Microstructural and Microvascular Phenotype of Sarcomere Mutation Carriers and Overt Hypertrophic Cardiomyopathy.

BACKGROUND: In hypertrophic cardiomyopathy (HCM), myocyte disarray and microvascular disease (MVD) have been implicated in adverse events, and recent evidence suggests that these may occur early. As novel therapy provides promise for disease modification, detection of phenotype development is an emerging priority. To evaluate their utility as early and disease-specific biomarkers, we measured myocardial microstructure and MVD in 3 HCM groups-overt, either genotype-positive (G+LVH+) or genotype-negative (G-LVH+), and subclinical (G+LVH-) HCM-exploring relationships with electrical changes and genetic substrate. METHODS: This was a multicenter collaboration to study 206 subjects: 101 patients with overt HCM (51 G+LVH+ and 50 G-LVH+), 77 patients with G+LVH-, and 28 matched healthy volunteers. All underwent 12-lead ECG, quantitative perfusion cardiac magnetic resonance imaging (measuring myocardial blood flow, myocardial perfusion reserve, and perfusion defects), and cardiac diffusion tensor imaging measuring fractional anisotropy (lower values expected with more disarray), mean diffusivity (reflecting myocyte packing/interstitial expansion), and second eigenvector angle (measuring sheetlet orientation). RESULTS: Compared with healthy volunteers, patients with overt HCM had evidence of altered microstructure (lower fractional anisotropy, higher mean diffusivity, and higher second eigenvector angle; all P<0.001) and MVD (lower stress myocardial blood flow and myocardial perfusion reserve; both P<0.001). Patients with G-LVH+ were similar to those with G+LVH+ but had elevated second eigenvector angle (P<0.001 after adjustment for left ventricular hypertrophy and fibrosis). In overt disease, perfusion defects were found in all G+ but not all G- patients (100% [51/51] versus 82% [41/50]; P=0.001). Patients with G+LVH- compared with healthy volunteers similarly had altered microstructure, although to a lesser extent (all diffusion tensor imaging parameters; P<0.001), and MVD (reduced stress myocardial blood flow [P=0.015] with perfusion defects in 28% versus 0 healthy volunteers [P=0.002]). Disarray and MVD were independently associated with pathological electrocardiographic abnormalities in both overt and subclinical disease after adjustment for fibrosis and left ventricular hypertrophy (overt: fractional anisotropy: odds ratio for an abnormal ECG, 3.3, P=0.01; stress myocardial blood flow: odds ratio, 2.8, P=0.015; subclinical: fractional anisotropy odds ratio, 4.0, P=0.001; myocardial perfusion reserve odds ratio, 2.2, P=0.049). CONCLUSIONS: Microstructural alteration and MVD occur in overt HCM and are different in G+ and G- patients. Both also occur in the absence of hypertrophy in sarcomeric mutation carriers, in whom changes are associated with electrocardiographic abnormalities. Measurable changes in myocardial microstructure and microvascular function are early-phenotype biomarkers in the emerging era of disease-modifying therapy.

Myocardial Involvement After Hospitalization for COVID-19 Complicated by Troponin Elevation: A Prospective, Multicenter, Observational Study.

BACKGROUND: Acute myocardial injury in hospitalized patients with coronavirus disease 2019 (COVID-19) has a poor prognosis. Its associations and pathogenesis are unclear. Our aim was to assess the presence, nature, and extent of myocardial damage in hospitalized patients with troponin elevation. METHODS: Across 25 hospitals in the United Kingdom, 342 patients with COVID-19 and an elevated troponin level (COVID+/troponin+) were enrolled between June 2020 and March 2021 and had a magnetic resonance imaging scan within 28 days of discharge. Two prospective control groups were recruited, comprising 64 patients with COVID-19 and normal troponin levels (COVID+/troponin-) and 113 patients without COVID-19 or elevated troponin level matched by age and cardiovascular comorbidities (COVID-/comorbidity+). Regression modeling was performed to identify predictors of major adverse cardiovascular events at 12 months. RESULTS: Of the 519 included patients, 356 (69%) were men, with a median (interquartile range) age of 61.0 years (53.8, 68.8). The frequency of any heart abnormality, defined as left or right ventricular impairment, scar, or pericardial disease, was 2-fold greater in cases (61% [207/342]) compared with controls (36% [COVID+/troponin-] versus 31% [COVID-/comorbidity+]; P<0.001 for both). More cases than controls had ventricular impairment (17.2% versus 3.1% and 7.1%) or scar (42% versus 7% and 23%; P<0.001 for both). The myocardial injury pattern was different, with cases more likely than controls to have infarction (13% versus 2% and 7%; P<0.01) or microinfarction (9% versus 0% and 1%; P<0.001), but there was no difference in nonischemic scar (13% versus 5% and 14%; P=0.10). Using the Lake Louise magnetic resonance imaging criteria, the prevalence of probable recent myocarditis was 6.7% (23/342) in cases compared with 1.7% (2/113) in controls without COVID-19 (P=0.045). During follow-up, 4 patients died and 34 experienced a subsequent major adverse cardiovascular event (10.2%), which was similar to controls (6.1%; P=0.70). Myocardial scar, but not previous COVID-19 infection or troponin, was an independent predictor of major adverse cardiovascular events (odds ratio, 2.25 [95% CI, 1.12-4.57]; P=0.02). CONCLUSIONS: Compared with contemporary controls, patients with COVID-19 and elevated cardiac troponin level have more ventricular impairment and myocardial scar in early convalescence. However, the proportion with myocarditis was low and scar pathogenesis was diverse, including a newly described pattern of microinfarction. REGISTRATION: URL: https://www.isrctn.com; Unique identifier: 58667920.

