DRDr II: Detecting the Severity Level of Diabetic Retinopathy Using Mask RCNN and Transfer Learning
This work addresses the problem of accurately classifying the severity of Diabetic Retinopathy for ophthalmologists, offering an incremental improvement in diagnostic tools.
This paper presents DRDr II, a hybrid machine learning and deep learning model that detects the severity level of Diabetic Retinopathy. It achieves over 92% accuracy in predicting the correct severity levels using a dataset of over 35 thousand fundus images.
DRDr II is a hybrid of machine learning and deep learning worlds. It builds on the successes of its antecedent, namely, DRDr, that was trained to detect, locate, and create segmentation masks for two types of lesions (exudates and microaneurysms) that can be found in the eyes of the Diabetic Retinopathy (DR) patients; and uses the entire model as a solid feature extractor in the core of its pipeline to detect the severity level of the DR cases. We employ a big dataset with over 35 thousand fundus images collected from around the globe and after 2 phases of preprocessing alongside feature extraction, we succeed in predicting the correct severity levels with over 92% accuracy.