Dataset Information

Estimation of biological heart age using cardiovascular magnetic resonance radiomics.

ABSTRACT: We developed a novel interpretable biological heart age estimation model using cardiovascular magnetic resonance radiomics measures of ventricular shape and myocardial character. We included 29,996 UK Biobank participants without cardiovascular disease. Images were segmented using an automated analysis pipeline. We extracted 254 radiomics features from the left ventricle, right ventricle, and myocardium of each study. We then used Bayesian ridge regression with tenfold cross-validation to develop a heart age estimation model using the radiomics features as the model input and chronological age as the model output. We examined associations of radiomics features with heart age in men and women, observing sex-differential patterns. We subtracted actual age from model estimated heart age to calculate a "heart age delta", which we considered as a measure of heart aging. We performed a phenome-wide association study of 701 exposures with heart age delta. The strongest correlates of heart aging were measures of obesity, adverse serum lipid markers, hypertension, diabetes, heart rate, income, multimorbidity, musculoskeletal health, and respiratory health. This technique provides a new method for phenotypic assessment relating to cardiovascular aging; further studies are required to assess whether it provides incremental risk information over current approaches.

SUBMITTER: Raisi-Estabragh Z

PROVIDER: S-EPMC9329281 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimation of biological heart age using cardiovascular magnetic resonance radiomics.

Raisi-Estabragh Zahra Z Salih Ahmed A Gkontra Polyxeni P Atehortúa Angélica A Radeva Petia P Boscolo Galazzo Ilaria I Menegaz Gloria G Harvey Nicholas C NC Lekadir Karim K Petersen Steffen E SE

Scientific reports 20220727 1

We developed a novel interpretable biological heart age estimation model using cardiovascular magnetic resonance radiomics measures of ventricular shape and myocardial character. We included 29,996 UK Biobank participants without cardiovascular disease. Images were segmented using an automated analysis pipeline. We extracted 254 radiomics features from the left ventricle, right ventricle, and myocardium of each study. We then used Bayesian ridge regression with tenfold cross-validation to develo ...[more]

PMID: 35896705

Similar Datasets

Project description:BackgroundRadial self-navigated (RSN) whole-heart coronary cardiovascular magnetic resonance angiography (CCMRA) is a free-breathing technique that estimates and corrects for respiratory motion. However, RSN has been limited to a 1D rigid correction which is often insufficient for patients with complex respiratory patterns. The goal of this work is therefore to improve the robustness and quality of 3D radial CCMRA by incorporating both 3D motion information and nonrigid intra-acquisition correction of the data into a framework called focused navigation (fNAV).MethodsWe applied fNAV to 500 data sets from a numerical simulation, 22 healthy subjects, and 549 cardiac patients. In each of these cohorts we compared fNAV to RSN and respiratory resolved extradimensional golden-angle radial sparse parallel (XD-GRASP) reconstructions of the same data. Reconstruction times for each method were recorded. Motion estimate accuracy was measured as the correlation between fNAV and ground truth for simulations, and fNAV and image registration for in vivo data. Percent vessel sharpness was measured in all simulated data sets and healthy subjects, and a subset of patients. Finally, subjective image quality analysis was performed by a blinded expert reviewer who chose the best image for each in vivo data set and scored on a Likert scale 0-4 in a subset of patients by two reviewers in consensus.ResultsThe reconstruction time for fNAV images was significantly higher than RSN (6.1 ± 2.1 min vs 1.4 ± 0.3, min, p < 0.025) but significantly lower than XD-GRASP (25.6 ± 7.1, min, p < 0.025). Overall, there is high correlation between the fNAV and reference displacement estimates across all data sets (0.73 ± 0.29). For simulated data, healthy subjects, and patients, fNAV lead to significantly sharper coronary arteries than all other reconstruction methods (p < 0.01). Finally, in a blinded evaluation by an expert reviewer fNAV was chosen as the best image in 444 out of 571 data sets (78%; p < 0.001) and consensus grades of fNAV images (2.6 ± 0.6) were significantly higher (p < 0.05) than uncorrected (1.7 ± 0.7), RSN (1.9 ± 0.6), and XD-GRASP (1.8 ± 0.8).ConclusionfNAV is a promising technique for improving the quality of RSN free-breathing 3D whole-heart CCMRA. This novel approach to respiratory self-navigation can derive 3D nonrigid motion estimations from an acquired 1D signal yielding statistically significant improvement in image sharpness relative to 1D translational correction as well as XD-GRASP reconstructions. Further study of the diagnostic impact of this technique is therefore warranted to evaluate its full clinical utility.