Quality assurance of late gadolinium enhancement cardiac magnetic resonance images: a deep learning classifier for confidence in the presence or absence of abnormality with potential to prompt real-time image optimization.

BACKGROUND: Late gadolinium enhancement (LGE) of the myocardium has significant diagnostic and prognostic implications, with even small areas of enhancement being important. Distinguishing between definitely normal and definitely abnormal LGE images is usually straightforward, but diagnostic uncertainty arises when reporters are not sure whether the observed LGE is genuine or not. This uncertainty might be resolved by repetition (to remove artifact) or further acquisition of intersecting images, but this must take place before the scan finishes. Real-time quality assurance by humans is a complex task requiring training and experience, so being able to identify which images have an intermediate likelihood of LGE while the scan is ongoing, without the presence of an expert is of high value. This decision-support could prompt immediate image optimization or acquisition of supplementary images to confirm or refute the presence of genuine LGE. This could reduce ambiguity in reports. METHODS: Short-axis, phase-sensitive inversion recovery late gadolinium images were extracted from our clinical cardiac magnetic resonance (CMR) database and shuffled. Two, independent, blinded experts scored each individual slice for "LGE likelihood" on a visual analog scale, from 0 (absolute certainty of no LGE) to 100 (absolute certainty of LGE), with 50 representing clinical equipoise. The scored images were split into two classes-either "high certainty" of whether LGE was present or not, or "low certainty." The dataset was split into training, validation, and test sets (70:15:15). A deep learning binary classifier based on the EfficientNetV2 convolutional neural network architecture was trained to distinguish between these categories. Classifier performance on the test set was evaluated by calculating the accuracy, precision, recall, F1-score, and area under the receiver operating characteristics curve (ROC AUC). Performance was also evaluated on an external test set of images from a different center. RESULTS: One thousand six hundred and forty-five images (from 272 patients) were labeled and split at the patient level into training (1151 images), validation (247 images), and test (247 images) sets for the deep learning binary classifier. Of these, 1208 images were "high certainty" (255 for LGE, 953 for no LGE), and 437 were "low certainty". An external test comprising 247 images from 41 patients from another center was also employed. After 100 epochs, the performance on the internal test set was accuracy = 0.94, recall = 0.80, precision = 0.97, F1-score = 0.87, and ROC AUC = 0.94. The classifier also performed robustly on the external test set (accuracy = 0.91, recall = 0.73, precision = 0.93, F1-score = 0.82, and ROC AUC = 0.91). These results were benchmarked against a reference inter-expert accuracy of 0.86. CONCLUSION: Deep learning shows potential to automate quality control of late gadolinium imaging in CMR. The ability to identify short-axis images with intermediate LGE likelihood in real-time may serve as a useful decision-support tool. This approach has the potential to guide immediate further imaging while the patient is still in the scanner, thereby reducing the frequency of recalls and inconclusive reports due to diagnostic indecision.

Technical development and feasibility of a reusable vest to integrate cardiovascular magnetic resonance with electrocardiographic imaging.

BACKGROUND: Electrocardiographic imaging (ECGI) generates electrophysiological (EP) biomarkers while cardiovascular magnetic resonance (CMR) imaging provides data about myocardial structure, function and tissue substrate. Combining this information in one examination is desirable but requires an affordable, reusable, and high-throughput solution. We therefore developed the CMR-ECGI vest and carried out this technical development study to assess its feasibility and repeatability in vivo. METHODS: CMR was prospectively performed at 3T on participants after collecting surface potentials using the locally designed and fabricated 256-lead ECGI vest. Epicardial maps were reconstructed to generate local EP parameters such as activation time (AT), repolarization time (RT) and activation recovery intervals (ARI). 20 intra- and inter-observer and 8 scan re-scan repeatability tests. RESULTS: 77 participants were recruited: 27 young healthy volunteers (HV, 38.9 ± 8.5 years, 35% male) and 50 older persons (77.0 ± 0.1 years, 52% male). CMR-ECGI was achieved in all participants using the same reusable, washable vest without complications. Intra- and inter-observer variability was low (correlation coefficients [rs] across unipolar electrograms = 0.99 and 0.98 respectively) and scan re-scan repeatability was high (rs between 0.81 and 0.93). Compared to young HV, older persons had significantly longer RT (296.8 vs 289.3 ms, p = 0.002), ARI (249.8 vs 235.1 ms, p = 0.002) and local gradients of AT, RT and ARI (0.40 vs 0.34 ms/mm, p = 0,01; 0.92 vs 0.77 ms/mm, p = 0.03; and 1.12 vs 0.92 ms/mm, p = 0.01 respectively). CONCLUSION: Our high-throughput CMR-ECGI solution is feasible and shows good reproducibility in younger and older participants. This new technology is now scalable for high throughput research to provide novel insights into arrhythmogenesis and potentially pave the way for more personalised risk stratification. CLINICAL TRIAL REGISTRATION: Title: Multimorbidity Life-Course Approach to Myocardial Health-A Cardiac Sub-Study of the MRC National Survey of Health and Development (NSHD) (MyoFit46). National Clinical Trials (NCT) number: NCT05455125. URL: https://clinicaltrials.gov/ct2/show/NCT05455125?term=MyoFit&draw=2&rank=1.

Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning.

BACKGROUND: Measurement of cardiac structure and function from images (e.g. volumes, mass and derived parameters such as left ventricular (LV) ejection fraction [LVEF]) guides care for millions. This is best assessed using cardiovascular magnetic resonance (CMR), but image analysis is currently performed by individual clinicians, which introduces error. We sought to develop a machine learning algorithm for volumetric analysis of CMR images with demonstrably better precision than human analysis. METHODS: A fully automated machine learning algorithm was trained on 1923 scans (10 scanner models, 13 institutions, 9 clinical conditions, 60,000 contours) and used to segment the LV blood volume and myocardium. Performance was quantified by measuring precision on an independent multi-site validation dataset with multiple pathologies with n = 109 patients, scanned twice. This dataset was augmented with a further 1277 patients scanned as part of routine clinical care to allow qualitative assessment of generalization ability by identifying mis-segmentations. Machine learning algorithm ('machine') performance was compared to three clinicians ('human') and a commercial tool (cvi42, Circle Cardiovascular Imaging). FINDINGS: Machine analysis was quicker (20 s per patient) than human (13 min). Overall machine mis-segmentation rate was 1 in 479 images for the combined dataset, occurring mostly in rare pathologies not encountered in training. Without correcting these mis-segmentations, machine analysis had superior precision to three clinicians (e.g. scan-rescan coefficients of variation of human vs machine: LVEF 6.0% vs 4.2%, LV mass 4.8% vs. 3.6%; both P < 0.05), translating to a 46% reduction in required trial sample size using an LVEF endpoint. CONCLUSION: We present a fully automated algorithm for measuring LV structure and global systolic function that betters human performance for speed and precision.

Study protocol: MyoFit46-the cardiac sub-study of the MRC National Survey of Health and Development.

BACKGROUND: The life course accumulation of overt and subclinical myocardial dysfunction contributes to older age mortality, frailty, disability and loss of independence. The Medical Research Council National Survey of Health and Development (NSHD) is the world's longest running continued surveillance birth cohort providing a unique opportunity to understand life course determinants of myocardial dysfunction as part of MyoFit46-the cardiac sub-study of the NSHD. METHODS: We aim to recruit 550 NSHD participants of approximately 75 years+ to undertake high-density surface electrocardiographic imaging (ECGI) and stress perfusion cardiovascular magnetic resonance (CMR). Through comprehensive myocardial tissue characterization and 4-dimensional flow we hope to better understand the burden of clinical and subclinical cardiovascular disease. Supercomputers will be used to combine the multi-scale ECGI and CMR datasets per participant. Rarely available, prospectively collected whole-of-life data on exposures, traditional risk factors and multimorbidity will be studied to identify risk trajectories, critical change periods, mediators and cumulative impacts on the myocardium. DISCUSSION: By combining well curated, prospectively acquired longitudinal data of the NSHD with novel CMR-ECGI data and sharing these results and associated pipelines with the CMR community, MyoFit46 seeks to transform our understanding of how early, mid and later-life risk factor trajectories interact to determine the state of cardiovascular health in older age. TRIAL REGISTRATION: Prospectively registered on ClinicalTrials.gov with trial ID: 19/LO/1774 Multimorbidity Life-Course Approach to Myocardial Health- A Cardiac Sub-Study of the MCRC National Survey of Health and Development (NSHD).

The Prognostic Significance of Quantitative Myocardial Perfusion: An Artificial Intelligence-Based Approach Using Perfusion Mapping.

BACKGROUND: Myocardial perfusion reflects the macro- and microvascular coronary circulation. Recent quantitation developments using cardiovascular magnetic resonance perfusion permit automated measurement clinically. We explored the prognostic significance of stress myocardial blood flow (MBF) and myocardial perfusion reserve (MPR, the ratio of stress to rest MBF). METHODS: A 2-center study of patients with both suspected and known coronary artery disease referred clinically for perfusion assessment. Image analysis was performed automatically using a novel artificial intelligence approach deriving global and regional stress and rest MBF and MPR. Cox proportional hazard models adjusting for comorbidities and cardiovascular magnetic resonance parameters sought associations of stress MBF and MPR with death and major adverse cardiovascular events (MACE), including myocardial infarction, stroke, heart failure hospitalization, late (>90 day) revascularization, and death. RESULTS: A total of 1049 patients were included with a median follow-up of 605 (interquartile range, 464-814) days. There were 42 (4.0%) deaths and 188 MACE in 174 (16.6%) patients. Stress MBF and MPR were independently associated with both death and MACE. For each 1 mL·g-1·min-1 decrease in stress MBF, the adjusted hazard ratios for death and MACE were 1.93 (95% CI, 1.08-3.48, P=0.028) and 2.14 (95% CI, 1.58-2.90, P<0.0001), respectively, even after adjusting for age and comorbidity. For each 1 U decrease in MPR, the adjusted hazard ratios for death and MACE were 2.45 (95% CI, 1.42-4.24, P=0.001) and 1.74 (95% CI, 1.36-2.22, P<0.0001), respectively. In patients without regional perfusion defects on clinical read and no known macrovascular coronary artery disease (n=783), MPR remained independently associated with death and MACE, with stress MBF remaining associated with MACE only. CONCLUSIONS: In patients with known or suspected coronary artery disease, reduced MBF and MPR measured automatically inline using artificial intelligence quantification of cardiovascular magnetic resonance perfusion mapping provides a strong, independent predictor of adverse cardiovascular outcomes.

