Evaluation of MRI Denoising Methods Using Unsupervised Learning.

Evaluation of MRI Denoising Methods Using Unsupervised Learning.
复制标题

DOI:
10.3389/frai.2021.642731
复制
发表时间:
2021
影响因子:
4
通讯作者:
Ventura J
Ventura J
中科院分区:
其他
文献类型:
--
作者:
Moreno López M;Frederick JM;Ventura J

文献摘要

参考文献

被引文献

相似文献

在本文中,我们评估了两种无监督的方法去噪磁共振图像(MRI)在复杂的图像空间中使用的原始信息,k空间举行。第一种方法是基于Stein的无偏风险估计,而第二种方法是基于盲点网络,这限制了网络的接收域。这两种方法在两个不同的数据集上进行测试,一个包含真实的膝关节MRI,另一个包含合成脑MRI。这些数据集包含有关复图像空间的信息,这些信息将用于去噪目的。这两个网络进行比较,对一个国家的最先进的算法,非本地均值(NLM)使用定量和定性的措施。对于大多数给定的指标和定性测量,这两种网络的性能都优于NLM,并且它们被证明是可靠的去噪方法。
In this paper we evaluate two unsupervised approaches to denoise Magnetic Resonance Images (MRI) in the complex image space using the raw information that k-space holds. The first method is based on Stein’s Unbiased Risk Estimator, while the second approach is based on a blindspot network, which limits the network’s receptive field. Both methods are tested on two different datasets, one containing real knee MRI and the other consists of synthetic brain MRI. These datasets contain information about the complex image space which will be used for denoising purposes. Both networks are compared against a state-of-the-art algorithm, Non-Local Means (NLM) using quantitative and qualitative measures. For most given metrics and qualitative measures, both networks outperformed NLM, and they prove to be reliable denoising methods.
DOI: 10.1109/tmi.2009.2026575
发表时间: 2010-02-01
影响因子: 10.6
作者:
Gal, Yaniv;Mehnert, Andrew J. H.;Crozier, Stuart
通讯作者: Crozier, Stuart
DOI: 10.1016/j.bspc.2013.10.007
发表时间: 2014-01-01
影响因子: 5.1
作者:
Mohan, J.;Krishnaveni, V.;Guo, Yanhui
通讯作者: Guo, Yanhui
DOI: 10.1109/42.816072
发表时间: 1999-11-01
影响因子: 10.6
作者:
Kwan, RKS;Evans, AC;Pike, GB
通讯作者: Pike, GB
DOI: 10.1007/bfb0046947
发表时间: 1996-01-01
期刊: VISUALIZATION IN BIOMEDICAL COMPUTING
影响因子: --
作者:
Kwan, RKS;Evans, AC;Pike, GB
通讯作者: Pike, GB
DOI: 10.1038/s41598-020-69932-w
发表时间: 2020-08-18
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Eun, Da-In;Jang, Ryoungwoo;Kim, Namkug
通讯作者: Kim, Namkug