Single-breath-hold 3-D CINE imaging of the left ventricle using Cartesian sampling

Analysis of confounders of the image quality of a high-resolution isotropic three-dimensional Dixon water-fat late gadolinium enhancement technique

BACKGROUND

Three-dimensional (3D) water-fat separated late gadolinium enhancement (LGE) imaging is a cardiovascular magnetic resonance imaging technique allowing simultaneous assessment of and discrimination between cardiac fibrosis and myocardial fatty infiltration. The aim of this study is to systematically analyze the image quality of a 3D water-fat separated LGE research sequence and identify confounders of image quality METHODS: In total, 126 patients and 12 healthy volunteers were included. Patients were included with inflammatory bowel disease (n=35), muscular dystrophy (n=38), hypertrophic cardiomyopathy (n=23) and paroxysmal atrial fibrillation (n=30). 3D water-fat separated LGE images were acquired at 1.5T (n=122) or 3T (n=16). Image quality was subjectively rated (4-point Likert scale) in six categories (overall image quality [OV], blood-myocardium border sharpness, LGE-remote/healthy myocardium border sharpness, fat suppression, myocardial nulling [MN], anatomical structures [AS]), additionally, the contrast ratio was calculated. Cardiac function, acquisition conditions, and demographic data were investigated as potential confounders for image quality and contrast ratio.

RESULTS

Fat suppression had the highest quality score (2.54±0.72), followed by AS (2.11±0.94) and MN (2.01±0.78). In total, 18 parameters showed a significant correlation with multiple image quality categories, most of which related to cardiac function, such as the cardiac index, which significantly correlated with OV (Wald Chi-squared=4.35; p<0.05), LGE-remote/healthy myocardium border sharpness (Wald Chi-squared=5.03; p<0.05), and AS (Wald Chi-square=16.00; p<0.001). Left ventricular mass index to height showed significant correlation with OV (Wald Chi-squared=7.57; p<0.01), blood-myocardium border sharpness (Wald Chi-squared=7.35; p<0.01), and contrast ratio (Wald Chi-squared=5.50; p<0.05). Furthermore, demographic parameters, such as body mass index (BMI), were identified as significant confounders, showing a notable correlation between BMI and the depiction of AS. (Wald Chi-square=11.14; p<0.01).

CONCLUSION

In this study, 3D water-fat separated LGE imaging shows satifactory image quality, especially for water-fat separation. However, image quality may be affected by several other parameters such as patient obesity, high myocardial mass, and cardiac function. Trial Registration: 3000339.

A review of deep learning-based reconstruction methods for accelerated MRI using spatiotemporal and multi-contrast redundancies

Accelerated magnetic resonance imaging (MRI) has played an essential role in reducing data acquisition time for MRI. Acceleration can be achieved by acquiring fewer data points in k-space, which results in various artifacts in the image domain. Conventional reconstruction methods have resolved the artifacts by utilizing multi-coil information, but with limited robustness. Recently, numerous deep learning-based reconstruction methods have been developed, enabling outstanding reconstruction performances with higher acceleration. Advances in hardware and developments of specialized network architectures have produced such achievements. Besides, MRI signals contain various redundant information including multi-coil redundancy, multi-contrast redundancy, and spatiotemporal redundancy. Utilization of the redundant information combined with deep learning approaches allow not only higher acceleration, but also well-preserved details in the reconstructed images. Consequently, this review paper introduces the basic concepts of deep learning and conventional accelerated MRI reconstruction methods, followed by review of recent deep learning-based reconstruction methods that exploit various redundancies. Lastly, the paper concludes by discussing the challenges, limitations, and potential directions of future developments.

Multi-class point cloud completion networks for 3D cardiac anatomy reconstruction from cine magnetic resonance images

Cine magnetic resonance imaging (MRI) is the current gold standard for the assessment of cardiac anatomy and function. However, it typically only acquires a set of two-dimensional (2D) slices of the underlying three-dimensional (3D) anatomy of the heart, thus limiting the understanding and analysis of both healthy and pathological cardiac morphology and physiology. In this paper, we propose a novel fully automatic surface reconstruction pipeline capable of reconstructing multi-class 3D cardiac anatomy meshes from raw cine MRI acquisitions. Its key component is a multi-class point cloud completion network (PCCN) capable of correcting both the sparsity and misalignment issues of the 3D reconstruction task in a unified model. We first evaluate the PCCN on a large synthetic dataset of biventricular anatomies and observe Chamfer distances between reconstructed and gold standard anatomies below or similar to the underlying image resolution for multiple levels of slice misalignment. Furthermore, we find a reduction in reconstruction error compared to a benchmark 3D U-Net by 32% and 24% in terms of Hausdorff distance and mean surface distance, respectively. We then apply the PCCN as part of our automated reconstruction pipeline to 1000 subjects from the UK Biobank study in a cross-domain transfer setting and demonstrate its ability to reconstruct accurate and topologically plausible biventricular heart meshes with clinical metrics comparable to the previous literature. Finally, we investigate the robustness of our proposed approach and observe its capacity to successfully handle multiple common outlier conditions.

A new compressed sensing cine cardiac MRI sequence with free-breathing real-time acquisition and fully automated motion-correction: A comprehensive evaluation

PURPOSE

The purpose of this study was to compare a new free-breathing compressed sensing cine (FB-CS) cardiac magnetic resonance imaging (CMR) to the standard reference multi-breath-hold segmented cine (BH-SEG) CMR in an unselected population.

MATERIALS AND METHODS

From January to April 2021, 52 consecutive adult patients who underwent both conventional BH-SEG CMR and new FB-CS CMR with fully automated respiratory motion correction were retrospectively enrolled. There were 29 men and 23 women with a mean age of 57.7 ± 18.9 (standard deviation [SD]) years (age range: 19.0-90.0 years) and a mean cardiac rate of 74.6 ± 17.9 (SD) bpm. For each patient, short-axis stacks were acquired with similar parameters providing a spatial resolution of 1.8 × 1.8 × 8.0 mm3 and 25 cardiac frames. Acquisition and reconstruction times, image quality (Likert scale from 1 to 4), left and right ventricular volumes and ejection fractions, left ventricular mass, and global circumferential strain were assessed for each sequence.

