Improving the efficiency and accuracy of CMR with AI - review of evidence and proposition of a roadmap to clinical translation.

Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment of heart disease; however, limitations of CMR include long exam times and high complexity compared to other cardiac imaging modalities. Recently advancements in artificial intelligence (AI) technology have shown great potential to address many CMR limitations. While the developments are remarkable, translation of AI-based methods into real-world CMR clinical practice remains at a nascent stage and much work lies ahead to realize the full potential of AI for CMR. Herein we review recent cutting-edge and representative examples demonstrating how AI can advance CMR in areas such as exam planning, accelerated image reconstruction, post-processing, quality control, classification and diagnosis. These advances can be applied to speed up and simplify essentially every application including cine, strain, late gadolinium enhancement, parametric mapping, 3D whole heart, flow, perfusion and others. AI is a unique technology based on training models using data. Beyond reviewing the literature, this paper discusses important AI-specific issues in the context of CMR, including (1) properties and characteristics of datasets for training and validation, (2) previously published guidelines for reporting CMR AI research, (3) considerations around clinical deployment, (4) responsibilities of clinicians and the need for multi-disciplinary teams in the development and deployment of AI in CMR, (5) industry considerations, and (6) regulatory perspectives. Understanding and consideration of all these factors will contribute to the effective and ethical deployment of AI to improve clinical CMR.

Automated detection of cardiac rest period for trigger delay calculation for image-based navigator coronary magnetic resonance angiography.

BACKGROUND: Coronary magnetic resonance angiography (coronary MRA) is increasingly being considered as a clinically viable method to investigate coronary artery disease (CAD). Accurate determination of the trigger delay to place the acquisition window within the quiescent part of the cardiac cycle is critical for coronary MRA in order to reduce cardiac motion. This is currently reliant on operator-led decision making, which can negatively affect consistency of scan acquisition. Recently developed deep learning (DL) derived software may overcome these issues by automation of cardiac rest period detection. METHODS: Thirty individuals (female, n = 10) were investigated using a 0.9 mm isotropic image-navigator (iNAV)-based motion-corrected coronary MRA sequence. Each individual was scanned three times utilising different strategies for determination of the optimal trigger delay: (1) the DL software, (2) an experienced operator decision, and (3) a previously utilised formula for determining the trigger delay. Methodologies were compared using custom-made analysis software to assess visible coronary vessel length and coronary vessel sharpness for the entire vessel length and the first 4 cm of each vessel. RESULTS: There was no difference in image quality between any of the methodologies for determination of the optimal trigger delay, as assessed by visible coronary vessel length, coronary vessel sharpness for each entire vessel and vessel sharpness for the first 4 cm of the left mainstem, left anterior descending or right coronary arteries. However, vessel length of the left circumflex was slightly greater using the formula method. The time taken to calculate the trigger delay was significantly lower for the DL-method as compared to the operator-led approach (106 ± 38.0 s vs 168 ± 39.2 s, p < 0.01, 95% CI of difference 25.5-98.1 s). CONCLUSIONS: Deep learning-derived automated software can effectively and efficiently determine the optimal trigger delay for acquisition of coronary MRA and thus may simplify workflow and improve reproducibility.

Fully automated background phase correction using M-estimate SAmple consensus (MSAC)-Application to 2D and 4D flow.

PURPOSE: Flow quantification by phase-contrast MRI is hampered by spatially varying background phase offsets. Correction performance by polynomial regression on stationary tissue may be affected by outliers such as wrap-around or constant flow. Therefore, we propose an alternative, M-estimate SAmple Consensus (MSAC) to reject outliers, and improve and fully automate background phase correction. METHODS: The MSAC technique fits polynomials to randomly drawn small samples from the image. Over several trials, it aims to find the best consensus set of valid pixels by rejecting outliers to the fit and minimizing the residuals of the remaining pixels. The robustness of MSAC to its few parameters was investigated and verified using third-order polynomial correction fits on a total of 118 2D flow (97 with wrap-around) and 18 4D flow data sets (14 with wrap-around), acquired at 1.5 T and 3 T. Background phase was compared with standard stationary correction and phantom correction. Pulmonary/systemic flow ratios in 2D flow were derived, and exemplary 4D flow analysis was performed. RESULTS: The MSAC technique is robust over a range of parameter choices, and a unique set of parameters is suitable for both 2D and 4D flow. In 2D flow, phase errors were significantly reduced by MSAC compared with stationary correction (p = 0.005), and stationary correction shows larger errors in pulmonary/systemic flow ratios compared with MSAC. In 4D flow, MSAC shows similar performance as stationary correction. CONCLUSIONS: The MSAC method provides fully automated background phase correction to 2D and 4D flow data and shows improved robustness over stationary correction, especially with outliers present.

