Clinical assessment of an AI tool for measuring biventricular parameters on cardiac MR.

Introduction: Cardiac magnetic resonance (CMR) is of diagnostic and prognostic value in a range of cardiopulmonary conditions. Current methods for evaluating CMR studies are laborious and time-consuming, contributing to delays for patients. As the demand for CMR increases, there is a growing need to automate this process. The application of artificial intelligence (AI) to CMR is promising, but the evaluation of these tools in clinical practice has been limited. This study assessed the clinical viability of an automatic tool for measuring cardiac volumes on CMR. Methods: Consecutive patients who underwent CMR for any indication between January 2022 and October 2022 at a single tertiary centre were included prospectively. For each case, short-axis CMR images were segmented by the AI tool and manually to yield volume, mass and ejection fraction measurements for both ventricles. Automated and manual measurements were compared for agreement and the quality of the automated contours was assessed visually by cardiac radiologists. Results: 462 CMR studies were included. No statistically significant difference was demonstrated between any automated and manual measurements (p > 0.05; independent T-test). Intraclass correlation coefficient and Bland-Altman analysis showed excellent agreement across all metrics (ICC > 0.85). The automated contours were evaluated visually in 251 cases, with agreement or minor disagreement in 229 cases (91.2%) and failed segmentation in only a single case (0.4%). The AI tool was able to provide automated contours in under 90 s. Conclusions: Automated segmentation of both ventricles on CMR by an automatic tool shows excellent agreement with manual segmentation performed by CMR experts in a retrospective real-world clinical cohort. Implementation of the tool could improve the efficiency of CMR reporting and reduce delays between imaging and diagnosis.

Machine learning cardiac-MRI features predict mortality in newly diagnosed pulmonary arterial hypertension.

Aims: Pulmonary arterial hypertension (PAH) is a rare but serious disease associated with high mortality if left untreated. This study aims to assess the prognostic cardiac magnetic resonance (CMR) features in PAH using machine learning. Methods and results: Seven hundred and twenty-three consecutive treatment-naive PAH patients were identified from the ASPIRE registry; 516 were included in the training, and 207 in the validation cohort. A multilinear principal component analysis (MPCA)-based machine learning approach was used to extract mortality and survival features throughout the cardiac cycle. The features were overlaid on the original imaging using thresholding and clustering of high- and low-risk of mortality prediction values. The 1-year mortality rate in the validation cohort was 10%. Univariable Cox regression analysis of the combined short-axis and four-chamber MPCA-based predictions was statistically significant (hazard ratios: 2.1, 95% CI: 1.3, 3.4, c-index = 0.70, P = 0.002). The MPCA features improved the 1-year mortality prediction of REVEAL from c-index = 0.71 to 0.76 (P ≤ 0.001). Abnormalities in the end-systolic interventricular septum and end-diastolic left ventricle indicated the highest risk of mortality. Conclusion: The MPCA-based machine learning is an explainable time-resolved approach that allows visualization of prognostic cardiac features throughout the cardiac cycle at the population level, making this approach transparent and clinically interpretable. In addition, the added prognostic value over the REVEAL risk score and CMR volumetric measurements allows for a more accurate prediction of 1-year mortality risk in PAH.

Diagnostic accuracy of CT pulmonary angiography in suspected pulmonary hypertension.

