Artificial Intelligence for Contrast-Free MRI: Scar Assessment in Myocardial Infarction Using Deep Learning-Based Virtual Native Enhancement.

BACKGROUND: Myocardial scars are assessed noninvasively using cardiovascular magnetic resonance late gadolinium enhancement (LGE) as an imaging gold standard. A contrast-free approach would provide many advantages, including a faster and cheaper scan without contrast-associated problems. METHODS: Virtual native enhancement (VNE) is a novel technology that can produce virtual LGE-like images without the need for contrast. VNE combines cine imaging and native T1 maps to produce LGE-like images using artificial intelligence. VNE was developed for patients with previous myocardial infarction from 4271 data sets (912 patients); each data set comprises slice position-matched cine, T1 maps, and LGE images. After quality control, 3002 data sets (775 patients) were used for development and 291 data sets (68 patients) for testing. The VNE generator was trained using generative adversarial networks, using 2 adversarial discriminators to improve the image quality. The left ventricle was contoured semiautomatically. Myocardial scar volume was quantified using the full width at half maximum method. Scar transmurality was measured using the centerline chord method and visualized on bull's-eye plots. Lesion quantification by VNE and LGE was compared using linear regression, Pearson correlation (R), and intraclass correlation coefficients. Proof-of-principle histopathologic comparison of VNE in a porcine model of myocardial infarction also was performed. RESULTS: VNE provided significantly better image quality than LGE on blinded analysis by 5 independent operators on 291 data sets (all P<0.001). VNE correlated strongly with LGE in quantifying scar size (R, 0.89; intraclass correlation coefficient, 0.94) and transmurality (R, 0.84; intraclass correlation coefficient, 0.90) in 66 patients (277 test data sets). Two cardiovascular magnetic resonance experts reviewed all test image slices and reported an overall accuracy of 84% for VNE in detecting scars when compared with LGE, with specificity of 100% and sensitivity of 77%. VNE also showed excellent visuospatial agreement with histopathology in 2 cases of a porcine model of myocardial infarction. CONCLUSIONS: VNE demonstrated high agreement with LGE cardiovascular magnetic resonance for myocardial scar assessment in patients with previous myocardial infarction in visuospatial distribution and lesion quantification with superior image quality. VNE is a potentially transformative artificial intelligence-based technology with promise in reducing scan times and costs, increasing clinical throughput, and improving the accessibility of cardiovascular magnetic resonance in the near future.

The Role of Cardiovascular Magnetic Resonance Imaging in Patients with Cardiac Arrhythmias.

Cardiac arrhythmias are associated with significant morbidity, mortality and poor quality of life. Cardiovascular magnetic resonance (CMR) imaging, with its unsurpassed capability of non-invasive tissue characterisation, high accuracy, and reproducibility of measurements, plays an integral role in determining the underlying aetiology of cardiac arrhytmias. CMR can reliably diagnose previous myocardial infarction, non-ischemic cardiomyopathy, characterise congenital heart disease and valvular pathologies, and also detect the underlying substrate concealed on conventional investigations in a significant proportion of patients with arrhythmias. Determining the underlying substrate of arrhythmia is of paramount importance for treatment planning and prognosis. However, CMR imaging in patients with irregular heart rates can be problematic. Understanding the different ways to overcome the limitations of CMR in arrhythmia is essential for providing high-quality imaging, comprehensive information, and definitive answers in this diverse group of patients.

Toward Replacing Late Gadolinium Enhancement With Artificial Intelligence Virtual Native Enhancement for Gadolinium-Free Cardiovascular Magnetic Resonance Tissue Characterization in Hypertrophic Cardiomyopathy.