RESULTS

FB-CS CMR acquisition time was significantly shorter (123.8 ± 28.4 [SD] s vs. 267.2 ± 39.3 [SD] s for BH-SEG CMR; P < 0.0001) at the penalty of a longer reconstruction time (271.4 ± 68.7 [SD] s vs. 9.9 ± 2.1 [SD] s for BH-SEG CMR; P < 0.0001). In patients without arrhythmia or dyspnea, FB-CS CMR provided subjective image quality that was not different from that of BH-SEG CMR (P = 0.13). FB-CS CMR improved image quality in patients with arrhythmia (n = 18; P = 0.002) or dyspnea (n = 7; P = 0.02), and the edge sharpness was improved at end-systole and end-diastole (P = 0.0001). No differences were observed between the two techniques in ventricular volumes and ejection fractions, left ventricular mass or global circumferential strain in patients in sinus rhythm or with cardiac arrhythmia.

CONCLUSION

This new FB-CS CMR addresses respiratory motion and arrhythmia-related artifacts without compromising the reliability of ventricular functional assessment.

Deep Learning-Based Reconstruction for Cardiac MRI: A Review

Cardiac magnetic resonance (CMR) is an essential clinical tool for the assessment of cardiovascular disease. Deep learning (DL) has recently revolutionized the field through image reconstruction techniques that allow unprecedented data undersampling rates. These fast acquisitions have the potential to considerably impact the diagnosis and treatment of cardiovascular disease. Herein, we provide a comprehensive review of DL-based reconstruction methods for CMR. We place special emphasis on state-of-the-art unrolled networks, which are heavily based on a conventional image reconstruction framework. We review the main DL-based methods and connect them to the relevant conventional reconstruction theory. Next, we review several methods developed to tackle specific challenges that arise from the characteristics of CMR data. Then, we focus on DL-based methods developed for specific CMR applications, including flow imaging, late gadolinium enhancement, and quantitative tissue characterization. Finally, we discuss the pitfalls and future outlook of DL-based reconstructions in CMR, focusing on the robustness, interpretability, clinical deployment, and potential for new methods.

A 72-channel receive array coil allows whole-heart cine MRI in two breath holds

BACKGROUND

A new 72-channel receive array coil and sensitivity encoding, compressed (C-SENSE) and noncompressed (SENSE), were investigated to decrease the number of breath-holds (BHs) for cardiac magnetic resonance (CMR).

METHODS

Three-T CMRs were performed using the 72-channel coil with SENSE-2/4/6 and C-SENSE-2/4/6 accelerated short-axis cine two-dimensional balanced steady-state free precession sequences. A 16-channel coil with SENSE-2 served as reference. Ten healthy subjects were included. BH-time was kept under 15 s. Data were compared in terms of image quality, biventricular function, number of BHs, and scan times.

RESULTS

BHs decreased from 7 with C-SENSE-2 (scan time 70 s, 2 slices/BH) to 3 with C-SENSE-4 (scan time 42 s, 4-5 slices/BH) and 2 with C-SENSE-6 (scan time 28 s, 7 slices/BH). Compared to reference, image sharpness was similar for SENSE-2/4/6, slightly inferior for C-SENSE-2/4/6. Blood-to-myocardium contrast was unaffected. C-SENSE-4/6 was given lower qualitative median scores, but images were considered diagnostically adequate to excellent, with C-SENSE-6 suboptimal. Biventricular end-diastolic (EDV), end-systolic (ESV) and stroke volumes, ejection fractions (EF), cardiac outputs, and left ventricle (LV)-mass were similar for SENSE-2/4/6 with no systematic bias and clinically appropriate limits of agreements. C-SENSE slightly underestimated LV-EDV (-6.38 ± 6.0 mL, p < 0.047), LV-ESV (-7.94 ± 6.0 mL, p < 0.030) and overestimated LV-EF (3.16 ± 3.10%; p < 0.047) with C-SENSE-4. Bland-Altman analyses revealed minor systematic biases in these variables with C-SENSE-2/4/6 and for LV-mass with C-SENSE-6.

CONCLUSIONS

Using the 72-channel coil, short-axis CMR for quantifying biventricular function was feasible in two BHs where SENSE slightly outperformed C-SENSE.

Simultaneous multi-parametric acquisition and reconstruction techniques in cardiac magnetic resonance imaging: Basic concepts and status of clinical development

Simultaneous multi-parametric acquisition and reconstruction techniques (SMART) are gaining attention for their potential to overcome some of cardiovascular magnetic resonance imaging's (CMR) clinical limitations. The major advantages of SMART lie within their ability to simultaneously capture multiple "features" such as cardiac motion, respiratory motion, T1/T2 relaxation. This review aims to summarize the overarching theory of SMART, describing key concepts that many of these techniques share to produce co-registered, high quality CMR images in less time and with less requirements for specialized personnel. Further, this review provides an overview of the recent developments in the field of SMART by describing how they work, the parameters they can acquire, their status of clinical testing and validation, and by providing examples for how their use can improve the current state of clinical CMR workflows. Many of the SMART are in early phases of development and testing, thus larger scale, controlled trials are needed to evaluate their use in clinical setting and with different cardiac pathologies.

