Uncertainty Estimation and Propagation in Accelerated MRI Reconstruction
This addresses safety concerns for clinical applications like real-time treatment guidance and automated segmentation by providing well-calibrated uncertainty estimates, though it is incremental as it builds on existing hierarchical variational autoencoder ideas.
The paper tackles the problem of unreliable deep learning-based MRI reconstructions, which can hallucinate structures and fail unexpectedly, by proposing a probabilistic reconstruction method (PHiRec) that produces high-quality reconstructions and substantially better-calibrated uncertainty quantification than baselines.
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.