A novel few-shot classification framework for diabetic retinopathy detection and grading

•We proposed a fully automated Computer-Aided Diagnosis system for Diabetic Retinopathy (DR). Two specific problems have been addressed, namely, DR detection and DR grading for severity assessment.•Novel deep learning framework called DRNet has been developed for DR detection and DR grading.•Maximum mean accuracy, sensitivity and specificity of 99.72%, 99.86%, and 99.62% achieved for DR detection.•Achieved a maximum mean accuracy of 99.18%, sensitivity of 97.41%, and specificity of 99.56% in DR grading.