期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 40, 期 1, 页码 239-250出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2020.3025065
关键词
Image reconstruction; Uncertainty; Magnetic resonance imaging; Biomedical imaging; Data models; Training; Probabilistic logic; Uncertainty quantification; VAE; MRI reconstruction; SURE
类别
资金
- NIH [R01EB009690, R01EB026136]
This study aims to quantify the uncertainty in image recovery with DL models by developing a probabilistic reconstruction scheme using VAEs. Empirical experiments show that adversarial losses introduce more uncertainty, while recurrent unrolled nets reduce prediction uncertainty and risk.
Reliable MRI is crucial for accurate interpretation in therapeutic and diagnostic tasks. However, undersampling during MRI acquisition as well as the overparameterized and non-transparent nature of deep learning (DL) leaves substantial uncertainty about the accuracy of DL reconstruction. With this in mind, this study aims to quantify the uncertainty in image recovery with DL models. To this end, we first leverage variational autoencoders (VAEs) to develop a probabilistic reconstruction scheme that maps out (low-quality) short scans with aliasing artifacts to the diagnostic-quality ones. The VAE encodes the acquisition uncertainty in a latent code and naturally offers a posterior of the image from which one can generate pixel variance maps using Monte-Carlo sampling. Accurately predicting risk requires knowledge of the bias as well, for which we leverage Stein's Unbiased Risk Estimator (SURE) as a proxy for mean-squared-error (MSE). A range of empirical experiments is performed for Knee MRI reconstruction under different training losses (adversarial and pixel-wise) and unrolled recurrent network architectures. Our key observations indicate that: 1) adversarial losses introduce more uncertainty; and 2) recurrent unrolled nets reduce the prediction uncertainty and risk.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据