Challenges for augmenting intelligence in cardiac imaging.

Artificial Intelligence (AI), through deep learning, has brought automation and predictive capabilities to cardiac imaging. However, despite considerable investment, tangible health-care cost reductions remain unproven. Although AI holds promise, there has been insufficient time for both methodological development and prospective clinical trials to establish its advantage over human interpretations in terms of its effect on patient outcomes. Challenges such as data scarcity, privacy issues, and ethical concerns impede optimal AI training. Furthermore, the absence of a unified model for the complex structure and function of the heart and evolving domain knowledge can introduce heuristic biases and influence underlying assumptions in model development. Integrating AI into diverse institutional picture archiving and communication systems and devices also presents a clinical hurdle. This hurdle is further compounded by an absence of high-quality labelled data, difficulty sharing data between institutions, and non-uniform and inadequate gold standards for external validations and comparisons of model performance in real-world settings. Nevertheless, there is a strong push in industry and academia for AI solutions in medical imaging. This Series paper reviews key studies and identifies challenges that require a pragmatic change in the approach for using AI for cardiac imaging, whereby AI is viewed as augmented intelligence to complement, not replace, human judgement. The focus should shift from isolated measurements to integrating non-linear and complex data towards identifying disease phenotypes-emphasising pattern recognition where AI excels. Algorithms should enhance imaging reports, enriching patients' understanding, communication between patients and clinicians, and shared decision making. The emergence of professional standards and guidelines is essential to address these developments and ensure the safe and effective integration of AI in cardiac imaging.

Electrophysiological Characterization of Subclinical and Overt Hypertrophic Cardiomyopathy by Magnetic Resonance Imaging-Guided Electrocardiography.

BACKGROUND: Ventricular arrhythmia in hypertrophic cardiomyopathy (HCM) relates to adverse structural change and genetic status. Cardiovascular magnetic resonance (CMR)-guided electrocardiographic imaging (ECGI) noninvasively maps cardiac structural and electrophysiological (EP) properties. OBJECTIVES: The purpose of this study was to establish whether in subclinical HCM (genotype [G]+ left ventricular hypertrophy [LVH]-), ECGI detects early EP abnormality, and in overt HCM, whether the EP substrate relates to genetic status (G+/G-LVH+) and structural phenotype. METHODS: This was a prospective 211-participant CMR-ECGI multicenter study of 70 G+LVH-, 104 LVH+ (51 G+/53 G-), and 37 healthy volunteers (HVs). Local activation time (AT), corrected repolarization time, corrected activation-recovery interval, spatial gradients (GAT/GRTc), and signal fractionation were derived from 1,000 epicardial sites per participant. Maximal wall thickness and scar burden were derived from CMR. A support vector machine was built to discriminate G+LVH- from HV and low-risk HCM from those with intermediate/high-risk score or nonsustained ventricular tachycardia. RESULTS: Compared with HV, subclinical HCM showed mean AT prolongation (P = 0.008) even with normal 12-lead electrocardiograms (ECGs) (P = 0.009), and repolarization was more spatially heterogenous (GRTc: P = 0.005) (23% had normal ECGs). Corrected activation-recovery interval was prolonged in overt vs subclinical HCM (P < 0.001). Mean AT was associated with maximal wall thickness; spatial conduction heterogeneity (GAT) and fractionation were associated with scar (all P < 0.05), and G+LVH+ had more fractionation than G-LVH+ (P = 0.002). The support vector machine discriminated subclinical HCM from HV (10-fold cross-validation accuracy 80% [95% CI: 73%-85%]) and identified patients at higher risk of sudden cardiac death (accuracy 82% [95% CI: 78%-86%]). CONCLUSIONS: In the absence of LVH or 12-lead ECG abnormalities, HCM sarcomere gene mutation carriers express an aberrant EP phenotype detected by ECGI. In overt HCM, abnormalities occur more severely with adverse structural change and positive genetic status.

Diagnosis and prognosis of abnormal cardiac scintigraphy uptake suggestive of cardiac amyloidosis using artificial intelligence: a retrospective, international, multicentre, cross-tracer development and validation study.

