Deep Learning of Retinal Imaging: A Useful Tool for Coronary Artery Calcium Score Prediction in Diabetic Patients

Cardiovascular diseases (CVD) are one of the leading causes death in developed countries. Previous studies suggest that retina blood vessels provide relevant information on cardiovascular risk. Retina fundus imaging (RFI) is a cheap medical test already regularly performed diabetic population as screening retinopathy (DR). Since diabetes major cause CVD, we wanted to explore use Deep Learning architectures RFI tool for predicting CV risk this population. Particularly, coronary artery calcium (CAC) score marker, and train convolutional neural network (CNN) predict whether it surpasses certain threshold defined by experts. The preliminary experiments reduced set clinically verified patients show promising accuracies. In addition, observed elementary clinical data positively correlated with suffering from disease. We found results both informational cues complementary, propose two applications can benefit combination image analysis data.