Deep learning based automated left ventricle segmentation and flow quantification in 4D flow cardiac MRI.

BACKGROUND: 4D flow MRI enables assessment of cardiac function and intra-cardiac blood flow dynamics from a single acquisition. However, due to the poor contrast between the chambers and surrounding tissue, quantitative analysis relies on the segmentation derived from a registered cine MRI acquisition. This requires an additional acquisition and is prone to imperfect spatial and temporal inter-scan alignment. Therefore, in this work we developed and evaluated deep learning-based methods to segment the left ventricle (LV) from 4D flow MRI directly. METHODS: We compared five deep learning-based approaches with different network structures, data pre-processing and feature fusion methods. For the data pre-processing, the 4D flow MRI data was reformatted into a stack of short-axis view slices. Two feature fusion approaches were proposed to integrate the features from magnitude and velocity images. The networks were trained and evaluated on an in-house dataset of 101 subjects with 67,567 2D images and 3030 3D volumes. The performance was evaluated using various metrics including Dice, average surface distance (ASD), end-diastolic volume (EDV), end-systolic volume (ESV), LV ejection fraction (LVEF), LV blood flow kinetic energy (KE) and LV flow components. The Monte Carlo dropout method was used to assess the confidence and to describe the uncertainty area in the segmentation results. RESULTS: Among the five models, the model combining 2D U-Net with late fusion method operating on short-axis reformatted 4D flow volumes achieved the best results with Dice of 84.52% and ASD of 3.14 mm. The best averaged absolute and relative error between manual and automated segmentation for EDV, ESV, LVEF and KE was 19.93 ml (10.39%), 17.38 ml (22.22%), 7.37% (13.93%) and 0.07 mJ (5.61%), respectively. Flow component results derived from automated segmentation showed high correlation and small average error compared to results derived from manual segmentation. CONCLUSIONS: Deep learning-based methods can achieve accurate automated LV segmentation and subsequent quantification of volumetric and hemodynamic LV parameters from 4D flow MRI without requiring an additional cine MRI acquisition.

Signal intensity and volume of carotid intraplaque hemorrhage on magnetic resonance imaging and the risk of ipsilateral cerebrovascular events: The Plaque At RISK (PARISK) study.

BACKGROUND: The Plaque At RISK (PARISK) study demonstrated that patients with a carotid plaque with intraplaque hemorrhage (IPH) have an increased risk of recurrent ipsilateral ischemic cerebrovascular events. It was previously reported that symptomatic carotid plaques with IPH showed higher IPH signal intensity ratios (SIR) and larger IPH volumes than asymptomatic plaques. We explored whether IPH SIR and IPH volume are associated with future ipsilateral ischemic cerebrovascular events beyond the presence of IPH. METHODS: Transient ischemic attack and ischemic stroke patients with mild-to-moderate carotid stenosis and an ipsilateral IPH-positive carotid plaque (n = 89) from the PARISK study were included. The clinical endpoint was a new ipsilateral ischemic cerebrovascular event during 5 years of follow-up, while the imaging-based endpoint was a new ipsilateral brain infarct on brain magnetic resonance imaging (MRI) after 2 years (n = 69). Trained observers delineated IPH, a hyperintense region compared to surrounding muscle tissue on hyper T1-weighted magnetic resonance images. The IPH SIR was the maximal signal intensity in the IPH region divided by the mean signal intensity of adjacent muscle tissue. The associations between IPH SIR or volume and the clinical and imaging-based endpoint were investigated using Cox proportional hazard models and logistic regression, respectively. RESULTS: During 5.1 (interquartile range: 3.1-5.6) years of follow-up, 21 ipsilateral cerebrovascular ischemic events were identified. Twelve new ipsilateral brain infarcts were identified on the 2-year neuro MRI. There was no association for IPH SIR or IPH volume with the clinical endpoint (hazard ratio (HR): 0.89 [95% confidence interval: 0.67-1.10] and HR: 0.91 [0.69-1.19] per 100-µL increase, respectively) nor with the imaging-based endpoint (odds ratio (OR): 1.04 [0.75-1.45] and OR: 1.21 [0.87-1.68] per 100-µL increase, respectively). CONCLUSION: IPH SIR and IPH volume were not associated with future ipsilateral ischemic cerebrovascular events. Therefore, quantitative assessment of IPH of SIR and volume does not seem to provide additional value beyond the presence of IPH for stroke risk assessment. TRIAL REGISTRATION: The PARISK study was registered on ClinicalTrials.gov with ID NCT01208025 on September 21, 2010 (https://clinicaltrials.gov/study/NCT01208025).

Establishing minimally important differences for cardiac MRI end-points in pulmonary arterial hypertension.