OBJECTIVES: Computed tomography (CT) pulmonary angiography is widely used in patients with suspected pulmonary hypertension (PH). However, the diagnostic and prognostic significance remains unclear. The aim of this study was to (a) build a diagnostic CT model and (b) test its prognostic significance. METHODS: Consecutive patients with suspected PH undergoing routine CT pulmonary angiography and right heart catheterisation (RHC) were identified. Axial and reconstructed images were used to derive CT metrics. Multivariate regression analysis was performed in the derivation cohort to identify a diagnostic CT model to predict mPAP ≥ 25 mmHg (the existing ESC guideline definition of PH) and > 20 mmHg (the new threshold proposed at the 6th World Symposium on PH). In the validation cohort, sensitivity, specificity and compromise CT thresholds were identified with receiver operating characteristic (ROC) analysis. The prognostic value of the CT model was assessed using Kaplan-Meier analysis. RESULTS: Between 2012 and 2016, 491 patients were identified. In the derivation cohort (n = 247), a CT model was identified including pulmonary artery diameter, right ventricular outflow tract thickness, septal angle and left ventricular area. In the validation cohort (n = 244), the model was diagnostic, with an area under the ROC curve of 0.94/0.91 for mPAP ≥ 25/> 20 mmHg respectively. In the validation cohort, 93 patients died; mean follow-up was 42 months. The diagnostic thresholds for the CT model were prognostic, log rank, all p < 0.01. DISCUSSION: In suspected PH, a diagnostic CT model had diagnostic and prognostic utility. KEY POINTS: • Diagnostic CT models have high diagnostic accuracy in a tertiary referral population of with suspected PH. • Diagnostic CT models stratify patients by mortality in suspected PH.

Magnetic Resonance Imaging in the Prognostic Evaluation of Patients with Pulmonary Arterial Hypertension.

RATIONALE: Prognostication is important when counseling patients and defining treatment strategies in pulmonary arterial hypertension (PAH). OBJECTIVES: To determine the value of magnetic resonance imaging (MRI) metrics for prediction of mortality in PAH. METHODS: Consecutive patients with PAH undergoing MRI were identified from the ASPIRE (Assessing the Spectrum of Pulmonary Hypertension Identified at a Referral Centre) pulmonary hypertension registry. MEASUREMENTS AND MAIN RESULTS: During the follow-up period of 42 (range, 17-142) months 576 patients were studied and 221 (38%) died. A derivation cohort (n = 288; 115 deaths) and validation cohort (n = 288; 106 deaths) were identified. We used multivariate Cox regression and found two independent MRI predictors of death (P < 0.01): right ventricular end-systolic volume index adjusted for age and sex, and the relative area change of the pulmonary artery. A model of MRI and clinical data constructed from the derivation cohort predicted mortality in the validation cohort at 1 year (sensitivity, 70 [95% confidence interval (CI), 53-83]; specificity, 62 [95% CI, 62-68]; positive predictive value [PPV], 24 [95% CI, 16-32]; negative predictive value [NPV], 92 [95% CI, 87-96]) and at 3 years (sensitivity, 77 [95% CI, 67-85]; specificity, 73 [95% CI, 66-85]; PPV, 56 [95% CI, 47-65]; and NPV, 87 [95% CI, 81-92]). The model was more accurate in patients with idiopathic PAH at 3 years (sensitivity, 89 [95% CI, 65-84]; specificity, 76 [95% CI, 65-84]; PPV, 60 [95% CI, 46-74]; and NPV, 94 [95% CI, 85-98]). CONCLUSIONS: MRI measurements reflecting right ventricular structure and stiffness of the proximal pulmonary vasculature are independent predictors of outcome in PAH. In combination with clinical data MRI has moderate prognostic accuracy in the evaluation of patients with PAH.

Longitudinal and transverse right ventricular function in pulmonary hypertension: cardiovascular magnetic resonance imaging study from the ASPIRE registry.

Right ventricular (RV) function is a strong predictor of outcome in cardiovascular diseases. Two components of RV function, longitudinal and transverse motion, have been investigated in pulmonary hypertension (PH). However, their individual clinical significance remains uncertain. The aim of this study was to determine the factors associated with transverse and longitudinal RV motion in patients with PH. In 149 treatment-naive patients with PH and 16 patients with suspected PH found to have mean pulmonary arterial pressure of <20 mmHg, cardiovascular magnetic resonance imaging was performed within 24 hours of right heart catheterization. In patients with PH, fractional longitudinal motion (fractional tricuspid annulus to apex distance [f-TAAD]) was significantly greater than fractional transverse motion (fractional septum to free wall distance [f-SFD]; P = 0.002). In patients without PH, no significant difference between f-SFD and f-TAAD was identified (P = 0.442). Longitudinal RV motion was singularly associated with RV ejection fraction independent of age, invasive hemodynamics, and cardiac magnetic resonance measurements (P = 0.024). In contrast, transverse RV motion was independently associated with left ventricular eccentricity (P = 0.036) in addition to RV ejection fraction (P = 0.014). In conclusion, RV motion is significantly greater in the longitudinal direction in patients with PH, whereas patients without PH have equal contributions of transverse and longitudinal motion. Longitudinal RV motion is primarily associated with global RV pump function in PH. Transverse RV motion not only reflects global pump function but is independently influenced by ventricular interaction in patients with PH.

