ORNL, UT project could save vision of millions
Feb 17, 2009 - 4:59:36 AM
OAK RIDGE, Tenn., Feb. 17, 2009 -- In the blink of an eye, people at risk of becoming blind can now be screened for eye diseases such as diabetic retinopathy and age-related macular degeneration.
Using a technology originally developed at the Department of Energy's Oak Ridge National Laboratory to understand semiconductor defects, three locations in Memphis have been equipped with digital cameras that take pictures of the retina. Those images are relayed to a center where they are analyzed and the patient knows in minutes whether he or she needs additional medical attention.
Once we've taken pictures of the eyes, we transmit that information to our database, where it is compared to thousands of images of known retinal disease states, said Ken Tobin, who led the ORNL team that developed the technology. From there, the computer system is able to determine whether the patient passes the screening or it provides a follow-up plan that includes seeing an ophthalmologist.
Already, this technology is making a difference as two patients at the Church Health Center in Memphis have been identified as needing laser treatment for moderate and severe diabetic retinopathy and macular edema, both conditions that can lead to blindness.
While some cameras have been installed, others will be installed at several rural and urban health care centers serving the Mississippi Delta. Another camera is planned for a federally funded health center in Chattanooga. Eventually, the goal is to have hundreds of cameras throughout the United States and beyond. If disease can be detected early, treatments can preserve vision and significantly reduce the occurrence of debilitating blindness.
This project takes advantage of ORNL's proprietary content-based image retrieval technology, which quickly sorts through large databases and finds visually similar images. For more than a decade manufacturers of semiconductors have used this technology to rapidly scan hundreds of thousands of tiny semiconductors to learn quickly about problems in the manufacturing process.
Our approach allows us to adapt a proven technology to describe key regions of the retina, and this information can then be used to index images in a content-based image retrieval library, Tobin said. What separates this from other methods is that we have automated the process of diagnosing retinal disease by capturing the expert knowledge of an ophthalmologist in a patient archive.
Leading the medical portion of the project is Edward Chaum, an ophthalmologist and Plough Foundation professor of retinal diseases at the University of Tennessee Health Science Center (
All rights reserved by RxPG Medical Solutions Private Limited ( www.rxpgnews.com )