Beat-to-beat respiratory motion correction with near 100% efficiency: a quantitative assessment using high-resolution coronary artery imaging

This study quantitatively assesses the effectiveness of retrospective beat-to-beat respiratory motion correction (B2B-RMC) at near 100% efficiency using high-resolution coronary artery imaging. Three-dimensional (3D) spiral images were obtained in a coronary respiratory motion phantom with B2B-RMC and navigator gating. In vivo, targeted 3D coronary imaging was performed in 10 healthy subjects using B2B-RMC spiral and navigator gated balanced steady-state free-precession (nav-bSSFP) techniques. Vessel diameter and sharpness in proximal and mid arteries were used as a measure of respiratory motion compensation effectiveness and compared between techniques. Phantom acquisitions with B2B-RMC were sharper than those acquired with navigator gating (B2B-RMC vs. navigator gating: 1.01±0.02 mm⁻¹ vs. 0.86±0.08 mm⁻¹, P<.05). In vivo B2B-RMC respiratory efficiency was significantly and substantially higher (99.7%±0.5%) than nav-bSSFP (44.0%±8.9%, P<.0001). Proximal and mid vessel sharpnesses were similar (B2B-RMC vs. nav-bSSFP, proximal: 1.00±0.14 mm⁻¹ vs. 1.08±0.11 mm⁻¹, mid: 1.01±0.11 mm⁻¹ vs. 1.05±0.12 mm⁻¹; both P=not significant [ns]). Mid vessel diameters were not significantly different (2.85±0.39 mm vs. 2.80±0.35 mm, P=ns), but proximal B2B-RMC diameters were slightly higher (2.85±0.38 mm vs. 2.70±0.34 mm, P<.05), possibly due to contrast differences. The respiratory efficiency of B2B-RMC is less variable and significantly higher than navigator gating. Phantom and in vivo vessel sharpness and diameter values suggest that respiratory motion compensation is equally effective.     

Feasibility of coronary artery wall thickening assessment in asymptomatic coronary artery disease using phase-sensitive dual-inversion recovery MRI at 3 T

Objectives

The purpose of this study was to (a) investigate the image quality of phase-sensitive dual-inversion recovery (PS-DIR) coronary wall imaging in healthy subjects and in subjects with known coronary artery disease (CAD) and to (b) investigate the utilization of PS-DIR at 3 T in the assessment of coronary artery thickening in subjects with asymptomatic but variable degrees of CAD.

Materials and Methods

A total of 37 subjects participated in this institutional review board-approved and HIPAA-compliant study. These included 21 subjects with known CAD as identified on multidetector computed tomography angiography (MDCT). Sixteen healthy subjects without known history of CAD were included. All subjects were scanned using free-breathing PS-DIR magnetic resonance imaging (MRI) for the assessment of coronary wall thickness at 3 T. Lumen–tissue contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR) and quantitative vessel parameters including lumen area and wall thickness were measured. Statistical analyses were performed.

Results

PS-DIR was successfully completed in 76% of patients and in 88% of the healthy subjects. Phase-sensitive signed-magnitude reconstruction, compared to modulus-magnitude images, significantly improved lumen–tissue CNR in healthy subjects (26.73 ± 11.95 vs. 14.65 ± 9.57, P < .001) and in patients (21.45 ± 7.61 vs. 16.65 ± 5.85, P < .001). There was no difference in image CNR and SNR between groups. In arterial segments free of plaques, coronary wall was thicker in patients in comparison to healthy subjects (1.74 ± 0.27 mm vs. 1.17 ± 0.14 mm, P < .001), without a change in lumen area (4.51 ± 2.42 mm² vs. 5.71 ± 3.11 mm², P = .25).

Conclusions

This is the first study to demonstrate the feasibility of successfully obtaining vessel wall images at 3 T using PS-DIR in asymptomatic patients with known variable degrees of CAD as detected by MDCT. This was achieved with a fixed subject-invariant planning of blood signal nulling. With that limitation alleviated, PS-DIR coronary wall MRI is capable of detecting arterial thickening and positive arterial remodeling at 3 T in asymptomatic CAD.     

