Direct Classification of Type 2 Diabetes From Retinal Fundus Images in a Population-based Sample From The Maastricht Study

TL;DR

This study demonstrates that deep neural networks can classify Type 2 Diabetes from retinal fundus images with promising accuracy, highlighting potential for non-invasive screening methods.

Contribution

It introduces a multi-target learning approach and a simple image combination technique that improve T2D classification performance from retinal images.

Findings

Multi-target learning achieved AUC = 0.746.

Combining images from both eyes increased AUC to 0.758.

Referral of uncertain cases to specialists enhances accuracy.

Abstract

Type 2 Diabetes (T2D) is a chronic metabolic disorder that can lead to blindness and cardiovascular disease. Information about early stage T2D might be present in retinal fundus images, but to what extent these images can be used for a screening setting is still unknown. In this study, deep neural networks were employed to differentiate between fundus images from individuals with and without T2D. We investigated three methods to achieve high classification performance, measured by the area under the receiver operating curve (ROC-AUC). A multi-target learning approach to simultaneously output retinal biomarkers as well as T2D works best (AUC = 0.746 [$\pm$0.001]). Furthermore, the classification performance can be improved when images with high prediction uncertainty are referred to a specialist. We also show that the combination of images of the left and right eye per individual can further improve the classification performance (AUC = 0.758 [$\pm$0.003]), using a simple averaging approach. The results are promising, suggesting the feasibility of screening for T2D from retinal fundus images.