Remember meForgot password?
    Log in with Twitter

article imageArtificial intelligence used to combat blindness

By Tim Sandle     May 17, 2017 in Science
Scientists from Byers Eye Institute at Stanford University have discovered the means to use artificial intelligence to combat a complication of diabetes that affects the eyes, leading to vision loss.
The focus of the research is with the application of deep-learning methods to produce an automated algorithm designed to detect diabetic retinopathy from the scanning of images of the eye. The technology is a type of ‘deep learning’. Deep Learning is a new area of machine learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: ‘true’ Artificial Intelligence. The algorithm is based on more than 75,000 images, taken from the back of the eye, and relating to a wide range of patients representing several ethnicities. The images included a mix of health patients and those with the condition.
Diabetic retinopathy refers to a condition that damages the blood vessels at the back of the eye. In some cases it can lead to blindness. The condition affects up to 80 percent of people who have had diabetes for 20 years or more. The development of the condition is of major health concern, since all people with diabetes mellitus are at risk – those with Type I diabetes and those with Type II diabetes.
Diabetic retinopathy is very hard to detect and often there are often no signs or symptoms. Early detection and treatment is very important in relation to protecting a person from vision loss. This was the reason behind developing the algorithm. An advantage with the technique is that it does not require any specialized computer equipment in order to grade the images. The algorithm can be used on a common personal computer or even a smartphone, with standard processing speed.
Commenting on the development of the tool, lead researcher Dr. Theodore Leng said: "What we showed is that an artificial intelligence-based grading algorithm can be used to identify, with high reliability, which patients should be referred to an ophthalmologist for further evaluation and treatment.” The algorithm was tested out using several leading ophthalmologists.
The scientist added: “If properly implemented on a worldwide basis, this algorithm has the potential to reduce the workload on doctors and increase the efficiency of limited healthcare resources.”
One area where the technology will be of greatest use is in parts of the world where there are few ophthalmologists. The study is published in the journal Ophthalmology and it comes under the title “Automated Identification of Diabetic Retinopathy Using Deep Learning.”
More about Diabetes, Artificial intelligence, Blindness
More news from