Cine-MRI and P-MRS for evaluation of myocardial energy metabolism and function following coronary artery bypass graft

Previous studies investigated the effect of successful coronary artery bypass grafting (CABG) upon left ventricular function. The relationship between myocardial metabolism and heart function after CABG remains unclear. We investigated the relationship between high-energy phosphate (HEP) and cardiac function following CABG using cine magnetic resonance imaging (cine-MRI) and phosphorus-31 magnetic resonance spectroscopy (³¹P-MRS). A retrospective study was approved by the institutional review board. MRI and ³¹P-MRS examinations were reviewed of 37 patients with multivessel disease who underwent CABG. 13 of these patients selected for the retrospective analysis had ≥70% stenosis in the proximal left anterior descending artery (LAD) and left ventricular ejection fraction (LVEF) <40%. LVEF was evaluated using cine-MRI. HEP such as phosphocreatine (PCr) and adenosine triphosphate (β-ATP) was measured using ³¹P-MRS to calculate PCr/β-ATP ratio. Cine-MRI and ³¹P-MRS measurements were performed before and after CABG, respectively. Ten normal healthy volunteers served as controls. ³¹P-MRS in 13 patients showed that post-CABG PCr/β-ATP ratio was significantly higher than that of pre-CABG (pre-CABG vs. post-CABG, 1.43±0.24 vs. 1.71±0.29, P<.05), but both ratios were significantly lower than control group (2.13±0.21, P<.05). With the change of the ratio, the left ventricle function was significantly improved (LVEF: pre-CABG vs. post-CABG: 35.7±12.9 vs. 45.6±17.2, P<.05).     

Dose assessment according to changes in algorithm in cardiac CT

The principal objective of this study was to determine the effects of the application of the adaptive statistical iterative reconstruction (ASIR) technique in combination with another two factors (body mass index (BMI) and tube potential) on radiation dose in cardiac computed tomography (CT). For quantitative analysis, regions of interest were positioned on the central region of the great coronary artery, the right coronary artery, and the left anterior descending artery, after which the means and standard deviations of measured CT numbers were obtained. For qualitative analysis, images taken from the major coronary arteries (right coronary, left anterior descending, and left circumflex) were graded on a scale of 1–5, with 5 indicating the best image quality. Effective dose, which was calculated by multiplying the value of the dose length product by a standard conversion factor of 0.017 for the chest, was employed as a measure of radiation exposure dose. In cardiac CT in patients with BMI of less than 25 kg/m², the use of 40% ASIR in combination with a low tube potential of 100 kVp resulted in a significant reduction in the radiation dose without compromising diagnostic quality. Additionally, the combination of the 120 kVp protocol and the application of 40% ASIR application for patients with BMI higher than 25 kg/m² yielded similar results.     

Detection and dosimetry of gamma ray emitted from thallium-201 and technetium-99m based on chemiluminescence technique

This report describes the detection and dosimetry of gamma ray emitted from Thallium-201 (²⁰¹Tl) and Technetium-99m (^99mTc) based on chemiluminescence technique. H₂O₂ produced by two gamma emitter radioisotopes of ²⁰¹Tl and ^99mTc were quantitatively measured by chemiluminescence method. Upon producing H₂O₂ in a luminol alkaline solution, in the presence of diperiodatocuprate, as catalyst a chemical reaction was accrued and consequently the emitted light was measured. The determined H₂O₂ concentration was correlated with the gamma ray detection and dosimetry. The sensitivity of chemiluminescence technique for ²⁰¹Tl and ^99mTc dosimetry was determined to be 0.20 and 0.08 MBq/l (Mega Becquerel per liter) respectively (R.S.D. = %5, N = 3). The plotted calibration curves showed detection limits of 3.24 and 1.76 MBq/l for ²⁰¹Tl and ^99mTc, respectively.     

Free-breathing 3-dimensional steady-state free precession coronary magnetic resonance angiography: comparison of four navigator gating techniques

This work compared the performance of four navigator gating algorithms [accept/reject (A/R), diminishing variance algorithm (DVA), phase ordering with automatic window selection (PAWS) and retrospective gating (RETRO)] in suppressing respiratory motion artifacts in free-breathing 3D balanced steady-state free precession coronary MRA. In 10 volunteers, the right coronary artery (RCA) or the left anterior descending artery (LAD) was imaged (both if time permitted) at 1.5 T with the four gating techniques in random order. Vessel signal, vessel contrast and motion suppression were scored by the consensus of two blinded readers. In 15 imaged vessels (nine RCA and six LAD), PAWS provided significantly better image quality than A/R (P<.05), DVA (P=.02) and RETRO (P=.002). While the quality difference between A/R and DVA was not statistically significant, both algorithms yielded significantly better image quality than RETRO. PAWS and DVA were the most efficient algorithms, providing an approximately 20% and 40% relative increase in average navigator efficiency compared to A/R and RETRO, respectively.     

