This is an archived version of CCC's website. Please visit the new ccc website for the latest information.

Relevant Links

Link to Original Paper
Media Contact


retinopathy, algorithms


feed icon

feed icon

feed icon


Computer Based Diabetic Retinopathy Screening

Diabetic retinopathy (DR) is a complication resulting from the diabetes. According to the National Eye Institute estimation 40-45% of the diabetics suffer from certain level of diabetic retinopathy. The estimated incidence rate of DR is 30% and 80% respectively for diabetics with 5 and 15 years of history. DR is classified into two categories, four stages: (Mild, moderate and severe) non-proliferative retinopathy, and profilerative retinopathy. Early detection of DR allows timely therapeutic treatments to slow down the DR development.

The objective of the computer based DR detection system is to use computer algorithms to recognize well defined DR symptoms, especially the ones that appear at the earliest stages. Since 2002 the Texas Advanced DR detection system (TADRS) has been under active research and development under the leadership of Dr. Steve Liu. The system is designed as a tool for patients and their care providers to detect and track the DR so that medical interventions can be implemented timely. TADRS is based on a "light-weight" system architecture to support its broad deployment to remote locations. The goal is to allow diabetics have their retinal photos screened more regularly and conveniently at lower costs. Following the divide-and-conquer strategy, detection algorithms are modularized yet integrated, so that different level of processing power can be deployed to service sites as needed. The system is under multi-year, multi-site clinical trials with very promising results.

Jyh-Charn (Steve) Liu, Texas A&M University

Agencies/Institutions (that have supported the research):
Texas A&M University


Current Highlight | Past Highlights

Computing Research Highlight of the Week is a service of the Computing Community Consortium and the Computing Research Association designed to highlight some of the exciting and important recent research results in the computing fields. Each week a new highlight is chosen by CRA and CCC staff and volunteers from submissions from the computing community. Want your research featured? Submit it!.