues would be beneficial for feature extraction and overall disease management. This work presents a fully automated approach for HRF segmentation in spectral domain optical coherence tomography(SD-OCT) images.

Methods : This study includes SD-OCT data acquired at the University of Bonn (Heidelberg Spectralis; image resolution of 786x496 pixels,scan width 30°). The dataset contained 3669 B-scans from 56 patients (10 diabetic macular edema,46 AMD).
A modified U-Net architecture with a densenet-169 backbone was implemented for the semantic segmentation. A point of innovation is the use of a patch-based strategy that ensures the model encoder is trained on enough pixels of interest. To elaborate, as a pre-processing step, we define the retinal pigment epithelium(RPE) layer for each B-scan (using a previously trained model for OCT layer segmentation). An automated dataloader takes the B-scan, HRF ground truth annotation and the RPE denotation as inputs and generates random patches(8x64x64) for each image around the HRF and RPE denoted pixels(location chosen randomly). These patches are then fed into the U-Net encoder, trained with a compound loss function derived from Dice and focal loss. This strategy allows the encoder to train on pathologically important pixels around the inner/outer retina.

Results : Our trained model performed well,considering the high class-imbalance of the HRF and non-HRF pixels. The current reported HRF segmentation performance in the literature is an average precision(AP) of 0.71. Our baseline AP was similar(AP 0.70) following a similar strategy. Using our patch-based strategy with region of interest selection, the AP improved to 0.75. The AP was 0.69 when trained with a ResNet50 backbone. Overall, the combination of Dice-focal loss generated higher segmentation performance.

Conclusions : This study presents a pipeline for semantic segmentation of HRFs corresponding to hard exudative and hyperpigmentation. Implementation of a patch-based strategy to improve region of interest selection for the model encoder, and combination of Dice and focal loss improve the current state of the art performance for HRF segmentation.

This is a 2021 ARVO Annual Meeting abstract.

×
×

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.

×