Dynamic contrast-enhanced MRI with Gd-EOB-DTPA for the quantitative assessment of early-stage liver fibrosis induced by carbon tetrachloride in rabbits

PurposeTo explore quantitative parameters obtained by dynamic contrast-enhanced magnetic resonance imaging (DCE MRI) with Gd-EOB-DTPA in discriminating early-stage liver fibrosis (LF) in a rabbit model.Materials and methodsLF was established in 60 rabbits by the injection of 50% CCl₄ oil solution, whereas 30 rabbits served as the control group. All rabbits underwent pathological examination to determine the LF stage using the METAVIR classification system. DCE MRI was performed, and quantitative parameters, including K^trans, K_ep, V_e, V_p and Re were measured and evaluated among the different LF stages using spearman correlation coefficients and receiver operating characteristic curve.ResultsIn all, 24, 25, and 22 rabbits had stage F0, stage F1, and stage F2 LF, respectively. K^trans (r = 0.803) increased, and K_ep (r = −0.495) and Re (r = −0.701) decreased with LF stage progression (P < 0.001), while no significant correlation was found for V_e or V_p. K^trans and Re were significantly different between all LF stage pairs compared (F0 vs. F1, F0 vs. F2, F1 vs. F2, F0 vs. F1-F2, P < 0.05). With the exception of F0 vs. F1, K_ep differed significantly between stages (P < 0.05). The AUC of K^trans was higher than that of other quantitative parameters, with an AUC of 0.92, 0.99, 0.94 and 0.92 for staging F0 vs. F1, F0 vs. F2, F1 vs. F2, and F0 vs. F1-F2, respectively.ConclusionAmong quantitative parameters of Gd-EOB-DTPA DCE MRI, K^trans was the best predictor for quantitatively differentiating early-stage LF.     

Field-driven creep motion of a composite domain wall in a Pt/Co/Pt/Co/Pt multilayer wire

We have studied the field-driven motion of a pair of coupled Bloch domain walls in a perpendicular magnetic anisotropy Pt/Co/Pt/Co/Pt multilayer Hall bar. The nucleation of an isolated but coincident pair of walls in the two Co layers, observed by Kerr microscopy, took place at an artificial nucleation site created by Ga⁺ ion irradiation. The average velocity v of the wall motion was calculated from time-resolved magnetotransport measurements at fixed driving field H, where the influence of the extraordinary Hall effect leads to the observation of voltages at the longitudinal resistance probes. We observed a good fit to the scaling relation lnv∝H^−1/4, consistent the motion of a single 1-dimensional wall moving in a 2-dimensional disordered medium in the creep regime: the two walls are coupled together into a 1-dimensional composite object.     

Understanding the influence of external perturbation on aziridinium ion formation

A density functional theory study is performed to understand the effect of discrete water molecules during Az⁺ ion formation in nitrogen mustards. A comparative study in gas phase, and implicit and explicit solvation models of three drug molecules (mustine, chlorambucil and melphalan) is reported. Noteworthy changes in the structure and C–N stretching frequencies of the transition states have been observed in the presence of explicit water molecules. Presence of explicit water molecules reduces the positive charge around the tricyclic Az⁺ ring, and hence stabilising it. Both activation energy and rate constants are seen to be significantly affected in the presence of discrete water molecules.     

Experimental evaluation of dual acceptance window weighting function for right coronary MR angiography at 3.0T

To shorten scanning time and increase the feasibility of experimental results, we performed right coronary artery magnetic resonance angiography (CMRA) at 3.0 T using dual acceptance window weighting function in 25 normal subjects. We examined these subjects using conventional navigator with fixed gating window and 6 dual acceptance window weighted gating (DAWG) sequences with different central weighted ratio (CWR). Compared with the conventional navigator sequence, DAWG sequences with CWRs of 20% and 25% increased the scanning efficiency by 30% and 26% respectively (P<.05), while maintaining good image quality; further the corresponding scanning time decreased from 2.12–1.64 and 1.69 min, respectively (P<.05). However, CWRs less than 15% caused image degradation to some extent. The coronary artery lengths and diameters did not show statistically significant differences between the two techniques (P>.05). Briefly, to avoid the problems caused by low navigator efficiency and to maintain comparable image quality, the weighted gating parameters of 3 mm width central acceptance window and 15 mm width outer acceptance window with CWR between 20% and 25% are recommended for right CMRA at 3 T.     