Low-dose contrast-enhanced time-resolved angiography with stochastic trajectories with iterative reconstruction (IT-TWIST-MRA) in brain arteriovenous shunt.

OBJECTIVES: To assess the feasibility of low-dose contrast-enhanced four-dimensional (4D) time-resolved angiography with stochastic trajectories (TWIST) with iterative reconstruction (hereafter IT-TWIST-MRA) covering the whole brain and to compare IT-TWIST-MRA and TWIST-MRA with reference to digital subtraction angiography (DSA) in the evaluation of arteriovenous shunts (AVS). METHODS: Institutional Review Board approval was obtained for this observational study, and the requirement for written informed consent was waived. Twenty-nine patients with known AVS underwent TWIST-MRA on a 3-T MRI scanner, using low-dose injection (0.02 mmol/kg) of gadolinium-based contrast agent (GBCA) with each of Fourier and iterative reconstruction between September 2016 and October 2019. Visual evaluation of image quality was conducted for delineation of (a) the normal cerebral arteries and veins and (b) AVS feeder, shunt, and drainer vessels. Region-of-interest evaluation was conducted to evaluate bolus sharpness and baseline signal fluctuation in the signal intensity of the cerebral vessels. We compared the detection of AVS between TWIST-MRA and IT-TWIST-MRA. The paired-samples Wilcoxon test was used to test the differences between TWIST-MRA and IT-TWIST-MRA. RESULTS: Visualization scores for normal vasculature and AVS angioarchitecture were significantly better for images produced using IT-TWIST-MRA than those using TWIST-MRA. Peak signal and the enhancement slope of the time-intensity curve were significantly higher for IT-TWIST-MRA than for TWIST-MRA, except for the superior sagittal sinus (SSS). Baseline intensity fluctuation was significantly lower for IT-TWIST-MRA than for TWIST, except for SSS. CONCLUSIONS: IT-TWIST-MRA yields clinically feasible 4D MR-DSA images and delineates AVS even with low-dose GBCA. KEY POINTS: • Iterative reconstruction significantly improves the image quality of TWIST-MRA covering the whole brain. • The short temporal footprint and denoising effect of iterative reconstruction enhances the quality of 4D-MRA. • IT-TWIST-MRA yields clinically feasible images of AVS with low-dose GBCA.

Quantitative mechanical dyssynchrony in dilated cardiomyopathy measured by deformable registration algorithm.

OBJECTIVES: To investigate the diagnostic value and reproducibility of deformable registration algorithm (DRA)-derived mechanical dyssynchrony parameters in dilated cardiomyopathy (DCM) patients. METHODS: The present study included 80 DCM patients (40 with normal QRS duration (NQRS-DCM); 40 with left bundle branch block (LBBB-DCM)) and 20 healthy volunteers. The balanced steady-state free-precession (bSSFP) cine images were acquired using a 3.0T scanner. Mechanical dyssynchrony parameters were calculated based on DRA-derived segmental strain, including uniformity ratio estimate (URE) and standard derivation of time-to-peak (T2Psd) parameters in circumferential, radial, and longitudinal orientations. RESULTS: DCM patients showed significant mechanical dyssynchrony reflected by both URE and T2Psd parameters compared with controls. Among DCM patients, LBBB-DCM showed decreased CURE (0.78 ± 0.21 vs. 0.93 ± 0.05, p < 0.001) and RURE (0.69 ± 0.14 vs. 0.83 ± 0.15, p = 0.001), and increased T2Psd-Ecc (median with interquartile range, 94.1 (54.4-123.2) ms vs. 63.7 (44.9-80.4) ms, p = 0.003) and T2Psd-Err (91.1 (61.1-103.2) ms vs. 62.3 (46.3-104.5) ms, p = 0.041) compared with NQRS-DCM patients. CURE showed a strong correlation with QRS duration (r = - 0.54, p < 0.001), with maximum AUC (0.791) to differentiate LBBB-DCM from NQRS-DCM patients. Improved intra- and inter-observer reproducibility was found using URE indices (coefficient of variation (CoV), 1.20-3.17%) than T2Psd parameters (CoV, 15.28-41.18%). CONCLUSIONS: The DRA-based CURE showed significant correlation with QRS duration and the highest discriminatory value between LBBB-DCM and NQRS-DCM patients. URE indices showed greater reproducibility compared with T2Psd parameters for assessing myocardial dyssynchrony in DCM patients. KEY POINTS: • The strain analyses based on DRA suggested that DCM patients have varying degrees of mechanical dyssynchrony and there is a significant difference from normal controls. • CURE showed the strongest correlation with QRS duration and was the best parameter for differentiating DCM patients with normal QRS duration from patients with LBBB, and with normal controls. • URE indices showed improved reproducibility compared with T2Psd parameters in all three orientations (circumferential, radial, and longitudinal).

