Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging.

Cardiac magnetic resonance imaging (CMR) is the gold standard for cardiac function assessment and plays a crucial role in diagnosing cardiovascular disease (CVD). However, its widespread application has been limited by the heavy resource burden of CMR interpretation. Here, to address this challenge, we developed and validated computerized CMR interpretation for screening and diagnosis of 11 types of CVD in 9,719 patients. We propose a two-stage paradigm consisting of noninvasive cine-based CVD screening followed by cine and late gadolinium enhancement-based diagnosis. The screening and diagnostic models achieved high performance (area under the curve of 0.988 ± 0.3% and 0.991 ± 0.0%, respectively) in both internal and external datasets. Furthermore, the diagnostic model outperformed cardiologists in diagnosing pulmonary arterial hypertension, demonstrating the ability of artificial intelligence-enabled CMR to detect previously unidentified CMR features. This proof-of-concept study holds the potential to substantially advance the efficiency and scalability of CMR interpretation, thereby improving CVD screening and diagnosis.

Left ventricular strain changes at high altitude in rats: a cardiac magnetic resonance tissue tracking imaging study.

BACKGROUND: Long-term exposure to a high altitude environment with low pressure and low oxygen could cause abnormalities in the structure and function of the heart. Myocardial strain is a sensitive indicator for assessing myocardial dysfunction, monitoring myocardial strain is of great significance for the early diagnosis and treatment of high altitude heart-related diseases. This study applies cardiac magnetic resonance tissue tracking technology (CMR-TT) to evaluate the changes in left ventricular myocardial function and structure in rats in high altitude environment. METHODS: 6-week-old male rats were randomized into plateau hypoxia rats (plateau group, n = 21) as the experimental group and plain rats (plain group, n = 10) as the control group. plateau group rats were transported from Chengdu (altitude: 360 m), a city in a plateau located in southwestern China, to the Qinghai-Tibet Plateau (altitude: 3850 m), Yushu, China, and then fed for 12 weeks there, while plain group rats were fed in Chengdu(altitude: 360 m), China. Using 7.0 T cardiac magnetic resonance (CMR) to evaluate the left ventricular ejection fraction (EF), end-diastolic volume (EDV), end-systolic volume (ESV) and stroke volume (SV), as well as myocardial strain parameters including the peak global longitudinal (GLS), radial (GRS), and circumferential strain (GCS). The rats were euthanized and a myocardial biopsy was obtained after the magnetic resonance imaging scan. RESULTS: The plateau rats showed more lower left ventricular GLS and GRS (P < 0.05) than the plain rats. However, there was no statistically significant difference in left ventricular EDV, ESV, SV, EF and GCS compared to the plain rats (P > 0.05). CONCLUSIONS: After 12 weeks of exposure to high altitude low-pressure hypoxia environment, the left ventricular global strain was partially decreased and myocardium is damaged, while the whole heart ejection fraction was still preserved, the myocardial strain was more sensitive than the ejection fraction in monitoring cardiac function.

Diagnostic value of LGE and T1 mapping in multiple myeloma patients'heart.

BACKGROUND: Unidentified heart failure occurs in patients with multiple myeloma when their heart was involved. CMR with late gadolinium enhancement (LGE) and T1 mapping can identify myocardial amyloid infiltrations. PURPOSE: To explore the role of CMR with late gadolinium enhancement (LGE) and T1 mapping for detection of multiple myeloma patients'heart. MATERIAL AND METHODS: A total of 16 MM patients with above underwent CMR (3.0-T) with T1 mapping (pre-contrast and post-contrast) and LGE imaging. In addition, 26 patients with non-obstructive hypertrophic cardiomyopathy and 26 healthy volunteers were compared to age- and sex-matched healthy controls without a history of cardiac disease, diabetes mellitus, or normal in CMR. All statistical analyses were performed using the statistical software GraphPad Prism. The measurement data were represented by median (X) and single sample T test was adopted. Enumeration data were represented by examples and Chi-tested was adopted. All tests were two-sided, and P values < 0.05 were considered statistically significant. RESULTS: In MM group, LVEF was lower than healthy controls and higher than that of non-obstructive hypertrophic cardiomyopathy group, but without statistically significant difference (%: 49.1 ± 17.5 vs. 55.6 ± 10.3, 40.4 ± 15.6, all P > 0.05). Pre-contrast T1 values of MM group were obviously higher than those of healthy controls and non-obstructive hypertrophic cardiomyopathy group (ms:1462.0 ± 71.3vs. 1269.3 ± 42.3, 1324.0 ± 45.1, all P < 0.05). 16 cases (100%) in MM group all had LGE. CONCLUSION: LGE joint T1 mapping wider clinical use techniques and follow-up the patients'disease severity.

Multimodality imaging in arrhythmogenic cardiomyopathy - From diagnosis to management.