BACKGROUND: Cardiac magnetic resonance (CMR) is the gold standard technique to assess biventricular volumes and function, and is increasingly being considered as an end-point in clinical studies. Currently, with the exception of right ventricular (RV) stroke volume and RV end-diastolic volume, there is only limited data on minimally important differences (MIDs) reported for CMR metrics. Our study aimed to identify MIDs for CMR metrics based on US Food and Drug Administration recommendations for a clinical outcome measure that should reflect how a patient "feels, functions or survives". METHODS: Consecutive treatment-naïve patients with pulmonary arterial hypertension (PAH) between 2010 and 2022 who had two CMR scans (at baseline prior to treatment and 12 months following treatment) were identified from the ASPIRE registry. All patients were followed up for 1 additional year after the second scan. For both scans, cardiac measurements were obtained from a validated fully automated segmentation tool. The MID in CMR metrics was determined using two distribution-based (0.5sd and minimal detectable change) and two anchor-based (change difference and generalised linear model regression) methods benchmarked to how a patient "feels" (emPHasis-10 quality of life questionnaire), "functions" (incremental shuttle walk test) or "survives" for 1-year mortality to changes in CMR measurements. RESULTS: 254 patients with PAH were included (mean±sd age 53±16 years, 79% female and 66% categorised as intermediate risk based on the 2022 European Society of Cardiology/European Respiratory Society risk score). We identified a 5% absolute increase in RV ejection fraction and a 17 mL decrease in RV end-diastolic or end-systolic volumes as the MIDs for improvement. Conversely, a 5% decrease in RV ejection fraction and a 10 mL increase in RV volumes were associated with worsening. CONCLUSIONS: This study establishes clinically relevant CMR MIDs for how a patient "feels, functions or survives" in response to PAH treatment. These findings provide further support for the use of CMR as a clinically relevant clinical outcome measure and will aid trial size calculations for studies using CMR.

Plain language summaryPulmonary arterial hypertension (PAH) is a disease of the vessels of the lung that causes their narrowing and stiffening. As a result, the heart pumping blood into these diseased lung vessels has to work harder and eventually gets worn out. PAH can affect patients' ability to function in daily activities and impact their quality of life. It also reduces their life expectancy dramatically. Patients are, therefore, often monitored and undergo several investigations to adapt treatment according to their situation. These investigations include a survey of how a patient feels (the emPHasis-10 questionnaire), functions (walking test) and how well the heart is coping with the disease (MRI of the heart). Until now, it is unclear how changes on MRI of the heart reflect changes in how a patient feels and functions. Our study identified patients that had the emPHasis-10 questionnaire, walking test and MRI of the heart at both the time of PAH diagnosis and one year later. This allowed us to compare how the changes in the different tests relate to each other. And because previous research identified thresholds for important changes in the emPHasis-10 questionnaire and the walking tests, we were able to use these tests as a benchmark for changes in the MRI of the heart. Our study identified thresholds for change on heart MRI that might indicate whether a patient has improved or worsened. This finding might have implications for how patients are monitored in clinical practice and future research on PAH treatments.

Increased incidence of napkin-ring sign plaques on cervicocerebral computed tomography angiography associated with the risk of acute ischemic stroke occurrence.

OBJECTIVES: Carotid atherosclerosis plays an essential role in the occurrence of ischemic stroke. This study aimed to investigate whether a larger burden of napkin-ring sign (NRS) plaques on cervicocerebral computed tomography angiography (CTA) increased the risk of acute ischemic stroke (AIS). METHODS: This retrospective, single-center, cross-sectional study enrolled patients with NRS plaques identified in the subclavian arteries, brachiocephalic trunk, carotid arterial system, and vertebrobasilar circulation on contrast-enhanced cervicocerebral CTA. Patients were divided into AIS and non-AIS groups based on imaging within 12 h of symptom onset. Univariate and multivariate logistic regression analyses were performed to determine the risk factor of AIS occurrence. RESULTS: A total of 202 patients (66.72 years ± 8.97, 157 men) were evaluated. Plaques with NRS in each subject of the AIS group (N = 98) were significantly more prevalent than that in the control group (N = 104) (1.96 ± 1.17 vs 1.41 ± 0.62). In the AIS group, there were substantially more NRS plaques on the ipsilateral side than contralateral side (1.55 ± 0.90 vs. 0.41 ± 0.66). NRS located on the ipsilateral side of the AIS showed an area under the receiver curve (AUC) of 0.86 to identify ischemic stroke. NRS plaque amounts were an independent risk factor for AIS occurrence (odds ratio, 1.86) after adjusting for other factors. CONCLUSIONS: Increased incidence of napkin-ring sign plaques on cervicocerebral CTA was positively associated with AIS occurrence, which could aid in detecting asymptomatic atherosclerotic patients at high risk of AIS in routine screening or emergency settings. CLINICAL RELEVANCE STATEMENT: Napkin-ring sign plaque provides an important imaging target for estimating acute ischemic stroke risk and identifying high-risk patients in routine screening or emergency settings, so that timely anti-atherosclerotic therapy can be used for prevention. KEY POINTS: • This cross-sectional study investigated the association between high-risk carotid artery plaques and acute ischemic stroke. • Increased incidence of napkin-ring sign plaques on cervicocerebral computed tomography angiography is positively associated with acute ischemic stroke occurrence. • Napkin-ring signs help identify risky patients prone to acute ischemic stroke to facilitate prevention.

The association between antiplatelet therapy and changes in intraplaque hemorrhage in patients with mild to moderate symptomatic carotid stenosis: a longitudinal MRI study.

