Diabetic retinopathy (DR) is one of the major causes of blindness worldwide. It is a diabetes complication that occurs after the damage of the blood vessels in the light-sensitive tissue in the retina. So, early detection of DR could reduce the severity of the disease and help ophthalmologists in treating and investigating it more efficiently. In this paper, we developed a computer-aided diagnosis (CAD) system that can detect early signs of DR using both optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) images. Our system is able to segment the blood vessels from two retinal plexuses using OCTA images. Also, it segments twelve different retinal layers from OCT scans. Then, seven different features are extracted from both segmented OCTA plexuses and OCT layers. Finally, these features are fused to generate a comprehensive diagnostic non-invasive tool for detecting early signs of DR. A total number of 76 cases (23 normal and 53 DR) were used in evaluating the performance of the proposed systems. Using 4-fold cross-validation, our proposed system achieved an average accuracy of 100%. These results show the potential of the proposed system.