Hybrid Classification Approach Utilizing DenseUNet+ for Diabetic Macular Edema Disorder Detection

Abstract

Diabetic macular edema (DME) poses a significant threat to vision. It is characterized by the enlargement of the macula due to the accumulation of plasma in the extracellular space of the retina. Detection of DME, crucial for timely intervention, traditionally relies on manual inspection of images, which is time-consuming and prone to human error. Leveraging advancements in computer-assisted diagnostics, this study proposes a novel approach utilizing the DenseUNet+ architecture tailored for precise segmentation across diverse image modalities. The proposed method integrates data from four modalities within dense block structures, followed by linear operations and concatenation to enhance feature representation. Evaluation using ResNet101V2 and DenseNet201 demonstrates superior performance, with accuracy exceeding 95% and 99%, respectively, showcasing their efficacy in screening retinal optical coherence tomography (OCT) images for DME. This research highlights the potential of deep learning techniques to enhance ophthalmologists’ abilities to efficiently screen, diagnose, and manage DME, thus reducing the risk of irreversible vision loss.