Health Life

Novel deep learning method enables clinic-ready automated screening for diabetes-related eye disease

Predicted retinal thickness on fundus images. Credit: Helmholtz Zentrum München

Researchers at Helmholtz Zentrum München together with LMU University Eye Hospital Munich and the Technical University of Munich (TUM) created a novel deep learning method that makes automated screenings for eye diseases such as diabetic retinopathy more efficient. Reducing the amount of expensive annotated image data that is required for the training of the algorithm, the method is attractive for clinics. In the use case of diabetic retinopathy, the researchers developed a screening algorithm that needs 75 percent less annotated data and achieves the same diagnostic performance of human experts.

In recent years, clinics have taken first steps towards artificial intelligence and deep learning to automate medical screenings. However, training a deep learning for accurate screening and diagnosis prediction requires large sets of annotated data and clinics often struggle with expensive expert labeling. Researchers were therefore looking for ways to reduce the need for costly annotated data while still maintaining the high performance of the algorithm.

Use case diabetic retinopathy

Diabetic retinopathy is a diabetes-related eye disease damaging the retina and can ultimately lead to blindness. Measuring the retinal thickness is an important procedure to diagnose the disease in risk patients. To do so, most clinics take photographs of the fundus—the surface of the back of the eye. In order to automate the screening of these images, clinics started to apply deep learning algorithms. These algorithms require large sets of fundus images with expensive annotations in order to be trained to screen correctly.

The LMU University Eye Hospital Munich owns a population-size data set containing over 120,000 unannotated fundus and co-registered OCT images. OCT (optical coherence tomography) allows for precise information about the retinal thickness but is not commonly available in every eye care center. The LMU provided their

Health article

Colon Polyps | NIDDK

View or Print All Sections

Colon polyps are growths on the lining of your colon and rectum. Most polyps are not cancerous, but some may develop into cancer over time. Removing polyps can help prevent colorectal cancer.

Most people with colon polyps don’t have symptoms. Experts aren’t sure what causes colon polyps. Research suggests that certain factors, such as age and family history, can increase your chances of developing colon polyps.

Doctors can find colon polyps only by using certain tests or procedures. Your doctor may take a medical and family history, perform a physical exam, or request a stool test or other tests.

Doctors treat colon polyps by removing them. Doctors use special tools during a colonoscopy or flexible sigmoidoscopy to remove colon polyps.

Research suggests eating more fruits, vegetables, and other foods with fiber may lower your chances of developing colon polyps. Losing weight if you’re overweight and not gaining weight if you’re already at a healthy weight may also help prevent polyps.

The National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) and other components of the National Institutes of Health (NIH) conduct and support research into many diseases and conditions.

Related Conditions & Diseases

This content is provided as a service of the National Institute of Diabetes and Digestive and Kidney Diseases
(NIDDK), part of the National Institutes of Health. The NIDDK translates and disseminates research findings to increase knowledge and understanding about health and disease among patients, health professionals, and the public. Content produced by the NIDDK is carefully reviewed by NIDDK scientists