BACKGROUND: Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for noninvasive myocardial tissue characterization but requires intravenous contrast agent administration. It is highly desired to develop a contrast agent-free technology to replace LGE for faster and cheaper CMR scans. METHODS: A CMR virtual native enhancement (VNE) imaging technology was developed using artificial intelligence. The deep learning model for generating VNE uses multiple streams of convolutional neural networks to exploit and enhance the existing signals in native T1 maps (pixel-wise maps of tissue T1 relaxation times) and cine imaging of cardiac structure and function, presenting them as LGE-equivalent images. The VNE generator was trained using generative adversarial networks. This technology was first developed on CMR datasets from the multicenter Hypertrophic Cardiomyopathy Registry, using hypertrophic cardiomyopathy as an exemplar. The datasets were randomized into 2 independent groups for deep learning training and testing. The test data of VNE and LGE were scored and contoured by experienced human operators to assess image quality, visuospatial agreement, and myocardial lesion burden quantification. Image quality was compared using a nonparametric Wilcoxon test. Intra- and interobserver agreement was analyzed using intraclass correlation coefficients (ICC). Lesion quantification by VNE and LGE were compared using linear regression and ICC. RESULTS: A total of 1348 hypertrophic cardiomyopathy patients provided 4093 triplets of matched T1 maps, cines, and LGE datasets. After randomization and data quality control, 2695 datasets were used for VNE method development and 345 were used for independent testing. VNE had significantly better image quality than LGE, as assessed by 4 operators (n=345 datasets; P<0.001 [Wilcoxon test]). VNE revealed lesions characteristic of hypertrophic cardiomyopathy in high visuospatial agreement with LGE. In 121 patients (n=326 datasets), VNE correlated with LGE in detecting and quantifying both hyperintensity myocardial lesions (r=0.77-0.79; ICC=0.77-0.87; P<0.001) and intermediate-intensity lesions (r=0.70-0.76; ICC=0.82-0.85; P<0.001). The native CMR images (cine plus T1 map) required for VNE can be acquired within 15 minutes and producing a VNE image takes less than 1 second. CONCLUSIONS: VNE is a new CMR technology that resembles conventional LGE but without the need for contrast administration. VNE achieved high agreement with LGE in the distribution and quantification of lesions, with significantly better image quality.

Incremental value of left atrial booster and reservoir strain in predicting atrial fibrillation in patients with hypertrophic cardiomyopathy: a cardiovascular magnetic resonance study.

BACKGROUND: Left atrial (LA) size and function are known predictors of new onset atrial fibrillation (AF) in hypertrophic cardiomyopathy (HCM) patients. Components of LA deformation including reservoir, conduit, and booster function provide additional information on atrial mechanics. Whether or not LA deformation can augment our ability to predict the risk of new onset AF in HCM patients beyond standard measurements is unknown. METHODS: We assessed LA size, function, and deformation on cardiovascular magnetic resonance (CMR) in 238 genotyped HCM patients and compared this with twenty age, sex, blood pressure and body mass index matched control subjects. We further evaluated the determinants of new onset AF in HCM patients. RESULTS: Compared to control subjects, HCM patients had higher LA antero-posterior diameter, lower LA ejection fraction and lower LA reservoir (19.9 [17.1, 22.2], 21.6 [19.9, 22.9], P = 0.047) and conduit strain (10.6 ± 4.4, 13.7 ± 3.3, P = 0.002). LA booster strain did not differ between healthy controls and HCM patients, but HCM patients who developed new onset AF (n = 33) had lower booster strain (7.6 ± 3.3, 9.5 ± 3.0, P = 0.001) than those that did not (n = 205). In separate multivariate models, age, LA ejection fraction, and LA booster and reservoir strain were each independent determinants of AF. Age ≥ 55 years was the strongest determinant (HR 6.62, 95% CI 2.79-15.70), followed by LA booster strain ≤ 8% (HR 3.69, 95% CI 1.81-7.52) and LA reservoir strain ≤ 18% (HR 2.56, 95% CI 1.24-5.27). Conventional markers of HCM phenotypic severity, age and sudden death risk factors were associated with LA strain components. CONCLUSIONS: LA strain components are impaired in HCM and, together with age, independently predicted the risk of new onset AF. Increasing age and phenotypic severity were associated with LA strain abnormalities. Our findings suggest that the routine assessment of LA strain components and consideration of age could augment LA size in predicting risk of AF, and potentially guide prophylactic anticoagulation use in HCM.

Iatrogenic Lutembacher Syndrome after Percutaneous Mitral Commissurotomy.

Atrial septal defects (ASDs) are common immediately after percutaneous mitral commissurotomy (PMC). They are usually small, hemodynamically insignificant, and tend to decrease or disappear within 6 to 12 months. Herein, a case is described of persistent ASD in a patient with mitral valve stenosis who had undergone successful PMC three years previously. The patient had signs and symptoms of right heart failure and severe tricuspid regurgitation (TR) with borderline right ventricular systolic function on echocardiography, in addition to the ASD. Cardiac magnetic resonance (CMR) imaging played a significant role in decision-making by clarifying the anatomy of the ASD and severity of the shunt, measuring right ventricular systolic function, and providing absolute quantification for TR. The right ventricular systolic function was normal on CMR, rendering the patient suitable for surgical treatment. Persistent iatrogenic ASDs have become an increasingly common finding after invasive procedures requiring trans-septal puncture and the manipulation of catheters. Multimodality imaging can provide significant aid in the management of patients with valvular heart disease complicated by iatrogenic shunts.