Quantification of myocardial strain in patients with isolated left ventricular non-compaction and healthy subjects using deformable registration algorithm: comparison with feature tracking.

BACKGROUND: Systolic dysfunction of the left ventricle is frequently associated with isolated left ventricular non-compaction (iLVNC). Clinically, the ejection fraction (EF) is the primary index of cardiac function. However, changes of EF usually occur later in the disease course. Feature tracking (FT) and deformable registration algorithm (DRA) have become appealing techniques for myocardial strain assessment. METHODS: Thirty patients with iLVNC (36.7 ± 13.3 years old) and fifty healthy volunteers (42.3 ± 13.6 years old) underwent cardiovascular magnetic resonance (CMR) examination on a 1.5 T MR scanner. Strain values in the radial, circumferential, longitudinal directions were analyzed based on the short-axis and long-axis cine images using FT and DRA methods. The iLVNC patients were further divided based on the ejection fraction, into EF ≥ 50% group (n = 11) and EF < 50% group (n = 19). Receiver-operating-characteristic (ROC) analysis was performed to assess the diagnostic performance of the global strain values. Intraclass correlation coefficient (ICC) analysis was used to evaluate the intra- and inter-observer agreement. RESULTS: Global radial strain (GRS) was statistically lower in EF ≥ 50% group compared with control group [GRS (DRA)/% vs. controls: 34.6 ± 7.0 vs. 37.6 ± 7.2, P < 0.001; GRS (FT)/% vs. controls: 37.4 ± 13.2 vs. 56.9 ± 16.4, P < 0.01]. ROC analysis of global strain values derived from DRA and FT demonstrated high area under curve (range, 0.743-0.854). DRA showed excellent intra- and inter-observer agreement of global strain in both iLVNC patients (ICC: 0.995-0.999) and normal controls (ICC: 0.934-0.996). While for FT analysis, global radial strain of normal controls showed moderate intra-observer (ICC: 0.509) and poor inter-observer agreement (ICC: 0.394). CONCLUSIONS: In patients with iLVNC, DRA can be used to quantitatively analyze the strain of left ventricle, with global radial strain being an earlier marker of LV systolic dysfunction. DRA has better reproducibility in evaluating both the global and segmental strain.

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.

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

OBJECTIVES: Our objectives were to evaluate a single-breath-hold approach for Cartesian 3-D CINE imaging of the left ventricle with a nearly isotropic resolution of [Formula: see text] and a breath-hold duration of [Formula: see text]19 s against a standard stack of 2-D CINE slices acquired in multiple breath-holds. Validation is performed with data sets from ten healthy volunteers. MATERIALS AND METHODS: A Cartesian sampling pattern based on the spiral phyllotaxis and a compressed sensing reconstruction method are proposed to allow 3-D CINE imaging with high acceleration factors. The fully integrated reconstruction uses multiple graphics processing units to speed up the reconstruction. The 2-D CINE and 3-D CINE are compared based on ventricular function parameters, contrast-to-noise ratio and edge sharpness measurements. RESULTS: Visual comparisons of corresponding short-axis slices of 2-D and 3-D CINE show an excellent match, while 3-D CINE also allows reformatting to other orientations. Ventricular function parameters do not significantly differ from values based on 2-D CINE imaging. Reconstruction times are below 4 min. CONCLUSION: We demonstrate single-breath-hold 3-D CINE imaging in volunteers and three example patient cases, which features fast reconstruction and allows reformatting to arbitrary orientations.

