Automated inversion time selection for late gadolinium-enhanced cardiac magnetic resonance imaging.

OBJECTIVES: To develop and share a deep learning method that can accurately identify optimal inversion time (TI) from multi-vendor, multi-institutional and multi-field strength inversion scout (TI scout) sequences for late gadolinium enhancement cardiac MRI. MATERIALS AND METHODS: Retrospective multicentre study conducted on 1136 1.5-T and 3-T cardiac MRI examinations from four centres and three scanner vendors. Deep learning models, comprising a convolutional neural network (CNN) that provides input to a long short-term memory (LSTM) network, were trained on TI scout pixel data from centres 1 to 3 to identify optimal TI, using ground truth annotations by two readers. Accuracy within 50 ms, mean absolute error (MAE), Lin's concordance coefficient (LCCC) and reduced major axis regression (RMAR) were used to select the best model from validation results, and applied to holdout test data. Robustness of the best-performing model was also tested on imaging data from centre 4. RESULTS: The best model (SE-ResNet18-LSTM) produced accuracy of 96.1%, MAE 22.9 ms and LCCC 0.47 compared to ground truth on the holdout test set and accuracy of 97.3%, MAE 15.2 ms and LCCC 0.64 when tested on unseen external (centre 4) data. Differences in vendor performance were observed, with greatest accuracy for the most commonly represented vendor in the training data. CONCLUSION: A deep learning model was developed that can identify optimal inversion time from TI scout images on multi-vendor data with high accuracy, including on previously unseen external data. We make this model available to the scientific community for further assessment or development. CLINICAL RELEVANCE STATEMENT: A robust automated inversion time selection tool for late gadolinium-enhanced imaging allows for reproducible and efficient cross-vendor inversion time selection. KEY POINTS: • A model comprising convolutional and recurrent neural networks was developed to extract optimal TI from TI scout images. • Model accuracy within 50 ms of ground truth on multi-vendor holdout and external data of 96.1% and 97.3% respectively was achieved. • This model could improve workflow efficiency and standardise optimal TI selection for consistent LGE imaging.

Combination of computed tomography angiography with coronary artery calcium score for improved diagnosis of coronary artery disease: a collaborative meta-analysis of stable chest pain patients referred for invasive coronary angiography.

OBJECTIVES: Coronary computed tomography angiography (CCTA) has higher diagnostic accuracy than coronary artery calcium (CAC) score for detecting obstructive coronary artery disease (CAD) in patients with stable chest pain, while the added diagnostic value of combining CCTA with CAC is unknown. We investigated whether combining coronary CCTA with CAC score can improve the diagnosis of obstructive CAD compared with CCTA alone. METHODS: A total of 2315 patients (858 women, 37%) aged 61.1 ± 10.2 from 29 original studies were included to build two CAD prediction models based on either CCTA alone or CCTA combined with the CAC score. CAD was defined as at least 50% coronary diameter stenosis on invasive coronary angiography. Models were built by using generalized linear mixed-effects models with a random intercept set for the original study. The two CAD prediction models were compared by the likelihood ratio test, while their diagnostic performance was compared using the area under the receiver-operating-characteristic curve (AUC). Net benefit (benefit of true positive versus harm of false positive) was assessed by decision curve analysis. RESULTS: CAD prevalence was 43.5% (1007/2315). Combining CCTA with CAC improved CAD diagnosis compared with CCTA alone (AUC: 87% [95% CI: 86 to 89%] vs. 80% [95% CI: 78 to 82%]; p < 0.001), likelihood ratio test 236.3, df: 1, p < 0.001, showing a higher net benefit across almost all threshold probabilities. CONCLUSION: Adding the CAC score to CCTA findings in patients with stable chest pain improves the diagnostic performance in detecting CAD and the net benefit compared with CCTA alone. CLINICAL RELEVANCE STATEMENT: CAC scoring CT performed before coronary CTA and included in the diagnostic model can improve obstructive CAD diagnosis, especially when CCTA is non-diagnostic. KEY POINTS: • The combination of coronary artery calcium with coronary computed tomography angiography showed significantly higher AUC (87%, 95% confidence interval [CI]: 86 to 89%) for diagnosis of coronary artery disease compared to coronary computed tomography angiography alone (80%, 95% CI: 78 to 82%, p < 0.001). • Diagnostic improvement was mostly seen in patients with non-diagnostic C. • The improvement in diagnostic performance and the net benefit was consistent across age groups, chest pain types, and genders.

Sixty years of the Bruce protocol: reappraising the contemporary role of exercise stress testing with electrocardiographic monitoring.