Cardiac magnetic resonance for ventricular arrhythmias: a systematic review and meta-analysis.

BACKGROUND: Cardiac magnetic resonance (CMR) allows comprehensive myocardial tissue characterisation, revealing areas of myocardial inflammation or fibrosis that may predispose to ventricular arrhythmias (VAs). With this study, we aimed to estimate the prevalence of structural heart disease (SHD) and decipher the prognostic implications of CMR in selected patients presenting with significant VAs. METHODS: Electronic databases were searched for studies enrolling adult patients that underwent CMR for diagnostic or prognostic purposes in the setting of significant VAs. A random effects model meta-analysis of proportions was performed to estimate the prevalence of SHD. HRs were pooled together in order to evaluate the prognostic value of CMR. RESULTS: The prevalence of SHD was reported in 18 studies. In all-comers with significant VAs, the pooled rate of SHD post-CMR evaluation was 39% (24% in the subgroup of premature ventricular contractions and/or non-sustained ventricular tachycardia vs 63% in the subgroup of more complex VAs). A change in diagnosis after use of CMR ranged from 21% to 66% with a pooled average of 35% (29%-41%). A non-ischaemic cardiomyopathy was the most frequently identified SHD (56%), followed by ischaemic heart disease (21%) and hypertrophic cardiomyopathy (5%). After pooling together data from six studies, we found that the presence of late gadolinium enhancement was associated with increased risk of major adverse outcomes in patients with significant VAs (pooled HR: 1.79; 95% CI 1.33 to 2.42). CONCLUSION: CMR is a valuable tool in the diagnostic and prognostic evaluation of patients with VAs. CMR should be considered early after initial evaluation in the diagnostic algorithm for VAs of unclear aetiology as this strategy may also define prognosis and improve risk stratification.

Cardiovascular Magnetic Resonance Before Invasive Coronary Angiography in Suspected Non-ST-Segment Elevation Myocardial Infarction.

BACKGROUND: In suspected non-ST-segment elevation myocardial infarction (NSTEMI), this presumed diagnosis may not hold true in all cases, particularly in patients with nonobstructive coronary arteries (NOCA). Additionally, in multivessel coronary artery disease, the presumed infarct-related artery may be incorrect. OBJECTIVES: This study sought to assess the diagnostic utility of cardiac magnetic resonance (CMR) before invasive coronary angiogram (ICA) in suspected NSTEMI. METHODS: A total of 100 consecutive stable patients with suspected acute NSTEMI (70% male, age 62 ± 11 years) prospectively underwent CMR pre-ICA to assess cardiac function (cine), edema (T2-weighted imaging, T1 mapping), and necrosis/scar (late gadolinium enhancement). CMR images were interpreted blinded to ICA findings. The clinical care and ICA teams were blinded to CMR findings until post-ICA. RESULTS: Early CMR (median 33 hours postadmission and 4 hours pre-ICA) confirmed only 52% (52 of 100) of patients had subendocardial infarction, 15% transmural infarction, 18% nonischemic pathologies (myocarditis, Takotsubo and other forms of cardiomyopathies), and 11% normal CMR; 4% were nondiagnostic. Subanalyses according to ICA findings showed that, in patients with obstructive coronary artery disease (73 of 100), CMR confirmed only 84% (61 of 73) had MI, 10% (7 of 73) nonischemic pathologies, and 5% (4 of 73) normal. In patients with NOCA (27 of 100), CMR found MI in only 22% (6 of 27 true MI with NOCA), and reclassified the presumed diagnosis of NSTEMI in 67% (18 of 27: 11 nonischemic pathologies, 7 normal). In patients with CMR-MI and obstructive coronary artery disease (61 of 100), CMR identified a different infarct-related artery in 11% (7 of 61). CONCLUSIONS: In patients presenting with suspected NSTEMI, a CMR-first strategy identified MI in 67%, nonischemic pathologies in 18%, and normal findings in 11%. Accordingly, CMR has the potential to affect at least 50% of all patients by reclassifying their diagnosis or altering their potential management.

