Deep Neural Network Learning for Detection and Grading of Diabetic Retinopathy
Akshay Jakkidi Reddy1, James B. Martel2*
1Department of Ophthalmology, California Northstate University, Rancho Cordova, USA
2Department of Graduate Medical Education, California Northstate University, Elk Grove, USA
Purpose. To automate the retinal screening process and to improve chances of early detection/diagnosis of diabetic retinopathy which may reduce vision impairment cases due to the disease
Methods. Experiments were conducted on EYEPACS dataset that had retinal fundus images of patients with diabetic retinopathy in all severity levels. Based on the learning done by the Inception networks during the training phase, the images were classified to 5 classes based on the severity as: Normal, Mild, Moderate, severe and proliferative diabetic retinopathy. The images were augmented to increase the number of images with the disease and were randomly chosen for the training, validation and test datasets.
Results: The training was conducted using the Inception network for 100 epochs and validation accuracy was tested every 1000 iterations on a total of 109,540 images. The major misclassifications that occurred were between the adjacent classes of severity. It achieved a sensitivity of 94.6%, specificity of 81.4%, accuracy of 92% and precision of 93.2%.
Conclusion: The retinal fundus images were examined and automated using Inception network by training the images from scratch. This model can be applied for detection of other retinal diseases, as the model weights are learnt to recognize subtle features present in the retinal images.