Automated quantitative characterisation of retinal vascular leakage and microaneurysms in ultra-widefield fluorescein angiography

Abstract

Summary Ultra-widefield fluorescein angiography (UWFA) is an emerging imaging modality used to characterize pathology in the retinal vasculature such as microaneurysms (MA) and vascular leakage. Despites its potential value for diagnosis and disease surveillance, objective quantitative assessment of retinal pathology by UWFA is currently limited because it requires laborious manual segmentation by trained human graders. In this report, we describe a novel fully automated software platform, which segments MAs and leakage areas in native and dewarped UWFA images with retinal vascular disease. Comparison of the algorithm to human grader generated gold standards demonstrated significant strong correlations for MA and leakage areas (ICC=0.78-0.87 and ICC=0.70-0.86, respectively, p=2.1×10-7 to 3.5×10-10 and p=7.8×10-6 to 1.3×10-9, respectively). These results suggest the algorithm performs similarly to human graders in MA and leakage segmentation and may be of significant utility in clinical and research settings.

Ultrawide Field Imaging in Diabetic Retinopathy: Exploring the Role of Quantitative Metrics

“…There have also been attempts at automated microaneurysm quantification on UWF-FA images [ 24 , 25 ]. Perhaps the most widely adopted method was that described by Ehlers et al, which performed well against manual grading and had high repeatability between early phase and late phase angiogram counts [ 26 ].…”

Automated measurement of leakage on wide-field angiography in the assessment of retinal vasculitis

“…More recently, Ehlers et al published an automated quantification algorithm for UWFFA images in diabetic patients [8]. The algorithm was developed using expert readers performing manual quantification to provide iterative feedback.…”

“…Quantification of imaging endpoints can provide ordinal variables at specific timepoints and continuous variables that can be followed over time to determine changes in both the clinical and research setting. Using software to analyze angiographic leakage as a numeric endpoint has demonstrated utility in non-inflammatory disease such as diabetic retinopathy [8]. The use of automated leakage analysis in inflammatory disease is less studied but can provide a powerful variable by which to monitor disease.…”

Factors Affecting Predominantly Peripheral Lesion Identification and Grading

“…1,2,6,7 This ability would be particularly important given the increased interest in developing rapid automated H/Ma counting techniques for UWF images and its potential use in clinical trials and research studies. [8][9][10][11] In principle, PPL grading based on H/Ma counts and based on qualitative grading should be similar; however, the agreement rate between both techniques across individual DR severity levels and various devices has not been established. 12 This consideration may be particularly important for early DR, where small differences in H/Ma counts can substantially affect PPL grading.…”