Diagnostic utility of electrocardiogram for screening of cardiac injury on cardiac magnetic resonance in post-hospitalised COVID-19 patients: A prospective multicenter study.

BACKGROUND: The role of ECG in ruling out myocardial complications on cardiac magnetic resonance (CMR) is unclear. We examined the clinical utility of ECG in screening for cardiac abnormalities on CMR among post-hospitalised COVID-19 patients. METHODS: Post-hospitalised patients (n = 212) and age, sex and comorbidity-matched controls (n = 38) underwent CMR and 12­lead ECG in a prospective multicenter follow-up study. Participants were screened for routinely reported ECG abnormalities, including arrhythmia, conduction and R wave abnormalities and ST-T changes (excluding repolarisation intervals). Quantitative repolarisation analyses included corrected QT (QTc), corrected QT dispersion (QTc disp), corrected JT (JTc) and corrected T peak-end (cTPe) intervals. RESULTS: At a median of 5.6 months, patients had a higher burden of ECG abnormalities (72.2% vs controls 42.1%, p = 0.001) and lower LVEF but a comparable cumulative burden of CMR abnormalities than controls. Patients with CMR abnormalities had more ECG abnormalities and longer repolarisation intervals than those with normal CMR and controls (82% vs 69% vs 42%, p < 0.001). Routinely reported ECG abnormalities had poor discriminative ability (area-under-the-receiver-operating curve: AUROC) for abnormal CMR, AUROC 0.56 (95% CI 0.47-0.65), p = 0.185; worse among female than male patients. Adding JTc and QTc disp improved the AUROC to 0.64 (95% CI 0.55-0.74), p = 0.002, the sensitivity of the ECG increased from 81.6% to 98.0%, negative predictive value from 84.7% to 96.3%, negative likelihood ratio from 0.60 to 0.13, and reduced sex-dependence variabilities of ECG diagnostic parameters. CONCLUSION: Post-hospitalised COVID-19 patients have more ECG abnormalities than controls. Normal ECGs, including normal repolarisation intervals, reliably exclude CMR abnormalities in male and female patients.

Is the heart involved or not? The diagnostic value of cardiovascular magnetic resonance imaging in the assessment of non-cardiac malignancies and metastatic cardiac tumours.

Cardiovascular magnetic resonance (CMR) is a radiation-free, high-spatial resolution technique which provides dynamic assessment of the heart and pericardial tissue. This is particularly useful for the evaluation and characterisation of non-cardiac tumours close to the pericardium for the exclusion of cardiovascular infiltration, and also for the assessment of the extent of myocardial invasion of cardiac metastases. This information can help make key decisions on further management in oncology multidisciplinary meetings. The CMR evaluation and main types of sequences acquired are detailed in this case series to illustrate the application of CMR in the assessment of non-cardiac malignancies and its importance in guiding management.

Cardiovascular Magnetic Resonance Parametric Mapping Techniques for the Assessment of Chronic Coronary Syndromes.

The term chronic coronary syndromes encompasses a variety of clinical presentations of coronary artery disease (CAD), ranging from stable angina due to epicardial coronary artery disease to microvascular coronary dysfunction. Cardiac magnetic resonance (CMR) imaging has an established role in the diagnosis, prognostication and treatment planning of patients with CAD. Recent advances in parametric mapping CMR techniques have added value in the assessment of patients with chronic coronary syndromes, even without the need for gadolinium contrast administration. Furthermore, quantitative perfusion CMR techniques have enabled the non-invasive assessment of myocardial blood flow and myocardial perfusion reserve and can reliably identify multivessel coronary artery disease and microvascular dysfunction. This review summarizes the clinical applications and the prognostic value of the novel CMR parametric mapping techniques in the setting of chronic coronary syndromes and discusses their strengths, pitfalls and future directions.

Bolus Intravenous Procainamide in Patients with Frequent Ventricular Ectopics during Cardiac Magnetic Resonance Scanning: A Way to Ensure High Quality Imaging.