Arrhythmogenic Cardiomyopathy (AC), an inherited cardiac disorder characterized by myocardial fibrofatty replacement, carries a significant risk of sudden cardiac death (SCD) due to ventricular arrhythmias. A comprehensive multimodality imaging approach, including echocardiography, cardiac magnetic resonance imaging (CMR), and cardiac computed tomography (CCT), allows for accurate diagnosis, effective risk stratification, vigilant monitoring, and appropriate intervention, leading to improved patient outcomes and the prevention of SCD. Echocardiography is primary tool ventricular morphology and function assessment, CMR provides detailed visualization, CCT is essential in early stages for excluding congenital anomalies and coronary artery disease. Echocardiography is preferred for follow-up, with CMR capturing changes over time. The strategic use of these imaging methods aids in confirming AC, differentiating it from other conditions, tracking its progression, managing complications, and addressing end-stage scenarios.

Light-Chain Cardiac Amyloidosis: Cardiac Magnetic Resonance for Assessing Response to Chemotherapy.

OBJECTIVE: Cardiac magnetic resonance (CMR) is a diagnostic tool that provides precise and reproducible information about cardiac structure, function, and tissue characterization, aiding in the monitoring of chemotherapy response in patients with light-chain cardiac amyloidosis (AL-CA). This study aimed to evaluate the feasibility of CMR in monitoring responses to chemotherapy in patients with AL-CA. MATERIALS AND METHODS: In this prospective study, we enrolled 111 patients with AL-CA (50.5% male; median age, 54 [interquartile range, 49-63] years). Patients underwent longitudinal monitoring using biomarkers and CMR imaging. At follow-up after chemotherapy, patients were categorized into superior and inferior response groups based on their hematological and cardiac laboratory responses to chemotherapy. Changes in CMR findings across therapies and differences between response groups were analyzed. RESULTS: Following chemotherapy (before vs. after), there were significant increases in myocardial T2 (43.6 ± 3.5 ms vs. 44.6 ± 4.1 ms; P = 0.008), recovery in right ventricular (RV) longitudinal strain (median of -9.6% vs. -11.7%; P = 0.031), and decrease in RV extracellular volume fraction (ECV) (median of 53.9% vs. 51.6%; P = 0.048). These changes were more pronounced in the superior-response group. Patients with superior cardiac laboratory response showed significantly greater reductions in RV ECV (-2.9% [interquartile range, -8.7%-1.1%] vs. 1.7% [-5.5%-7.1%]; P = 0.017) and left ventricular ECV (-2.0% [-6.0%-1.3%] vs. 2.0% [-3.0%-5.0%]; P = 0.01) compared with those with inferior response. CONCLUSION: Cardiac amyloid deposition can regress following chemotherapy in patients with AL-CA, particularly showing more prominent regression, possibly earlier, in the RV. CMR emerges as an effective tool for monitoring associated tissue characteristics and ventricular functional recovery in patients with AL-CA undergoing chemotherapy, thereby supporting its utility in treatment response assessment.

3D cine-magnetic resonance imaging using spatial and temporal implicit neural representation learning (STINR-MR).

Objective. 3D cine-magnetic resonance imaging (cine-MRI) can capture images of the human body volume with high spatial and temporal resolutions to study anatomical dynamics. However, the reconstruction of 3D cine-MRI is challenged by highly under-sampled k-space data in each dynamic (cine) frame, due to the slow speed of MR signal acquisition. We proposed a machine learning-based framework, spatial and temporal implicit neural representation learning (STINR-MR), for accurate 3D cine-MRI reconstruction from highly under-sampled data.Approach. STINR-MR used a joint reconstruction and deformable registration approach to achieve a high acceleration factor for cine volumetric imaging. It addressed the ill-posed spatiotemporal reconstruction problem by solving a reference-frame 3D MR image and a corresponding motion model that deforms the reference frame to each cine frame. The reference-frame 3D MR image was reconstructed as a spatial implicit neural representation (INR) network, which learns the mapping from input 3D spatial coordinates to corresponding MR values. The dynamic motion model was constructed via a temporal INR, as well as basis deformation vector fields (DVFs) extracted from prior/onboard 4D-MRIs using principal component analysis. The learned temporal INR encodes input time points and outputs corresponding weighting factors to combine the basis DVFs into time-resolved motion fields that represent cine-frame-specific dynamics. STINR-MR was evaluated using MR data simulated from the 4D extended cardiac-torso (XCAT) digital phantom, as well as two MR datasets acquired clinically from human subjects. Its reconstruction accuracy was also compared with that of the model-based non-rigid motion estimation method (MR-MOTUS) and a deep learning-based method (TEMPEST).Main results. STINR-MR can reconstruct 3D cine-MR images with high temporal (<100 ms) and spatial (3 mm) resolutions. Compared with MR-MOTUS and TEMPEST, STINR-MR consistently reconstructed images with better image quality and fewer artifacts and achieved superior tumor localization accuracy via the solved dynamic DVFs. For the XCAT study, STINR reconstructed the tumors to a mean ± SD center-of-mass error of 0.9 ± 0.4 mm, compared to 3.4 ± 1.0 mm of the MR-MOTUS method. The high-frame-rate reconstruction capability of STINR-MR allows different irregular motion patterns to be accurately captured.Significance. STINR-MR provides a lightweight and efficient framework for accurate 3D cine-MRI reconstruction. It is a 'one-shot' method that does not require external data for pre-training, allowing it to avoid generalizability issues typically encountered in deep learning-based methods.

