AI to Accelerate Diagnosis of Retinal Disorders

New-Stem-Cell-Treatment-Can-Cure-Macular-Degeneration

Artificial Intelligence-based neural network reviews more than 200,000 eye scans with optical coherence tomography to create two- and three-dimensional representations of retinal tissue

The findings of the study was published on February 22, 2018 in journal of Cell. Researchers from Shiley Eye Institute at UC San Diego Health and University of California San Diego School of Medicine, with colleagues in China, Germany and Texas developed new software for detection of retinal disorders for speeding up diagnosis and treatment. The study was focused macular degeneration and diabetic macular edema, which are two major causes of blindness. This machine learning technique was found to be as accurate as trained ophthalmologist. It generates most referred treatment to the patients within 30 seconds with 95% accuracy.

Conventional approaches to diagnose retinal disorders are laborious and expensive. They require millions of images to program AI system. In this study, researchers used AI-based convolutional neural network, which was capable of reviewing more than 200,000 eye scans with optical coherence tomography. It is a noninvasive technology, which transmits light to retina to creating two- and three-dimensional representations of tissue.

“Artificial intelligence (AI) has huge potential to revolutionize disease diagnosis and management by doing analyses and classifications involving immense amounts of data that are difficult for human experts—and doing them rapidly,” said senior author Kang Zhang, MD, PhD, professor of ophthalmology at Shiley Eye Institute and founding director of the Institute for Genomic Medicine at UC San Diego School of Medicine.

Speed and accuracy are the most important steps in medical diagnoses and treatment. Simple and relatively inexpensive AI-based tool could help various medical resources and specialists in efficient treatment of disorders. Furthermore, AI technology can also differentiate between benign and malignant lesions in just one scan. The scientists are sharing data their data through open-source so that other research organizations can develop potential applications.

You may be interested

Eight Hours Sleep Duration Linked to Cardiovascular Risk
Healthcare
Healthcare

Eight Hours Sleep Duration Linked to Cardiovascular Risk

Mohit Joshi - January 3, 2019

News study revealed that sleeping for ten hours may elevate risk of mortality by 30% as compared to sleeping for seven hours Researchers from Keele University conducted…

Tax Deductions and Credits Can Take a Chunk of Money Off Your Tax Bill
Business
Business

Tax Deductions and Credits Can Take a Chunk of Money Off Your Tax Bill

Pareesh Phulkar - January 2, 2019

When you’re climbing uphill on a mountain of owed taxes, you may easily panic. However, it might not be as scary as it might initially look. As…

Claim your Child and Dependent Care Tax Credit Today with H&R Block 2019
Business
Business

Claim your Child and Dependent Care Tax Credit Today with H&R Block 2019

Pareesh Phulkar - January 2, 2019

Paying for child care or adult dependent care is one of the costly monthly expenses many families face. But without care, your children can't leave home to…

Most from this category