Propagation and Attribution of Uncertainty in Medical Imaging Pipelines

TL;DR

This paper introduces a method to propagate and attribute uncertainty through cascaded deep learning models in medical imaging pipelines, enhancing explainability and joint uncertainty estimation.

Contribution

We propose a novel approach to propagate and decompose uncertainty across multiple models in medical imaging pipelines, enabling better interpretability.

Findings

Propagated uncertainty correlates with input uncertainty.

The method quantifies contributions of each pipeline stage to overall uncertainty.

Joint uncertainty estimation improves understanding of model predictions.

Abstract

Uncertainty estimation, which provides a means of building explainable neural networks for medical imaging applications, have mostly been studied for single deep learning models that focus on a specific task. In this paper, we propose a method to propagate uncertainty through cascades of deep learning models in medical imaging pipelines. This allows us to aggregate the uncertainty in later stages of the pipeline and to obtain a joint uncertainty measure for the predictions of later models. Additionally, we can separately report contributions of the aleatoric, data-based, uncertainty of every component in the pipeline. We demonstrate the utility of our method on a realistic imaging pipeline that reconstructs undersampled brain and knee magnetic resonance (MR) images and subsequently predicts quantitative information from the images, such as the brain volume, or knee side or patient's sex. We quantitatively show that the propagated uncertainty is correlated with input uncertainty and compare the proportions of contributions of pipeline stages to the joint uncertainty measure.