• Home
  • Search
  • Validation of Deep Learning-based Automatic Retinal Layer Segmentation Algorithms for AMD with Two SD-OCT Devices
  • Cite Icon4
  • https://doi.org/10.1016/j.xops.2024.100670Copy DOI Icon

Validation of Deep Learning-based Automatic Retinal Layer Segmentation Algorithms for AMD with Two SD-OCT Devices

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

PurposeSegmentations of retinal layers in spectral-domain optical coherence tomography (SD-OCT) images serve as a crucial tool for identifying and analyzing the progression of various retinal diseases, encompassing a broad spectrum of abnormalities associated with age-related macular degeneration (AMD). The training of deep-learning algorithms necessitates well-defined ground-truth labels, validated by experts, to delineate boundaries accurately. However, this resource-intensive process has constrained the widespread application of such algorithms across diverse OCT devices. This work validates deep learning image segmentation models across multiple OCT devices by testing robustness in generating clinically relevant metrics. DesignProspective, comparative study. ParticipantsAdults over 50 years of age with no AMD to advanced AMD, as defined in the Age-Related Eye Disease Study (AREDS)), in at least one eye, were enrolled. 402 SD-OCT scans were used in this study. MethodsWe evaluate two separate state-of-the-art segmentation algorithms through a training process using images obtained from one OCT device (Heidelberg-Spectralis) and subsequent testing using images acquired from two OCT devices (Heidelberg-Spectralis and Zeiss-Cirrus). This assessment is performed on a dataset that encompasses a range of retinal pathologies, spanning from disease-free conditions to severe forms of AMD, with a focus on evaluating the device independence of the algorithms. Main Outcome MeasuresPerformance metrics (mean-squared-error, mean-absolute-error, dice-coefficients) for the segmentations of the internal limiting membrane (ILM), retinal-pigment-epithelium (RPE), and RPE to Bruch’s-membrane (BM) region, along with en face thickness maps, volumetric estimations (in mm3). Violin plots and Bland-Altman plots comparing predictions against ground-truth are also presented. ResultsThe UNet and DeepLabv3, trained on Spectralis B-scans, demonstrate clinically useful outcomes when applied to Cirrus test B-scans. Review of the Cirrus test-data by two independent annotators revealed that the aggregated-mean-absolute-error in pixels for ILM was 1.82±0.24 (equivalent to 7.0±0.9 μm) and for RPE was 2.46±0.66 (9.5±2.6 μm). Additionally, the dice-similarity-coefficient for the RPE-drusen complex (RPE-DC) region, comparing predictions to ground truth, reached 0.87±0.01. ConclusionIn the pursuit of task-specific goals such as retinal layer segmentation, a segmentation network has the capacity to acquire domain-independent features from a large training dataset. This enables the utilization of the network to execute tasks in domains where ground truth is hard to generate.

Similar Papers
  • Research Article
  • Citations21

Local Anatomic Precursors to New-Onset Geographic Atrophy in Age-Related Macular Degeneration as Defined on OCT

  • Dec 22, 2020
  • Ophthalmology Retina
  • Malini Veerappan Pasricha +30
  • Research Article
  • Citations8

To Peel or Not to Peel: Pars Plana Vitrectomy with Macular Membrane Peel in Eyes with Abnormalities of Vitreomacular Interface and Coexisting Dry Age-Related Macular Degeneration

  • Feb 11, 2020
  • Clinical Ophthalmology (Auckland, N.Z.)
  • Olga Furashova +1
  • Research Article
  • Citations157

Assessment of Artifacts and Reproducibility across Spectral- and Time-Domain Optical Coherence Tomography Devices

  • Jul 09, 2009
  • Ophthalmology
  • Joseph Ho +7
  • PDF
  • Research Article
  • Citations46

In Vivo Multimodal Imaging of Drusenoid Lesions in Rhesus Macaques

  • Nov 03, 2017
  • Scientific Reports
  • Glenn Yiu +8
  • Research Article
  • Citations9

MULTIMODAL ASSESSMENTS OF DRUSENOID PIGMENT EPITHELIAL DETACHMENTS IN THE AGE-RELATED EYE DISEASE STUDY 2 ANCILLARY SPECTRAL-DOMAIN OPTICAL COHERENCE TOMOGRAPHY STUDY COHORT.

  • May 01, 2022
  • Retina (Philadelphia, Pa.)
  • Alisa T Thavikulwat +6
  • Research Article
  • Citations2

Comparison between Spectral-domain and Swept-source OCT Angiography Scans for the Measurement of Hyperreflective Foci in Age-related Macular Degeneration

  • Oct 21, 2024
  • Ophthalmology Science
  • Gissel Herrera +13
  • Research Article

Characteristics of spectral-domain optical coherence tomography of drusen in atrophic age-related macular degeneration

  • May 25, 2014
  • Chinese Journal of Ocular Fundus Diseases
  • Shasha Yang +2
  • Research Article
  • Citations141

Spectral-Domain Optical Coherence Tomography Characteristics of Intermediate Age-related Macular Degeneration

  • Sep 08, 2012
  • Ophthalmology
  • Jessica N Leuschen +11
  • Book Chapter
  • Citations26

Fundus Autofluorescence Imaging in Age-Related Macular Degeneration and Geographic Atrophy

  • Dec 28, 2009
  • Srilaxmi Bearelly +1
  • Research Article
  • Citations43

Lifecycles of Individual Subretinal Drusenoid Deposits and Evolution of Outer Retinal Atrophy in Age-Related Macular Degeneration

  • Oct 31, 2019
  • Ophthalmology. Retina
  • Yuhua Zhang +7
  • Research Article
  • Citations46

QUANTITATIVE ANALYSIS OF THE INNER RETINAL LAYER THICKNESSES IN AGE-RELATED MACULAR DEGENERATION USING CORRECTED OPTICAL COHERENCE TOMOGRAPHY SEGMENTATION.

  • Aug 01, 2018
  • Retina
  • Ilkay Kilic Muftuoglu +5
  • Discussion
  • Citations23

Predictors of AMD Treatment Response

  • Oct 31, 2012
  • Ophthalmology
  • Sanjeewa S Wickremasinghe +5
  • Research Article
  • Citations81

Segmentation of the Geographic Atrophy in Spectral-Domain Optical Coherence Tomography and Fundus Autofluorescence Images

  • Dec 30, 2013
  • Investigative Opthalmology & Visual Science
  • Zhihong Hu +5
  • Research Article
  • Citations7

LamNet: A Lesion Attention Maps-Guided Network for the Prediction of Choroidal Neovascularization Volume in SD-OCT Images.

  • Apr 01, 2022
  • IEEE Journal of Biomedical and Health Informatics
  • Yuhan Zhang +5
  • Research Article
  • Citations156

Choroidal Neovascularization Analyzed on Ultrahigh-Speed Swept-Source Optical Coherence Tomography Angiography Compared to Spectral-Domain Optical Coherence Tomography Angiography

  • Feb 04, 2016
  • American Journal of Ophthalmology
  • Eduardo A Novais +15
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.