Improved simulation of domain wall bowing in metallic laminations using a new spline model

After a critical review of earlier calculations of the bowed shape of domain walls in eddy current limited motion, a more refined numerical technique for such calculations is developed. The shape of the wall is approximated by a continuous linear spline function rather than by discontinuous segments. As a peeliminary application the shape and eddy current drag of a domain wall spanning an ideal lamination and in steady state motion are calculated for all integral values of reduced wall speed u between 1 and 50. (Here u = 8VM²D²?π³γ?, V is the velocity of the wall along a sheet of thickness D and resistivity ?, γ is its specific surface energy density and 2M is the change in magnetization it effects). The mobility obeys the equation $\text{μ = (2.016 ± 0.003)(??MD)u}{}^{\mathrm{<mtext>1</mtext><mtext>2</mtext>}}$ for 8 ≤ nu ≤ 60 in excellent agreement with earlier calculations. No evidence for inst ability was encountered although at u = 15 the wall shape is reliably determined and bowed well beyond Carr's criterion. The results do suggest, however, that at some value of u between 15 and 50 the wall shape may become slightly re-entrant so that it can no longer be accurately represented as a single valued function of depth in the lamination.     

The initial stage in the nonlinear motion of a domain wall in garnet films

A study of the domain-wall motion in single-crystal garnet films of the YBiFeGa system with a perpendicular magnetic anisotropy, activated by a constant in-plane bias field H _p parallel to the wall plane and a pulsed drive field H _g of an amplitude corresponding to the nonlinear region of the domain-wall velocity vs. the H _g relation is reported. The earlier data suggesting the existence of an initial phase of motion, where the wall is accelerated to a high instantaneous velocity, have been confirmed. The wall behavior in the initial phase has been shown to be affected by the field H _p and the drive-field pulse rise time. A possible mechanism of the wall structure transformation after the application of the H _g pulse is considered. It has been established that the dependence of the wall velocity on H _p in the saturation region disagrees with theory.     

Localized Spectroscopy from Anatomically Matched Compartments: Improved Sensitivity and Localization for CardiacP MRS in Humans

Several pioneering studies have demonstrated that localized³¹P NMR spectroscopy of the human heart might become an important diagnostic tool in cardiology. The main limitation is due to the low sensitivity of these experiments, allowing only crude spatial resolution. We have implemented a three-dimensional version of SLOOP (“spectral localization with optimal pointspread function”) on a clinical instrument. SLOOP takes advantage of all availablea prioriinformation to match the size and the shape of the sensitive volumes to the anatomical structures in the examined subject. Thus, SLOOP reduces the contamination from adjacent organs and improves the sensitivity compared to conventional techniques such as ISIS or chemical shift imaging (CSI). Initial studies were performed on six healthy volunteers at 1.5 T. The good localization properties are demonstrated by the absence of resonances from blood in the heart spectra, and by PCr-free spectra from the liver. Compared to conventional CSI, the signal-to-noise ratio of the SLOOP heart spectra was improved by approximately 30%. Taking into account the varying excitation angle in the inhomogeneous B₁field of the surface coil, the SLOOP model computes the local spin saturation at every point in space. Therefore, no global saturation correction is required in the quantitative evaluation of local spectra. In this study, we found a PCr/γ-ATP ratio in the left ventricular wall of 1.90 ± 0.33 (mean ± standard deviation).     

Competition of two mechanisms of retardation of domain walls in the molecular ferrimagnet [Mn{(R/S)-pn}]2[Mn{(R/S-pn}2(H2O)][Cr(CN)6]2

The temperature dependence of the magnetization reversal dynamics of the chiral molecular ferrimagnet [Mn{(R/S)-pn}]₂[Mn{(R/S)-pn}₂(H₂O)][Cr(CN)₆]₂ has been studied at low frequencies of 1–1400 Hz, which are characteristic of the domain wall motion. It has been found from the Cole-Cole plots that domain walls undergo relaxation (at temperatures T > 10 K) and creep (at T < 10 K), and the main parameters determining these modes and the transition between them have been determined. It has been shown that the quantitative regularities of the transition between the modes of the domain wall motion correspond to the concepts of the competition between the contributions of two mechanisms to the domain wall retardation (the periodic Peierls relief and random structural defects).     

