June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
Deep Learning Facilitated Study of the Rate of Change in Photoreceptor Outer Segment (OS) Metrics in X-Linked Retinitis Pigmentosa (xlRP)
Author Affiliations & Notes
  • Yi-Zhong Wang
    Retina Foundation of the Southwest, Dallas, Texas, United States
    Ophthalmology, The University of Texas Southwestern Medical Center, Dallas, Texas, United States
  • Katherine Juroch
    Retina Foundation of the Southwest, Dallas, Texas, United States
  • Yineng Chen
    Center for Preventive Ophthalmology and Biostatistics, Department of Ophthalmology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, United States
  • Gui-Shuang Ying
    Center for Preventive Ophthalmology and Biostatistics, Department of Ophthalmology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, United States
  • David G Birch
    Retina Foundation of the Southwest, Dallas, Texas, United States
    Ophthalmology, The University of Texas Southwestern Medical Center, Dallas, Texas, United States
  • Footnotes
    Commercial Relationships   Yi-Zhong Wang None; Katherine Juroch None; Yineng Chen None; Gui-Shuang Ying None; David Birch None
  • Footnotes
    Support  Foundation Fighting Blindness Individual Investigator Research Award and EY09076
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 4640. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Yi-Zhong Wang, Katherine Juroch, Yineng Chen, Gui-Shuang Ying, David G Birch; Deep Learning Facilitated Study of the Rate of Change in Photoreceptor Outer Segment (OS) Metrics in X-Linked Retinitis Pigmentosa (xlRP). Invest. Ophthalmol. Vis. Sci. 2023;64(8):4640.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To evaluate the longitudinal change in OS metrics for monitoring disease progression in xlRP with the assistance of a deep learning model (DLM) for automatic segmentation of retinal layers in OCT images.

Methods : In this retrospective cohort study, SD-OCT volume scans obtained from 70 eyes of 35 patients with xlRP were included for longitudinal analysis. A subset of this dataset was previously used to examine the change of ellipsoid zone (EZ) width (Birch et al., JAMA Ophthalmol, 2013). Baseline mean age (SD) was 18.1 (10.4) years. Mean follow-up length was 6.5 (4.1) years. The inclusion criteria included: (1) volume scans with EZ band within the scan limit and had visible EZ in at least 3 B-scans, (2) a minimum 2-year follow-up. A total of 405 volume scans, composed of 194 low-density scans (mean B-scan separation 0.25 mm) and 211 high-density scans (mean B-scan separation 0.069 mm), were first segmented using a DLM (Wang & Birch, Front. Med., 2022), then manually corrected for the errors made by the DLM for the boundary lines of EZ and apical RPE. OS metrics (OS length, EZ area, and OS volume) were subsequently measured from the 3D EZ-RPE layer of each volume scan. Linear mixed-effects models that account for both inter-eye correlation and longitudinal correlation were used to determine the progression rate of OS metrics and the associated factors including baseline age, baseline OS metrics values, and length of follow-up.

Results : The overall mean (SD) progression rate was -0.35 (0.53) μm/year for OS length, -0.89 (1.11) mm2/year for EZ area, and -0.017 (0.02) mm3/year for OS volume. In multivariable analysis, OS metrics progression rate was strongly associated with their baseline values, with faster decline in eyes with larger baseline value (p<0.0001, Table). Progression rate in EZ area was non-linearly associated with the baseline age (p=0.0116), while progression rate in EZ area and OS volume were non-linearly associated with the length of follow-up (p<0.014).

Conclusions : These results provide evidence to support using OS metrics as biomarkers to monitor the progression of xlRP and as the outcome measures to evaluate treatment effects. Given that their progression rates are dependent on their baseline values, the baseline values of OS metrics should be considered in the design and statistical analysis of future clinical trials.

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

 

×
×

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.

×