Analysis of left ventricle regional myocardial motion for cardiac radioablation: Left ventricular motion analysis.

PURPOSE: Left ventricle (LV) regional myocardial displacement due to cardiac motion was assessed using cardiovascular magnetic resonance (CMR) cine images to establish region-specific margins for cardiac radioablation treatments. METHODS: CMR breath-hold cine images and LV myocardial tissue contour points were analyzed for 200 subjects, including controls (n = 50) and heart failure (HF) patients with preserved ejection fraction (HFpEF, n = 50), mid-range ejection fraction (HFmrEF, n = 50), and reduced ejection fraction (HFrEF, n = 50). Contour points were divided into segments according to the 17-segment model. For each patient, contour point displacements were determined for the long-axis (all 17 segments) and short-axis (segments 1-12) directions. Mean overall, tangential (longitudinal or circumferential), and normal (radial) displacements were calculated for the 17 segments and for each segment level. RESULTS: The greatest overall motion was observed in the control group-long axis: 4.5 ± 1.2 mm (segment 13 [apical anterior] epicardium) to 13.8 ± 3.0 mm (segment 6 [basal anterolateral] endocardium), short axis: 4.3 ± 0.8 mm (segment 9 [mid inferoseptal] epicardium) to 11.5 ± 2.3 mm (segment 1 [basal anterior] endocardium). HF patients exhibited lesser motion, with the smallest overall displacements observed in the HFrEF group-long axis: 4.3 ± 1.7 mm (segment 13 [apical anterior] epicardium) to 10.6 ± 3.4 mm (segment 6 [basal anterolateral] endocardium), short axis: 3.9 ± 1.3 mm (segment 8 [mid anteroseptal] epicardium) to 7.4 ± 2.8 mm (segment 1 [basal anterior] endocardium). CONCLUSIONS: This analysis provides an estimate of epicardial and endocardial displacement for the 17 segments of the LV for patients with normal and impaired LV function. This reference data can be used to establish treatment planning margin guidelines for cardiac radioablation. Smaller margins may be used for patients with higher degree of impaired heart function, depending on the LV segment.

Right ventricular scalloping index as cardiac magnetic resonance-derived marker for diagnosis of arrhythmogenic right ventricular cardiomyopathy.

BACKGROUND: The cardiac magnetic resonance (CMR) evaluation of right ventricular (RV) morphologic abnormalities in patients with arrhythmogenic right ventricular cardiomyopathy (ARVC) is subjective. Here, we aimed to use a quantitative index, the right ventricular scalloping index (RVSI), to standardize the measurement of RV free wall scalloping and aid in the imaging diagnosis. METHODS: We retrospectively included 15 patients with definite ARVC and 45 age- and sex-matched patients with idiopathic right ventricular outflow tract ventricular arrhythmia (RVOT-VA) as controls. The RVSI was measured from cine images on four-chamber view to evaluate its ability to distinguish between ARVC and RVOT-VA patients. Other cardiac functional parameters including strain analysis were also performed. RESULTS: The RVSI was significantly higher in the ARVC than RVOT-VA group (1.56 ± 0.23 vs 1.30 ± 0.08, p < 0.001). The diagnostic performance of the RVSI was superior to the RV global longitudinal, circumferential, and radial strains, RV ejection fraction, and RV end-diastolic volume index. The RVSI demonstrated high intraobserver and interobserver reliability (intraclass correlation coefficient, 0.94 and 0.96, respectively). RVSI was a strong discriminator between ARVC and RVOT-VA patients (area under curve [AUC], 0.91; 95% CI, 0.82-0.99). A cutoff value of RVSI ≥1.49 provided an accuracy of 90.0%, specificity of 97.8%, sensitivity of 66.7%, positive predictive value (PPV) of 90.9%, and a negative predictive value (NPV) of 89.8%. In a multivariable analysis, a family history of ARVC or sudden cardiac death (odds ratio, 38.71; 95% CI, 1.48-1011.05; p = 0.028) and an RVSI ≥1.49 (odds ratio, 64.72; 95% CI, 4.58-914.63; p = 0.002) remained predictive of definite ARVC. CONCLUSION: RVSI is a quantitative method with good performance for the diagnosis of definite ARVC.

Convolutional LSTM model for cine image prediction of abdominal motion.

