Uncertainty Estimation and Propagation in Accelerated MRI Reconstruction

TL;DR

This paper introduces PHiRec, a probabilistic MRI reconstruction method that provides high-quality images with well-calibrated uncertainty estimates, crucial for safe clinical application and downstream tasks like segmentation.

Contribution

The paper presents a novel probabilistic reconstruction technique using hierarchical variational autoencoders that improves uncertainty calibration in MRI reconstructions.

Findings

PHiRec achieves superior uncertainty calibration compared to baselines.

Uncertainty estimates can be propagated to downstream segmentation tasks.

PHiRec provides well-calibrated segmentation uncertainty estimates.

Abstract

MRI reconstruction techniques based on deep learning have led to unprecedented reconstruction quality especially in highly accelerated settings. However, deep learning techniques are also known to fail unexpectedly and hallucinate structures. This is particularly problematic if reconstructions are directly used for downstream tasks such as real-time treatment guidance or automated extraction of clinical paramters (e.g. via segmentation). Well-calibrated uncertainty quantification will be a key ingredient for safe use of this technology in clinical practice. In this paper we propose a novel probabilistic reconstruction technique (PHiRec) building on the idea of conditional hierarchical variational autoencoders. We demonstrate that our proposed method produces high-quality reconstructions as well as uncertainty quantification that is substantially better calibrated than several strong baselines. We furthermore demonstrate how uncertainties arising in the MR econstruction can be propagated to a downstream segmentation task, and show that PHiRec also allows well-calibrated estimation of segmentation uncertainties that originated in the MR reconstruction process.