Mobile-Ready Automated Triage of Diabetic Retinopathy Using Digital Fundus Images

TL;DR

This paper introduces a lightweight deep learning model using MobileNetV3 for efficient diabetic retinopathy screening from fundus images, suitable for resource-limited settings, with high accuracy and real-world deployment considerations.

Contribution

The paper presents a novel mobile-optimized deep learning framework with a CORAL head for ordered disease severity modeling, improving DR screening efficiency and accuracy.

Findings

Achieved a QWK score of 0.9019 and 80.03% accuracy.

Demonstrated effective deployment on mobile devices.

Validated robustness through extensive cross-validation.

Abstract

Diabetic Retinopathy (DR) is a major cause of vision impairment worldwide. However, manual diagnosis is often time-consuming and prone to errors, leading to delays in screening. This paper presents a lightweight automated deep learning framework for efficient assessment of DR severity from digital fundus images. We use a MobileNetV3 architecture with a Consistent Rank Logits (CORAL) head to model the ordered progression of disease while maintaining computational efficiency for resource-constrained environments. The model is trained and validated on a combined dataset of APTOS 2019 and IDRiD images using a preprocessing pipeline including circular cropping and illumination normalization. Extensive experiments including 3-fold cross-validation and ablation studies demonstrate strong performance. The model achieves a Quadratic Weighted Kappa (QWK) score of 0.9019 and an accuracy of 80.03 percent. Additionally, we address real-world deployment challenges through model calibration to reduce overconfidence and optimization for mobile devices. The proposed system provides a scalable and practical tool for early-stage diabetic retinopathy screening.