Abstract
Diabetic Retinopathy (DR) is the principal cause of vision loss that interrupts the regular interaction of vascular, neural, and retinal constituents leading to impaired neuronal function and retinal abnormalities. Diagnosis of DR from Optical Coherence Tomography (OCT) image is difficult and time-consuming because several small features must be identified and graded, which results in a strenuous diagnosis when integrated with the complexity of the grading system. This study focuses on classifying DR from normal Spectral Domain-OCT (SD-OCT) images using the Directed Acyclic Graph (DAG) network without any pre-processing techniques. The proposed DAG-CNN model comprises 16 convolutional blocks, which learns multi-scale features automatically from multiple layers in the convolutional network and combines them effectively for the DR and normal prediction. The proposed model is tested on the public OCTID_DR and private LFH_DR SD-OCT databases containing DR and healthy OCT images. The model achieved an accuracy, precision, recall, F1-score, and AUC on OCTID_DR database of 0.9841, 0.9727, 0.9818, 0.9772, and 0.9836, respectively; and on LFH_DR database the respective values are 0.9988, 1, 0.9976, 0.9988, and 0.9988 with only 0.1569 Million of learnable parameters. This method significantly reduces the number of learnable parameters and the model’s computational complexity in terms of memory required and FLoating point OPerations (FLOPs). Guided Gradient-weighted Class Activation Mapping (Grad-CAM) is performed to highlight the regions of SD-OCT images that contribute to the decision of the classifier. Our model significantly surpasses the accuracy of the existing models with lower resource consumption and higher real-time performance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have