Using Machine learning to detect Diabetic Retinopathy
Lily Peng, MD, PhD belonging from medicine background joined Google where she started working as Product Manager for medical imaging. In my previous post, I explained how deep learning was used to classify skin lesions as benign, malignant or one of their sub-types.
A specific type of neural network optimized for image classification called a deep convolutional neural network was trained using a retrospective development data set of 128 175 retinal images, which were graded 3 to 7 times for diabetic retinopathy, diabetic macular edema, and image gradability by a panel of 54 US licensed ophthalmologists and ophthalmology senior residents between May and December 2015. The resultant algorithm was validated in January and February 2016 using 2 separate data sets, both graded by at least 7 US board-certified ophthalmologists with high intragrader consistency.
In this evaluation of retinal fundus photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy and can be applied to modern medications for better outcomes.