the DIARETDB1 diabetic retinopathy database and evaluation protocol

TLDR

Automatic diagnosis of diabetic retinopathy from digital fundus images is a prominent research area, promising new medical products and cost savings, yet algorithm maturity cannot be assessed without a widely accepted, ground‑truth database and strict evaluation protocol. The study proposes an evaluation methodology and describes an image database with ground truth. The authors propose an evaluation methodology and provide an image database with ground truth. The publicly available database enables benchmarking of diagnosis algorithms and facilitates comparison of algorithm maturity for technology transfer from research to clinical practice.

Abstract

Automatic diagnosis of diabetic retinopathy from digital fundus images has been an active research topic in the medical image processing community. The research interest is justified by the excellent potential for new products in the medical industry and significant reductions in health care costs. However, the maturity of proposed algorithms cannot be judged due to the lack of commonly accepted and representative image database with a verified ground truth and strict evaluation protocol. In this study, an evaluation methodology is proposed and an image database with ground truth is described. The database is publicly available for benchmarking diagnosis algorithms. With the proposed database and protocol, it is possible to compare different algorithms, and correspondingly, analyse their maturity for technology transfer from the research laboratories to the medical practice.