BACKGROUND: The diagnosis of cardiac amyloidosis can be established non-invasively by scintigraphy using bone-avid tracers, but visual assessment is subjective and can lead to misdiagnosis. We aimed to develop and validate an artificial intelligence (AI) system for standardised and reliable screening of cardiac amyloidosis-suggestive uptake and assess its prognostic value, using a multinational database of 99mTc-scintigraphy data across multiple tracers and scanners. METHODS: In this retrospective, international, multicentre, cross-tracer development and validation study, 16 241 patients with 19 401 scans were included from nine centres: one hospital in Austria (consecutive recruitment Jan 4, 2010, to Aug 19, 2020), five hospital sites in London, UK (consecutive recruitment Oct 1, 2014, to Sept 29, 2022), two centres in China (selected scans from Jan 1, 2021, to Oct 31, 2022), and one centre in Italy (selected scans from Jan 1, 2011, to May 23, 2023). The dataset included all patients referred to whole-body 99mTc-scintigraphy with an anterior view and all 99mTc-labelled tracers currently used to identify cardiac amyloidosis-suggestive uptake. Exclusion criteria were image acquisition at less than 2 h (99mTc-3,3-diphosphono-1,2-propanodicarboxylic acid, 99mTc-hydroxymethylene diphosphonate, and 99mTc-methylene diphosphonate) or less than 1 h (99mTc-pyrophosphate) after tracer injection and if patients' imaging and clinical data could not be linked. Ground truth annotation was derived from centralised core-lab consensus reading of at least three independent experts (CN, TT-W, and JN). An AI system for detection of cardiac amyloidosis-associated high-grade cardiac tracer uptake was developed using data from one centre (Austria) and independently validated in the remaining centres. A multicase, multireader study and a medical algorithmic audit were conducted to assess clinician performance compared with AI and to evaluate and correct failure modes. The system's prognostic value in predicting mortality was tested in the consecutively recruited cohorts using cox proportional hazards models for each cohort individually and for the combined cohorts. FINDINGS: The prevalence of cases positive for cardiac amyloidosis-suggestive uptake was 142 (2%) of 9176 patients in the Austrian, 125 (2%) of 6763 patients in the UK, 63 (62%) of 102 patients in the Chinese, and 103 (52%) of 200 patients in the Italian cohorts. In the Austrian cohort, cross-validation performance showed an area under the curve (AUC) of 1·000 (95% CI 1·000-1·000). Independent validation yielded AUCs of 0·997 (0·993-0·999) for the UK, 0·925 (0·871-0·971) for the Chinese, and 1·000 (0·999-1·000) for the Italian cohorts. In the multicase multireader study, five physicians disagreed in 22 (11%) of 200 cases (Fleiss' kappa 0·89), with a mean AUC of 0·946 (95% CI 0·924-0·967), which was inferior to AI (AUC 0·997 [0·991-1·000], p=0·0040). The medical algorithmic audit demonstrated the system's robustness across demographic factors, tracers, scanners, and centres. The AI's predictions were independently prognostic for overall mortality (adjusted hazard ratio 1·44 [95% CI 1·19-1·74], p<0·0001). INTERPRETATION: AI-based screening of cardiac amyloidosis-suggestive uptake in patients undergoing scintigraphy was reliable, eliminated inter-rater variability, and portended prognostic value, with potential implications for identification, referral, and management pathways. FUNDING: Pfizer.

The Impact of Bariatric Surgery on Coronary Microvascular Function Assessed Using Automated Quantitative Perfusion CMR.

BACKGROUND: Coronary microvascular function is impaired in patients with obesity, contributing to myocardial dysfunction and heart failure. Bariatric surgery decreases cardiovascular mortality and heart failure, but the mechanisms are unclear. OBJECTIVES: The authors studied the impact of bariatric surgery on coronary microvascular function in patients with obesity and its relationship with metabolic syndrome. METHODS: Fully automated quantitative perfusion cardiac magnetic resonance and metabolic markers were performed before and 6 months after bariatric surgery. RESULTS: Compared with age- and sex-matched healthy volunteers, 38 patients living with obesity had lower stress myocardial blood flow (MBF) (P = 0.001) and lower myocardial perfusion reserve (P < 0.001). A total of 27 participants underwent paired follow-up 6 months post-surgery. Metabolic abnormalities reduced significantly at follow-up including mean body mass index by 11 ± 3 kg/m2 (P < 0.001), glycated hemoglobin by 9 mmol/mol (Q1-Q3: 4-19 mmol/mol; P < 0.001), fasting insulin by 142 ± 131 pmol/L (P < 0.001), and hepatic fat fraction by 5.6% (2.6%-15.0%; P < 0.001). Stress MBF increased by 0.28 mL/g/min (-0.02 to 0.75 mL/g/min; P = 0.003) and myocardial perfusion reserve by 0.13 (-0.25 to 1.1; P = 0.036). The increase in stress MBF was lower in those with preoperative type 2 diabetes mellitus (0.1 mL/g/min [-0.09 to 0.46 mL/g/min] vs 0.75 mL/g/min [0.31-1.25 mL/g/min]; P = 0.002). Improvement in stress MBF was associated with reduction in fasting insulin (beta = -0.45 [95% CI: -0.05 to 0.90]; P = 0.03). CONCLUSIONS: Coronary microvascular function is impaired in patients with obesity, but can be improved significantly with bariatric surgery. Improvements in microvascular function are associated with improvements in insulin resistance but are attenuated in those with preoperative type 2 diabetes mellitus.

