Hybrid Deep Learning Gaussian Process for Diabetic Retinopathy Diagnosis and Uncertainty Quantification

TL;DR

This paper introduces a hybrid deep learning-Gaussian process model for diabetic retinopathy diagnosis that enhances prediction robustness and provides uncertainty quantification, improving interpretability and diagnostic support.

Contribution

It presents a novel hybrid approach combining deep learning with Gaussian processes for DR diagnosis and uncertainty estimation, addressing limitations of binary classification models.

Findings

Uncertainty quantification improves interpretability.

Hybrid model outperforms traditional CNNs in small datasets.

Source code is publicly available for reproducibility.

Abstract

Diabetic Retinopathy (DR) is one of the microvascular complications of Diabetes Mellitus, which remains as one of the leading causes of blindness worldwide. Computational models based on Convolutional Neural Networks represent the state of the art for the automatic detection of DR using eye fundus images. Most of the current work address this problem as a binary classification task. However, including the grade estimation and quantification of predictions uncertainty can potentially increase the robustness of the model. In this paper, a hybrid Deep Learning-Gaussian process method for DR diagnosis and uncertainty quantification is presented. This method combines the representational power of deep learning, with the ability to generalize from small datasets of Gaussian process models. The results show that uncertainty quantification in the predictions improves the interpretability of the method as a diagnostic support tool. The source code to replicate the experiments is publicly available at https://github.com/stoledoc/DLGP-DR-Diagnosis.