INTRODUCTION: Carotid atherosclerotic intraplaque hemorrhage (IPH) predicts stroke. Patients with a history of stroke are treated with antiplatelet agents to prevent secondary cardiovascular events. A positive association between previous antiplatelet use and IPH was reported in a cross-sectional analysis. We investigated changes in IPH over two years in patients who recently started versus those with continued antiplatelet use. METHODS: In the Plaque at Risk (PARISK) study, symptomatic patients with <70% ipsilateral carotid stenosis underwent carotid plaque MRI at baseline and after two years to determine IPH presence and volume. Participants were categorized into new users (starting antiplatelet therapy following the index event) and continued users (previous use of antiplatelet therapy before the index event). The association between previous antiplatelet therapy and the presence of IPH at baseline MRI was investigated using multivariable logistic regression analysis. IPH volume change over a period of two years, defined as the difference in volume between follow-up and baseline, was investigated in each group with a Wilcoxon signed-rank test. The IPH volume change was categorized as progression, regression, or no change. Using multivariable logistic regression, we investigated the association between new antiplatelet use and 1) newly developed ipsilateral or contralateral IPH and 2) IPH volume progression. RESULTS: A total of 108 patients underwent carotid MRI at baseline and follow-up. At baseline, previous antiplatelet therapy was associated with any IPH (OR=5.6, 95% CI: 1.3-23.1; p=0.02). Ipsilateral IPH volume did not change significantly during the two years in patients who continued receiving antiplatelet agents (86.4 mm3 [18.2-235.9] vs. 59.3 mm3 [11.4-260.3]; p=0.6) nor in the new antiplatelet users (n=31) (61.5 mm3 [0.0-166.9] vs. 27.7 mm3 [9.5-106.4]; p=0.4). Similar results of a nonsignificant change in contralateral IPH volume during those two years were observed in both groups (p>0.05). No significant associations were found between new antiplatelet use and newly developed IPH at two years (odds ratio (OR)=1.0, 95% CI:0.1-7.4) or the progression of IPH (ipsilateral: OR=2.4, 95% CI:0.3-19.1; contralateral: OR=0.3, 95% CI:0.01-8.5). CONCLUSION: Although the baseline association between IPH and previous antiplatelet therapy was confirmed in this larger cohort, the new onset of antiplatelet therapy after TIA/stroke was not associated with newly developed IPH or progression of IPH volume over the subsequent two years.

Age- and sex-specific reference values of biventricular flow components and kinetic energy by 4D flow cardiovascular magnetic resonance in healthy subjects.

BACKGROUND: Advances in four-dimensional flow cardiovascular magnetic resonance (4D flow CMR) have allowed quantification of left ventricular (LV) and right ventricular (RV) blood flow. We aimed to (1) investigate age and sex differences of 4D flow CMR-derived LV and RV relative flow components and kinetic energy (KE) parameters indexed to end-diastolic volume (KEiEDV) in healthy subjects; and (2) assess the effects of age and sex on these parameters. METHODS: We performed 4D flow analysis in 163 healthy participants (42% female; mean age 43 ± 13 years) of a prospective registry study (NCT03217240) who were free of cardiovascular diseases. Relative flow components (direct flow, retained inflow, delayed ejection flow, residual volume) and multiple phasic KEiEDV (global, peak systolic, average systolic, average diastolic, peak E-wave, peak A-wave) for both LV and RV were analysed. RESULTS: Compared with men, women had lower median LV and RV residual volume, and LV peak and average systolic KEiEDV, and higher median values of RV direct flow, RV global KEiEDV, RV average diastolic KEiEDV, and RV peak E-wave KEiEDV. ANOVA analysis found there were no differences in flow components, peak and average systolic, average diastolic and global KEiEDV for both LV and RV across age groups. Peak A-wave KEiEDV increased significantly (r = 0.458 for LV and 0.341 for RV), whereas peak E-wave KEiEDV (r = - 0.355 for LV and - 0.318 for RV), and KEiEDV E/A ratio (r = - 0.475 for LV and - 0.504 for RV) decreased significantly, with age. CONCLUSION: These data using state-of-the-art 4D flow CMR show that biventricular flow components and kinetic energy parameters vary significantly by age and sex. Age and sex trends should be considered in the interpretation of quantitative measures of biventricular flow. Clinical trial registration  https://www. CLINICALTRIALS: gov . Unique identifier: NCT03217240.

4D Flow cardiovascular magnetic resonance consensus statement: 2023 update.

Hemodynamic assessment is an integral part of the diagnosis and management of cardiovascular disease. Four-dimensional cardiovascular magnetic resonance flow imaging (4D Flow CMR) allows comprehensive and accurate assessment of flow in a single acquisition. This consensus paper is an update from the 2015 '4D Flow CMR Consensus Statement'. We elaborate on 4D Flow CMR sequence options and imaging considerations. The document aims to assist centers starting out with 4D Flow CMR of the heart and great vessels with advice on acquisition parameters, post-processing workflows and integration into clinical practice. Furthermore, we define minimum quality assurance and validation standards for clinical centers. We also address the challenges faced in quality assurance and validation in the research setting. We also include a checklist for recommended publication standards, specifically for 4D Flow CMR. Finally, we discuss the current limitations and the future of 4D Flow CMR. This updated consensus paper will further facilitate widespread adoption of 4D Flow CMR in the clinical workflow across the globe and aid consistently high-quality publication standards.

The transmural activation interval: a new mapping tool to identify ventricular tachycardia substrates in right ventricular cardiomyopathy.