Objective.In this study, we tackle the challenge of latency in magnetic resonance linear accelerator (MR-Linac) systems, which compromises target coverage accuracy in gated real-time radiotherapy. Our focus is on enhancing motion prediction precision in abdominal organs to address this issue. We developed a convolutional long short-term memory (convLSTM) model, utilizing 2D cine magnetic resonance (cine-MR) imaging for this purpose.Approach.Our model, featuring a sequence-to-one architecture with six input frames and one output frame, employs structural similarity index measure (SSIM) as loss function. Data was gathered from 17 cine-MRI datasets using the Philips Ingenia MR-sim system and an Elekta Unity MR-Linac equivalent sequence, focusing on regions of interest (ROIs) like the stomach, liver, pancreas, and kidney. The datasets varied in duration from 1 to 10 min.Main results.The study comprised three main phases: hyperparameter optimization, individual training, and transfer learning with or without fine-tuning. Hyperparameters were initially optimized to construct the most effective model. Then, the model was individually applied to each dataset to predict images four frames ahead (1.24-3.28 s). We evaluated the model's performance using metrics such as SSIM, normalized mean square error, normalized correlation coefficient, and peak signal-to-noise ratio, specifically for ROIs with target motion. The average SSIM values achieved were 0.54, 0.64, 0.77, and 0.66 for the stomach, liver, kidney, and pancreas, respectively. In the transfer learning phase with fine-tuning, the model showed improved SSIM values of 0.69 for the liver and 0.78 for the kidney, compared to 0.64 and 0.37 without fine-tuning.Significance. The study's significant contribution is demonstrating the convLSTM model's ability to accurately predict motion for multiple abdominal organs using a Unity-equivalent MR sequence. This advancement is key in mitigating latency issues in MR-Linac radiotherapy, potentially improving the precision and effectiveness of real-time treatment for abdominal cancers.

Assessment and validation of glottic motion using cone-beam CT and real-time cine MRI.

PURPOSE: This study aimed to assess the margin for the planning target volume (PTV) using the Van Herk formula. We then validated the proposed margin by real-time magnetic resonance imaging (MRI). METHODS: An analysis of cone-beam computed tomography (CBCT) data from early glottic cancer patients was performed to evaluate organ motion. Deformed clinical target volumes (CTV) after rigid registration were acquired using the Velocity program (Varian Medical Systems, Palo Alto, CA, USA). Systematic (Σ) and random errors (σ) were evaluated. The margin for the PTV was defined as 2.5 Σ + 0.7 σ according to the Van Herk formula. To validate this margin, we accrued healthy volunteers. Sagittal real-time cine MRI was conducted using the ViewRay system (ViewRay Inc., Oakwood Village, OH, USA). Within the obtained sagittal images, the vocal cord was delineated. The movement of the vocal cord was summed up and considered as the internal target volume (ITV). We then assessed the degree of overlap between the ITV and the PTV (vocal cord plus margins) by calculating the volume overlap ratio, represented as (ITV∩PTV)/ITV. RESULTS: CBCTs of 17 early glottic patients were analyzed. Σ and σ were 0.55 and 0.57 for left-right (LR), 0.70 and 0.60 for anterior-posterior (AP), and 1.84 and 1.04 for superior-inferior (SI), respectively. The calculated margin was 1.8 mm (LR), 2.2 mm (AP), and 5.3 mm (SI). Four healthy volunteers participated for validation. A margin of 3 mm (AP) and 5 mm (SI) was applied to the vocal cord as the PTV. The average volume overlap ratio between ITV and PTV was 0.92 (range 0.85-0.99) without swallowing and 0.77 (range 0.70-0.88) with swallowing. CONCLUSION: By evaluating organ motion by using CBCT, the margin was 1.8 (LR), 2.2 (AP), and 5.3 mm (SI). The margin acquired using CBCT fitted well in real-time cine MRI. Given that swallowing during radiotherapy can result in a substantial displacement, it is crucial to consider strategies aimed at minimizing swallowing and related motion.

The usefulness of speckle tracking echocardiography for the prediction of cardiac involvement in patients with biopsy-proven sarcoidosis.