The cardiovascular response to exercise has long been a focus of interest. Over a century ago, the first descriptions of electrocardiographic changes occurring during exercise highlighted the possible relevance of this dynamic assessment. In this background, the inception of the Bruce protocol circa 60 years ago allowed for a major leap in this field by providing a standardized framework with which to address this issue, by means of an integrated and structured methodology. Since then, exercise stress testing with electrocardiographic monitoring (ExECG) has become one of the most widely appraised tests in cardiovascular medicine. Notably, past few decades have been profoundly marked by substantial advances in the approach to cardiovascular disease, challenging prior notions concerning both its physiopathology and overall management. Among these, the ever-evolving presentations of cardiovascular disease coupled with the development and implementation of several novel diagnostic modalities (both invasive and noninvasive) has led to a shifting paradigm in the application of ExECG. This technique, however, has continuously shown to be of added value across various momentums of the cardiovascular continuum, as depicted in several contemporary guidelines. This review provides a pragmatical reflexion on the development of ExECG, presenting a comprehensive overview concerning the current role of this modality, its challenges, and its future perspectives.

The Association of Leptin with Left Ventricular Hypertrophy in End-Stage Kidney Disease Patients on Dialysis.

Left ventricular hypertrophy (LVH) is a common cardiovascular complication in end-stage kidney disease (ESKD) patients. We aimed at studying the association of LVH with adiponectin and leptin levels, cardiovascular stress/injury biomarkers and nutritional status in these patients. We evaluated the LV mass (LVM) and calculated the LVM index (LVMI) in 196 ESKD patients on dialysis; the levels of hemoglobin, calcium, phosphorus, parathyroid hormone, albumin, adiponectin, leptin, N-terminal pro B-type natriuretic peptide (NT-proBNP) and growth differentiation factor (GDF)-15 were analyzed. ESKD patients with LVH (n = 131) presented higher NT-proBNP and GDF-15, lower hemoglobin and, after adjustment for gender, lower leptin levels compared with non-LVH patients. LVH females also showed lower leptin than the non-LVH female group. In the LVH group, LVMI presented a negative correlation with leptin and a positive correlation with NT-proBNP. Leptin emerged as an independent determinant of LVMI in both groups, and NT-proBNP in the LVH group. Low hemoglobin and leptin and increased calcium, NT-proBNP and dialysis vintage are associated with an increased risk of developing LVH. In ESKD patients on dialysis, LVH is associated with lower leptin values (especially in women), which are negatively correlated with LVMI, and with higher levels of biomarkers of myocardial stress/injury. Leptin and NT-proBNP appear as independent determinants of LVMI; dialysis vintage, hemoglobin, calcium, NT-proBNP and leptin emerged as predicting markers for LVH development. Further studies are needed to better understand the role of leptin in LVH in ESKD patients.

Mitral annular disjunction: Beyond mitral valve prolapse.

Mitral annular disjunction (MAD) is an easily identifiable entity on transthoracic echocardiography, but is still poorly recognized or ignored. It is often associated with mitral valve prolapse and is itself a risk marker for ventricular arrhythmias and sudden cardiac death, but the management and risk stratification of these patients is not systematized. Two clinical cases of MAD associated with mitral valve prolapse and ventricular arrhythmias are presented. The first case is of a patient with a history of surgical intervention on the mitral valve due to Barlow's disease. He presented to the emergency department with sustained monomorphic ventricular tachycardia requiring emergent electrical cardioversion. MAD with transmural fibrosis at the level of the inferolateral wall was documented. The second report is of a young woman with palpitations and frequent premature ventricular contractions on Holter with documentation of valvular prolapse and MAD, and focuses on the risk stratification approach. The present article offers a review of the literature regarding the arrhythmic risk of MAD and mitral valve prolapse, as well as a review of risk stratification in these patients.

Syncope in the athlete - Minor changes, major diagnosis!

We report the case of a 17-year-old athlete who resorted to the emergency department for palpitations and dizziness while exercising. He mentioned two exercise-associated episodes of syncope in the last six months. He was tachycardic and hypotensive. The electrocardiogram showed regular wide complex tachycardia, left bundle branch block morphology with superior axis restored to sinus rhythm after electrical cardioversion. In sinus rhythm, it showed T-wave inversion in V1-V5. Transthoracic echocardiography revealed mild dilation and dysfunction of the right ventricle (RV) with global hypocontractility. Cardiac magnetic resonance (CMR) revealed a RV end diastolic volume indexed to body surface area of 180 ml/m2, global hypokinesia and RV dyssynchrony, subepicardial late enhancement in the distal septum and in the middle segment of the inferoseptal wall. The patient underwent a genetic study which showed a mutation in the gene that encodes the desmocolin-2 protein (DSC-2), which is involved in the pathogenesis of arrhythmogenic right ventricular cardiomyopathy (ARVC). According to the modified Task Force Criteria for this diagnosis, the patient presented four major criteria for ARVC. Thus, a subcutaneous cardioverter was implanted, and the patient was followed up at the cardiology department. Arrhythmogenic right ventricular cardiomyopathy diagnosis is based on structural, functional, electrophysiological and genetic criteria reflecting underlying histological changes. This case depicts the essential characteristics for disease recognition.