High-resolution dynamic CE-MRA of the thorax enabled by iterative TWIST reconstruction.

PURPOSE: To evaluate the clinical benefit of using a new iterative reconstruction technique fully integrated on a standard clinical scanner and reconstruction system using a TWIST acquisition for high-resolution dynamic three-dimensional contrast-enhanced MR angiography (CE-MRA). METHODS: Low-dose, high-resolution TWIST datasets of 11 patients were reconstructed using both standard GRAPPA-based reconstruction for reference and iterative reconstruction, which reduces the temporal footprint of reconstructed images. Image quality of both techniques was assessed by two experienced readers, as well as quantitatively evaluated using a time-signal curve analysis. RESULTS: Image quality scores consistently and significantly improved by using iterative reconstruction compared with the standard approach. Most notably, the delineation of small to mid-size vasculature improved from a mean Likert score between "nondiagnostic" and "poor" for standard to between "good" and "excellent" for iterative reconstruction. The full width at half maximum of the contrast agent bolus computed from the time-signal curve was also reduced by iterative reconstruction, allowing for more precise bolus timing. CONCLUSION: Iterative reconstruction can substantially improve high-resolution dynamic CE-MRA image quality, most notably in small to mid-size vasculature. Dynamic CE-MRA with iterative reconstruction could become an alternative to conventional static 3D CE-MRA, thus simplifying the clinical workflow. Magn Reson Med 77:833-840, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Accelerating multi-echo water-fat MRI with a joint locally low-rank and spatial sparsity-promoting reconstruction.

OBJECTIVES: Our aim was to demonstrate the benefits of using locally low-rank (LLR) regularization for the compressed sensing reconstruction of highly-accelerated quantitative water-fat MRI, and to validate fat fraction (FF) and [Formula: see text] relaxation against reference parallel imaging in the abdomen. MATERIALS AND METHODS: Reconstructions using spatial sparsity regularization (SSR) were compared to reconstructions with LLR and the combination of both (LLR+SSR) for up to seven fold accelerated 3-D bipolar multi-echo GRE imaging. For ten volunteers, the agreement with the reference was assessed in FF and [Formula: see text] maps. RESULTS: LLR regularization showed superior noise and artifact suppression compared to reconstructions using SSR. Remaining residual artifacts were further reduced in combination with SSR. Correlation with the reference was excellent for FF with [Formula: see text] = 0.99 (all methods) and good for [Formula: see text] with [Formula: see text] = [0.93, 0.96, 0.95] for SSR, LLR and LLR+SSR. The linear regression gave slope and bias (%) of (0.99, 0.50), (1.01, 0.19) and (1.01, 0.10), and the hepatic FF/[Formula: see text] standard deviation was 3.5%/12.1 s[Formula: see text], 1.9%/6.4 s[Formula: see text] and 1.8%/6.3 s[Formula: see text] for SSR, LLR and LLR+SSR, indicating the least bias and highest SNR for LLR+SSR. CONCLUSION: A novel reconstruction using both spatial and spectral regularization allows obtaining accurate FF and [Formula: see text] maps for prospectively highly accelerated acquisitions.

Introduction of a cascaded segmentation pipeline for parametric T1 mapping in cardiovascular magnetic resonance to improve segmentation performance.

The manual and often time-consuming segmentation of the myocardium in cardiovascular magnetic resonance is increasingly automated using convolutional neural networks (CNNs). This study proposes a cascaded segmentation (CASEG) approach to improve automatic image segmentation quality. First, an object detection algorithm predicts a bounding box (BB) for the left ventricular myocardium whose 1.5 times enlargement defines the region of interest (ROI). Then, the ROI image section is fed into a U-Net based segmentation. Two CASEG variants were evaluated: one using the ROI cropped image solely (cropU) and the other using a 2-channel-image additionally containing the original BB image section (crinU). Both were compared to a classical U-Net segmentation (refU). All networks share the same hyperparameters and were tested on basal and midventricular slices of native and contrast enhanced (CE) MOLLI T1 maps. Dice Similarity Coefficient improved significantly (p < 0.05) in cropU and crinU compared to refU (81.06%, 81.22%, 72.79% for native and 80.70%, 79.18%, 71.41% for CE data), while no significant improvement (p < 0.05) was achieved in the mean absolute error of the T1 time (11.94 ms, 12.45 ms, 14.22 ms for native and 5.32 ms, 6.07 ms, 5.89 ms for CE data). In conclusion, CASEG provides an improved geometric concordance but needs further improvement in the quantitative outcome.