Isotropic 3D compressed sensing (CS) based sequence is comparable to 2D-LGE in left ventricular scar quantification in different disease entities

The goal of this study was to evaluate a three-dimensional compressed sensing (3D-CS) LGE prototype sequence for the detection and quantification of myocardial fibrosis in patients with chronic myocardial infarction (CMI) and myocarditis (MYC) compared with a 2D-LGE standard. Patients with left-ventricular LGE due to CMI (n = 33) or MYC (n = 20) were prospectively recruited. 2D-LGE and 3D-CS images were acquired in random order at 1.5 Tesla. 3D-CS short axis (SAX) images were reconstructed corresponding to 2D SAX images. LGE was quantitatively assessed on patient and segment level using semi-automated threshold methods. Image quality (4-point scoring system), Contrast-ratio (CR) and acquisition times were compared. There was no significant difference between 2D and 3D sequences regarding global LGE (%) (CMI [2D-LGE: 11.4 ± 7.5; 3D-LGE: 11.5 ± 8.5; p = 0.99]; MYC [2D-LGE: 27.0 ± 15.7; 3D-LGE: 26.2 ± 13.1; p = 0.70]) and segmental LGE-extent (p = 0.63). 3D-CS identified papillary infarction in 5 cases which was not present in 2D images. 2D-LGE acquisition time was shorter (2D: median: 06:59 min [IQR: 05:51-08:18]; 3D: 14:48 min [12:45-16:57]). 3D-CS obtained better quality scores (2D: 2.06 ± 0.56 vs. 3D: 2.29 ± 0.61). CR did not differ (p = 0.63) between basal and apical regions in 3D-CS images but decreased significantly in 2D apical images (CR basal: 2D: 0.77 ± 0.11, 3D: 0.59 ± 0.10; CR apical: 2D: 0.64 ± 0.17, 3D: 0.53 ± 0.11). 3D-LGE shows high congruency with standard LGE and allows better identification of small lesions. However, the current 3D-CS LGE sequence did not provide PSIR reconstruction and acquisition time was longer.

Cardiac MR: From Theory to Practice

Cardiovascular disease (CVD) is the leading single cause of morbidity and mortality, causing over 17. 9 million deaths worldwide per year with associated costs of over $800 billion. Improving prevention, diagnosis, and treatment of CVD is therefore a global priority. Cardiovascular magnetic resonance (CMR) has emerged as a clinically important technique for the assessment of cardiovascular anatomy, function, perfusion, and viability. However, diversity and complexity of imaging, reconstruction and analysis methods pose some limitations to the widespread use of CMR. Especially in view of recent developments in the field of machine learning that provide novel solutions to address existing problems, it is necessary to bridge the gap between the clinical and scientific communities. This review covers five essential aspects of CMR to provide a comprehensive overview ranging from CVDs to CMR pulse sequence design, acquisition protocols, motion handling, image reconstruction and quantitative analysis of the obtained data. (1) The basic MR physics of CMR is introduced. Basic pulse sequence building blocks that are commonly used in CMR imaging are presented. Sequences containing these building blocks are formed for parametric mapping and functional imaging techniques. Commonly perceived artifacts and potential countermeasures are discussed for these methods. (2) CMR methods for identifying CVDs are illustrated. Basic anatomy and functional processes are described to understand the cardiac pathologies and how they can be captured by CMR imaging. (3) The planning and conduct of a complete CMR exam which is targeted for the respective pathology is shown. Building blocks are illustrated to create an efficient and patient-centered workflow. Further strategies to cope with challenging patients are discussed. (4) Imaging acceleration and reconstruction techniques are presented that enable acquisition of spatial, temporal, and parametric dynamics of the cardiac cycle. The handling of respiratory and cardiac motion strategies as well as their integration into the reconstruction processes is showcased. (5) Recent advances on deep learning-based reconstructions for this purpose are summarized. Furthermore, an overview of novel deep learning image segmentation and analysis methods is provided with a focus on automatic, fast and reliable extraction of biomarkers and parameters of clinical relevance.

A completely automated pipeline for 3D reconstruction of human heart from 2D cine magnetic resonance slices

Cardiac magnetic resonance (CMR) imaging is a valuable modality in the diagnosis and characterization of cardiovascular diseases, since it can identify abnormalities in structure and function of the myocardium non-invasively and without the need for ionizing radiation. However, in clinical practice, it is commonly acquired as a collection of separated and independent 2D image planes, which limits its accuracy in 3D analysis. This paper presents a completely automated pipeline for generating patient-specific 3D biventricular heart models from cine magnetic resonance (MR) slices. Our pipeline automatically selects the relevant cine MR images, segments them using a deep learning-based method to extract the heart contours, and aligns the contours in 3D space correcting possible misalignments due to breathing or subject motion first using the intensity and contours information from the cine data and next with the help of a statistical shape model. Finally, the sparse 3D representation of the contours is used to generate a smooth 3D biventricular mesh. The computational pipeline is applied and evaluated in a CMR dataset of 20 healthy subjects. Our results show an average reduction of misalignment artefacts from 1.82 ± 1.60 mm to 0.72 ± 0.73 mm over 20 subjects, in terms of distance from the final reconstructed mesh. The high-resolution 3D biventricular meshes obtained with our computational pipeline are used for simulations of electrical activation patterns, showing agreement with non-invasive electrocardiographic imaging. The automatic methodologies presented here for patient-specific MR imaging-based 3D biventricular representations contribute to the efficient realization of precision medicine, enabling the enhanced interpretability of clinical data, the digital twin vision through patient-specific image-based modelling and simulation, and augmented reality applications. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.

