Optimisation of an automated drusen-quantifying software for the analysis of drusen distribution in patients with age-related macular degeneration

Abstract

The purpose of this study is to optimise the settings of the Retinal Image Analysis Laboratory (RIALAB), a semi-automatic drusen quantification software, in planning for high-throughput quantification of drusen in clinical studies of age-related macular degeneration (AMD). A comparison of five different settings in RIALAB was made on 67 images from the Rotterdam eye study (population-based study) and 56 images from the fellow eye of patients with active neovascular AMD in King's College Hospital, London (hospital-based study). The 'Few Outer' setting was the best setting, with it being most appropriate for 52 (77.6%) of the Rotterdam cohort and 47 (83.9%) for the London cohort. Pearson's χ(2)-test revealed both results to be statistically significant (P<0.0001). RIALAB is a viable algorithm and software package that can detect, quantify, and analyse drusen efficiently in both population-based and hospital-based studies. We have shown that the 'Few Outer' drusen setting can be employed as the default setting, with fine-tuning only needed in a minority of cases, thus helping to speed up workflow.