Deep learning of retinal imaging: a useful tool for coronary artery calcium score prediction in diabetic patients

Abstract

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