Alternating Learning Approach for Variational Networks and Undersampling Pattern in Parallel MRI Applications.
Alternating Learning Approach for Variational Networks and Undersampling Pattern in Parallel MRI Applications.
复制标题
DOI：
10.1109/tci.2022.3176129
复制
发表时间：
2022
影响因子：
5.4
通讯作者：
Regatte, Ravinder R.
中科院分区：
文献类型：
--
作者：
Zibetti, Marcelo Victor Wust;Knoll, Florian;Regatte, Ravinder R.
关键词：
提出了一种交替学习方法，用于学习加速并行磁共振成像（MRI）中的采样模式（SP）和变分网络（VN）的参数。我们研究了四种变化的学习方法，交替之间的SP，使用偏置加速子集选择，并提高参数的VN，使用ADAM。这些变化包括使用单调或非单调交替步骤和系统地降低学习率。算法学习将在未来扫描中使用的有效对，包括捕获较少k空间样本的SP，其中生成的欠采样伪影通过VN重建去除。在两个不同的数据集上以不同的加速因子（AF）将通过所提出的方法获得的VN和SP的质量与不同的方法（包括其他类型的联合学习方法和最新重建）进行比较。与其他方法相比，我们在视觉上和深度学习中常用的三种不同品质因数（RMSE，SSIM和HFEN）上观察到了改善，从2到20，使用大脑和膝关节数据集。与使用VN测试的下一个最佳方法相比，改进范围从1%到62%。所提出的方法表现出稳定的性能，在不同的初始训练条件下获得相似的学习SP。我们观察到，这种改进不仅是由于学习的采样密度，也是由于学习的样本在k空间中的位置。所提出的方法能够学习有效的SP和重建VN对，改善3D笛卡尔加速并行MRI应用。
This work proposes an alternating learning approach to learn the sampling pattern (SP) and the parameters of variational networks (VN) in accelerated parallel magnetic resonance imaging (MRI). We investigate four variations of the learning approach, that alternates between improving the SP, using bias-accelerated subset selection, and improving parameters of the VN, using ADAM. The variations include the use of monotone or non-monotone alternating steps and systematic reduction of learning rates. The algorithms learn an effective pair to be used in future scans, including an SP that captures fewer k-space samples in which the generated undersampling artifacts are removed by the VN reconstruction. The quality of the VNs and SPs obtained by the proposed approaches is compared against different methods, including other kinds of joint learning methods and state-of-art reconstructions, on two different datasets at various acceleration factors (AF). We observed improvements visually and in three different figures of merit commonly used in deep learning (RMSE, SSIM, and HFEN) on AFs from 2 to 20 with brain and knee joint datasets when compared to the other approaches. The improvements ranged from 1% to 62% over the next best approach tested with VNs. The proposed approach has shown stable performance, obtaining similar learned SPs under different initial training conditions. We observe that the improvement is not only due to the learned sampling density, it is also due to the learned position of samples in k-space. The proposed approach was able to learn effective pairs of SPs and reconstruction VNs, improving 3D Cartesian accelerated parallel MRI applications.
登录
查看更多内容
影响因子：
3.3
作者：
Hammernik K;Klatzer T;Kobler E;Recht MP;Sodickson DK;Pock T;Knoll F
通讯作者：
Knoll F
DOI：
10.1097/01.rmr.0000136558.09801.dd
发表时间：
2004-08-01
期刊：
Topics in magnetic resonance imaging : TMRI
影响因子：
--
作者：
Blaimer, Martin;Breuer, Felix;Jakob, Peter M
通讯作者：
Jakob, Peter M
影响因子：
10.6
作者：
Halder, Justin P.;Kim, Daeun
通讯作者：
Kim, Daeun
影响因子：
3.3
作者：
Johnson, Casey P.;Thedens, Daniel R.;Magnotta, Vincent A.
通讯作者：
Magnotta, Vincent A.
影响因子：
2.5
作者：
Boyer, Claire;Bigot, Jeremie;Weiss, Pierre
通讯作者：
Weiss, Pierre