New machine learning developed by google researchers to detect diabetes retinopathy

By  ,  Onlymyhealth editorial team
Nov 30, 2016

And here comes the good news for patients suffering from diabetes facing related complications. It is a deep learning algorithm capable of interpreting signs of DR in retinal photographs. This new  potential technique is great for doctors as it will help them to  screen more patients, especially in underserved communities with restricted funds.

 

diabetes neuropathy

 

The techniques used previously are laser and anti-VEGF therapy factor in efficacy, safety, cost, and pragmatic issues. Google research team began studying whether machine learning could be used to screen for diabetic retinopathy (DR).

 

This study was published in the Journal of the American Medical Association. This paper demonstrates the technology benefits. It is estimated that the deep neural networks can be trained, using large data sets and without having to specify lesion-based features, to identify diabetic retinopathy or diabetic macular edema in retinal fundus images with high sensitivity and high specificity.

 

These results demonstrate that deep neural networks can be trained, using large data sets and without having to specify lesion-based features, to identify diabetic retinopathy or diabetic macular edema in retinal fundus images with high sensitivity and high specificity.


However, this  algorithm has been trained to identify only diabetic retinopathy and diabetic macular edema.

 

News Source: BetaNews

Image Source: Getty

Read More: Health News

Loading...
Is it Helpful Article?YES687 Views 0 Comment
I have read the Privacy Policy and the Terms and Conditions. I provide my consent for my data to be processed for the purposes as described and receive communications for service related information.
This website uses cookie or similar technologies, to enhance your browsing experience and provide personalised recommendations. By continuing to use our website, you agree to our Privacy Policy and Cookie Policy. OK