INTRODUCTION: Cardiac sarcoidosis (CS) is commonly diagnosed based on clinical criteria and abnormalities in noninvasive imaging reported in patients with biopsy-proven extracardiac sarcoidosis. Electrocardiogram and two-dimensional echocardiography have a low sensitivity for CS detection. Cardiovascular magnetic resonance imaging (CMR) and positron emission tomography (PET) have limitations in terms of cost and availability. OBJECTIVES: This study aimed to assess the usefulness of left ventricular longitudinal strain, measured using two-dimensional speckle tracking echocardiography (STE), for the prediction of late gadolinium enhancement (LGE) presence in CMR in patients with biopsy-proven sarcoidosis. PATIENTS AND METHODS: A total of 119 patients with biopsy-proven extracardiac sarcoidosis were divided, according to the clinical criteria proposed by the 2014 Heart Rhythm Society expert consensus statement (HRS 2014), into two groups: 43 individuals with "probable cardiac sarcoidosis", CS(+) and 76 individuals without cardiac sarcoidosis, CS (-). Data from echocardiography, CMR, 12-lead ECG and 24 h Holter monitoring were analyzed. RESULTS: Left ventricular global longitudinal strain (LV-GLS) was slightly reduced in the entire sarcoidosis group (-18.61± 2.96), no difference between the CS (+) and CS (-) subgroups was found (-18.0% ± 3.2% and -18.9% ± 2.8%, respectively; p = .223). No cut-off value for LV-GLS was identified that could predict the presence of LGE. Segmental longitudinal strain impairment partially correlated with the presence of LGE on CMR. CONCLUSIONS: In our cohort of sarcoidosis patients, segmental longitudinal strain proved more helpful in the diagnostic process than LV-GLS. The ultimate role of STE in the diagnosis of CS remains to be established.

Cardiac Magnetic Resonance to Predict Cardiac Mass Malignancy: The CMR Mass Score.

BACKGROUND: Multimodality imaging is currently suggested for the noninvasive diagnosis of cardiac masses. The identification of cardiac masses' malignant nature is essential to guide proper treatment. We aimed to develop a cardiac magnetic resonance (CMR)-derived model including mass localization, morphology, and tissue characterization to predict malignancy (with histology as gold standard), to compare its accuracy versus the diagnostic echocardiographic mass score, and to evaluate its prognostic ability. METHODS: Observational cohort study of 167 consecutive patients undergoing comprehensive echocardiogram and CMR within 1-month time interval for suspected cardiac mass. A definitive diagnosis was achieved by histological examination or, in the case of cardiac thrombi, by histology or radiological resolution after adequate anticoagulation treatment. Logistic regression was performed to assess CMR-derived independent predictors of malignancy, which were included in a predictive model to derive the CMR mass score. Kaplan-Meier curves and Cox regression were used to investigate the prognostic ability of predictors. RESULTS: In CMR, mass morphological features (non-left localization, sessile, polylobate, inhomogeneity, infiltration, and pericardial effusion) and mass tissue characterization features (first-pass perfusion and heterogeneity enhancement) were independent predictors of malignancy. The CMR mass score (range, 0-8 and cutoff, ≥5), including sessile appearance, polylobate shape, infiltration, pericardial effusion, first-pass contrast perfusion, and heterogeneity enhancement, showed excellent accuracy in predicting malignancy (areas under the curve, 0.976 [95% CI, 0.96-0.99]), significantly higher than diagnostic echocardiographic mass score (areas under the curve, 0.932; P=0.040). The agreement between the diagnostic echocardiographic mass and CMR mass scores was good (κ=0.66). A CMR mass score of ≥5 predicted a higher risk of all-cause death (P<0.001; hazard ratio, 5.70) at follow-up. CONCLUSIONS: A CMR-derived model, including mass morphology and tissue characterization, showed excellent accuracy, superior to echocardiography, in predicting cardiac masses malignancy, with prognostic implications.

Percutaneous intramyocardial septal radiofrequency ablation after 5-year follow-up.

OBJECTIVE: The objective is to evaluate the 5-year follow-up results of percutaneous intramyocardial septal radiofrequency ablation (PIMSRA) for hypertrophic obstructive cardiomyopathy (HOCM), including clinical status, electrocardiographic and echocardiographic characteristics. METHODS: 27 patients (age: 44.3±15.5 years; 67% men, 33% women) with severely symptomatic HOCM who underwent PIMSRA from October 2016 to September 2017 were included. Their clinical status, resting and exercise stress echocardiography, electrocardiography and cardiac MRI (CMRI) after long-term follow-up were assessed. RESULTS: One patient died of intracerebral haemorrhage 1 year post procedurally. The New York Heart Association class, Canadian Cardiovascular Society class and exercise-induced syncopal attacks improved significantly in 26 patients (all p<0.01). Left ventricular (LV) outflow tract gradients revealed sustained reduction (resting: from 95.0 to 9.0 mm Hg, p<0.001; post exercise: from 130.5 to 21.0 mm Hg, p<0.001). The echocardiographic evaluation revealed decreased septal thickness, LV posterior wall thickness and left atrial (LA) diameter (all p<0.001). CMRI data revealed decrease in LV mass index and LA volume index and increase in LV end-diastolic volume index and stroke volume index between baseline and long-term follow-up (all p<0.05). The global longitudinal strain of LV improved from (-11.9%±3.7%) before the procedure to (-13.1%±3.9%) at the last check (p<0.001). Malignant ventricular arrhythmia and heart failure events were not observed. CONCLUSIONS: PIMSRA can effectively alleviate symptoms in patients with HOCM and improve their hemodynamics in the long term. TRIAL REGISTRATION NUMBER: NCT02888132.

Cardiac MRI feature-tracking-derived torsion mechanics in systolic and diastolic dysfunction in systemic light-chain cardiac amyloidosis.

