Chen Zhuo, Gong Yiwen, Chen Haiyang, Emu Yixin, Gao Juan, Zhou Zhongjie, Shen Yiwen, Tang Xin, Hua Sha, Jin Wei, Hu Chenxi
National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
Department of Cardiovascular Medicine, Heart Failure Center, Ruijin Hospital Lu Wan Branch, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
J Cardiovasc Magn Reson. 2024;26(2):101123. doi: 10.1016/j.jocmr.2024.101123. Epub 2024 Nov 7.
Cardiac balanced steady state free precession (bSSFP) cine imaging suffers from banding and flow artifacts induced by off-resonance. The work aimed to develop a twofold phase cycling sequence with a neural network-based reconstruction (2P-SSFP+Network) for a joint suppression of banding and flow artifacts in cardiac cine imaging.
A dual-encoder neural network was trained on 1620 pairs of phase-cycled left ventricular (LV) cine images collected from 18 healthy subjects. Twenty healthy subjects and 25 patients were prospectively scanned using the proposed 2P-SSFP sequence. bSSFP cine of a single RF phase increment (1P-SSFP), bSSFP cine of a single radiofrequency (RF) phase increment with a network-based artifact reduction (1P-SSFP+Network), the averaging of the two phase-cycled images (2P-SSFP+Average), and the proposed method were mutually compared, in terms of artifact suppression performance in the LV, generalizability over altered scan parameters and scanners, suppression of large-area banding artifacts in the left atrium (LA), and accuracy of downstream segmentation tasks.
In the healthy subjects, 2P-SSFP+Network showed robust suppressions of artifacts across a range of phase combinations. Compared with 1P-SSFP and 2P-SSFP+Average, 2P-SSFP+Network improved banding artifacts (3.85 ± 0.67 and 4.50 ± 0.45 vs 5.00 ± 0.00, P < 0.01 and P = 0.02, respectively), flow artifacts (3.35 ± 0.78 and 2.10 ± 0.77 vs 4.90 ± 0.20, both P < 0.01), and overall image quality (3.25 ± 0.51 and 2.30 ± 0.60 vs 4.75 ± 0.25, both P < 0.01). 1P-SSFP+Network and 2P-SSFP+Network achieved a similar artifact suppression performance, yet the latter had fewer hallucinations (two-chamber, 4.25 ± 0.51 vs 4.85 ± 0.45, P = 0.04; four-chamber, 3.45 ± 1.21 vs 4.65 ± 0.50, P = 0.03; and left atrium (LA), 3.35 ± 1.00 vs 4.65 ± 0.45, P < 0.01). Furthermore, in the pulmonary veins and LA, 1P-SSFP+Network could not eliminate banding artifacts since they occupied a large area, whereas 2P-SSFP+Network reliably suppressed the artifacts. In the downstream automated myocardial segmentation task, 2P-SSFP+Network achieved more accurate segmentations than 1P-SSFP with different phase increments.
2P-SSFP+Network jointly suppresses banding and flow artifacts while manifesting a good generalizability against variations of anatomy and scan parameters. It provides a feasible solution for robust suppression of the two types of artifacts in bSSFP cine imaging.
心脏平衡稳态自由进动（bSSFP）电影成像存在由失谐引起的带状伪影和流动伪影。本研究旨在开发一种基于神经网络重建的双相位循环序列（2P-SSFP+网络），以联合抑制心脏电影成像中的带状伪影和流动伪影。
使用从18名健康受试者收集的1620对相位循环左心室（LV）电影图像训练双编码器神经网络。对20名健康受试者和25名患者使用所提出的2P-SSFP序列进行前瞻性扫描。将单个射频（RF）相位增量的bSSFP电影（1P-SSFP）、基于网络的伪影减少的单个射频（RF）相位增量的bSSFP电影（1P-SSFP+网络）、两个相位循环图像的平均值（2P-SSFP+平均）以及所提出的方法在左心室伪影抑制性能、扫描参数和扫描仪改变时的通用性、左心房（LA）大面积带状伪影的抑制以及下游分割任务的准确性方面进行相互比较。
在健康受试者中，2P-SSFP+网络在一系列相位组合中均表现出强大的伪影抑制能力。与1P-SSFP和2P-SSFP+平均相比，2P-SSFP+网络改善了带状伪影（分别为3.85±0.67和4.50±0.45对5.00±0.00，P<0.01和P=0.02）、流动伪影（分别为3.35±0.78和2.10±0.77对4.90±0.20，均P<0.01）以及整体图像质量（分别为3.25±0.51和2.30±0.60对4.75±0.25，均P<0.01）。1P-SSFP+网络和2P-SSFP+网络实现了相似的伪影抑制性能，但后者的幻觉较少（双腔，4.25±0.51对4.85±0.45，P=0.04；四腔，3.45±1.21对4.65±0.50，P=0.03；左心房（LA），3.35±1.00对4.65±0.45，P<0.01）。此外，在肺静脉和左心房中，1P-SSFP+网络由于带状伪影占据大面积而无法消除，而2P-SSFP+网络可靠地抑制了伪影。在下游自动心肌分割任务中，2P-SSFP+网络比具有不同相位增量的1P-SSFP实现了更准确的分割。
2P-SSFP+网络联合抑制带状伪影和流动伪影，同时对解剖结构和扫描参数的变化具有良好的通用性。它为在bSSFP电影成像中稳健抑制这两种类型的伪影提供了一种可行的解决方案。
