Yu Q, et al. - Diabetic retinopathy (DR) lesions were quantitatively evaluated employing the authors' validated machine learning algorithms. In addition, physicians were provided an automated and precise approach to follow the progression of DR and the outcome of interventions. Researchers conducted retrospective analyses of 3,496 color fundus photography images from 19 patients with clinically significant diabetic macular edema undergoing conbercept treatment. They obtained the modified seven-field fundus images at baseline and at the third, sixth, and twelfth month visit, whereas they obtained the modified two-field fundus images at the other monthly visits. The change in the area change of intraretinal hemorrhage and hard exudate lesions during the course of conbercept treatment were quantitatively analyzed in the present study. The area of intraretinal hemorrhage was reduced by 62.49% from baseline to the end of the study. Further, there was a decrease in the mean total area of hard exudates by 41.1% at the twelfth-month vs the first visit. During conbercept treatment, there was a significant decrease in the area of intraretinal hemorrhage. Fluctuation in the hard exudates area was observed during loading then it subsequently declined at the twelfth month. They identified the automated system as promising to be a precise and objective approach for monitoring the progression of DR and outcomes of interventions in clinical settings