Deep Learning-Based ECG-Free Cardiac Navigation for Multi-Dimensional and Motion-Resolved Continuous Magnetic Resonance Imaging

For the clinical assessment of cardiac vitality, time-continuous tomographic imaging of the heart is used. To further detect e.g., pathological tissue, multiple imaging contrasts enable a thorough diagnosis using magnetic resonance imaging (MRI). For this purpose, time-continous and multi-contrast imaging protocols were proposed. The acquired signals are binned using navigation approaches for a motion-resolved reconstruction. Mostly, external sensors such as electrocardiograms (ECG) are used for navigation, leading to additional workflow efforts. Recent sensor-free approaches are based on pipelines requiring prior knowledge, e.g., typical heart rates. We present a sensor-free, deep learning-based navigation that diminishes the need for manual feature engineering or the necessity of prior knowledge compared to previous works. A classifier is trained to estimate the R-wave timepoints in the scan directly from the imaging data. Our approach is evaluated on 3-D protocols for continuous cardiac MRI, acquired in-vivo and free-breathing with single or multiple imaging contrasts. We achieve an accuracy of > 98% on previously unseen subjects, and a well comparable image quality with the state-of-the-art ECG-based reconstruction. Our method enables an ECG-free workflow for continuous cardiac scans with simultaneous anatomic and functional imaging with multiple contrasts. It can be potentially integrated without adapting the sampling scheme to other continuous sequences by using the imaging data for navigation and reconstruction.

Compressed Sensing Real-Time Cine Reduces CMR Arrhythmia-Related Artifacts

Background and objective: Cardiac magnetic resonance (CMR) is a key tool for cardiac work-up. However, arrhythmia can be responsible for arrhythmia-related artifacts (ARA) and increased scan time using segmented sequences. The aim of this study is to evaluate the effect of cardiac arrhythmia on image quality in a comparison of a compressed sensing real-time (CS_rt) cine sequence with the reference prospectively gated segmented balanced steady-state free precession (Cine_ref) technique regarding ARA. Methods: A total of 71 consecutive adult patients (41 males; mean age = 59.5 ± 20.1 years (95% CI: 54.7–64.2 years)) referred for CMR examination with concomitant irregular heart rate (defined by an RR interval coefficient of variation >10%) during scanning were prospectively enrolled. For each patient, two cine sequences were systematically acquired: first, the reference prospectively triggered multi-breath-hold Cine_ref sequence including a short-axis stack, one four-chamber slice, and a couple of two-chamber slices; second, an additional single breath-hold CS_rt sequence providing the same slices as the reference technique. Two radiologists independently assessed ARA and image quality (overall, acquisition, and edge sharpness) for both techniques. Results: The mean heart rate was 71.8 ± 19.0 (SD) beat per minute (bpm) (95% CI: 67.4–76.3 bpm) and its coefficient of variation was 25.0 ± 9.4 (SD) % (95% CI: 22.8–27.2%). Acquisition was significantly faster with CS_rt than with Cine_ref (Cine_ref: 556.7 ± 145.4 (SD) s (95% CI: 496.7–616.7 s); CS_rt: 23.9 ± 7.9 (SD) s (95% CI: 20.6–27.1 s); p < 0.0001). A total of 599 pairs of cine slices were evaluated (median: 8 (range: 6–14) slices per patient). The mean proportion of ARA-impaired slices per patient was 85.9 ± 22.7 (SD) % using Cine_ref, but this was figure was zero using CS_rt (p < 0.0001). The European CMR registry artifact score was lower with CS_rt (median: 1 (range: 0–5)) than with Cine_ref (median: 3 (range: 0–3); p < 0.0001). Subjective image quality was higher in CS_rt than in Cine_ref (median: 3 (range: 1–3) versus 2 (range: 1–4), respectively; p < 0.0001). In line, edge sharpness was higher on CS_rt cine than on Cine_ref images (0.054 ± 0.016 pixel⁻¹ (95% CI: 0.050–0.057 pixel⁻¹) versus 0.042 ± 0.022 pixel⁻¹ (95% CI: 0.037–0.047 pixel⁻¹), respectively; p = 0.0001). Conclusion: Compressed sensing real-time cine drastically reduces arrhythmia-related artifacts and thus improves cine image quality in patients with arrhythmia.

60-S Retrogated Compressed Sensing 2D Cine of the Heart: Sharper Borders and Accurate Quantification

Background and objective: Real-time compressed sensing cine (CS_rt) provides reliable quantification for both ventricles but may alter image quality. The aim of this study was to assess image quality and the accuracy of left (LV) and right ventricular (RV) volumes, ejection fraction and mass quantifications based on a retrogated segmented compressed sensing 2D cine sequence (CS_rg). Methods: Thirty patients were enrolled. Each patient underwent the reference retrogated segmented steady-state free precession cine sequence (SSFP_ref), the real-time CS_rt cine and the segmented retrogated prototype CS_rg sequence providing the same slices. Functional parameters quantification and image quality rating were performed on SSFP_ref and CS_rg images sets. The edge sharpness, which is an estimate of the edge spread function, was assessed for the three sequences. Results: The mean scan time was: SSFP_ref = 485.4 ± 83.3 (SD) s (95% CI: 454.3–516.5) and CS_rg = 58.3 ± 15.1 (SD) s (95% CI: 53.7–64.2) (p < 0.0001). CS_rg subjective image quality score (median: 4; range: 2–4) was higher than the one provided by CS_rt (median: 3; range: 2–4; p = 0.0008) and not different from SSFP_ref overall quality score (median: 4; range: 2–4; p = 0.31). CS_rg provided similar LV and RV functional parameters to those assessed with SSFP_ref (p > 0.05). Edge sharpness was significantly better with CS_rg (0.083 ± 0.013 (SD) pixel⁻¹; 95% CI: 0.078–0.087) than with CS_rt (0.070 ± 0.011 (SD) pixel⁻¹; 95% CI: 0.066–0.074; p = 0.0004) and not different from the reference technique (0.075 ± 0.016 (SD) pixel⁻¹; 95% CI: 0.069–0.081; p = 0.0516). Conclusions: CS_rg cine provides in one minute an accurate quantification of LV and RV functional parameters without compromising subjective and objective image quality.