AIMS: In right ventricular cardiomyopathy (RVCM), intramural scar may prevent rapid transmural activation, which may facilitate subepicardial ventricular tachycardia (VT) circuits. A critical transmural activation delay determined during sinus rhythm (SR) may identify VT substrates in RVCM. METHODS AND RESULTS: Consecutive patients with RVCM who underwent detailed endocardial-epicardial mapping and ablation for scar-related VT were enrolled. The transmural activation interval (TAI, first endocardial to first epicardial activation) and maximal activation interval (MAI, first endocardial to last epicardial activation) were determined in endocardial-epicardial point pairs located <10 mm apart. VT-related sites were determined by conventional substrate mapping and limited activation mapping when possible. Nineteen patients (46 ± 16 years, 84% male, 63% arrhythmogenic right ventricular cardiomyopathy, 37% exercise-induced arrhythmogenic remodelling) were inducible for 44 VT [CL 283 (interquartile range, IQR 240-325)ms]. A total of 2569 endocardial-epicardial coupled point pairs were analysed, including 98 (4%) epicardial VT-related sites.The TAI and MAI were significantly longer at VT-related sites compared with other electroanatomical scar sites [TAI median 31 (IQR 11-50) vs. 2 (-7-11)ms, P < 0.001; MAI median 65 (IQR 45-87) vs. 23 (13-39)ms, P < 0.001]. TAI and MAI allowed highly accurate identification of epicardial VT-related sites (optimal cut-off TAI 17 ms and MAI 45 ms, both AUC 0.81). Both TAI and MAI had a better predictive accuracy for VT-related sites than endocardial and epicardial voltage and electrogram (EGM) duration (AUC 0.51-0.73). CONCLUSION: The transmural activation delay in SR can be used to identify VT substrates in patients with RVCM and predominantly hemodynamically non-tolerated VT, and may be an important new mapping tool for substrate-based ablation.

Automated 4D flow cardiac MRI pipeline to derive peak mitral inflow diastolic velocities using short-axis cine stack: two centre validation study against echocardiographic pulse-wave doppler.

BACKGROUND: Measurement of peak velocities is important in the evaluation of heart failure. This study compared the performance of automated 4D flow cardiac MRI (CMR) with traditional transthoracic Doppler echocardiography (TTE) for the measurement of mitral inflow peak diastolic velocities. METHODS: Patients with Doppler echocardiography and 4D flow cardiac magnetic resonance data were included retrospectively. An established automated technique was used to segment the left ventricular transvalvular flow using short-axis cine stack of images. Peak mitral E-wave and peak mitral A-wave velocities were automatically derived using in-plane velocity maps of transvalvular flow. Additionally, we checked the agreement between peak mitral E-wave velocity derived by 4D flow CMR and Doppler echocardiography in patients with sinus rhythm and atrial fibrillation (AF) separately. RESULTS: Forty-eight patients were included (median age 69 years, IQR 63 to 76; 46% female). Data were split into three groups according to heart rhythm. The median peak E-wave mitral inflow velocity by automated 4D flow CMR was comparable with Doppler echocardiography in all patients (0.90 ± 0.43 m/s vs 0.94 ± 0.48 m/s, P = 0.132), sinus rhythm-only group (0.88 ± 0.35 m/s vs 0.86 ± 0.38 m/s, P = 0.54) and in AF-only group (1.33 ± 0.56 m/s vs 1.18 ± 0.47 m/s, P = 0.06). Peak A-wave mitral inflow velocity results had no significant difference between Doppler TTE and automated 4D flow CMR (0.81 ± 0.44 m/s vs 0.81 ± 0.53 m/s, P = 0.09) in all patients and sinus rhythm-only groups. Automated 4D flow CMR showed a significant correlation with TTE for measurement of peak E-wave in all patients group (r = 0.73, P < 0.001) and peak A-wave velocities (r = 0.88, P < 0.001). Moreover, there was a significant correlation between automated 4D flow CMR and TTE for peak-E wave velocity in sinus rhythm-only patients (r = 0.68, P < 0.001) and AF-only patients (r = 0.81, P = 0.014). Excellent intra-and inter-observer variability was demonstrated for both parameters. CONCLUSION: Automated dynamic peak mitral inflow diastolic velocity tracing using 4D flow CMR is comparable to Doppler echocardiography and has excellent repeatability for clinical use. However, 4D flow CMR can potentially underestimate peak velocity in patients with AF.

Acute vasodilator response testing in the adult Fontan circulation using non-invasive 4D Flow MRI: a proof-of-principle study.

BACKGROUND: Pulmonary vasodilator therapy in Fontan patients can improve exercise tolerance. We aimed to assess the potential for non-invasive testing of acute vasodilator response using four-dimensional (D) flow MRI during oxygen inhalation. MATERIALS AND METHODS: Six patients with well-functioning Fontan circulations were prospectively recruited and underwent cardiac MRI. Ventricular anatomical imaging and 4D Flow MRI were acquired at baseline and during inhalation of oxygen. Data were compared with six age-matched healthy volunteers with 4D Flow MRI scans acquired at baseline. RESULTS: All six patients tolerated the MRI scan well. The dominant ventricle had a left ventricular morphology in all cases. On 4D Flow MRI assessment, two patients (Patients 2 and 6) showed improved cardiac filling with improved preload during oxygen administration, increased mitral inflow, increased maximum E-wave kinetic energy, and decreased systolic peak kinetic energy. Patient 1 showed improved preload only. Patient 5 showed no change, and patient 3 had equivocal results. Patient 4, however, showed a decrease in preload and cardiac filling/function with oxygen. DISCUSSION: Using oxygen as a pulmonary vasodilator to assess increased pulmonary venous return as a marker for positive acute vasodilator response would provide pre-treatment assessment in a more physiological state - the awake patient. This proof-of-concept study showed that it is well tolerated and has shown changes in some stable patients with a Fontan circulation.

Validation of Artificial Intelligence Cardiac MRI Measurements: Relationship to Heart Catheterization and Mortality Prediction.