Right ventricular sex differences in patients with idiopathic pulmonary arterial hypertension characterised by magnetic resonance imaging: pair-matched case controlled study.

PURPOSE: Sex differences exist in both the prevalence and survival of patients with idiopathic pulmonary arterial hypertension (IPAH). Men are less frequently affected by the condition but have worse outcome as compared to females. We sought to characterise the sex related differences in right ventricular remodelling in age matched male and female patients with IPAH using cardiac magnetic resonance imaging (MRI). METHODS: A case controlled pair-matched study was conducted with patients matched by age and sex. Steady state free precession (SSFP) MRI of the heart was performed at 1.5T. Cardiac volume, function and mass measurements were corrected for age, sex and BSA according to reference data. RESULTS: 40 age and sex matched patients with IPAH were identified. The mean age was 57 (SD 17) in both male and female cohorts. Men had proportionally lower right ventricular (RV) ejection fraction, RV stroke volume and LV stroke volume than females, p=0.028, p=0.007 and p=0.013, respectively. However, there was no significant difference in RV mass or haemodynamic indices of mPAP and PVR between males and females. CONCLUSION: Male patients with IPAH have proportionally worse RV function despite similar afterload. We hypothesise that adaptive remodelling of the RV in response to increased afterload in IPAH is more effective in females.

LGE patterns in pulmonary hypertension do not impact overall mortality.

OBJECTIVES: The goal of this study was to determine the prognostic value of late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) features in patients with pulmonary hypertension. BACKGROUND: The prognostic significance of LGE in the clinical assessment of patients with pulmonary hypertension remains uncertain. METHODS: Consecutive patients with suspected pulmonary hypertension seen at a specialist pulmonary hypertension referral center who underwent right heart catheterization and CMR with LGE imaging within 48 h were identified. Short-axis late-enhancement imaging was performed using a 3-dimensional gradient spoiled echocardiography sequence on a 1.5-T scanner. Three groups were identified: 1) no late enhancement of the myocardium; 2) late enhancement at the right ventricular insertion points (LGE-IP); and 3) late enhancement involving the right ventricular insertion points and the interventricular septum (LGE-S). RESULTS: Of 194 patients, 162 had pulmonary hypertension. LGE was identified in 135 of 162 (83%) patients with pulmonary hypertension, and 47 (29%) of patients demonstrated LGE-S. Patients with LGE-S had significantly higher right ventricular end-diastolic volume index (p = 0.013) and lower mixed venous oxygen saturation (p = 0.045) than patients with LGE-IP alone. The presence of LGE-S (p = 0.022), but not LGE-IP alone, right ventricular end-systolic volume (p = 0.045), right ventricular ejection fraction (p = 0.034), mixed venous oxygen saturation (p = 0.021), mean right atrial pressure (0.027), and male sex (p = 0.002) predicted mortality. At multivariate analysis, male sex was the only significant predictor of mortality independent of covariate predictors (p = 0.027). CONCLUSIONS: The presence of LGE at the right ventricular insertion points is suggestive of the presence of pulmonary hypertension. LGE may also be more extensive, involving the septum; however, after multivariable analysis including other factors associated with pulmonary hypertension, septal LGE was not associated with an increase in overall mortality.

Dynamic contrast-enhanced magnetic resonance imaging in patients with pulmonary arterial hypertension.

