{"id":5475,"date":"2023-09-14T15:25:55","date_gmt":"2023-09-14T15:25:55","guid":{"rendered":"https:\/\/dailyai.com\/?p=5475"},"modified":"2023-09-14T15:25:55","modified_gmt":"2023-09-14T15:25:55","slug":"ai-detects-parkinsons-other-disease-risk-in-retina-scans","status":"publish","type":"post","link":"https:\/\/dailyai.com\/da\/2023\/09\/ai-detects-parkinsons-other-disease-risk-in-retina-scans\/","title":{"rendered":"AI opdager risiko for Parkinson og andre sygdomme i nethindescanninger"},"content":{"rendered":"

Researchers from University College London and Moorfields Eye Hospital have developed an AI model that can detect a patient\u2019s risk of a variety of diseases by analyzing an image of their retina.<\/strong><\/p>\n

It\u2019s not the first time that AI has been used to analyze retinal scans<\/a>, but the approach the researchers took with their RETFound model will accelerate developments in this area of medicine.<\/p>\n

Standard machine learning models are usually trained on a large set of curated data. If you wanted your model to be able to identify the retina of a person at risk of a specific disease, you\u2019d need to train it on a huge amount of representative images.<\/p>\n

Preparing medical imaging data for machine learning is very expensive and takes a long time. Unlike the basic kind of data labeling outsourced to low-cost countries<\/a>, medical images need to be analyzed and labeled by a specialist physician.<\/p>\n

The researchers that created RETFound, took a different approach and trained their model by means of self-supervised learning (SSL).<\/p>\n

Instead of using curated and labeled images, they trained the model on 1.6 million unlabeled retinal images.<\/p>\n

\n

A foundation model for generalizable disease detection from retinal images – Nature https:\/\/t.co\/M2g0L4MMl4<\/a><\/p>\n

\u2014 nature (@Nature) September 13, 2023<\/a><\/p>\n<\/blockquote>\n