Lazy Luna: Extendible software for multilevel reader comparison in cardiovascular magnetic resonance imaging.

BACKGROUND AND OBJECTIVES: Cardiovascular Magnetic Resonance (CMR) imaging is a growing field with increasing diagnostic utility in clinical routine. Quantitative diagnostic parameters are typically calculated based on contours or points provided by readers, e.g. natural intelligences (NI) such as clinicians or researchers, and artificial intelligences (AI). As clinical applications multiply, evaluating the precision and reproducibility of quantitative parameters becomes increasingly important. Although segmentation challenges for AIs and guidelines for clinicians provide quality assessments and regulation, the methods ought to be combined and streamlined for clinical applications. The goal of the developed software, Lazy Luna (LL), is to offer a flexible evaluation tool that is readily extendible to new sequences and scientific endeavours. METHODS: An interface was designed for LL, which allows for comparing annotated CMR images. Geometric objects ensure precise calculations of metric values and clinical results regardless of whether annotations originate from AIs or NIs. A graphical user interface (GUI) is provided to make the software available to non-programmers. The GUI allows for an interactive inspection of image datasets as well as implementing tracing procedures, which follow statistical reader differences in clinical results to their origins in individual image contours. The backend software builds on a set of meta-classes, which can be extended to new imaging sequences and clinical parameters. Following an agile development procedure with clinical feedback allows for a quick implementation of new classes, figures and tables for evaluation. RESULTS: Two application cases present LL's extendibility to clinical evaluation and AI development contexts. The first concerns T1 parametric mapping images segmented by two expert readers. Quantitative result differences are traced to reveal typical segmentation dissimilarities from which these differences originate. The meta-classes are extended to this new application scenario. The second applies to the open source Late Gadolinium Enhancement (LGE) quantification challenge for AI developers "Emidec", which illustrates LL's usability as open source software. CONCLUSION: The presented software Lazy Luna allows for an automated multilevel comparison of readers as well as identifying qualitative reasons for statistical reader differences. The open source software LL can be extended to new application cases in the future.

Fully automated AI-based cardiac motion parameter extraction - application to mitral and tricuspid valves on long-axis cine MR images.

PURPOSE: In cardiac MRI, valve motion parameters can be useful for the diagnosis of cardiac dysfunction. In this study, a fully automated AI-based valve tracking system was developed and evaluated on 2- or 4-chamber view cine series on a large cardiac MR dataset. Automatically derived motion parameters include atrioventricular plane displacement (AVPD), velocities (AVPV), mitral or tricuspid annular plane systolic excursion (MAPSE, TAPSE), or longitudinal shortening (LS). METHOD: Two sequential neural networks with an intermediate processing step are applied to localize the target and track the landmarks throughout the cardiac cycle. Initially, a localisation network is used to perform heatmap regression of the target landmarks, such as mitral, tricuspid valve annulus as well as apex points. Then, a registration network is applied to track these landmarks using deformation fields. Based on these outputs, motion parameters were derived. RESULTS: The accuracy of the system resulted in deviations of 1.44 ± 1.32 mm, 1.51 ± 1.46 cm/s, 2.21 ± 1.81 mm, 2.40 ± 1.97 mm, 2.50 ± 2.06 mm for AVPD, AVPV, MAPSE, TAPSE and LS, respectively. Application on a large patient database (N = 5289) revealed a mean MAPSE and LS of 9.5 ± 3.0 mm and 15.9 ± 3.9 % on 2-chamber and 4-chamber views, respectively. A mean TAPSE and LS of 13.4 ± 4.7 mm and 21.4 ± 6.9 % was measured. CONCLUSION: The results demonstrate the versatility of the proposed system for automatic extraction of various valve-related motion parameters.