Acquiring high-quality cardiac magnetic resonance (CMR) images in patients with frequent ventricular arrhythmias remains a challenge. We examined the safety and efficacy of procainamide when administered on the scanner table prior to CMR scanning to suppress ventricular ectopy and acquire high-quality images. Fifty consecutive patients (age 53.0 [42.0-58.0]; 52% female, left ventricular ejection fraction 55 ± 9%) were scanned in a 1.5 T scanner using a standard cardiac protocol. Procainamide was administered at intermittent intravenous bolus doses of 50 mg every minute until suppression of the ectopics or a maximum dose of 10 mg/kg. The average dose of procainamide was 567 ± 197 mg. Procainamide successfully suppressed premature ventricular contractions (PVCs) in 82% of patients, resulting in high-quality images. The baseline blood pressure (BP) was mildly reduced (mean change systolic BP -12 ± 9 mmHg; diastolic BP -4 ± 9 mmHg), while the baseline heart rate (HR) remained relatively unchanged (mean HR change -1 ± 6 bpm). None of the patients developed proarrhythmic changes. Bolus intravenous administration of procainamide prior to CMR scanning is a safe and effective alternative approach for suppressing PVCs and acquiring high-quality images in patients with frequent PVCs and normal or only mildly reduced systolic function.

Cardiac Magnetic Resonance to Detect the Underlying Substrate in Patients with Frequent Idiopathic Ventricular Arrhythmias.

BACKGROUND: A routine diagnostic work-up does not identify structural abnormalities in a substantial proportion of patients with idiopathic ventricular arrhythmias (VAs). We investigated the added value of cardiac magnetic resonance (CMR) imaging in this group of patients. METHODS: A single-centre prospective study was undertaken of 72 patients (mean age 46 ± 16 years; 53% females) with frequent premature ventricular contractions (PVCs ≥ 500/24 h) and/or non-sustained ventricular tachycardia (NSVT), an otherwise normal electrocardiogram, normal echocardiography and no coronary artery disease. RESULTS: CMR provided an additional diagnostic yield in 54.2% of patients. The most prevalent diagnosis was previous myocarditis (23.6%) followed by possible PVC-related cardiomyopathy (20.8%), non-ischaemic cardiomyopathy (8.3%) and ischaemic heart disease (1.4%). The predictors of abnormal CMR findings were male gender, age and PVCs/NSVT non-outflow tract-related or with multiple morphologies. Patients with VAs had an impaired peak left ventricular (LV) global radial strain (GRS) compared with the controls (28.88% (IQR: 25.87% to 33.97%) vs. 36.65% (IQR: 33.19% to 40.2%), p < 0.001) and a global circumferential strain (GCS) (-17.66% (IQR: -19.62% to -16.23%) vs. -20.66% (IQR: -21.72% to -19.6%), p < 0.001). CONCLUSION: CMR reveals abnormalities in a significant proportion of patients with frequent idiopathic VAs. Male gender, age and non-outflow tract PVC origin can be clinical indicators for CMR referral.

The role of catheter ablation in the management of patients with implantable cardioverter defibrillators presenting with electrical storm.

OBJECTIVE: Electrical storm (ES) is not uncommon among patients with an implantable cardioverter defibrillator (ICD) in situ. Catheter ablation (CA) may suppress the arrhythmia in the acute setting and prevent ES recurrence. METHODS: Nineteen consecutive patients with an ICD in situ presenting with ES underwent electrophysiologic studies followed by CA. CA outcome was classified as a complete success if both clinical and non-clinical tachycardia were successfully ablated, partial success if ≥1 non-clinical tachycardia episodes were still inducible post-CA, and failure if clinical tachycardia could not be abolished. Patients were followed for a median period (IQR) of 5.6 (1.8-13.7) months. The primary endpoint was event-free survival from ES recurrence. The secondary endpoint was event-free survival from a composite of ES and/or sustained ventricular tachycardia (VT) recurrence. RESULTS: Clinical arrhythmia was successfully ablated in 14 out of 19 (73.7%) cases after a single CA procedure. A completely successful CA outcome was associated with significantly increased ES-free survival compared with a partially successful or failed procedure (Log rank P=0.039). Nevertheless, patients with acute suppression of all tachycardia episodes (n=11), relative to those with a partially successful or a failed CA procedure (n=8), did not differ in incidence of the composite endpoint of sustained VT or ES (Log rank P=0.278). CONCLUSION: A single CA procedure can acutely suppress clinical arrhythmia in three-quarters of cases. A completely successful CA outcome can prolong ES-free survival; however, sporadic ICD therapies cannot be abrogated.