Combined effect of demagnetizing field and induced magnetic anisotropy on the magnetic properties of manganese-zinc ferrite composites

This work is devoted to the analysis of factors responsible for the high-frequency shift of the complex permeability (μ^?) dispersion region in polymer composites of manganese-zinc (MnZn) ferrite, as well as to the increase in their thermomagnetic stability. The magnetic spectra of the ferrite and its composites with polyurethane (MnZn-PU) and polyaniline (MnZn-PANI) are measured in the frequency range from 1 MHz to 3 GHz in a longitudinal magnetization field of up to 700 Ое and in the temperature interval from −20 °С to +150 °С. The approximation of the magnetic spectra by a model, which takes into account the role of domain wall motion and magnetization rotation, allows one to determine the specific contribution of resonance processes associated with domain wall motion and the natural ferromagnetic resonance to the μ^?. It is established that, at high frequencies, the μ^? of the MnZn ferrite is determined solely by magnetization rotation, which occurs in the region of natural ferromagnetic resonance when the ferrite is in the “single domain” state. In the polymer composites of the MnZn ferrite, the high-frequency permeability is also determined mainly by the magnetization rotation; however, up to high values of magnetizing fields, there is a contribution of domain wall motion, thus the “single domain” state in ferrite is not reached. The frequency and temperature dependence of μ^? in polymer composites are governed by demagnetizing field and the induced magnetic anisotropy. The contribution of the induced magnetic anisotropy is crucial for MnZn-PANI. It is attributed to the elastic stresses that arise due to the domain wall pinning by a polyaniline film adsorbed on the surface of the ferrite during in-situ polymerization.     

MRI of myocardial function: motion tracking techniques

Methods for the noninvasive measurement of three-dimensional myocardial motion with MRI have recently been developed using presaturation tagging and velocity-encoded phase maps. The quality of clinical cardiac MRI studies has also recently improved with the advent of breath-hold scanning. The combination of breath-hold imaging with tagging and velocity-encoding sequences has made the measurement of myocardial wall motion in patients a simple and reproducible exam. These methods make it possible to quantify the severity and extent of regional heart wall motion abnormalities both at rest and during stress. This article reviews the MRI techniques developed for these applications.     

B(1)(+)/actual flip angle and reception sensitivity mapping methods: simulation and comparison

Knowledge of the spatial distribution of transmission field B₁⁺ and reception sensitivity maps is important in high-field (≥3 T) human magnetic resonance (MR) imaging for several reasons: these include post-acquisition correction of intensity inhomogeneities, which may affect the quality of images; modeling and design of radiofrequency (RF) coils and pulses; validating theoretical models for electromagnetic field calculations; testing the compatibility with MR environment of biomedical implants. Moreover, inhomogeneities in the RF field are an essential source of error for quantitative MR spectroscopy. Recent studies have also shown that B₁⁺ and reception sensitivity maps can be used for direct calculation of tissue electrical parameters and for estimating the local specific absorption rate (SAR) in vivo.Several B₁⁺ mapping techniques have been introduced in the past few years based on actual flip angle (FA) mapping, but, to date, none has emerged as a standard. For reception sensitivity calculation, the signal intensity equation can be used where the nominal FA distribution must be replaced with the actual FA distribution calculated by one of the B₁⁺ mapping techniques.This study introduces a quantitative comparison between two known methods for B₁⁺/actual FA and reception sensitivity mapping: the double-angle method (DAM) and the fitting (FIT) method. Experimental data obtained using DAM and FIT methods are also compared with numerical simulation results.     

Tagged cine magnetic resonance imaging to quantify regional mechanical changes after acute myocardial infarction