Comparison between pre- and post-contrast cardiac MRI cine images: the impact on ventricular volume and strain measurement.

To explore whether contrast agent administration will affect ventricular volume and strain parameters measured on cardiac magnetic resonance cine images. This prospective study enrolled 88 patients, including 32 patients with cardiac amyloidosis (CA), 32 patients with hypertrophic cardiomyopathy (HCM), and 24 control participants, to perform steady-state free precession (SSFP)-cine imaging twice, respectively before and after contrast agent injection. Indexed left and right ventricular (LV and RV) volume and LV strain parameters (peak radial strain [PRS], peak circumferential strain [PCS], peak longitudinal strain [PLS]) were analyzed and compared between the pre- and post-contrast cine groups. Compared to the group of pre-contrast cine, the end-diastolic volume index (EDVi) and end-systolic volume index (ESVi) significantly increased in the group using post-contrast cine images (all p < 0.05), especially in the right ventricle. After contrast injection, the right ventricular ejection fraction (RVEF) decreased significantly (p < 0.05), while the left ventricular ejection fraction (LVEF) only reduced for patients with HCM (p < 0.05). The PRS (37.1 ± 15.2 vs. 32.0 ± 15.4, p < 0.001) and PCS (- 14.9 ± 4.3 vs. - 14.0 ± 4.1, p < 0.001) derived from post-contrast cine images reduced significantly in all patients and this tendency remained in subgroup analysis except for PCS in the control group. The administration of a contrast agent may influence the measurements of ventricular volume and strain. Acquiring pre-contrast cine images were suggested for patients who required more accurate right ventricle evaluation or precise strain assessment.

Neural network-based fully automated cardiac resting phase detection algorithm compared with manual detection in patients.

Background: A cardiac resting phase is used when performing free-breathing cardiac magnetic resonance examinations. Purpose: The purpose of this study was to test a cardiac resting phase detection system based on neural networks in clinical practice. Material and Methods: Four chamber-view cine images were obtained from 32 patients and analyzed. The rest duration, start point, and end point were compared between that determined by the experts and general operators, and a similar comparison was done between that determined by the experts and neural networks: the normalized root-mean-square error (RMSE) was also calculated. Results: Unlike manual detection, the neural network was able to determine the resting phase almost simultaneously as the image was obtained. The rest duration and start point were not significantly different between the neural network and expert (p = .30, .90, respectively), whereas the end point was significantly different between the two groups (p < .05). The start point was not significantly different between the general operator and expert (p = .09), whereas the rest duration and end point were significantly different between the two groups (p < .05). The normalized RMSEs of the rest duration, start point, and end point of the neural network were 0.88, 0.64, and 0.33 ms, respectively, which were lower than those of the general operator (normalized RMSE values were 0.98, 0.68, and 0.51 ms, respectively). Conclusions: The neural network can determine the resting phase instantly with better accuracy than the manual detection of general operators.

Introduction of Lazy Luna an automatic software-driven multilevel comparison of ventricular function quantification in cardiovascular magnetic resonance imaging.

Cardiovascular magnetic resonance imaging is the gold standard for cardiac function assessment. Quantification of clinical results (CR) requires precise segmentation. Clinicians statistically compare CRs to ensure reproducibility. Convolutional Neural Network developers compare their results via metrics. Aim: Introducing software capable of automatic multilevel comparison. A multilevel analysis covering segmentations and CRs builds on a generic software backend. Metrics and CRs are calculated with geometric accuracy. Segmentations and CRs are connected to track errors and their effects. An interactive GUI makes the software accessible to different users. The software's multilevel comparison was tested on a use case based on cardiac function assessment. The software shows good reader agreement in CRs and segmentation metrics (Dice > 90%). Decomposing differences by cardiac position revealed excellent agreement in midventricular slices: > 90% but poorer segmentations in apical (> 71%) and basal slices (> 74%). Further decomposition by contour type locates the largest millilitre differences in the basal right cavity (> 3 ml). Visual inspection shows these differences being caused by different basal slice choices. The software illuminated reader differences on several levels. Producing spreadsheets and figures concerning metric values and CR differences was automated. A multilevel reader comparison is feasible and extendable to other cardiac structures in the future.

Improving robustness of automatic cardiac function quantification from cine magnetic resonance imaging using synthetic image data.