Background Cardiac MRI measurements have diagnostic and prognostic value in the evaluation of cardiopulmonary disease. Artificial intelligence approaches to automate cardiac MRI segmentation are emerging but require clinical testing. Purpose To develop and evaluate a deep learning tool for quantitative evaluation of cardiac MRI functional studies and assess its use for prognosis in patients suspected of having pulmonary hypertension. Materials and Methods A retrospective multicenter and multivendor data set was used to develop a deep learning-based cardiac MRI contouring model using a cohort of patients suspected of having cardiopulmonary disease from multiple pathologic causes. Correlation with same-day right heart catheterization (RHC) and scan-rescan repeatability was assessed in prospectively recruited participants. Prognostic impact was assessed using Cox proportional hazard regression analysis of 3487 patients from the ASPIRE (Assessing the Severity of Pulmonary Hypertension In a Pulmonary Hypertension Referral Centre) registry, including a subset of 920 patients with pulmonary arterial hypertension. The generalizability of the automatic assessment was evaluated in 40 multivendor studies from 32 centers. Results The training data set included 539 patients (mean age, 54 years ± 20 [SD]; 315 women). Automatic cardiac MRI measurements were better correlated with RHC parameters than were manual measurements, including left ventricular stroke volume (r = 0.72 vs 0.68; P = .03). Interstudy repeatability of cardiac MRI measurements was high for all automatic measurements (intraclass correlation coefficient range, 0.79-0.99) and similarly repeatable to manual measurements (all paired t test P > .05). Automated right ventricle and left ventricle cardiac MRI measurements were associated with mortality in patients suspected of having pulmonary hypertension. Conclusion An automatic cardiac MRI measurement approach was developed and tested in a large cohort of patients, including a broad spectrum of right ventricular and left ventricular conditions, with internal and external testing. Fully automatic cardiac MRI assessment correlated strongly with invasive hemodynamics, had prognostic value, were highly repeatable, and showed excellent generalizability. Clinical trial registration no. NCT03841344 Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Ambale-Venkatesh and Lima in this issue. An earlier incorrect version appeared online. This article was corrected on June 27, 2022.

Longitudinal Changes in Left Ventricular Blood Flow Kinetic Energy After Myocardial Infarction: Predictive Relevance for Cardiac Remodeling.

BACKGROUND: Four-dimensional (4D) flow cardiac magnetic resonance (cardiac MR) imaging provides quantification of intracavity left ventricular (LV) flow kinetic energy (KE) parameters in three dimensions. ST-elevation myocardial infarction (STEMI) patients have been shown to have altered intracardiac blood flow compared to controls; however, how 4D flow parameters change over time has not been explored previously. PURPOSE: Measure longitudinal changes in intraventricular flow post-STEMI and ascertain its predictive relevance of long-term cardiac remodeling. STUDY TYPE: Prospective. POPULATION: Thirty-five STEMI patients (M:F = 26:9, aged 56 ± 9 years). FIELD STRENGTH/SEQUENCE: A 3 T/3D EPI-based, fast field echo (FFE) free-breathing 4D-flow sequence with retrospective cardiac gating. ASSESSMENT: Serial imaging at 3-7 days (V1), 3-months (V2), and 12-months (V3) post-STEMI, including the following protocol: functional imaging for measuring volumes and 4D-flow for calculating parameters including systolic and peakE-wave LVKE, normalized to end-diastolic volume (iEDV) and stroke volume (iSV). Data were analyzed by H.B. (3 years experience). Patients were categorized into two groups: preserved ejection fraction (pEF, if EF > 50%) and reduced EF (rEF, if EF < 50%). STATISTICAL TESTS: Independent sample t-tests were used to detect the statistical significance between any two cohorts. P < 0.05 was considered statistically significant. RESULTS: Across the cohort, systolic KEisv was highest at V1 (28.0 ± 4.4 µJ/mL). Patients with rEF retained significantly higher systolic KEisv than patients with pEF at V2 (18.2 ± 3.4 µJ/mL vs. 6.9 ± 0.6 µJ/mL, P < 0.001) and V3 (21.6 ± 5.1 µJ/mL vs. 7.4 ± 0.9 µJ/mL, P < 0.001). Patients with pEF had significantly higher peakE-wave KEiEDV than rEF patients throughout the study (V1: 25.4 ± 11.6 µJ/mL vs. 18.1 ± 9.9 µJ/mL, P < 0.03, V2: 24.0 ± 10.2 µJ/mL vs. 17.2 ± 12.2 µJ/mL, P < 0.05, V3: 27.7 ± 14.8 µJ/mL vs. 15.8 ± 7.6 µJ/mL, P < 0.04). DATA CONCLUSION: Systolic KE increased acutely following MI; in patients with pEF, this decreased over 12 months, while patients with rEF, this remained raised. Compared to patients with pEF, persistently lower peakE-wave KE in rEF patients is suggestive of early and fixed impairment in diastolic function. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 3.

Non-Invasive Assessment of Damping of Blood Flow Velocity Pulsatility in Cerebral Arteries With MRI.