Right Ventricular Volume and Function Assessment in Congenital Heart Disease Using CMR Compressed-Sensing Real-Time Cine Imaging

Background and objective: To evaluate the reliability of compressed-sensing (CS) real-time single-breath-hold cine imaging for quantification of right ventricular (RV) function and volumes in congenital heart disease (CHD) patients in comparison with the standard multi-breath-hold technique. Methods: Sixty-one consecutive CHD patients (mean age = 22.2 ± 9.0 (SD) years) were prospectively evaluated during either the initial work-up or after repair. For each patient, two series of cine images were acquired: first, the reference segmented multi-breath-hold steady-state free-precession sequence (SSFP_ref), including a short-axis stack, one four-chamber slice, and one long-axis slice; then, an additional real-time compressed-sensing single-breath-hold sequence (CS_rt) providing the same slices. Two radiologists independently assessed the image quality and RV volumes for both techniques, which were compared using the Wilcoxon test and paired Student’s t test, Bland–Altman, and linear regression analyses. The visualization of wall-motion disorders and tricuspid-regurgitation-related signal voids were also analyzed. Results: The mean acquisition time for CS_rt was 22.4 ± 6.2 (SD) s (95% CI: 20.8–23.9 s) versus 442.2 ± 89.9 (SD) s (95% CI: 419.2–465.2 s) for SSFP_ref (p < 0.001). The image quality of CS_rt was diagnostic in all examinations and was mostly rated as good (n = 49/61; 80.3%). There was a high correlation between SSFP_ref and CS_rt images regarding RV ejection fraction (49.8 ± 7.8 (SD)% (95% CI: 47.8–51.8%) versus 48.7 ± 8.6 (SD)% (95% CI: 46.5–50.9%), respectively; r = 0.94) and RV end-diastolic volume (192.9 ± 60.1 (SD) mL (95% CI: 177.5–208.3 mL) versus 194.9 ± 62.1 (SD) mL (95% CI: 179.0–210.8 mL), respectively; r = 0.98). In CS_rt images, tricuspid-regurgitation and wall-motion disorder visualization was good (area under receiver operating characteristic curve (AUC) = 0.87) and excellent (AUC = 1), respectively. Conclusions: Compressed-sensing real-time cine imaging enables, in one breath hold, an accurate assessment of RV function and volumes in CHD patients in comparison with standard SSFP_ref, allowing a substantial improvement in time efficiency.

Clinical Validation of a 3-Dimensional Ultrafast Cardiac Magnetic Resonance Protocol Including Single Breath-Hold 3-Dimensional Sequences

OBJECTIVES

This study sought to clinically validate a novel 3-dimensional (3D) ultrafast cardiac magnetic resonance (CMR) protocol including cine (anatomy and function) and late gadolinium enhancement (LGE), each in a single breath-hold.

BACKGROUND

CMR is the reference tool for cardiac imaging but is time-consuming.

METHODS

A protocol comprising isotropic 3D cine (Enhanced sensitivity encoding [SENSE] by Static Outer volume Subtraction [ESSOS]) and isotropic 3D LGE sequences was compared with a standard cine+LGE protocol in a prospective study of 107 patients (age 58 ± 11 years; 24% female). Left ventricular (LV) mass, volumes, and LV and right ventricular (RV) ejection fraction (LVEF, RVEF) were assessed by 3D ESSOS and 2D cine CMR. LGE (% LV) was assessed using 3D and 2D sequences.

RESULTS

Three-dimensional and LGE acquisitions lasted 24 and 22 s, respectively. Three-dimensional and LGE images were of good quality and allowed quantification in all cases. Mean LVEF by 3D and 2D CMR were 51 ± 12% and 52 ± 12%, respectively, with excellent intermethod agreement (intraclass correlation coefficient [ICC]: 0.96; 95% confidence interval [CI]: 0.94 to 0.97) and insignificant bias. Mean RVEF 3D and 2D CMR were 60.4 ± 5.4% and 59.7 ± 5.2%, respectively, with acceptable intermethod agreement (ICC: 0.73; 95% CI: 0.63 to 0.81) and insignificant bias. Both 2D and 3D LGE showed excellent agreement, and intraobserver and interobserver agreement were excellent for 3D LGE.

CONCLUSIONS

ESSOS single breath-hold 3D CMR allows accurate assessment of heart anatomy and function. Combining ESSOS with 3D LGE allows complete cardiac examination in <1 min of acquisition time. This protocol expands the indication for CMR, reduces costs, and increases patient comfort.

Retrospective respiratory motion correction in cardiac cine MRI reconstruction using adversarial autoencoder and unsupervised learning

The aim of this study was to develop a deep neural network for respiratory motion compensation in free-breathing cine MRI and evaluate its performance. An adversarial autoencoder network was trained using unpaired training data from healthy volunteers and patients who underwent clinically indicated cardiac MRI examinations. A U-net structure was used for the encoder and decoder parts of the network and the code space was regularized by an adversarial objective. The autoencoder learns the identity map for the free-breathing motion-corrupted images and preserves the structural content of the images, while the discriminator, which interacts with the output of the encoder, forces the encoder to remove motion artifacts. The network was first evaluated based on data that were artificially corrupted with simulated rigid motion with regard to motion-correction accuracy and the presence of any artificially created structures. Subsequently, to demonstrate the feasibility of the proposed approach in vivo, our network was trained on respiratory motion-corrupted images in an unpaired manner and was tested on volunteer and patient data. In the simulation study, mean structural similarity index scores for the synthesized motion-corrupted images and motion-corrected images were 0.76 and 0.93 (out of 1), respectively. The proposed method increased the Tenengrad focus measure of the motion-corrupted images by 12% in the simulation study and by 7% in the in vivo study. The average overall subjective image quality scores for the motion-corrupted images, motion-corrected images and breath-held images were 2.5, 3.5 and 4.1 (out of 5.0), respectively. Nonparametric-paired comparisons showed that there was significant difference between the image quality scores of the motion-corrupted and breath-held images (P < .05); however, after correction there was no significant difference between the image quality scores of the motion-corrected and breath-held images. This feasibility study demonstrates the potential of an adversarial autoencoder network for correcting respiratory motion-related image artifacts without requiring paired data.