Although having been the subject of intense research over the years, cardiac function quantification from MRI is still not a fully automatic process in the clinical practice. This is partly due to the shortage of training data covering all relevant cardiovascular disease phenotypes. We propose to synthetically generate short axis CINE MRI using a generative adversarial model to expand the available data sets that consist of predominantly healthy subjects to include more cases with reduced ejection fraction. We introduce a deep learning convolutional neural network (CNN) to predict the end-diastolic volume, end-systolic volume, and implicitly the ejection fraction from cardiac MRI without explicit segmentation. The left ventricle volume predictions were compared to the ground truth values, showing superior accuracy compared to state-of-the-art segmentation methods. We show that using synthetic data generated for pre-training a CNN significantly improves the prediction compared to only using the limited amount of available data, when the training set is imbalanced.

Evaluation and Comparison of Quantitative Right Ventricular Strain Assessment by Cardiac Magnetic Resonance in Pulmonary Hypertension Using Feature Tracking and Deformable Registration Algorithms.

RATIONALE AND OBJECTIVE: Deformable registration algorithms (DRA) has been used to detect left ventricular myocardial changes, however, its clinical utility in right ventricular (RV) function has not been evaluated. In this study, we aim to evaluate and compare quantitative RV strain assessment by cardiac magnetic resonance in pulmonary hypertension (PH) using feature tracking (FT) and DRA. MATERIALS AND METHODS: Thirty patients were confirmed to have PH using right heart catheterization, and 16 healthy controls were evaluated with cardiac magnetic resonance. Global and segmental RV strain was measured by DRA and FT methods. Intraclass correlation coefficients (ICCs), coefficient of variation, and Bland-Altman analysis were used to assess and compare the interobserver and intraobserver variability of the DRA and FT methods. RESULTS: DRA was more sensitive than FT in the detection of RV circumferential and septal dysfunction. The global longitudinal strain (GLS) obtained by the two methods was reduced in mild-moderate PH patients (mean pulmonary artery pressure≤45 mm Hg), and the GLS and global circumferential strain (GCS) were reduced in severe PH patients (mean pulmonary artery pressure >45 mm Hg). DRA and FT methods demonstrate similar observer agreement in global strain using ICC (ICC greater than 0.90), but RV strain derived from DRA had lower variability using COV ([8%-14%] for DRA versus [11%-39%] for FT).For segmental longitudinal strain, DRA showed higher ICC and lower COV compared with that of the FT method. Correlations between RVEF and RV global strain parameters were strong (p < 0.01):GLS-DRA, r = -0.696; GLS-FT, r = -0.832; GCS-DRA, r = -0.745; and GCS-FT, r = -0.817. GLS-DRA was weakly correlated with mPAP (r = 0.385, p < 0.05).In multiple linear regression analysis, RVEF and mPAP were independent predictors of GLS-DRA (R2 = 0.57, p < 0.01). CONCLUSIONS: The DRA method is more sensitive and robust for RV myocardial strain measurements than FT method.

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.

Fast TWIST with iterative reconstruction improves diagnostic accuracy of AVM of the hand.

Very high temporal and spatial resolution is mandatory for the diagnosis of arteriovenous malformations (AVM) of the hand. Until now, magnetic resonance imaging (MRI) has not fulfilled both requirements simultaneously. This study presents how the combination of a very fast TWIST MRI (time-resolved angiography with interleaved stochastic trajectories) sequence and iterative reconstructions optimizes temporal as well as spatial resolution. 11 patients were examined at a 3-T MRI scanner with two different TWIST protocols: the standard and the study protocol, acquiring a data set every 5.57 s and 1.44 s respectively. The study data was retrospectively iteratively reconstructed with different regularization factors (0.001, 0.002, 0.004, 0.008). Results were compared using the sign-test. P-values < 0.05 were regarded statistically significant. With a low amount of contrast medium, the temporal resolution of the study protocol enabled the differentiation of arteries from veins in all patients whereas the signal-to-noise ratio (SNR) deteriorated. Depending on the regularization factors, SNR, delineation of arterial feeders and non-involved hand and interdigital arteries, as well as artefact levels varied. Overall, iterative reconstruction with regularization factor 0.004 achieved the best results, consequently showing the ability of MRI as a reliable diagnostic method in AVMs of the hand.