BACKGROUND: Damping of heartbeat-induced pressure pulsations occurs in large arteries such as the aorta and extends to the small arteries and microcirculation. Since recently, 7 T MRI enables investigation of damping in the small cerebral arteries. PURPOSE: To investigate flow pulsatility damping between the first segment of the middle cerebral artery (M1) and the small perforating arteries using magnetic resonance imaging. STUDY TYPE: Retrospective. SUBJECTS: Thirty-eight participants (45% female) aged above 50 without history of heart failure, carotid occlusive disease, or cognitive impairment. FIELD STRENGTH/SEQUENCE: 3 T gradient echo (GE) T1-weighted images, spin-echo fluid-attenuated inversion recovery images, GE two-dimensional (2D) phase-contrast, and GE cine steady-state free precession images were acquired. At 7 T, T1-weighted images, GE quantitative-flow, and GE 2D phase-contrast images were acquired. ASSESSMENT: Velocity pulsatilities of the M1 and perforating arteries in the basal ganglia (BG) and semi-oval center (CSO) were measured. We used the damping index between the M1 and perforating arteries as a damping indicator (velocity pulsatilityM1 /velocity pulsatilityCSO/BG ). Left ventricular stroke volume (LVSV), mean arterial pressure (MAP), pulse pressure (PP), and aortic pulse wave velocity (PWV) were correlated with velocity pulsatility in the M1 and in perforating arteries, and with the damping index of the CSO and BG. STATISTICAL TESTS: Correlations of LVSV, MAP, PP, and PWV with velocity pulsatility in the M1 and small perforating arteries, and correlations with the damping indices were evaluated with linear regression analyses. RESULTS: PP and PWV were significantly positively correlated to M1 velocity pulsatility. PWV was significantly negatively correlated to CSO velocity pulsatility, and PP was unrelated to CSO velocity pulsatility (P = 0.28). PP and PWV were uncorrelated to BG velocity pulsatility (P = 0.25; P = 0.68). PWV and PP were significantly positively correlated with the CSO damping index. DATA CONCLUSION: Our study demonstrated a dynamic damping of velocity pulsatility between the M1 and small cerebral perforating arteries in relation to proximal stress. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 1.

Acute intra-cavity 4D flow cardiovascular magnetic resonance predicts long-term adverse remodelling following ST-elevation myocardial infarction.

BACKGROUND: Despite advancements in percutaneous coronary intervention, a significant proportion of ST-elevation myocardial infarction (STEMI) survivors develop long-term adverse left ventricular (LV) remodelling, which is associated with poor prognosis. Adverse remodelling is difficult to predict, however four-dimensional (4D) flow cardiovascular magnetic resonance (CMR) can measure various aspects of LV intra-cavity flow beyond LV ejection fraction and is well equipped for exploring the underlying mechanical processes driving remodelling. The aim for this study was to compare acute 4D flow CMR parameters between patients who develop adverse remodelling with patients who do not. METHODS: Fifty prospective 'first-event' STEMI patients underwent CMR 5 days post-reperfusion, which included cine-imaging, and 4D flow for assessing in-plane kinetic energy (KE), residual volume, peak-E and peak-A wave KE (indexed for LV end-diastolic volume [LVEDV]). All subjects underwent follow-up cine CMR imaging at 12 months to identify adverse remodelling (defined as 20% increase in LVEDV from baseline). Quantitative variables were compared using unpaired student's t-test. Tests were deemed statistically significant when p < 0.05. RESULTS: Patients who developed adverse LV remodelling by 12 months had significantly higher in-plane KE (54 ± 12 vs 42 ± 10%, p = 0.02), decreased proportion of direct flow (27 ± 9% vs 11 ± 4%, p < 0.01), increased proportion of delayed ejection flow (22 ± 9% vs 12 ± 2, p < 0.01) and increased proportion of residual volume after 2 consecutive cardiac cycles (64 ± 14 vs 34 ± 14%, p < 0.01), in their acute scan. CONCLUSION: Following STEMI, increased in-plane KE, reduced direct flow and increased residual volume in the acute scan were all associated with adverse LV remodelling at 12 months. Our results highlight the clinical utility of acute 4D flow in prognostic stratification in patients following myocardial infarction.

Training and clinical testing of artificial intelligence derived right atrial cardiovascular magnetic resonance measurements.

BACKGROUND: Right atrial (RA) area predicts mortality in patients with pulmonary hypertension, and is recommended by the European Society of Cardiology/European Respiratory Society pulmonary hypertension guidelines. The advent of deep learning may allow more reliable measurement of RA areas to improve clinical assessments. The aim of this study was to automate cardiovascular magnetic resonance (CMR) RA area measurements and evaluate the clinical utility by assessing repeatability, correlation with invasive haemodynamics and prognostic value. METHODS: A deep learning RA area CMR contouring model was trained in a multicentre cohort of 365 patients with pulmonary hypertension, left ventricular pathology and healthy subjects. Inter-study repeatability (intraclass correlation coefficient (ICC)) and agreement of contours (DICE similarity coefficient (DSC)) were assessed in a prospective cohort (n = 36). Clinical testing and mortality prediction was performed in n = 400 patients that were not used in the training nor prospective cohort, and the correlation of automatic and manual RA measurements with invasive haemodynamics assessed in n = 212/400. Radiologist quality control (QC) was performed in the ASPIRE registry, n = 3795 patients. The primary QC observer evaluated all the segmentations and recorded them as satisfactory, suboptimal or failure. A second QC observer analysed a random subcohort to assess QC agreement (n = 1018). RESULTS: All deep learning RA measurements showed higher interstudy repeatability (ICC 0.91 to 0.95) compared to manual RA measurements (1st observer ICC 0.82 to 0.88, 2nd observer ICC 0.88 to 0.91). DSC showed high agreement comparing automatic artificial intelligence and manual CMR readers. Maximal RA area mean and standard deviation (SD) DSC metric for observer 1 vs observer 2, automatic measurements vs observer 1 and automatic measurements vs observer 2 is 92.4 ± 3.5 cm2, 91.2 ± 4.5 cm2 and 93.2 ± 3.2 cm2, respectively. Minimal RA area mean and SD DSC metric for observer 1 vs observer 2, automatic measurements vs observer 1 and automatic measurements vs observer 2 was 89.8 ± 3.9 cm2, 87.0 ± 5.8 cm2 and 91.8 ± 4.8 cm2. Automatic RA area measurements all showed moderate correlation with invasive parameters (r = 0.45 to 0.66), manual (r = 0.36 to 0.57). Maximal RA area could accurately predict elevated mean RA pressure low and high-risk thresholds (area under the receiver operating characteristic curve artificial intelligence = 0.82/0.87 vs manual = 0.78/0.83), and predicted mortality similar to manual measurements, both p < 0.01. In the QC evaluation, artificial intelligence segmentations were suboptimal at 108/3795 and a low failure rate of 16/3795. In a subcohort (n = 1018), agreement by two QC observers was excellent, kappa 0.84. CONCLUSION: Automatic artificial intelligence CMR derived RA size and function are accurate, have excellent repeatability, moderate associations with invasive haemodynamics and predict mortality.