Multimodality imaging in cardiac amyloidosis: State-of-the-art review.

Amyloidosis is a systemic disease, characterized by deposition of amyloid fibrils in various organs, including the heart. For the diagnosis of cardiac amyloidosis (CA) it is required a high level of clinical suspicion and in the presence of clinical, laboratorial, and electrocardiographic red flags, a comprehensive multimodality imaging evaluation is warranted, including echocardiography, magnetic resonance, scintigraphy, and computed tomography, that will confirm diagnosis and define the CA subtype, which is of the utmost importance to plan a treatment strategy. We will review the use of multimodality imaging in the evaluation of CA, including the latest applications, and a practical flow-chart will sum-up this evidence.

Decoding the radiomic and proteomic phenotype of epicardial adipose tissue associated with adverse left atrial remodelling and post-operative atrial fibrillation in aortic stenosis.

AIMS: Epicardial adipose tissue (EAT) volume and attenuation on computed tomography (CT) have been associated with atrial fibrillation. Beyond these conventional CT measures, radiomics allows extraction of high-dimensional data and deep quantitative adipose tissue phenotyping, which may capture its underlying biology. We aimed to explore the EAT proteomic and CT-radiomic signatures associated with impaired left atrial (LA) remodelling and post-operative atrial fibrillation (POAF). METHODS AND RESULTS: We prospectively included 132 patients with severe aortic stenosis with no prior atrial fibrillation referred for aortic valve replacement. Pre-operative non-contrast CT images were obtained for extraction of EAT volume and other radiomic features describing EAT texture. The LA function was assessed by 2D-speckle-tracking echocardiography peak atrial longitudinal strain and peak atrial contraction strain. The EAT biopsies were performed during surgery for proteomic analysis by sequential windowed acquisition of all theoretical fragment ion mass spectra (SWATH-MS). The POAF incidence was monitored from surgery until discharge. Impaired LA function and incident POAF were associated with EAT up-regulation of inflammatory and thrombotic proteins, and down-regulation of cardioprotective proteins with anti-inflammatory and anti-lipotoxic properties. The EAT volume was independently associated with LA enlargement, impaired function, and POAF risk. On CT images, EAT texture of patients with POAF was heterogeneous and exhibited higher maximum grey-level values than sinus rhythm patients, which correlated with up-regulation of inflammatory and down-regulation of lipid droplet-formation EAT proteins. The CT radiomics of EAT provided an area under the curve of 0.80 (95% confidence interval: 0.68-0.92) for discrimination between patients with POAF and sinus rhythm. CONCLUSION: Pre-operative CT-radiomic profile of EAT detected adverse EAT proteomics and identified patients at risk of developing POAF.

CardiSort: a convolutional neural network for cross vendor automated sorting of cardiac MR images.

OBJECTIVES: To develop an image-based automatic deep learning method to classify cardiac MR images by sequence type and imaging plane for improved clinical post-processing efficiency. METHODS: Multivendor cardiac MRI studies were retrospectively collected from 4 centres and 3 vendors. A two-head convolutional neural network ('CardiSort') was trained to classify 35 sequences by imaging sequence (n = 17) and plane (n = 10). Single vendor training (SVT) on single-centre images (n = 234 patients) and multivendor training (MVT) with multicentre images (n = 434 patients, 3 centres) were performed. Model accuracy and F1 scores on a hold-out test set were calculated, with ground truth labels by an expert radiologist. External validation of MVT (MVTexternal) was performed on data from 3 previously unseen magnet systems from 2 vendors (n = 80 patients). RESULTS: Model sequence/plane/overall accuracy and F1-scores were 85.2%/93.2%/81.8% and 0.82 for SVT and 96.1%/97.9%/94.3% and 0.94 MVT on the hold-out test set. MVTexternal yielded sequence/plane/combined accuracy and F1-scores of 92.7%/93.0%/86.6% and 0.86. There was high accuracy for common sequences and conventional cardiac planes. Poor accuracy was observed for underrepresented classes and sequences where there was greater variability in acquisition parameters across centres, such as perfusion imaging. CONCLUSIONS: A deep learning network was developed on multivendor data to classify MRI studies into component sequences and planes, with external validation. With refinement, it has potential to improve workflow by enabling automated sequence selection, an important first step in completely automated post-processing pipelines. KEY POINTS: • Deep learning can be applied for consistent and efficient classification of cardiac MR image types. • A multicentre, multivendor study using a deep learning algorithm (CardiSort) showed high classification accuracy on a hold-out test set with good generalisation to images from previously unseen magnet systems. • CardiSort has potential to improve clinical workflows, as a vital first step in developing fully automated post-processing pipelines.