Fully self-gated free-running 3D Cartesian cardiac CINE with isotropic whole-heart coverage in less than 2 min

PURPOSE

To develop a novel fast water-selective free-breathing 3D Cartesian cardiac CINE scan with full self-navigation and isotropic whole-heart (WH) coverage.

METHODS

A free-breathing 3D Cartesian cardiac CINE scan with a water-selective balanced steady-state free precession and a continuous (non-ECG-gated) variable-density Cartesian sampling with spiral profile ordering, out-inward sampling and acquisition-adaptive alternating tiny golden and golden angle increment between spiral arms is proposed. Data is retrospectively binned based on respiratory and cardiac self-navigation signals. A translational respiratory-motion-corrected and cardiac-motion-resolved image is reconstructed with a multi-bin patch-based low-rank reconstruction (MB-PROST) within about 15 min. A respiratory-motion-resolved approach is also investigated. The proposed 3D Cartesian cardiac CINE is acquired in sagittal orientation in 1 min 50 s for 1.9 mm³ isotropic WH coverage. Left ventricular (LV) function parameters and image quality derived from a blinded reading of the proposed 3D CINE framework are compared against conventional multi-slice 2D CINE imaging in 10 healthy subjects and 10 patients with suspected cardiovascular disease.

RESULTS

The proposed framework provides free-breathing 3D cardiac CINE images with 1.9 mm³ spatial and about 45 ms temporal resolution in a short acquisition time (<2 min). LV function parameters derived from 3D CINE were in good agreement with 2D CINE (10 healthy subjects and 10 patients). Bias and confidence intervals were obtained for end-systolic volume, end-diastolic volume and ejection fraction of 0.1 ± 3.5 mL, -0.6 ± 8.2 mL and -0.1 ± 2.2%, respectively.

CONCLUSION

The proposed framework enables isotropic 3D Cartesian cardiac CINE under free breathing for fast assessment of cardiac anatomy and function.

Single breath-hold saturation recovery 3D cardiac T1 mapping via compressed SENSE at 3T

Objectives

To propose and validate a novel imaging sequence that uses a single breath-hold whole-heart 3D T1 saturation recovery compressed SENSE rapid acquisition (SACORA) at 3T.

Methods

The proposed sequence combines flexible saturation time sampling, compressed SENSE, and sharing of saturation pulses between two readouts acquired at different RR intervals. The sequence was compared with a 3D saturation recovery single-shot acquisition (SASHA) implementation with phantom and in vivo experiments (pre and post contrast; 7 pigs) and was validated against the reference inversion recovery spin echo (IR-SE) sequence in phantom experiments.

Results

Phantom experiments showed that the T1 maps acquired by 3D SACORA and 3D SASHA agree well with IR-SE. In vivo experiments showed that the pre-contrast and post-contrast T1 maps acquired by 3D SACORA are comparable to the corresponding 3D SASHA maps, despite the shorter acquisition time (15s vs. 188s, for a heart rate of 60 bpm). Mean septal pre-contrast T1 was 1453 ± 44 ms with 3D SACORA and 1460 ± 60 ms with 3D SASHA. Mean septal post-contrast T1 was 824 ± 66 ms and 824 ± 60 ms.

Conclusion

3D SACORA acquires 3D T1 maps in 15 heart beats (heart rate, 60 bpm) at 3T. In addition to its short acquisition time, the sequence achieves good T1 estimation precision and accuracy.

Electronic supplementary material

The online version of this article (10.1007/s10334-020-00848-2) contains supplementary material, which is available to authorized users.

CINENet: deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions

Cardiac CINE magnetic resonance imaging is the gold-standard for the assessment of cardiac function. Imaging accelerations have shown to enable 3D CINE with left ventricular (LV) coverage in a single breath-hold. However, 3D imaging remains limited to anisotropic resolution and long reconstruction times. Recently deep learning has shown promising results for computationally efficient reconstructions of highly accelerated 2D CINE imaging. In this work, we propose a novel 4D (3D + time) deep learning-based reconstruction network, termed 4D CINENet, for prospectively undersampled 3D Cartesian CINE imaging. CINENet is based on (3 + 1)D complex-valued spatio-temporal convolutions and multi-coil data processing. We trained and evaluated the proposed CINENet on in-house acquired 3D CINE data of 20 healthy subjects and 15 patients with suspected cardiovascular disease. The proposed CINENet network outperforms iterative reconstructions in visual image quality and contrast (+ 67% improvement). We found good agreement in LV function (bias ± 95% confidence) in terms of end-systolic volume (0 ± 3.3 ml), end-diastolic volume (− 0.4 ± 2.0 ml) and ejection fraction (0.1 ± 3.2%) compared to clinical gold-standard 2D CINE, enabling single breath-hold isotropic 3D CINE in less than 10 s scan and ~ 5 s reconstruction time.

Isotropic 3D Cartesian single breath-hold CINE MRI with multi-bin patch-based low-rank reconstruction

PURPOSE

To develop a novel acquisition and reconstruction framework for isotropic 3D Cartesian cardiac CINE within a single breath-hold for left ventricle (LV) and whole-heart coverage.

METHODS

A variable-density Cartesian acquisition with spiral profile ordering, out-inward sampling, and acquisition-adaptive alternating tiny golden/golden angle increment between spiral arms is proposed to provide incoherent and nonredundant sampling within and among cardiac phases. A novel multi-bin patch-based low-rank reconstruction, named MB-PROST, is proposed to exploit redundant information on a local (within a patch), nonlocal (similar patches within a spatial neighborhood), and temporal (among all cardiac phases) scale with an implicit motion alignment among patches. The proposed multi-bin patch-based low-rank reconstruction reconstruction is compared against compressed sensing reconstruction, whereas LV function parameters derived from the proposed 3D CINE framework are compared against those estimated from conventional multislice 2D CINE imaging in 10 healthy subjects and 15 patients.