Ventricular flow analysis and its association with exertional capacity in repaired tetralogy of Fallot: 4D flow cardiovascular magnetic resonance study.

BACKGROUND: Four-dimensional (4D) flow cardiovascular magnetic resonance (CMR) allows quantification of biventricular blood flow by flow components and kinetic energy (KE) analyses. However, it remains unclear whether 4D flow parameters can predict cardiopulmonary exercise testing (CPET) as a clinical outcome in repaired tetralogy of Fallot (rTOF). Current study aimed to (1) compare 4D flow CMR parameters in rTOF with age- and gender-matched healthy controls, (2) investigate associations of 4D flow parameters with functional and volumetric right ventricular (RV) remodelling markers, and CPET outcome. METHODS: Sixty-three rTOF patients (14 paediatric, 49 adult; 30 ± 15 years; 29 M) and 63 age- and gender-matched healthy controls (14 paediatric, 49 adult; 31 ± 15 years) were prospectively recruited at four centers. All underwent cine and 4D flow CMR, and all adults performed standardized CPET same day or within one week of CMR. RV remodelling index was calculated as the ratio of RV to left ventricular (LV) end-diastolic volumes. Four flow components were analyzed: direct flow, retained inflow, delayed ejection flow and residual volume. Additionally, three phasic KE parameters normalized to end-diastolic volume (KEiEDV), were analyzed for both LV and RV: peak systolic, average systolic and peak E-wave. RESULTS: In comparisons of rTOF vs. healthy controls, median LV retained inflow (18% vs. 16%, P = 0.005) and median peak E-wave KEiEDV (34.9 µJ/ml vs. 29.2 µJ/ml, P = 0.006) were higher in rTOF; median RV direct flow was lower in rTOF (25% vs. 35%, P < 0.001); median RV delayed ejection flow (21% vs. 17%, P < 0.001) and residual volume (39% vs. 31%, P < 0.001) were both greater in rTOF. RV KEiEDV parameters were all higher in rTOF than healthy controls (all P < 0.001). On multivariate analysis, RV direct flow was an independent predictor of RV function and CPET outcome. RV direct flow and RV peak E-wave KEiEDV were independent predictors of RV remodelling index. CONCLUSIONS: In this multi-scanner multicenter 4D flow CMR study, reduced RV direct flow was independently associated with RV dysfunction, remodelling and, to a lesser extent, exercise intolerance in rTOF patients. This supports its utility as an imaging parameter for monitoring disease progression and therapeutic response in rTOF. Clinical Trial Registration https://www.clinicaltrials.gov . Unique identifier: NCT03217240.

Right ventricular energetic biomarkers from 4D Flow CMR are associated with exertional capacity in pulmonary arterial hypertension.

BACKGROUND: Cardiovascular magnetic resonance (CMR) offers comprehensive right ventricular (RV) evaluation in pulmonary arterial hypertension (PAH). Emerging four-dimensional (4D) flow CMR allows visualization and quantification of intracardiac flow components and calculation of phasic blood kinetic energy (KE) parameters but it is unknown whether these parameters are associated with cardiopulmonary exercise test (CPET)-assessed exercise capacity, which is a surrogate measure of survival in PAH. We compared 4D flow CMR parameters in PAH with healthy controls, and investigated the association of these parameters with RV remodelling, RV functional and CPET outcomes. METHODS: PAH patients and healthy controls from two centers were prospectively enrolled to undergo on-site cine and 4D flow CMR, and CPET within one week. RV remodelling index was calculated as the ratio of RV to left ventricular (LV) end-diastolic volumes (EDV). Phasic (peak systolic, average systolic, and peak E-wave) LV and RV blood flow KE indexed to EDV (KEIEDV) and ventricular LV and RV flow components (direct flow, retained inflow, delayed ejection flow, and residual volume) were calculated. Oxygen uptake (VO2), carbon dioxide production (VCO2) and minute ventilation (VE) were measured and recorded. RESULTS: 45 PAH patients (46 ± 11 years; 7 M) and 51 healthy subjects (46 ± 14 years; 17 M) with no significant differences in age and gender were analyzed. Compared with healthy controls, PAH had significantly lower median RV direct flow, RV delayed ejection flow, RV peak E-wave KEIEDV, peak VO2, and percentage (%) predicted peak VO2, while significantly higher median RV residual volume and VE/VCO2 slope. RV direct flow and RV residual volume were significantly associated with RV remodelling, function, peak VO2, % predicted peak VO2 and VE/VCO2 slope (all P < 0.01). Multiple linear regression analyses showed RV direct flow to be an independent marker of RV function, remodelling and exercise capacity. CONCLUSION: In this 4D flow CMR and CPET study, RV direct flow provided incremental value over RVEF for discriminating adverse RV remodelling, impaired exercise capacity, and PAH with intermediate and high risk based on risk score. These data suggest that CMR with 4D flow CMR can provide comprehensive assessment of PAH severity, and may be used to monitor disease progression and therapeutic response. TRIAL REGISTRATION NUMBER: https://www. CLINICALTRIALS: gov . Unique identifier: NCT03217240.

