Article Text

Download PDFPDF
Repeatability of automated leakage quantification and microaneurysm identification utilising an analysis platform for ultra-widefield fluorescein angiography
  1. Alice Jiang1,
  2. Sunil Srivastava1,
  3. Natalia Figueiredo1,
  4. Amy Babiuch1,
  5. Ming Hu2,
  6. Jamie Reese1,
  7. Justis P Ehlers1
  1. 1 The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Instute, Cleveland, Ohio, USA
  2. 2 Quantitative Health Sciences, Cleveland Clinic, Cleveland, Ohio, USA
  1. Correspondence to Dr Justis P Ehlers, Cole Eye Institute, Cleveland, OH 44195, USA; ehlersj{at}


Ultra-widefield fluorescein angiography (UWFA) provides unique opportunities for panretinal assessment of retinal diseases. The objective quantification of UWFA features is a labour-intensive manual process, limiting its utility. The present study assesses the consistency/repeatability of an automated assessment platform for the characterisation of retinal vascular features, quantification of microaneurysms (MA) and leakage foci in UWFA images.

Methods An Institutional Review Board-approved retrospective image analysis study was performed on UWFA images. For each eye, two arteriovenous-phase images and two late-phase images were selected. Automated assessment was performed for retinal vascular features, MA identification and leakage segmentation. Panretinal and zonal assessment of metrics was performed.

Results There was a significant correlation between paired time points for retinal vessel area and vessel length on early images (Pearson r=0.92, p<0.0001; Pearson r=0.94, p<0.0001) and late images (Pearson r=0.92, p<0.0001; Pearson r=0.92, p<0.0001, respectively). Panretinal and zonal MA counts demonstrated high repeatability between images (all p<0.0001). Similarly, panretinal leakage area and zonal leakage areas were highly correlated (all p<0.001).

Conclusion This automated algorithm demonstrated very strong intrastudy correlation between paired time points in the same phases of the angiogram for quantifying retinal vascular characteristics, MA count and leakage parameters in UWFA images. These findings suggest significant flexibility in the platform for consistency in evaluating metrics over time and is encouraging for longitudinal assessment opportunities.

  • imaging
  • diagnostic tests/investigation
  • retina

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.


  • Contributors ACJ and JPE drafted and revised the manuscript. JPE provided conception/design for the project. All authors provided significant effort in the analysis/interpretation of data, reviewing the manuscript, final approval of the manuscript and agreed to be accountable for all aspects of the work.

  • Funding NIH/NEI K23-EY022947-01A1 (JPE); Research to Prevent Blindness (Cole Eye Institutional).

  • Competing interests JPE and SKS have patents pending related to this technology. No other specific conflicts exists for this study for any of the other authors. ACJ, NF, MH, AB, and JLR have competing interests. SKS's disclosures are as follows: Bausch and Lomb (C, R); Bioptigen (P); Allergan (R); Zeiss (C). JPE's disclosures are as follows: Bioptigen (C, P), Thrombogenics (C, R), Genentech (C,R), Leica (C, P), Roche (C), Zeiss (C), Alcon (C,R), Novartis (C), Aerpio (C, R), Allergan (C), Allegra (C); Novartis (C, R), Regeneron (C, R).

  • Patient consent for publication Not required.

  • Ethics approval This retrospective image analysis study was approved by the Cleveland Clinic Institutional Review Board.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Data availability statement Data are available upon request.

Linked Articles

  • At a glance
    Keith Barton James Chodosh Jost B Jonas