RESULTS

The proposed framework provides 3D cardiac CINE images with high spatial (1.9 mm³ ) and temporal resolution (˜50 ms) in a single breath-hold of ˜20 s for LV and ˜26 s for whole-heart coverage in healthy subjects. Shorter breath-hold durations of ˜13 to 15 s are feasible for LV coverage with slightly anisotropic resolution (1.9 × 1.9 × 2.5 mm) in patients. LV function parameters derived from 3D CINE were in good agreement with 2D CINE, with a bias of -0.1 mL/0.1 mL, -0.9 mL/-1.0 mL, -0.1%/-0.8%; and confidence intervals of ±1.7 mL/±3.7 mL, ±1.2 mL/±2.6 mL, and ±1.2%/±3.6% (10 healthy subjects/15 patients) for end-systolic volume, end-diastolic volume, and ejection fraction, respectively.

CONCLUSION

The proposed framework enables 3D isotropic cardiac CINE in a single breath-hold scan of ˜20 s/˜26 s for LV/whole-heart coverage, showing good agreement with clinical 2D CINE scans in terms of LV functional assessment.

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

Cardiac magnetic resonance (CMR) imaging is an important tool for the non-invasive assessment of cardiovascular disease. However, CMR suffers from long acquisition times due to the need of obtaining images with high temporal and spatial resolution, different contrasts, and/or whole-heart coverage. In addition, both cardiac and respiratory-induced motion of the heart during the acquisition need to be accounted for, further increasing the scan time. Several undersampling reconstruction techniques have been proposed during the last decades to speed up CMR acquisition. These techniques rely on acquiring less data than needed and estimating the non-acquired data exploiting some sort of prior information. Parallel imaging and compressed sensing undersampling reconstruction techniques have revolutionized the field, enabling 2- to 3-fold scan time accelerations to become standard in clinical practice. Recent scientific advances in CMR reconstruction hinge on the thriving field of artificial intelligence. Machine learning reconstruction approaches have been recently proposed to learn the non-linear optimization process employed in CMR reconstruction. Unlike analytical methods for which the reconstruction problem is explicitly defined into the optimization process, machine learning techniques make use of large data sets to learn the key reconstruction parameters and priors. In particular, deep learning techniques promise to use deep neural networks (DNN) to learn the reconstruction process from existing datasets in advance, providing a fast and efficient reconstruction that can be applied to all newly acquired data. However, before machine learning and DNN can realize their full potentials and enter widespread clinical routine for CMR image reconstruction, there are several technical hurdles that need to be addressed. In this article, we provide an overview of the recent developments in the area of artificial intelligence for CMR image reconstruction. The underlying assumptions of established techniques such as compressed sensing and low-rank reconstruction are briefly summarized, while a greater focus is given to recent advances in dictionary learning and deep learning based CMR reconstruction. In particular, approaches that exploit neural networks as implicit or explicit priors are discussed for 2D dynamic cardiac imaging and 3D whole-heart CMR imaging. Current limitations, challenges, and potential future directions of these techniques are also discussed.

Reconstruction techniques for cardiac cine MRI

The present survey describes the state-of-the-art techniques for dynamic cardiac magnetic resonance image reconstruction. Additionally, clinical relevance, main challenges, and future trends of this image modality are outlined. Thus, this paper aims to provide a general vision about cine MRI as the standard procedure in functional evaluation of the heart, focusing on technical methodologies.

Space-time variant weighted regularization in compressed sensing cardiac cine MRI

PURPOSE

To analyze the impact on image quality and motion fidelity of a motion-weighted space-time variant regularization term in compressed sensing cardiac cine MRI.

METHODS

k-t SPARSE-SENSE with temporal total variation (tTV) is used as the base reconstruction algorithm. Motion in the dynamic image is estimated by means of a robust registration technique for non-rigid motion. The resulting deformation fields are used to leverage the regularization term. The results are compared with standard k-t SPARSE-SENSE with tTV regularization as well as with an improved version of this algorithm that makes use of tTV and temporal Fast Fourier Transform regularization in x-f domain.

RESULTS

The proposed method with space-time variant regularization provides higher motion fidelity and image quality than the two previously reported methods. Difference images between undersampled reconstruction and fully sampled reference images show less systematic errors with the proposed approach.

CONCLUSIONS

Usage of a space-time variant regularization offers reconstructions with better image quality than the state of the art approaches used for comparison.

Will MRI of gastrointestinal function parallel the clinical success of cine cardiac MRI?

Cine cardiac MRI is generally accepted as the "gold-standard" for functional myocardial assessment. It only took a few years after the development of commercial MRI systems for functional cardiac imaging to be developed, with electrocardiogram (ECG)-gated cine imaging first reported in 1988. The function of the gastrointestinal (GI) tract is more complex to study compared to the heart. However, the idea of having a non-invasive tool to study the GI function that also allows the concurrent assessment of different aspects of this function has become more and more attractive in the gastroenterological field. This review summarises key literature of the last 5 years to describe the current status of MRI in respect to the evaluation of GI function, highlighting the gaps and challenges and the future prospects. As the clinical application of a new technique requires that its clinical utility is confirmed by demonstration of its ability to enable clinicians to make a diagnosis and/or predict the treatment response, this review also considers whether or not this has been achieved, and how MRI has been validated against techniques currently recognised as the gold standard in clinical practice.

