Risk Quantification in Deep MRI Reconstruction

Abstract

Reliable medical image recovery is crucial for accurate patient diagnoses, but little prior work has centered on quantifying uncertainty when using non-transparent deep learning approaches to reconstruct high-quality images from limited measured data. In this study, we develop methods to address these concerns, utilizing a VAE as a probabilistic recovery algorithm for pediatric knee MR imaging. Through our use of SURE, which examines the end-to-end network Jacobian, we demonstrate a new and rigorous metric for assessing risk in medical image recovery that applies universally across model architectures.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Edupuganti et al. "Risk Quantification in Deep MRI Reconstruction." NeurIPS 2020 Workshops: Deep_Inverse, 2020.

Markdown

[Edupuganti et al. "Risk Quantification in Deep MRI Reconstruction." NeurIPS 2020 Workshops: Deep_Inverse, 2020.](https://mlanthology.org/neuripsw/2020/edupuganti2020neuripsw-risk/)

BibTeX

@inproceedings{edupuganti2020neuripsw-risk,
  title     = {{Risk Quantification in Deep MRI Reconstruction}},
  author    = {Edupuganti, Vineet and Mardani, Morteza and Vasanawala, Shreyas and Pauly, John M.},
  booktitle = {NeurIPS 2020 Workshops: Deep_Inverse},
  year      = {2020},
  url       = {https://mlanthology.org/neuripsw/2020/edupuganti2020neuripsw-risk/}
}