Dynamic contrast-enhanced (DCE) time-resolved magnetic resonance (MR) imaging is a technique whereby the passage of an intravenous contrast bolus can be tracked through the pulmonary vascular system. The aim of this study was to investigate the prognostic significance of DCE-MR pulmonary blood transit times in patients with pulmonary arterial hypertension (PAH). Seventy-nine patients diagnosed with PAH underwent pulmonary DCE imaging at 1.5 T using a time-resolved three-dimensional spoiled gradient echo sequence. The prognostic significance of two DCE parameters, full width at half maximum (FWHM) of the first-pass clearance curve and pulmonary transit time (PTT), along with demographic and invasive catheter measurements, was evaluated by univariate and bivariate Cox proportional hazards regression and Kaplan-Meier analysis. DCE-MR transit times were most closely correlated with cardiac index (CI) and pulmonary vascular resistance index (PVRI) and were both found to be accurate for detecting reduced CI (FWHM area under the curve [AUC] at receiver operating characteristic analysis = 0.91 and PTT AUC = 0.92, respectively) and for detecting elevated PVRI (FWHM AUC = 0.88 and PTT AUC = 0.84, respectively). During the follow-up period, 25 patients died. Patients with longer measurements of FWHM (P = 0.0014) and PTT (P = 0.004) were associated with poor outcome at Kaplan-Meier analysis, and both parameters were strong predictors of adverse outcome from Cox proportional hazards analysis (P = 0.013 and 0.010, respectively). At bivariate analysis, DCE measurements predicted mortality independent of age, gender, and World Health Organization functional class; however, invasive hemodynamic indexes CI, PVRI, and DCE measurements were not independent of one another. In conclusion, DCE-MR transit times predict mortality in patients with PAH and are closely associated with clinical gold standards CI and PVRI.

Quantitative magnetic resonance imaging of pulmonary hypertension: a practical approach to the current state of the art.

Pulmonary hypertension is a condition of varied etiology, commonly associated with poor clinical outcome. Patients are categorized on the basis of pathophysiological, clinical, radiologic, and therapeutic similarities. Pulmonary arterial hypertension (PAH) is often diagnosed late in its disease course, with outcome dependent on etiology, disease severity, and response to treatment. Recent advances in quantitative magnetic resonance imaging (MRI) allow for better initial characterization and measurement of the morphologic and flow-related changes that accompany the response of the heart-lung axis to prolonged elevation of pulmonary arterial pressure and resistance and provide a reproducible, comprehensive, and noninvasive means of assessing the course of the disease and response to treatment. Typical features of PAH occur primarily as a result of increased pulmonary vascular resistance and the resultant increased right ventricular (RV) afterload. Several MRI-derived diagnostic markers have emerged, such as ventricular mass index, interventricular septal configuration, and average pulmonary artery velocity, with diagnostic accuracy similar to that of Doppler echocardiography. Furthermore, prognostic markers have been identified with independent predictive value for identification of treatment failure. Such markers include large RV end-diastolic volume index, low left ventricular end-diastolic volume index, low RV ejection fraction, and relative area change of the pulmonary trunk. MRI is ideally suited for longitudinal follow-up of patients with PAH because of its noninvasive nature and high reproducibility and is advantageous over other biomarkers in the study of PAH because of its sensitivity to change in morphologic, functional, and flow-related parameters. Further study on the role of MRI image based biomarkers in the clinical environment is warranted.

Prognostic value of cardiovascular magnetic resonance imaging measurements corrected for age and sex in idiopathic pulmonary arterial hypertension.

BACKGROUND: There are limited data on the prognostic value of cardiovascular magnetic resonance measurements in idiopathic pulmonary arterial hypertension, with no studies investigating the impact of correction of cardiovascular magnetic resonance indices for age and sex on prognostic value. METHODS AND RESULTS: Consecutive patients with idiopathic pulmonary arterial hypertension underwent cardiovascular magnetic resonance imaging at 1.5T. Steady-state free precession cardiac volumes and mass measurements were corrected for age, sex, and body surface area according to reference data and prognostic significance assessed. A total of 80 patients with idiopathic pulmonary arterial hypertension were identified, and 23 patients died during the mean follow-up of 32±14 months. Corrected for age, sex, and body surface area, right ventricular end-systolic volume (P=0.004) strongly predicted mortality, independent of World Health Organization functional class, mean right atrial pressure, cardiac index, and mixed venous oxygen saturations. CONCLUSIONS: Consideration should be given to correcting cardiovascular magnetic resonance measures for age, sex, and body surface area, particularly given the changing demographics of patients with idiopathic pulmonary arterial hypertension. Corrected right ventricular end-systolic volume is a strong prognostic marker in idiopathic pulmonary arterial hypertension, independent of invasively derived measurements, mean right atrial pressure cardiac index, and mixed venous oxygen saturations.

