Suppression of artifact-generating echoes in cine DENSE using deep learning.
Suppression of artifact-generating echoes in cine DENSE using deep learning.
复制标题
DOI：
10.1002/mrm.28832
复制
发表时间：
2021-10
影响因子：
3.3
通讯作者：
Epstein FH
中科院分区：
文献类型：
--
作者：
Abdi M;Feng X;Sun C;Bilchick KC;Meyer CH;Epstein FH
采用深度学习来抑制受激回波 (DENSE) 电影位移编码中产生伪影的 T1 弛豫回波，以减少扫描时间。 U-Net 经过训练，使用互补相位循环数据作为基本事实来抑制产生伪影的 T1 弛豫回波。开发了一种数据增强方法，可生成具有任意位移编码频率的合成 DENSE 图像，以抑制针对一定频率范围调制的 T1 弛豫回波。将生成的 U-Net (DAS-Net) 与作为替代方法的 k 空间零填充进行比较。在较短的屏气中获取的非相位循环 DENSE 图像由 DAS-Net 进行处理，并与通过相位循环获取的 DENSE 图像进行比较，以量化心肌应变。 DAS-Net有效抑制了T1弛豫回波及其伪影，对于以0.10周期/毫米的位移编码频率获取的DENSE图像，实现了均方根误差（RMSE）= 5.5±0.8和结构相似性指数（SSIM）= 0.85±0.02。 DAS-Net 优于零填充（RMSE = 5.8±1.5 vs 13.5±1.5，DAS-Net vs 零填充，p<0.01，SSIM = 0.83±0.04 vs 0.66±0.03，DAS-Net vs 零填充，p<0.01）。 DAS-Net 的非相位循环 DENSE 图像的应变数据与相位循环 DENSE 的应变非常一致。 DAS-Net 提供了一种有效的替代方法，用于抑制 DENSE MRI 中产生伪影的 T1 弛豫回波，与采用相位循环的 DENSE 相比，扫描时间减少 42%。
To employ deep learning for suppression of the artifact-generating T1-relaxation echo in cine displacement encoding with stimulated echoes (DENSE) for the purpose of reducing the scan time. A U-Net was trained to suppress the artifact-generating T1-relaxation echo using complementary phase-cycled data as the ground truth. A data augmentation method was developed that generates synthetic DENSE images with arbitrary displacement encoding frequencies to suppress the T1-relaxation echo modulated for a range of frequencies. The resulting U-Net (DAS-Net) was compared to a k-space zero-filling as an alternative method. Non-phase-cycled DENSE images acquired in shorter breath-holds were processed by DAS-Net and compared to DENSE images acquired with phase-cycling for the quantification of myocardial strain. DAS-Net effectively suppressed the T1-relaxation echo and its artifacts, and achieved root mean square error (RMSE) = 5.5±0.8 and structural similarity index (SSIM) = 0.85±0.02 for DENSE images acquired with a displacement encoding frequency of 0.10 cycles/mm. DAS-Net outperformed zero-filling (RMSE = 5.8±1.5 vs 13.5±1.5, DAS-Net vs zero-filling, p<0.01 and SSIM = 0.83±0.04 vs 0.66±0.03, DAS-Net vs zero-filling, p<0.01). Strain data for non-phase-cycled DENSE images with DAS-Net showed close agreement with strain from phase-cycled DENSE. DAS-Net provides an effective alternative approach for suppression of the artifact-generating T1-relaxation echo in DENSE MRI, enabling a 42% reduction in scan time compared to DENSE with phase-cycling.
登录
查看更多内容
影响因子：
3.3
作者：
Lin, Alexander P.;Bennett, Eric;Wisk, Lauren E.;Gharib, Morteza;Fraser, Scott E.;Wen, Han
通讯作者：
Wen, Han
影响因子：
4.4
作者：
Hales, Patrick W.;Pfeuffer, Josef;A. Clark, Chris
通讯作者：
A. Clark, Chris
影响因子：
3.3
作者：
Sampath, S;Derbyshire, JA;Prince, JL
通讯作者：
Prince, JL
影响因子：
4.4
作者：
Ryu, Kanghyun;Nam, Yoonho;Kim, Dong-Hyun
通讯作者：
Kim, Dong-Hyun
影响因子：
3.3
作者：
Callot, V;Bennett, E;Wen, H
通讯作者：
Wen, H