arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.01479cs.LG
收藏

基于扩散模型的联合不确定性估计贝叶斯MRI重建

Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Models

Graz University of Technology(格拉茨技术大学);University Medical Center Göttingen(哥廷根大学医学中心);German Centre for Cardiovascular Research (DZHK)(德国心血管研究中心);University of Göttingen(哥廷根大学)

Guanxiong Luo, Moritz Blumenthal, Martin Heide, Martin Uecker

AI总结:

该研究提出一种基于扩散模型的贝叶斯MRI重建框架,采用MCMC从后验分布采样,可输出MAP、MMSE估计及不确定性图,且适配不同采样方案与接收线圈,已在10倍欠采样公开数据集上验证性能。

摘要:

我们提出了一种框架,可实现从学习到的概率分布中高效采样以用于MRI重建。与传统的基于深度学习的MRI重建技术不同,该方法使用马尔可夫链蒙特卡洛(MCMC)方法,根据测得的k空间从后验分布中抽取样本。除了可通过传统方法获得的图像最大后验(MAP)估计外,还能计算最小均方误差(MMSE)估计和不确定性图。数据驱动的马尔可夫链由从给定图像数据库中学习到的生成模型构建,且与用于建模k空间测量的前向算子无关。这带来了灵活性,因为该方法可使用相同的预训练模型,应用于通过不同采样方案或接收线圈采集的k空间数据。此外,我们采用基于逆向扩散过程的框架,以能够利用先进的生成模型。我们在一个公开数据集上,使用k空间10倍欠采样的设置评估了该方法的性能。

英文摘要:

We introduce a framework that enables efficient sampling from learned probability distributions for MRI reconstruction. Different from conventional deep learning-based MRI reconstruction techniques, samples are drawn from the posterior distribution given the measured k-space using the Markov chain Monte Carlo (MCMC) method. In addition to the maximum a posteriori (MAP) estimate for the image, which can be obtained with conventional methods, the minimum mean square error (MMSE) estimate and uncertainty maps can also be computed. The data-driven Markov chains are constructed from the generative model learned from a given image database and are independent of the forward operator that is used to model the k-space measurement. This provides flexibility because the method can be applied to k-space acquired with different sampling schemes or receive coils using the same pre-trained models. Furthermore, we use a framework based on a reverse diffusion process to be able to utilize advanced generative models. The performance of the method is evaluated on an open dataset using 10-fold undersampling in k-space.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