Stage Aware Diagnosis of Diabetic Retinopathy via Ordinal Regression

TL;DR

This paper presents a novel ordinal regression framework for diabetic retinopathy detection using fundus images, achieving state-of-the-art accuracy and aligning well with clinical grading standards.

Contribution

It introduces an ordinal regression approach combined with specific preprocessing techniques, setting a new benchmark on the APTOS-2019 dataset.

Findings

QWK score of 0.8992, outperforming previous methods

Effective preprocessing pipeline improves classification accuracy

Framework aligns closely with clinical grading standards

Abstract

Diabetic Retinopathy (DR) has emerged as a major cause of preventable blindness in recent times. With timely screening and intervention, the condition can be prevented from causing irreversible damage. The work introduces a state-of-the-art Ordinal Regression-based DR Detection framework that uses the APTOS-2019 fundus image dataset. A widely accepted combination of preprocessing methods: Green Channel (GC) Extraction, Noise Masking, and CLAHE, was used to isolate the most relevant features for DR classification. Model performance was evaluated using the Quadratic Weighted Kappa, with a focus on agreement between results and clinical grading. Our Ordinal Regression approach attained a QWK score of 0.8992, setting a new benchmark on the APTOS dataset.