Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Prior

TL;DR

This paper introduces a Bayesian deep image prior method with Monte Carlo dropout for uncertainty quantification in medical image denoising, effectively reducing hallucinations and providing reliable uncertainty estimates.

Contribution

It extends deep image prior with a Bayesian approach to quantify uncertainty, addressing hallucinations and artifacts in medical image reconstruction.

Findings

Produces well-calibrated uncertainty estimates

Uncertainty correlates with reconstruction error

Reduces hallucinations in medical image denoising

Abstract

Uncertainty quantification in inverse medical imaging tasks with deep learning has received little attention. However, deep models trained on large data sets tend to hallucinate and create artifacts in the reconstructed output that are not anatomically present. We use a randomly initialized convolutional network as parameterization of the reconstructed image and perform gradient descent to match the observation, which is known as deep image prior. In this case, the reconstruction does not suffer from hallucinations as no prior training is performed. We extend this to a Bayesian approach with Monte Carlo dropout to quantify both aleatoric and epistemic uncertainty. The presented method is evaluated on the task of denoising different medical imaging modalities. The experimental results show that our approach yields well-calibrated uncertainty. That is, the predictive uncertainty correlates with the predictive error. This allows for reliable uncertainty estimates and can tackle the problem of hallucinations and artifacts in inverse medical imaging tasks.