Noninvasive estimation of PA pressure, flow, and resistance with CMR imaging: derivation and prospective validation study from the ASPIRE registry.

OBJECTIVES: The aim of this study was to develop a composite numerical model based on parameters from cardiac magnetic resonance (CMR) imaging for noninvasive estimation of the key hemodynamic measurements made at right heart catheterization (RHC). BACKGROUND: Diagnosis and assessment of disease severity in patients with pulmonary hypertension is reliant on hemodynamic measurements at RHC. A robust noninvasive approach that can estimate key RHC measurements is desirable. METHODS: A derivation cohort of 64 successive, unselected, treatment naive patients with suspected pulmonary hypertension from the ASPIRE (Assessing the Spectrum of Pulmonary Hypertension Identified at a Referral Centre) Registry, underwent RHC and CMR within 12 h. Predicted mean pulmonary arterial pressure (mPAP) was derived using multivariate regression analysis of CMR measurements. The model was tested in an independent prospective validation cohort of 64 patients with suspected pulmonary hypertension. Surrogate measures of pulmonary capillary wedge pressure (PCWP) and cardiac output (CO) were estimated by left atrial volumetry and pulmonary arterial phase contrast imaging, respectively. Noninvasive pulmonary vascular resistance (PVR) was calculated from the CMR-derived measurements, defined as: (CMR-predicted mPAP - CMR-predicted PCWP)/CMR phase contrast CO. RESULTS: The following composite statistical model of mPAP was derived: CMR-predicted mPAP = -4.6 + (interventricular septal angle × 0.23) + (ventricular mass index × 16.3). In the validation cohort a strong correlation between mPAP and MR estimated mPAP was demonstrated (R(2) = 0.67). For detection of the presence of pulmonary hypertension the area under the receiver-operating characteristic (ROC) curve was 0.96 (0.92 to 1.00; p < 0.0001). CMR-estimated PVR reliably identified invasive PVR ≥3 Wood units (WU) with a high degree of accuracy, the area under the ROC curve was 0.94 (0.88 to 0.99; p < 0.0001). CONCLUSIONS: CMR imaging can accurately estimate mean pulmonary artery pressure in patients with suspected pulmonary hypertension and calculate PVR by estimating all major pulmonary hemodynamic metrics measured at RHC.

Pulmonary artery relative area change detects mild elevations in pulmonary vascular resistance and predicts adverse outcome in pulmonary hypertension.

OBJECTIVE: The aim of this study was to evaluate the clinical use of magnetic resonance imaging measurements related to pulmonary artery stiffness in the evaluation of pulmonary hypertension (PH). MATERIALS AND METHODS: A total of 134 patients with suspected PH underwent right heart catheterization (RHC) and magnetic resonance imaging on a 1.5-T scanner within 2 days. Phase contrast imaging at the pulmonary artery trunk and cine cardiac views were acquired. Pulmonary artery area change (AC), relative AC (RAC), compliance (AC/pulse pressure from RHC), distensibility (RAC/pulse pressure from RHC), right ventricular functional indices, and right ventricular mass were all derived. Regression curve fitting identified the statistical model of best fit between RHC measurements and pulmonary artery stiffness indices. The diagnostic accuracy and prognostic value of noninvasive AC and RAC were also assessed. RESULTS: The relationship between pulmonary vascular resistance and pulmonary artery RAC was best reflected by an inverse linear model. Patients with mild elevation in pulmonary vascular resistance (<4 Woods units) demonstrated reduced RAC (P = 0.02) and increased right ventricular mass index (P < 0.0001) without significant loss of right ventricular function (P = 0.17). At follow-up of 0 to 40 months, 18 patients with PH had died (16%). Analysis of Kaplan-Meier plots showed that both AC and RAC predicted mortality (log-rank test, P = 0.046 and P = 0.012, respectively). Area change and RAC were also predictors of mortality using univariate Cox proportional hazards regression analysis (P = 0.046 and P = 0.03, respectively). CONCLUSIONS: Noninvasive assessment of pulmonary artery RAC is a marker sensitive to early increased vascular resistance in PH and is a predictor of adverse outcome.

