June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Machine Learning-Enhanced Longitudinal Ellipsoid Zone Integrity Assessment on OCT in the VISTA DME Study
Author Affiliations & Notes
  • Leina Lunasco
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Sari Yordi
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Hasan Cetin
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Gagan Kalra
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Christopher J. Mugnaini
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Katherine Wise
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Katherine E Talcott
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Carmen Calabrise
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Sunil K Srivastava
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Jamie Reese
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Justis P. Ehlers
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic, Cleveland, Ohio, United States
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Footnotes
    Commercial Relationships   Leina Lunasco None; Sari Yordi None; Hasan Cetin None; Gagan Kalra None; Christopher Mugnaini None; Katherine Wise None; Katherine Talcott Zeiss, Novartis, RegenxBio, Code F (Financial Support); Carmen Calabrise None; Sunil Srivastava Bausch and Lomb, Adverum, Novartis, and Regeneron, Code C (Consultant/Contractor), Regeneron, Allergan, and Gilead, Code F (Financial Support), Leica, Code P (Patent); Jamie Reese None; Justis Ehlers Aerpio, Alcon, Allegro, Allergan, Genentech/Roche, Novartis, Thrombogenics/Oxurion, Leica, Zeiss, Regeneron, Santen, Stealth, Adverum, IvericBIO, Apellis, Boehringer-Ingelheim, RegenxBIO, Code C (Consultant/Contractor), Aerpio, Alcon, Thrombogenics/Oxurion, Regeneron, Genentech, Novartis, Allergan, Boehringer-Ingelheim, IvericBio, Adverum, Code F (Financial Support), Leica, Code P (Patent)
  • Footnotes
    Support  NIH-NEI P30 Core Grant (IP30EY025585) (Cole Eye); Unrestricted Grants from The Research to Prevent Blindness, Inc (Cole Eye); Cleveland Eye Bank Foundation awarded to the Cole Eye Institute (Cole Eye); K23-EY022947-01A1 (JPE); Regeneron
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 3364 – F0173. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Leina Lunasco, Sari Yordi, Hasan Cetin, Gagan Kalra, Christopher J. Mugnaini, Katherine Wise, Katherine E Talcott, Carmen Calabrise, Sunil K Srivastava, Jamie Reese, Justis P. Ehlers; Machine Learning-Enhanced Longitudinal Ellipsoid Zone Integrity Assessment on OCT in the VISTA DME Study. Invest. Ophthalmol. Vis. Sci. 2022;63(7):3364 – F0173.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To compare the longitudinal dynamics of quantitative ellipsoid zone (EZ) integrity on OCT in eyes with diabetic macular edema (DME) when treated with laser photocoagulation or intravitreal aflibercept injection (IAI) in the Phase 3 VISTA study.

Methods : VISTA was a randomized phase 3 study in DME patients. This post-hoc analysis included 361 eyes treated with laser photocoagulation, 2mg IAI every 4 weeks (2q4), or every 8 weeks following 5 initial monthly doses (2q8). OCT images were evaluated using machine learning-assisted retinal layer mapping software. EZ integrity parameters were EZ-RPE central subfield thickness (CST, µm), EZ-RPE panmacular volume (mm3), and percentage of partial and total EZ attenuation (proportion of macular area with 20µm or less and 0µm EZ-RPE thickness, respectively).

Results : There were no baseline differences in EZ metrics between the laser group and IAI groups. At week 4, laser eyes showed worsening integrity parameters with IAI eyes already improving. At week 100, the EZ-RPE CST and Volume were significantly higher in the IAI group (p<0.0001), while partial and total EZ attenuation were significantly lower (p<0.0001) compared to the laser group.

Specifically, the pooled IAI group demonstrated significantly improved EZ integrity parameters compared to baseline, while the laser group demonstrated significant worsening at week 100 (Table 1) despite ~41% of laser patients receiving IAI between weeks 24 and 100. At week 100, 2q4 demonstrated significant improvement in total EZ attenuation whereas the improvement in 2q8 did not reach statistical significance (-32.5%, p<0.026; -24.3%, p=0.16 respectively), although all other EZ metrics significantly improved in both groups. There were significant correlations between EZ metrics and BCVA at week 100 (Table 2).

Conclusions : IAI therapy for DME was associated with sustained improvement of outer retinal integrity parameters through week 100, whereas laser demonstrated significant worsening in EZ integrity despite a large proportion of patients receiving IAI treatment in addition to laser. This may explain some of the differences in functional outcomes between treatment approaches and provide a potential biomarker for outer retinal integrity in response to therapeutic interventions.

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

 

Table 1. Mean changes in EZ metrics from baseline to Week 100.

Table 1. Mean changes in EZ metrics from baseline to Week 100.

 

Table 2. Correlation heat map of EZ Integrity Parameter and BCVA at Week 100.

Table 2. Correlation heat map of EZ Integrity Parameter and BCVA at Week 100.

×
×

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.

×