AIM: To describe the myocardial torsion mechanics in cardiac amyloidosis (CA), and evaluate the correlations between left ventricle (LV) torsion mechanics and conventional parameters using cardiac magnetic resonance imaging feature tracking (CMR-FT). MATERIALS AND METHODS: One hundred and thirty-nine patients with light-chain CA (AL-CA) were divided into three groups: group 1 with preserved systolic function (LV ejection fraction [LVEF] ≥50%, n=55), group 2 with mildly reduced systolic function (40% ≤ LVEF <50%, n=51), and group 3 with reduced systolic function (LVEF <40%, n=33), and compared with age- and gender-matched healthy controls (n=26). All patients underwent cine imaging and late gadolinium-enhancement (LGE). Cine images were analysed offline using CMR-FT to estimate torsion parameters. RESULTS: Global torsion, base-mid torsion, and peak diastolic torsion rate (diasTR) were significantly impaired in patients with preserved systolic function (p<0.05 for all), whereas mid-apex torsion and peak systolic torsion rate (sysTR) were preserved (p>0.05 for both) compared with healthy controls. In patients with mildly reduced systolic function, global torsion and base-mid torsion were lower compared to those with preserved systolic function (p<0.05 for both), while mid-apex torsion, sysTR, and diasTR were preserved (p>0.05 for all). In patients with reduced systolic function, only sysTR was significantly worse compared with mildly reduced systolic function (p<0.05). At multivariable analysis, right ventricle (RV) end-systolic volume RVESV index and NYHA class were independently related to global torsion, whereas LVEF was independently related to sysTR. RV ejection fraction (RVEF) was independently related to diasTR. LV global torsion performed well (AUC 0.71; 95% confidence interval [CI]: 0.61, 0.77) in discriminating transmural from non-transmural LGE in AL-CA patients. CONCLUSION: LV torsion mechanics derived by CMR-FT could help to monitor LV systolic and diastolic function in AL-CA patients and function as a new imaging marker for LV dysfunction and LGE transmurality.

Assessment of deep learning segmentation for real-time free-breathing cardiac magnetic resonance imaging at rest and under exercise stress.

In recent years, a variety of deep learning networks for cardiac MRI (CMR) segmentation have been developed and analyzed. However, nearly all of them are focused on cine CMR under breathold. In this work, accuracy of deep learning methods is assessed for volumetric analysis (via segmentation) of the left ventricle in real-time free-breathing CMR at rest and under exercise stress. Data from healthy volunteers (n = 15) for cine and real-time free-breathing CMR at rest and under exercise stress were analyzed retrospectively. Exercise stress was performed using an ergometer in the supine position. Segmentations of two deep learning methods, a commercially available technique (comDL) and an openly available network (nnU-Net), were compared to a reference model created via the manual correction of segmentations obtained with comDL. Segmentations of left ventricular endocardium (LV), left ventricular myocardium (MYO), and right ventricle (RV) are compared for both end-systolic and end-diastolic phases and analyzed with Dice's coefficient. The volumetric analysis includes the cardiac function parameters LV end-diastolic volume (EDV), LV end-systolic volume (ESV), and LV ejection fraction (EF), evaluated with respect to both absolute and relative differences. For cine CMR, nnU-Net and comDL achieve Dice's coefficients above 0.95 for LV and 0.9 for MYO, and RV. For real-time CMR, the accuracy of nnU-Net exceeds that of comDL overall. For real-time CMR at rest, nnU-Net achieves Dice's coefficients of 0.94 for LV, 0.89 for MYO, and 0.90 for RV and the mean absolute differences between nnU-Net and the reference are 2.9 mL for EDV, 3.5 mL for ESV, and 2.6% for EF. For real-time CMR under exercise stress, nnU-Net achieves Dice's coefficients of 0.92 for LV, 0.85 for MYO, and 0.83 for RV and the mean absolute differences between nnU-Net and reference are 11.4 mL for EDV, 2.9 mL for ESV, and 3.6% for EF. Deep learning methods designed or trained for cine CMR segmentation can perform well on real-time CMR. For real-time free-breathing CMR at rest, the performance of deep learning methods is comparable to inter-observer variability in cine CMR and is usable for fully automatic segmentation. For real-time CMR under exercise stress, the performance of nnU-Net could promise a higher degree of automation in the future.

Prognostic value of native T1 and extracellular volume in patients with immunoglubin light-chain amyloidosis.

