An Ensemble Method to Automatically Grade Diabetic Retinopathy with Optical Coherence Tomography Angiography Images

TL;DR

This paper presents an ensemble machine learning approach using multiple neural networks to automatically grade diabetic retinopathy from ultra-wide optical coherence tomography angiography images, achieving high accuracy on challenge datasets.

Contribution

It introduces an ensemble of state-of-the-art classification networks with multi-task learning for improved diabetic retinopathy grading from UW-OCTA images.

Findings

Achieved a QWK of 0.9346 and AUC of 0.9766 on internal data.

Achieved a QWK of 0.839 and AUC of 0.8978 on challenge data.

Demonstrated effectiveness of ensemble and multi-task learning strategies.

Abstract

Diabetic retinopathy (DR) is a complication of diabetes, and one of the major causes of vision impairment in the global population. As the early-stage manifestation of DR is usually very mild and hard to detect, an accurate diagnosis via eye-screening is clinically important to prevent vision loss at later stages. In this work, we propose an ensemble method to automatically grade DR using ultra-wide optical coherence tomography angiography (UW-OCTA) images available from Diabetic Retinopathy Analysis Challenge (DRAC) 2022. First, we adopt the state-of-the-art classification networks, i.e., ResNet, DenseNet, EfficientNet, and VGG, and train them to grade UW-OCTA images with different splits of the available dataset. Ultimately, we obtain 25 models, of which, the top 16 models are selected and ensembled to generate the final predictions. During the training process, we also investigate the multi-task learning strategy, and add an auxiliary classification task, the Image Quality Assessment, to improve the model performance. Our final ensemble model achieved a quadratic weighted kappa (QWK) of 0.9346 and an Area Under Curve (AUC) of 0.9766 on the internal testing dataset, and the QWK of 0.839 and the AUC of 0.8978 on the DRAC challenge testing dataset.