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·min 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.
The purpose of this study was to detect cardiovascular changes after mild severe acute respiratory syndrome-coronavirus-2 infection.
Concern exists that mild coronavirus disease 2019 may cause ...myocardial and vascular disease.
Participants were recruited from COVIDsortium, a 3-hospital prospective study of 731 health care workers who underwent first-wave weekly symptom, polymerase chain reaction, and serology assessment over 4 months, with seroconversion in 21.5% (n = 157). At 6 months post-infection, 74 seropositive and 75 age-, sex-, and ethnicity-matched seronegative control subjects were recruited for cardiovascular phenotyping (comprehensive phantom-calibrated cardiovascular magnetic resonance and blood biomarkers). Analysis was blinded, using objective artificial intelligence analytics where available.
A total of 149 subjects (mean age 37 years, range 18 to 63 years, 58% women) were recruited. Seropositive infections had been mild with case definition, noncase definition, and asymptomatic disease in 45 (61%), 18 (24%), and 11 (15%), respectively, with 1 person hospitalized (for 2 days). Between seropositive and seronegative groups, there were no differences in cardiac structure (left ventricular volumes, mass, atrial area), function (ejection fraction, global longitudinal shortening, aortic distensibility), tissue characterization (T1, T2, extracellular volume fraction mapping, late gadolinium enhancement) or biomarkers (troponin, N-terminal pro–B-type natriuretic peptide). With abnormal defined by the 75 seronegatives (2 SDs from mean, e.g., ejection fraction <54%, septal T1 >1,072 ms, septal T2 >52.4 ms), individuals had abnormalities including reduced ejection fraction (n = 2, minimum 50%), T1 elevation (n = 6), T2 elevation (n = 9), late gadolinium enhancement (n = 13, median 1%, max 5% of myocardium), biomarker elevation (borderline troponin elevation in 4; all N-terminal pro–B-type natriuretic peptide normal). These were distributed equally between seropositive and seronegative individuals.
Cardiovascular abnormalities are no more common in seropositive versus seronegative otherwise healthy, workforce representative individuals 6 months post–mild severe acute respiratory syndrome-coronavirus-2 infection.
Display omitted
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.
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).
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.
We present a fully automated algorithm for measuring LV structure and global systolic function that betters human performance for speed and precision.
Convolutional neural network (CNN) based segmentation methods provide an efficient and automated way for clinicians to assess the structure and function of the heart in cardiac MR images. While CNNs ...can generally perform the segmentation tasks with high accuracy when training and test images come from the same domain (e.g., same scanner or site), their performance often degrades dramatically on images from different scanners or clinical sites.
We propose a simple yet effective way for improving the network generalization ability by carefully designing data normalization and augmentation strategies to accommodate common scenarios in multi-site, multi-scanner clinical imaging data sets. We demonstrate that a neural network trained on a single-site single-scanner dataset from the UK Biobank can be successfully applied to segmenting cardiac MR images across different sites and different scanners without substantial loss of accuracy. Specifically, the method was trained on a large set of 3,975 subjects from the UK Biobank. It was then directly tested on 600 different subjects from the UK Biobank for intra-domain testing and two other sets for cross-domain testing: the ACDC dataset (100 subjects, 1 site, 2 scanners) and the BSCMR-AS dataset (599 subjects, 6 sites, 9 scanners).
The proposed method produces promising segmentation results on the UK Biobank test set which are comparable to previously reported values in the literature, while also performing well on cross-domain test sets, achieving a mean Dice metric of 0.90 for the left ventricle, 0.81 for the myocardium, and 0.82 for the right ventricle on the ACDC dataset; and 0.89 for the left ventricle, 0.83 for the myocardium on the BSCMR-AS dataset.
The proposed method offers a potential solution to improve CNN-based model generalizability for the cross-scanner and cross-site cardiac MR image segmentation task.
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.
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.
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+;
<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%;
<0.001 for both). The myocardial injury pattern was different, with cases more likely than controls to have infarction (13% versus 2% and 7%;
<0.01) or microinfarction (9% versus 0% and 1%;
<0.001), but there was no difference in nonischemic scar (13% versus 5% and 14%;
=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 (
=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%;
=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;
=0.02).
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.
URL: https://www.isrctn.com; Unique identifier: 58667920.
To develop a convolutional neural network (CNN) solution for landmark detection in cardiac MRI (CMR).
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.
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.
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.
Cardiac, Heart, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Feature Detection, Quantification, Supervised Learning, MR Imaging
Published under a CC BY 4.0 license.
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.
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).
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
<0.001) and MVD (lower stress myocardial blood flow and myocardial perfusion reserve; both
<0.001). Patients with G-LVH+ were similar to those with G+LVH+ but had elevated second eigenvector angle (
<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;
=0.001). Patients with G+LVH- compared with healthy volunteers similarly had altered microstructure, although to a lesser extent (all diffusion tensor imaging parameters;
<0.001), and MVD (reduced stress myocardial blood flow
=0.015 with perfusion defects in 28% versus 0 healthy volunteers
=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,
=0.01; stress myocardial blood flow: odds ratio, 2.8,
=0.015; subclinical: fractional anisotropy odds ratio, 4.0,
=0.001; myocardial perfusion reserve odds ratio, 2.2,
=0.049).
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.
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.