BACKGROUND: Cardiac involvement in patients with immunoglubin light-chain amyloidosis (AL) is a major determinant of treatment choice and prognosis, and early identification of high-risk patients can initiate intensive treatment strategies to achieve better survival. This study aimed to investigate the prognostic value of native T1 and ECV in patients with AL-cardiac amyloidosis (CA). METHODS: A total of 38 patients (mean age 59 ± 11 years) with AL diagnosed histopathologically from July 2017 to October 2021 were collected consecutively. All patients were performed 3.0-T cardiac magnetic resonance (CMR) including cine, T1 mapping, and late gadolinium enhancement (LGE). Pre- and post-contrast T1 mapping images were transferred to a dedicated research software package (CVI42 v5.11.3) to create parametric T1 and ECV values. In addition, clinical and laboratory data of all patients were collected, and patients or their family members were regularly followed up by telephone every 3 months. The starting point of follow-up was the time of definitive pathological diagnosis, and the main endpoint was all-cause death. Kaplan-Meier analysis and Cox proportional risk model were used to evaluate the association between native T1 and ECV and death in patients with CA. RESULTS: After a median follow-up of 27 (16, 37) months, 12 patients with CA died. Kaplan-Meier analysis showed that elevated native T1 and ECV were closely associated with poor prognosis in patients with CA. The survival rate of patients with ECV > 44% and native T1 > 1389ms were significantly lower than that of patients with ECV ≤ 44% and native T1 ≤ 1389ms (Log-rank P < 0.001), and was not associated with the presence of LGE. After adjusting for clinical risk factors and CMR measurements in a stepwise multivariate Cox regression model, ECV [risk ratio (HR):1.37, 95%CI: 1.09-1.73, P = 0.008] and native T1 (HR:1.01, 95%CI: 1.00-1.02, P = 0.037) remained independent predictors of all-cause mortality in patients with CA. CONCLUSIONS: Both native T1 and ECV were independently prognostic for mortality in patients with CA, and can be used as important indicators for clinical prognosis assessment of AL.

Cardiac magnetic resonance imaging in heart transplant recipients with biopsy-negative graft dysfunction.

AIMS: Graft dysfunction (GD) after heart transplantation (HTx) can develop without evidence of cell- or antibody-mediated rejection. Cardiac magnetic resonance imaging (CMR) has an evolving role in detecting rejection; however, its role in biopsy-negative GD has not been described. This study examines CMR findings, evaluates outcomes based on CMR results, and seeks to identify the possibility of rejection missed through endomyocardial biopsy by using CMR in HTx recipients with biopsy-negative GD. METHODS AND RESULTS: HTx recipients with GD [defined as a decrease in left ventricular ejection fraction (LVEF) by >5% and LVEF < 50%] in the absence of rejection by biopsy or allograft vasculopathy and who underwent CMR were included in the study. The primary outcome was a composite of all-cause mortality, re-transplantation, or persistent LVEF < 50%. Overall, 34 HTx recipients developed biopsy-negative GD and underwent CMR. Left ventricular late gadolinium enhancement (LGE) on CMR was observed in 16 patients with two distinct patterns: diffuse epicardial (n = 13) and patchy (n = 3) patterns. Patients with LGE developed GD later after HTx [4 (1.4-6.8) vs. 0.8 (0.3-1.2) years, P < 0.001], were more often symptomatic (88% vs. 56%, P = 0.06), and had greater haemodynamic derangement (pulmonary capillary wedge pressure: 19 ± 7 vs. 13 ± 3 mmHg, P = 0.002) as compared with those without LGE. No significant difference was observed in the primary composite outcome between patients with LGE and those without LGE (50% vs. 38% of patients with events, P = 0.515). During a median follow-up of 3.8 years, mean LVEF improved similarly in the LGE-negative (37-55%) and LGE-positive groups (32-55%) (P = 0.16). CONCLUSIONS: Biopsy-negative GD occurs with and without LGE when assessed by CMR, indicative of possible rejection/inflammation occurring only in a subset of patients. Irrespective of LGE, LVEF improvement occurs in most GD patients, suggesting that other neurohormonal or immunomodulatory mechanisms may also contribute to GD development.

SwinUNet: a multiscale feature learning approach to cardiovascular magnetic resonance parametric mapping for myocardial tissue characterization.

Objective.Cardiovascular magnetic resonance (CMR) can measure T1 and T2 relaxation times for myocardial tissue characterization. However, the CMR procedure for T1/T2 parametric mapping is time-consuming, making it challenging to scan heart patients routinely in clinical practice. This study aims to accelerate CMR parametric mapping with deep learning.Approach. A deep-learning model, SwinUNet, was developed to accelerate T1/T2 mapping. SwinUNet used a convolutional UNet and a Swin transformer to form a hierarchical 3D computation structure, allowing for analyzing CMR images spatially and temporally with multiscale feature learning. A comparative study was conducted between SwinUNet and an existing deep-learning model, MyoMapNet, which only used temporal analysis for parametric mapping. The T1/T2 mapping performance was evaluated globally using mean absolute error (MAE) and structural similarity index measure (SSIM). The clinical T1/T2 indices for characterizing the left-ventricle myocardial walls were also calculated and evaluated using correlation and Bland-Altman analysis.Main results. We performed accelerated T1 mapping with ≤4 heartbeats and T2 mapping with 2 heartbeats in reference to the clinical standard, which required 11 heartbeats for T1 mapping and 3 heartbeats for T2 mapping. SwinUNet performed well in all the experiments (MAE < 50 ms, SSIM > 0.8, correlation > 0.75, and Bland-Altman agreement limits < 100 ms for T1 mapping; MAE < 1 ms, SSIM > 0.9, correlation > 0.95, and Bland-Altman agreement limits < 1.5 ms for T2 mapping). When the maximal acceleration was used (2 heartbeats), SwinUNet outperformed MyoMapNet and gave measurement accuracy similar to the clinical standard.Significance. SwinUNet offers an optimal solution to CMR parametric mapping for assessing myocardial diseases quantitatively in clinical cardiology.