Diagnostic accuracy of cardiovascular magnetic resonance imaging of right ventricular morphology and function in the assessment of suspected pulmonary hypertension results from the ASPIRE registry.

BACKGROUND: Cardiovascular Magnetic Resonance (CMR) imaging is accurate and reproducible for the assessment of right ventricular (RV) morphology and function. However, the diagnostic accuracy of CMR derived RV measurements for the detection of pulmonary hypertension (PH) in the assessment of patients with suspected PH in the clinic setting is not well described. METHODS: We retrospectively studied 233 consecutive treatment naïve patients with suspected PH including 39 patients with no PH who underwent CMR and right heart catheterisation (RHC) within 48 hours. The diagnostic accuracy of multiple CMR measurements for the detection of mPAP ≥ 25 mmHg was assessed using Fisher's exact test and receiver operating characteristic (ROC) analysis. RESULTS: Ventricular mass index (VMI) was the CMR measurement with the strongest correlation with mPAP (r = 0.78) and the highest diagnostic accuracy for the detection of PH (area under the ROC curve of 0.91) compared to an ROC of 0.88 for echocardiography calculated mPAP. Late gadolinium enhancement, VMI ≥ 0.4, retrograde flow ≥ 0.3 L/min/m² and PA relative area change ≤ 15% predicted the presence of PH with a high degree of diagnostic certainty with a positive predictive value of 98%, 97%, 95% and 94% respectively. No single CMR parameter could confidently exclude the presence of PH. CONCLUSION: CMR is a useful alternative to echocardiography in the evaluation of suspected PH. This study supports a role for the routine measurement of ventricular mass index, late gadolinium enhancement and the use of phase contrast imaging in addition to right heart functional indices in patients undergoing diagnostic CMR evaluation for suspected pulmonary hypertension.

Black blood MRI has diagnostic and prognostic value in the assessment of patients with pulmonary hypertension.

OBJECTIVES: Double inversion recovery (DIR) "black blood" MRI suppresses the signal from flowing blood, slow flowing blood causes incomplete suppression resulting in pulmonary blood flow artefact (PFA). This study examines the diagnostic utility and prognostic value of a PFA scoring system in a mixed cohort of patients with pulmonary hypertension (PH). METHODS: DIR-MRI images were reviewed for 233 patients referred with suspected PH who underwent right heart catheterisation (RHC) within 48 h of MR. The degree of PFA was visually scored in all patients from 0 to 5 (0 = absent, 1 = segmental, 2 = lobar, 3 = distal main, 4 = proximal main and 5 = trunk). Pulmonary artery (PA), aorta (Ao), and PA main branch diameters were measured from which PA/Ao ratios and mean PA branch diameters (MPAB) were calculated. RESULTS: PFA >1 demonstrated high sensitivity (86%) and specificity (85%) for the diagnosis PH in our mixed patient cohort. A good correlation was found with PFA and haemodynamic parameters, PVR (r = 0.70), mPAP (r = 0.65) and CI (r = -0.53). PFA predicted mortality (P = 0.005) during the mean follow-up for 19 months. PFA scoring demonstrated good inter-observer agreement (k = 0.83). CONCLUSIONS: PFA scoring is of diagnostic and prognostic value in the assessment of patients with suspected PH. and is a predictor of mortality. KEY POINTS: • A simple magnetic resonance method of assessing pulmonary blood flow is presented • This involves a qualitative scoring system of black blood pulmonary flow artefacts • This is simple to perform and seems reproducible in pulmonary hypertension patients • The degree of artefact correlates well with right heart catheter measurements • Prominent pulmonary flow artefact predicts mortality in patients with pulmonary hypertension.