Project description:BackgroundDiscriminating hypertrophic cardiomyopathy (HCM) and hypertensive heart disease (HHD) is challenging, because both are characterized by left ventricular hypertrophy (LVH). Radiomics might be effective to differentiate HHD from HCM. Therefore, this study aimed to investigate discriminators and build discrimination models between HHD and HCM using multiparametric cardiac magnetic resonance (CMR) findings and radiomics score (radscore) derived from late gadolinium enhancement (LGE) and cine images.MethodsIn this single center, retrospective study, 421 HCM patients [median and interquartile range (IQR), 50.0 (38.0-59.0) years; male, 70.5%] from January 2017 to September 2021 and 200 HHD patients [median and IQR, 44.5 (35.0-57.0) years; male, 88.5%] from September 2015 to July 2022 were consecutively included and randomly stratified into a training group and a validation group at a ratio of 6:4. Multiparametric CMR findings were obtained using cvi42 software and radiomics features using Python software. After dimensional reduction, the radscore was calculated by summing the remaining radiomics features weighted by their coefficients. Multiparametric CMR findings and radscore that were statistically significant in univariate logistic regression were used to build combined discrimination models via multivariate logistic regression.ResultsAfter multivariate logistic regression, the maximal left ventricular end diastolic wall thickness (LVEDWT), left ventricular ejection fraction (LVEF), presence of LGE, cine radscore and LGE radscore were identified as significant characteristics and used to build a combined discrimination model. This model achieved an area under the receiver operator characteristic curve (AUC) of 0.979 (0.968-0.990) in the training group and 0.981 (0.967-0.995) in the validation group, significantly better than the model using multiparametric CMR findings alone (P<0.001).ConclusionsRadiomics features derived from cardiac cine and LGE images can effectively discriminate HHD from HCM.

Project description:BackgroundThe orifice area of mitral bioprostheses provides important information regarding their hemodynamic performance. It is usually calculated by transthoracic echocardiography (TTE), however, accurate and reproducible determination may be challenging. Cardiovascular magnetic resonance (CMR) has been proven as an accurate alternative for assessing aortic bioprostheses. However, whether CMR can be similarly applied for bioprostheses in the mitral position, particularly in the presence of frequently coincident arrhythmias, is unclear. The aim of the study is to test the feasibility of CMR to evaluate the orifice area of mitral bioprostheses.MethodsCMR planimetry was performed in 18 consecutive patients with mitral bioprostheses (n = 13 Hancock(R), n = 4 Labcore(R), n = 1 Perimount(R); mean time since implantation 4.5 +/- 3.9 years) in an imaging plane perpendicular to the transprosthetic flow using steady-state free-precession cine imaging under breath-hold conditions on a 1.5T MR system. CMR results were compared with pressure half-time derived orifice areas obtained by TTE.ResultsSix subjects were in sinus rhythm, 11 in atrial fibrillation, and 1 exhibited frequent ventricular extrasystoles. CMR image quality was rated as good in 10, moderate in 6, and significantly impaired in 2 subjects. In one prosthetic type (Perimount(R)), strong stent artifacts occurred. Orifice areas by CMR (mean 2.1 +/- 0.3 cm2) and TTE (mean 2.1 +/- 0.3 cm2) correlated significantly (r = 0.94; p < 0.001). Bland-Altman analysis showed a 95% confidence interval from -0.16 to 0.28 cm2 (mean difference 0.06 +/- 0.11 cm2; range -0.1 to 0.3 cm2). Intra- and inter-observer variabilities of CMR planimetry were 4.5 +/- 2.9% and 7.9 +/- 5.2%.ConclusionsThe assessment of mitral bioprostheses using CMR is feasible even in those with arrhythmias, providing orifice areas with close agreement to echocardiography and low observer dependency. Larger samples with a greater variety of prosthetic types and more cases of prosthetic dysfunction are required to confirm these preliminary results.

Project description:BackgroundThere are few data on practice patterns and trends for cardiovascular magnetic resonance (CMR) in pediatric and congenital heart disease. The Society for Cardiovascular Magnetic Resonance (SCMR) sought to address this deficiency by performing an international survey of CMR centers.MethodsSurveys consisting of 31 (2014) and 33 (2018) items were designed to collect data on the use of CMR for the evaluation of pediatric and congenital heart disease patients. They were sent to all SCMR members in 2014 and 2018. One response per center was collected.ResultsThere were 93 centers that responded in 2014 and 83 in 2018. The results that follow show data from 2014 and 2018 separated by a dash. The median annual number of pediatric/congenital CMR cases per center was 183-209. The median number of scanners for CMR was 2-2 (range, 1-8) with 58-63% using only 1.5T scanners and 4-4% using only 3T scanners. The mean number of attending/staff reading CMRs was 3.7-2.6; among them, 52-61% were pediatric or adult cardiologists and 47-38% were pediatric or adult radiologists. The median annual case volume per attending was 54-86. The median number of technologists per center doing CMRs was 4-5. The median scanner time allocated for a non-sedated examination was 75-75 min (range, 45-120). Among the 21 centers responding to both surveys, the mean annual case volume increased from 320 in 2014 to 445 in 2018; 17 (81%) of the centers had an increase in annual case volume. For this subgroup, the median attending/staff per center was 4 in both 2014 and 2018. The median scanner time allotted per study was unchanged at 90 min. The mean time for an attending/staff physician to perform a typical CMR examination including reporting was 143-141 min.ConclusionThese survey data provide a novel comprehensive view of CMR practice in pediatric and congenital heart disease. This information is useful for internal benchmarking, resource allocation, addressing practice variation, quality improvement initiatives, and identifying unmet needs.

Dataset Information

Estimation of biological heart age using cardiovascular magnetic resonance radiomics.

Publications

Estimation of biological heart age using cardiovascular magnetic resonance radiomics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets