Abstract
In this project, we present EyeMark, a system with advanced longitudinal image anal-
ysis tools for automated computation of biomarkers for diabetic retinopathy (DR) using
retinal fundus images. Specifically, we have developed tools for computation of microan-
eurysm (MA) appearance and disappearance rates (jointly known as turnover rates) for
use as a biomarker in quantifying DR progression risk along with longitudinal analysis of
other DR lesions. The availability of a reliable image-based biomarker will have high pos-
itive influence on various aspects of DR care, including screening, monitoring progres-
sion, drug discovery and clinical research.
Measuring MA turnover and longitudinal analysis of DR lesions involves two labor in-
tensive steps: careful alignment of current and baseline images, and marking of individual
lesions. This process is very time consuming and prone to error, if done entirely by human
graders. The primary goal of this project is to overcome these limitations by automating
both the steps involved in longitudinal analysis: accurate image registration, and lesion
identification.
We have designed and developed a prototype tool that robustly registers longitudinal
images (even with multiple lesion changes) and effectively detects and localizes DR le-
sions. This fully automated tool can work on the cloud to produces results in near constant
time (for large datasets), and also provide intuitive visualization tools for clinicians to more
effectively monitor DR progression. This commercialization readiness pilot (CRP) project
is intended to develop a regulatory strategy and a market access plan for EyeMark to
enable its introduction in the US market and foster commercial success.