Uncertainty aware and explainable diagnosis of retinal disease

TL;DR

This study integrates uncertainty estimation and explainability in deep learning models for retinal disease diagnosis, enhancing trustworthiness and clinical decision support by identifying uncertain cases and visualizing learned features.

Contribution

It introduces a novel approach combining uncertainty analysis with explainability for retinal disease diagnosis, aiding clinical decision-making and model transparency.

Findings

Uncertainty thresholds help identify cases needing expert review.

Visual explanations improve model interpretability.

Uncertainty information enhances clinical trust in AI predictions.

Abstract

Deep learning methods for ophthalmic diagnosis have shown considerable success in tasks like segmentation and classification. However, their widespread application is limited due to the models being opaque and vulnerable to making a wrong decision in complicated cases. Explainability methods show the features that a system used to make prediction while uncertainty awareness is the ability of a system to highlight when it is not sure about the decision. This is one of the first studies using uncertainty and explanations for informed clinical decision making. We perform uncertainty analysis of a deep learning model for diagnosis of four retinal diseases - age-related macular degeneration (AMD), central serous retinopathy (CSR), diabetic retinopathy (DR), and macular hole (MH) using images from a publicly available (OCTID) dataset. Monte Carlo (MC) dropout is used at the test time to generate a distribution of parameters and the predictions approximate the predictive posterior of a Bayesian model. A threshold is computed using the distribution and uncertain cases can be referred to the ophthalmologist thus avoiding an erroneous diagnosis. The features learned by the model are visualized using a proven attribution method from a previous study. The effects of uncertainty on model performance and the relationship between uncertainty and explainability are discussed in terms of clinical significance. The uncertainty information along with the heatmaps make the system more trustworthy for use in clinical settings.