PurposeThe conventional volumetric approaches of measuring cardiac function are load-dependent, and are not able to discriminate functional changes in the infarct, transition and remote myocardium. We examined phase-dependent regional mechanical changes in the infarct, transition and remote regions after acute myocardial infarction (MI) in a preclinical mouse model using cardiovascular magnetic resonance imaging (CMR).MethodsWe induced acute MI in six mice with left anterior descending coronary artery ligation. We then examined cardiac (infarct, transition and remote-zone) morphology and function utilizing 9.4 T high field CMR before and 2 weeks after the induction of acute MI. Myocardial scar tissue was evaluated by using CMR with late gadolinium enhancement (LGE). After determining global function through volumetric analysis, regional wall motion was evaluated by measuring wall thickening and radial velocities. Strain rate imaging was performed to assess circumferential contraction and relaxation at the myocardium, endocardium, and epicardium.ResultsThere was abnormal LGE in the anterior walls after acute MI suggesting a successful MI procedure. The transition zone consisted of a mixed signal intensity, while the remote zone contained viable myocardium. As expected, the infarct zone had demonstrated severely decreased myocardial velocities and strain rates, suggesting reduced contraction and relaxation function. Compared to pre-infarct baseline, systolic and diastolic velocities (v_S and v_D) were significantly reduced at the transition zone (v_S: −1.86 ± 0.16 cm/s vs −0.68 ± 0.13 cm/s, P < 0.001; v_D: 1.86 ± 0.17 cm/s vs 0.53 ± 0.06 cm/s, P < 0.001) and remote zone (v_S: −1.86 ± 0.16 cm/s vs −0.65 ± 0.12 cm/s, P < 0.001; v_D: 1.86 ± 0.16 cm/s vs 0.51 ± 0.04 cm/s, P < 0.001). Myocardial peak systolic and diastolic strain rates (SR_S and SR_D) were significantly lower in the transition zone (SR_S: −4.2 ± 0.3 s⁻¹ vs −1.3 ± 0.2 s⁻¹, P < 0.001; SR_D: 3.9 ± 0.3 s⁻¹ vs 1.3 ± 0.2 s⁻¹, P < 0.001) and remote zone (SR_S: −3.8 ± 0.3 s⁻¹ vs −1.4 ± 0.3 s⁻¹, P < 0.001; SR_D: 3.5 ± 0.2 s⁻¹ vs 1.5 ± 0.4 s⁻¹, P = 0.006). Endocardial and epicardial SR_S and SR_D were similarly reduced in the transition and remote zones compared to baseline.ConclusionsThis study, for the first time, utilized state-of-the art high-field CMR algorithms in a preclinical mouse model for a comprehensive and controlled evaluation of the regional mechanical changes in the transition and remote zones, after acute MI. Our data demonstrate that CMR can quantitatively monitor dynamic post-MI remodeling in the transition and remote zones, thereby serving as a gold standard tool for therapeutic surveillance.     

Correction of out-of-FOV motion artifacts using convolutional neural network

PurposeSubject motion during MRI scan can result in severe degradation of image quality. Existing motion correction algorithms rely on the assumption that no information is missing during motions. However, this assumption does not hold when out-of-FOV motion happens. Currently available algorithms are not able to correct for image artifacts introduced by out-of-FOV motion. The purpose of this study is to demonstrate the feasibility of incorporating convolutional neural network (CNN) derived prior image into solving the out-of-FOV motion problem.Methods and materialsA modified U-net network was proposed to correct out-of-FOV motion artifacts by incorporating motion parameters into the loss function. A motion model based data fidelity term was applied in combination with the CNN prediction to further improve the motion correction performance. We trained the CNN on 1113 MPRAGE images with simulated oscillating and sudden motion trajectories, and compared our algorithm to a gradient-based autofocusing (AF) algorithm in both 2D and 3D images. Additional experiment was performed to demonstrate the feasibility of transferring the networks to different dataset. We also evaluated the robustness of this algorithm by adding Gaussian noise to the motion parameters. The motion correction performance was evaluated using mean square error (NMSE), peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM).ResultsThe proposed algorithm outperformed AF-based algorithm for both 2D (NMSE: 0.0066 ± 0.0009 vs 0.0141 ± 0.008, P < .01; PSNR: 29.60 ± 0.74 vs 21.71 ± 0.27, P < .01; SSIM: 0.89 ± 0.014 vs 0.73 ± 0.004, P < .01) and 3D imaging (NMSE: 0.0067 ± 0.0008 vs 0.070 ± 0.021, P < .01; PSNR: 32.40 ± 1.63 vs 22.32 ± 2.378, P < .01; SSIM: 0.89 ± 0.01 vs 0.62 ± 0.03, P < .01). Robust reconstruction was achieved with 20% data missed due to the out-of-FOV motion.ConclusionIn conclusion, the proposed CNN-based motion correction algorithm can significantly reduce out-of-FOV motion artifacts and achieve better image quality compared to AF-based algorithm.