Clinical Significance of Myocardial Injury in Patients Hospitalized for COVID-19: A Prospective, Multicenter, Cohort Study.

BACKGROUND: Hospitalized COVID-19 patients with troponin elevation have a higher prevalence of cardiac abnormalities than control individuals. However, the progression and impact of myocardial injury on COVID-19 survivors remain unclear. OBJECTIVES: This study sought to evaluate myocardial injury in COVID-19 survivors with troponin elevation with baseline and follow-up imaging and to assess medium-term outcomes. METHODS: This was a prospective, longitudinal cohort study in 25 United Kingdom centers (June 2020 to March 2021). Hospitalized COVID-19 patients with myocardial injury underwent cardiac magnetic resonance (CMR) scans within 28 days and 6 months postdischarge. Outcomes were tracked for 12 months, with quality of life surveys (EuroQol-5 Dimension and 36-Item Short Form surveys) taken at discharge and 6 months. RESULTS: Of 342 participants (median age: 61.3 years; 71.1% male) with baseline CMR, 338 had a 12-month follow-up, 235 had a 6-month CMR, and 215 has baseline and follow-up quality of life surveys. Of 338 participants, within 12 months, 1.2% died; 1.8% had new myocardial infarction, acute coronary syndrome, or coronary revascularization; 0.8% had new myopericarditis; and 3.3% had other cardiovascular events requiring hospitalization. At 6 months, there was a minor improvement in left ventricular ejection fraction (1.8% ± 1.0%; P < 0.001), stable right ventricular ejection fraction (0.4% ± 0.8%; P = 0.50), no change in myocardial scar pattern or volume (P = 0.26), and no imaging evidence of continued myocardial inflammation. All pericardial effusions (26 of 26) resolved, and most pneumonitis resolved (95 of 101). EuroQol-5 Dimension scores indicated an overall improvement in quality of life (P < 0.001). CONCLUSIONS: Myocardial injury in severe hospitalized COVID-19 survivors is nonprogressive. Medium-term outcomes show a low incidence of major adverse cardiovascular events and improved quality of life. (COVID-19 Effects on the Heart; ISRCTN58667920).

Evaluating semi-supervision methods for medical image segmentation: applications in cardiac magnetic resonance imaging.

Purpose: Neural networks have potential to automate medical image segmentation but require expensive labeling efforts. While methods have been proposed to reduce the labeling burden, most have not been thoroughly evaluated on large, clinical datasets or clinical tasks. We propose a method to train segmentation networks with limited labeled data and focus on thorough network evaluation. Approach: We propose a semi-supervised method that leverages data augmentation, consistency regularization, and pseudolabeling and train four cardiac magnetic resonance (MR) segmentation networks. We evaluate the models on multiinstitutional, multiscanner, multidisease cardiac MR datasets using five cardiac functional biomarkers, which are compared to an expert's measurements using Lin's concordance correlation coefficient (CCC), the within-subject coefficient of variation (CV), and the Dice coefficient. Results: The semi-supervised networks achieve strong agreement using Lin's CCC ( > 0.8 ), CV similar to an expert, and strong generalization performance. We compare the error modes of the semi-supervised networks against fully supervised networks. We evaluate semi-supervised model performance as a function of labeled training data and with different types of model supervision, showing that a model trained with 100 labeled image slices can achieve a Dice coefficient within 1.10% of a network trained with 16,000+ labeled image slices. Conclusion: We evaluate semi-supervision for medical image segmentation using heterogeneous datasets and clinical metrics. As methods for training models with little labeled data become more common, knowledge about how they perform on clinical tasks, how they fail, and how they perform with different amounts of labeled data is useful to model developers and users.

Artificial intelligence in medical device software and high-risk medical devices - a review of definitions, expert recommendations and regulatory initiatives.

INTRODUCTION: Artificial intelligence (AI) encompasses a wide range of algorithms with risks when used to support decisions about diagnosis or treatment, so professional and regulatory bodies are recommending how they should be managed. AREAS COVERED: AI systems may qualify as standalone medical device software (MDSW) or be embedded within a medical device. Within the European Union (EU) AI software must undergo a conformity assessment procedure to be approved as a medical device. The draft EU Regulation on AI proposes rules that will apply across industry sectors, while for devices the Medical Device Regulation also applies. In the CORE-MD project (Coordinating Research and Evidence for Medical Devices), we have surveyed definitions and summarize initiatives made by professional consensus groups, regulators, and standardization bodies. EXPERT OPINION: The level of clinical evidence required should be determined according to each application and to legal and methodological factors that contribute to risk, including accountability, transparency, and interpretability. EU guidance for MDSW based on international recommendations does not yet describe the clinical evidence needed for medical AI software. Regulators, notified bodies, manufacturers, clinicians and patients would all benefit from common standards for the clinical evaluation of high-risk AI applications and transparency of their evidence and performance.

Automated In-Line Artificial Intelligence Measured Global Longitudinal Shortening and Mitral Annular Plane Systolic Excursion: Reproducibility and Prognostic Significance.