Association of global longitudinal strain by feature tracking cardiac magnetic resonance imaging with adverse outcomes among community-dwelling adults without cardiovascular disease: The Dallas Heart Study.

AIM: Left ventricular (LV) global longitudinal strain (GLS) may detect subtle abnormalities in myocardial contractility among individuals with normal LV ejection fraction (LVEF). However, the prognostic implications of GLS among healthy, community-dwelling adults is not well-established. METHODS AND RESULTS: Overall, 2234 community-dwelling adults (56% women, 47% Black) with LVEF ≥50% without a history of cardiovascular disease (CVD) from the Dallas Heart Study who underwent cardiac magnetic resonance (CMR) with GLS assessed by feature tracking CMR (FT-CMR) were included. The association of GLS with the risk of incident major adverse cardiovascular events (MACE; composite of incident myocardial infarction, incident heart failure [HF], hospitalization for atrial fibrillation, coronary revascularization, and all-cause death), and incident HF or death were assessed with adjusted Cox proportional hazards models. A total of 309 participants (13.8%) had MACE during a median follow-up duration of 17 years. Participants with the worst GLS (Q4) were more likely male and of the Black race with a history of tobacco use and diabetes with lower LVEF, higher LV end-diastolic volume, and higher LV mass index. Cumulative incidence of MACE was higher among participants with worse (Q4 vs. Q1) GLS (20.4% vs. 9.0%). In multivariable-adjusted Cox models that included clinical characteristics, cardiac biomarkers and baseline LVEF, worse GLS (Q4 vs. Q1) was associated with a significantly higher risk of MACE (hazard ratio [HR] 1.55, 95% confidence interval [CI] 1.07-2.24, p = 0.02) and incident HF or death (HR 1.57, 95% CI 1.03-2.38, p = 0.04). CONCLUSIONS: Impaired LV GLS assessed by FT-CMR among adults free of cardiovascular disease is associated with a higher risk of incident MACE and incident HF or death independent of cardiovascular risk factors, cardiac biomarkers and LVEF.

Myocardial perfusion in cardiac amyloidosis.

AIMS: Cardiac involvement is the main driver of clinical outcomes in systemic amyloidosis and preliminary studies support the hypothesis that myocardial ischaemia contributes to cellular damage. The aims of this study were to assess the presence and mechanisms of myocardial ischaemia using cardiovascular magnetic resonance (CMR) with multiparametric mapping and histopathological assessment. METHODS AND RESULTS: Ninety-three patients with cardiac amyloidosis (CA) (light-chain amyloidosis n = 42, transthyretin amyloidosis n = 51) and 97 without CA (three-vessel coronary disease [3VD] n = 47, unobstructed coronary arteries n = 26, healthy volunteers [HV] n = 24) underwent quantitative stress perfusion CMR with myocardial blood flow (MBF) mapping. Twenty-four myocardial biopsies and three explanted hearts with CA were analysed histopathologically. Stress MBF was severely reduced in patients with CA with lower values than patients with 3VD, unobstructed coronary arteries and HV (CA: 1.04 ± 0.51 ml/min/g, 3VD: 1.35 ± 0.50 ml/min/g, unobstructed coronary arteries: 2.92 ± 0.52 ml/min/g, HV: 2.91 ± 0.73 ml/min/g; CA vs. 3VD p = 0.011, CA vs. unobstructed coronary arteries p < 0.001, CA vs. HV p < 0.001). Myocardial perfusion abnormalities correlated with amyloid burden, systolic and diastolic function, structural parameters and blood biomarkers (p < 0.05). Biopsies demonstrated abnormal vascular endothelial growth factor staining in cardiomyocytes and endothelial cells, which may be related to hypoxia conditions. Amyloid infiltration in intramural arteries was associated with severe lumen reduction and severe reduction in capillary density. CONCLUSION: Cardiac amyloidosis is associated with severe inducible myocardial ischaemia demonstrable by histology and CMR stress perfusion mapping. Histological evaluation indicates a complex pathophysiology, where in addition to systolic and diastolic dysfunction, amyloid infiltration of the epicardial arteries and disruption and rarefaction of the capillaries play a role in contributing to myocardial ischaemia.