Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Prior
This addresses uncertainty quantification for medical imaging tasks, offering a method to reduce hallucinations and artifacts, though it is incremental as it builds on existing deep image prior techniques.
The paper tackled the problem of hallucinations and artifacts in medical image denoising by extending the deep image prior with a Bayesian approach using Monte Carlo dropout, resulting in well-calibrated uncertainty estimates where predictive uncertainty correlates with predictive error.
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.