Background Global longitudinal shortening (GL-Shortening) and the mitral annular plane systolic excursion (MAPSE) are known markers in heart failure patients, but measurement may be subjective and less frequently reported because of the lack of automated analysis. Therefore, a validated, automated artificial intelligence (AI) solution can be of strong clinical interest. Methods and Results The model was implemented on cardiac magnetic resonance scanners with automated in-line processing. Reproducibility was evaluated in a scan-rescan data set (n=160 patients). The prognostic association with adverse events (death or hospitalization for heart failure) was evaluated in a large patient cohort (n=1572) and compared with feature tracking global longitudinal strain measured manually by experts. Automated processing took ≈1.1 seconds for a typical case. On the scan-rescan data set, the model exceeded the precision of human expert (coefficient of variation 7.2% versus 11.1% for GL-Shortening, P=0.0024; 6.5% versus 9.1% for MAPSE, P=0.0124). The minimal detectable change at 90% power was 2.53 percentage points for GL-Shortening and 1.84 mm for MAPSE. AI GL-Shortening correlated well with manual global longitudinal strain (R2=0.85). AI MAPSE had the strongest association with outcomes (χ2, 255; hazard ratio [HR], 2.5 [95% CI, 2.2-2.8]), compared with AI GL-Shortening (χ2, 197; HR, 2.1 [95% CI,1.9-2.4]), manual global longitudinal strain (χ2, 192; HR, 2.1 [95% CI, 1.9-2.3]), and left ventricular ejection fraction (χ2, 147; HR, 1.8 [95% CI, 1.6-1.9]), with P<0.001 for all. Conclusions Automated in-line AI-measured MAPSE and GL-Shortening can deliver immediate and highly reproducible results during cardiac magnetic resonance scanning. These results have strong associations with adverse outcomes that exceed those of global longitudinal strain and left ventricular ejection fraction.

Association of Myocardial Fibrosis and Stroke Volume by Cardiovascular Magnetic Resonance in Patients With Severe Aortic Stenosis With Outcome After Valve Replacement: The British Society of Cardiovascular Magnetic Resonance AS700 Study.

Importance: Low-flow severe aortic stenosis (AS) has higher mortality than severe AS with normal flow. The conventional definition of low-flow AS is an indexed stroke volume (SVi) by echocardiography less than 35 mL/m2. Cardiovascular magnetic resonance (CMR) is the reference standard for quantifying left ventricular volumes and function from which SVi by CMR can be derived. Objective: To determine the association of left ventricular SVi by CMR with myocardial remodeling and survival among patients with severe AS after valve replacement. Design, Setting, and Participants: This multicenter longitudinal cohort study was conducted between January 2003 and May 2015 across 6 UK cardiothoracic centers. Patients with severe AS listed for either surgical aortic valve replacement (SAVR) or transcatheter aortic valve replacement (TAVR) were included. Patients underwent preprocedural echocardiography and CMR. Patients were stratified by echocardiography-derived aortic valve mean and/or peak gradient and SVi by CMR into 4 AS endotypes: low-flow, low-gradient AS; low-flow, high-gradient AS; normal-flow, low-gradient AS; and normal-flow, high-gradient AS. Patients were observed for a median of 3.6 years. Data were analyzed from September to November 2021. Exposures: SAVR or TAVR. Main Outcomes and Measures: All-cause and cardiovascular (CV) mortality after aortic valve intervention. Results: Of 674 included patients, 425 (63.1%) were male, and the median (IQR) age was 75 (66-80) years. The median (IQR) aortic valve area index was 0.4 (0.3-0.4) cm2/m2. Patients with low-flow AS endotypes (low gradient and high gradient) had lower left ventricular ejection fraction, mass, and wall thickness and increased all-cause and CV mortality than patients with normal-flow AS (all-cause mortality: hazard ratio [HR], 2.08; 95% CI, 1.37-3.14; P < .001; CV mortality: HR, 3.06; 95% CI, 1.79-5.25; P < .001). CV mortality was independently associated with lower SVi (HR, 1.64; 95% CI, 1.08-2.50; P = .04), age (HR, 2.54; 95% CI, 1.29-5.01; P = .001), and higher quantity of late gadolinium enhancement (HR, 2.93; 95% CI, 1.68-5.09; P < .001). CV mortality hazard increased more rapidly in those with an SVI less than 45 mL/m2. SVi by CMR was independently associated with age, atrial fibrillation, focal scar (by late gadolinium enhancement), and parameters of cardiac remodeling (left ventricular mass and left atrial volume). Conclusions and Relevance: In this cohort study, SVi by CMR was associated with CV mortality after aortic valve replacement, independent of age, focal scar, and ejection fraction. The unique capability of CMR to quantify myocardial scar, combined with other prognostically important imaging biomarkers, such as SVi by CMR, may enable comprehensive stratification of postoperative risk in patients with severe symptomatic AS.

Phenotyping hypertrophic cardiomyopathy using cardiac diffusion magnetic resonance imaging: the relationship between microvascular dysfunction and microstructural changes.

