Deep Learning Model to Identify Moderately Severe and Severe Non-proliferative Diabetic Retinopathy From 7-Field Colour Fundus Photographs

A deep learning model to identify eyes with moderately severe and severe nonproliferative diabetic retinopathy from 7-field color fundus photographs was previously developed and evaluated by leveraging a large cohort of patients with diabetes from the United States. This presentation reports the evaluation and performance of the deep learning model on an independent cohort of patients with diabetic retinopathy from Portugal.

{{assetTitle}}

Authors {{assetAuthors}}

Published date{{formattedPublishDate}}

{{assetDescription}}

Welcome to Medically

The Roche Science Hub

This website is a non-promotional global resource intended to facilitate transparent scientific exchange regarding developments in medical research, diagnostics, and disease management. It is intended for healthcare professionals.

Not a healthcare professional? Browse:

This global website is intended for healthcare professionals outside the UK, US, Canada and Australia. The content on this website may include scientific information about experimental or investigational compounds, indications and services that are not approved or valid in your jurisdiction. Registration status and prescribing information of medicinal products may differ between countries. Please refer to local product information for any medicinal products mentioned on this website. Information available on this website does not constitute professional medical advice, and Roche and Genentech accept no responsibility for access to or use of the same.

You are Leaving Medically

By following this link, you are leaving Roche Website and entering a site that is not owned or controlled by Roche. Roche does not take any responsibility for acces to or use of this website, nor for any content therein.