The Role of Artificial Intelligence in Predicting Outcomes by Cardiovascular Magnetic Resonance: A Comprehensive Systematic Review.

Background and Objectives: Interest in artificial intelligence (AI) for outcome prediction has grown substantially in recent years. However, the prognostic role of AI using advanced cardiac magnetic resonance imaging (CMR) remains unclear. This systematic review assesses the existing literature on AI in CMR to predict outcomes in patients with cardiovascular disease. Materials and Methods: Medline and Embase were searched for studies published up to November 2021. Any study assessing outcome prediction using AI in CMR in patients with cardiovascular disease was eligible for inclusion. All studies were assessed for compliance with the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results: A total of 5 studies were included, with a total of 3679 patients, with 225 deaths and 265 major adverse cardiovascular events. Three methods demonstrated high prognostic accuracy: (1) three-dimensional motion assessment model in pulmonary hypertension (hazard ratio (HR) 2.74, 95%CI 1.73−4.34, p < 0.001), (2) automated perfusion quantification in patients with coronary artery disease (HR 2.14, 95%CI 1.58−2.90, p < 0.001), and (3) automated volumetric, functional, and area assessment in patients with myocardial infarction (HR 0.94, 95%CI 0.92−0.96, p < 0.001). Conclusion: There is emerging evidence of the prognostic role of AI in predicting outcomes for three-dimensional motion assessment in pulmonary hypertension, ischaemia assessment by automated perfusion quantification, and automated functional assessment in myocardial infarction.

Mediation of the association between obesity and osteoarthritis by blood pressure, vessel wall stiffness and subclinical atherosclerosis.

OBJECTIVE: We investigated the role of blood pressure, vessel wall stiffness [pulse wave velocity (PWV)] and subclinical atherosclerosis markers [carotid intima-media thickness (cIMT), popliteal vessel wall thickness (pVWT)] as mediators of the association of obesity with OA. METHODS: We used cross-sectional data from a subset of the population-based NEO study (n = 6334). We classified clinical hand and knee OA by the ACR criteria, and structural knee OA, effusion and bone marrow lesions on MRI (n = 1285). cIMT was assessed with ultrasonography. pVWT was estimated on knee MRI (n = 1285), and PWV by abdominal velocity-encoded MRIs (n = 2580), in subpopulations. Associations between BMI and OA were assessed with logistic regression analyses, adjusted for age, sex and education. Blood pressure, cIMT, pVWT and PWV were added to the model to estimate mediation. RESULTS: The population consisted of 55% women, with a mean (s.d.) age of 56(6) years. Clinical hand OA was present in 8%, clinical knee OA in 10%, and structural knee OA in 12% of participants. BMI was positively associated with all OA outcomes. cIMT partially mediated the association of BMI with clinical hand OA [10.6 (6.2; 30.5)%], structural knee OA [3.1 (1.9; 7.3)%] and effusion [10.8 (6.0; 37.6)%]. Diastolic blood pressure [2.1 (1.6; 3.0)%] minimally mediated the association between BMI and clinical knee OA. PWV and pVWT did not mediate the association between BMI and OA. CONCLUSIONS: cIMT and diastolic blood pressure minimally mediated the association of BMI with OA. This suggests that such mediation is trivial in the middle-aged population.

Evaluation of pulse wave velocity for predicting major adverse cardiovascular events in post-infarcted patients; comparison of oscillometric and MRI methods.

Increased aortic pulse wave velocity (PWV) has been proved as a strong predictor of major adverse cardiovascular events (MACE) in patients after myocardial infarction (MI). Due to the various technical approaches the level of high PWV values show significant differences. We evaluated the cut-off PWV values for MACE prediction using cardiac magnetic resonance imaging (CMR) and oscillometric methods for validating the prognostic value of high PWV in post-infarcted patients. Phase contrast imaging (PCI) and oscillometric based Arteriograph (AG) were compared in this 6 years follow-up study, including 75 consecutive patients of whom 49 suffered previous ST-elevation myocardial infarction (STEMI). Patients received follow-up for MACE comprising all-cause death, non-fatal MI, ischemic stroke, hospitalization for heart failure and coronary revascularization. An acceptable agreement and significant correlation (rho: 0.332, p < 0.01) was found between AG and CMR derived PWV values. The absolute values, however, were significantly higher for AG (median (IQR): 10.4 (9.2-11.9) vs 6.44 (5.64-7.5) m/s; p < 0.001). Totally 51 MACE events occurred during the 6 years follow-up period in post-infarcted patients. Kaplan-Meier analysis in both methods showed significantly lower event-free survival in case of high PWV (CMR: >6.47 m/s, AG: >9.625 m/s, p < 0.001, respectively). Multivariate Cox regression revealed PWV as a predictor of MACE (PWV CMR hazard ratio (HR): 1.31 (CI: 1.1-1.7), PWV AG HR: 1.24 (CI: 1.0-1.5), p < 0.05, respectively). Increased PWV derived by AG and CMR methods are feasible for MACE prediction in post-infarcted patients. However, adjusted cut-off values of PWV are recommended for different techniques to improve individual risk stratification.