AIMS: Microvascular dysfunction in hypertrophic cardiomyopathy (HCM) is predictive of clinical decline, however underlying mechanisms remain unclear. Cardiac diffusion tensor imaging (cDTI) allows in vivo characterization of myocardial microstructure by quantifying mean diffusivity (MD), fractional anisotropy (FA) of diffusion, and secondary eigenvector angle (E2A). In this cardiac magnetic resonance (CMR) study, we examine associations between perfusion and cDTI parameters to understand the sequence of pathophysiology and the interrelation between vascular function and underlying microstructure. METHODS AND RESULTS: Twenty HCM patients underwent 3.0T CMR which included: spin-echo cDTI, adenosine stress and rest perfusion mapping, cine-imaging, and late gadolinium enhancement (LGE). Ten controls underwent cDTI. Myocardial perfusion reserve (MPR), MD, FA, E2A, and wall thickness were calculated per segment and further divided into subendocardial (inner 50%) and subepicardial (outer 50%) regions. Segments with wall thickness ≤11 mm, MPR ≥2.2, and no visual LGE were classified as 'normal'. Compared to controls, 'normal' HCM segments had increased MD (1.61 ± 0.09 vs. 1.46 ± 0.07 × 10-3 mm2/s, P = 0.02), increased E2A (60 ± 9° vs. 38 ± 12°, P < 0.001), and decreased FA (0.29 ± 0.04 vs. 0.35 ± 0.02, P = 0.002). Across all HCM segments, subendocardial regions had higher MD and lower MPR than subepicardial (MDendo 1.61 ± 0.08 × 10-3 mm2/s vs. MDepi 1.56 ± 0.18 × 10-3 mm2/s, P = 0.003, MPRendo 1.85 ± 0.83, MPRepi 2.28 ± 0.87, P < 0.0001). CONCLUSION: In HCM patients, even in segments with normal wall thickness, normal perfusion, and no scar, diffusion is more isotropic than in controls, suggesting the presence of underlying cardiomyocyte disarray. Increased E2A suggests the myocardial sheetlets adopt hypercontracted angulation in systole. Increased MD, most notably in the subendocardium, is suggestive of regional remodelling which may explain the reduced subendocardial blood flow.

Landmark Detection in Cardiac MRI by Using a Convolutional Neural Network.

PURPOSE: To develop a convolutional neural network (CNN) solution for landmark detection in cardiac MRI (CMR). MATERIALS AND METHODS: This retrospective study included cine, late gadolinium enhancement (LGE), and T1 mapping examinations from two hospitals. The training set included 2329 patients (34 089 images; mean age, 54.1 years; 1471 men; December 2017 to March 2020). A hold-out test set included 531 patients (7723 images; mean age, 51.5 years; 323 men; May 2020 to July 2020). CNN models were developed to detect two mitral valve plane and apical points on long-axis images. On short-axis images, anterior and posterior right ventricular (RV) insertion points and left ventricular (LV) center points were detected. Model outputs were compared with manual labels assigned by two readers. The trained model was deployed to MRI scanners. RESULTS: For the long-axis images, successful detection of cardiac landmarks ranged from 99.7% to 100% for cine images and from 99.2% to 99.5% for LGE images. For the short-axis images, detection rates were 96.6% for cine, 97.6% for LGE, and 98.7% for T1 mapping. The Euclidean distances between model-assigned and manually assigned labels ranged from 2 to 3.5 mm for different landmarks, indicating close agreement between model-derived landmarks and manually assigned labels. For all views and imaging sequences, no differences between the models' assessment of images and the readers' assessment of images were found for the anterior RV insertion angle or LV length. Model inference for a typical cardiac cine series took 610 msec with the graphics processing unit and 5.6 seconds with central processing unit. CONCLUSION: A CNN was developed for landmark detection on both long- and short-axis CMR images acquired with cine, LGE, and T1 mapping sequences, and the accuracy of the CNN was comparable with the interreader variation.Keywords: Cardiac, Heart, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Feature Detection, Quantification, Supervised Learning, MR Imaging Supplemental material is available for this article. Published under a CC BY 4.0 license.

A Computationally Efficient Approach to Segmentation of the Aorta and Coronary Arteries Using Deep Learning.

Early detection and diagnosis of coronary artery disease could reduce the risk of developing a heart attack. The coronary arteries are optimally visualised using computed tomography coronary angiography (CTCA) imaging. These images are reviewed by specialist radiologists who evaluate the coronary arteries for potential narrowing. A lack of radiologists in the UK is a constraint to timely diagnosis of coronary artery disease, particularly in the acute accident and emergency department setting. The development of automated methods by which coronary artery narrowing can be identified rapidly and accurately are therefore timely. Such complex computer based tools also need to be sufficiently computationally efficient that they can run on servers typically found in hospital settings, where graphical processing units for example are unavailable. We propose a fully automatic two-dimensional Unet model to segment the aorta and coronary arteries on CTCA images. Two models are trained to segment two regions of interest, (1) the aorta and the coronary arteries or (2) the coronary arteries alone. Our method achieves 91.20% and 88.80% dice similarity coefficient accuracy on regions of interest 1 and 2 respectively. Compared with a semi-automatic segmentation method, our model performs better when segmenting the coronary arteries alone. The performance of the proposed method is comparable to existing published two-dimensional or three-dimensional deep learning models. Importantly, the algorithmic and graphical processing unit memory efficiencies are maintained such that the model can be deployed without requiring graphical processing units, and therefore can be used in a hospital setting.