Automated Curved and Multiplanar Reformation for Screening of the Proximal Coronary Arteries in MR Angiography

Congenital anomalies of the coronary ostia can lead to sudden death. A screening solution would be useful to prevent adverse outcomes for the affected individuals. To be considered for integration into clinical routine, such a procedure must meet strict constraints in terms of invasiveness, time and user interaction. Imaging must be fast and seamlessly integrable into the clinical process. Non-contrast enhanced coronary magnetic resonance angiography (MRA) is well suited for this. Furthermore, planar reformations proved effective to reduce the acquired volumetric datasets to 2D images. These usually require time consuming user interaction, though. To fulfill the aforementioned challenges, we present a fully automated solution for imaging and reformatting of the proximal coronary arteries which enables rapid screening of these. The proposed pipeline consists of: (I) highly accelerated single breath-hold MRA data acquisition, (II) coronary ostia detection and vessel centerline extraction, and (III) curved planar reformation of the proximal coronary arteries, as well as multiplanar reformation of the coronary ostia. The procedure proved robust and effective in ten volunteer data sets. Imaging of the proximal coronary arteries took 24 ± 5 s and was successful within one breath-hold for all patients. The extracted centerlines achieve an overlap of 0.76 ± 0.18 compared to the reference standard and the average distance of the centerline points from the spherical surface for reformation was 1.1 ± 0.51 mm. The promising results encourage further experiments on patient data, particularly in coronary ostia anomaly screening.

Single-breath-hold abdominal [Formula: see text] mapping using 3D Cartesian Look-Locker with spatiotemporal sparsity constraints

OBJECTIVE

Our aim was to develop and validate a 3D Cartesian Look-Locker [Formula: see text] mapping technique that achieves high accuracy and whole-liver coverage within a single breath-hold.

MATERIALS AND METHODS

The proposed method combines sparse Cartesian sampling based on a spatiotemporally incoherent Poisson pattern and k-space segmentation, dedicated for high-temporal-resolution imaging. This combination allows capturing tissue with short relaxation times with volumetric coverage. A joint reconstruction of the 3D + inversion time (TI) data via compressed sensing exploits the spatiotemporal sparsity and ensures consistent quality for the subsequent multistep [Formula: see text] mapping. Data from the National Institute of Standards and Technology (NIST) phantom and 11 volunteers, along with reference 2D Look-Locker acquisitions, are used for validation. 2D and 3D methods are compared based on [Formula: see text] values in different abdominal tissues at 1.5 and 3 T.

RESULTS

[Formula: see text] maps obtained from the proposed 3D method compare favorably with those from the 2D reference and additionally allow for reformatting or volumetric analysis. Excellent agreement is shown in phantom [bias[Formula: see text] < 2%, bias[Formula: see text] < 5% for (120; 2000) ms] and volunteer data (3D and 2D deviation < 4% for liver, muscle, and spleen) for clinically acceptable scan (20 s) and reconstruction times (< 4 min).

CONCLUSION

Whole-liver [Formula: see text] mapping with high accuracy and precision is feasible in one breath-hold using spatiotemporally incoherent, sparse 3D Cartesian sampling.

Free-breathing whole-heart 3D cine magnetic resonance imaging with prospective respiratory motion compensation

PURPOSE

To develop and validate a new prospective respiratory motion compensation algorithm for free-breathing whole-heart 3D cine steady-state free precession (SSFP) imaging.

METHODS

In a 3D cine SSFP sequence, 4 excitations per cardiac cycle are re-purposed to prospectively track heart position. Specifically, their 1D image is reconstructed and routed into the scanner's standard diaphragmatic navigator processing system. If all 4 signals are in end-expiration, cine image data from the entire cardiac cycle is accepted for image reconstruction. Prospective validation was carried out in patients (N = 17) by comparing in each a conventional breath-hold 2D cine ventricular short-axis stack and a free-breathing whole-heart 3D cine data set.

RESULTS

All 3D cine SSFP acquisitions were successful and the mean scan time was 5.9 ± 2.7 min. Left and right ventricular end-diastolic, end-systolic, and stroke volumes by 3D cine SSFP were all larger than those from 2D cine SSFP. This bias was < 6% except for right ventricular end-systolic volume that was 12%. The 3D cine images had a lower ventricular blood-to-myocardium contrast ratio, contrast-to-noise ratio, mass, and subjective quality score.

CONCLUSION

The novel prospective respiratory motion compensation method for 3D cine SSFP imaging was robust and efficient and yielded slightly larger ventricular volumes and lower mass compared to breath-hold 2D cine imaging. Magn Reson Med 80:181-189, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Clinical evaluation of time-of-flight MR angiography with sparse undersampling and iterative reconstruction for cerebral aneurysms

Compressed sensing (CS) MRI has just been introduced to research areas as an innovative approach to accelerate MRI. CS is expected to achieve higher k-space undersampling by exploiting the underlying sparsity in an appropriate transform domain. MR angiography (MRA) provides high spatial resolution information on arteries; however, a relatively long acquisition time is necessary to cover a wide volume. Reduction of acquisition time by CS for time-of-flight (TOF) MR angiography (Sparse-TOF) is beneficial in clinical examinations; therefore, the clinical validity of Sparse-TOF needs to be investigated. The aim of this study was to compare the diagnostic capability of TOF MRA between parallel imaging (PI)-TOF with an acceleration factor of 3 (annotated as 3×) and Sparse-TOF (3× and 5×) in patients with cerebral aneurysms. PI-TOF (3×) and Sparse-TOF (3× and 5×) imaging were performed in 20 patients using a 3 T MRI system. Aneurysms in PI-TOF (3×) and Sparse-TOF (3× and 5×) were blindly rated as visible or scarcely visible by neuroradiologists. The neck, height and width of aneurysms were also measured. Twenty-six aneurysms were visualized and rated as visible in PI-TOF (3×) and Sparse-TOF (3× and 5×), with excellent agreement between two raters. No significant differences were found in measured neck, height or width of aneurysms among them. Sparse-TOF (3× and 5×) were acquired and reconstructed within 6 min, and cerebral aneurysms were visible in both of them with equivalent quality to PI-TOF (3×). Sparse-TOF (5×) is a good alternative to PI-TOF (3×) to visualize cerebral aneurysms.