Validation of Artificial Intelligence Cardiac MRI Measurements: Relationship to Heart Catheterization and Mortality Prediction

Alabed, Samer; Alandejani, Faisal; Dwivedi, Krit; Karunasaagarar, Kavitasagary; Sharkey, Michael J.; Garg, Pankaj; Koning, Patrick J.H. de; Tóth, Attila; Shahin, Yousef; Johns, Christopher; Mamalakis, Michail; Stott, Sarah; Capener, David; Wood, Steve; Metherall, Peter; Rothman, Alexander; Condliffe, Robin; Hamilton, Neil W.; Wild, Jim M.; O’Regan, Declan P.; Li, Haiping; Kiely, David G.; Geest, Rob J. van der; Swift, Andrew J.

doi:10.1148/radiol.229014

Cited by 8 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence (AI)-based automatic segmentation of LV and RV endocardial and epicardial borders in the short-axis stacks was performed to generate volume curves throughout the cardiac cycle. 14 In our study cohort, manual adjustments of AI segmented contours, typically in the apical slices, were performed in 32/169 (18.9%) cases after visually reviewing the contours. Papillary and trabecular muscles were included in the volume calculation.…”

Section: Methodsmentioning

confidence: 99%

Aortic flow is associated with aging and exercise capacity

Zhao,

Garg,

Assadi

et al. 2023

European Heart Journal Open

Self Cite

View full text Add to dashboard Cite

Aims Increased blood flow eccentricity in the aorta has been associated with aortic (AO) pathology, however, its association with exercise capacity has not been investigated. This study aimed to assess the relationships between flow eccentricity parameters derived from 2-dimensional (2D) phase-contrast (PC) cardiovascular magnetic resonance (CMR) imaging and aging and cardiopulmonary exercise test (CPET) in a cohort of healthy subjects. Methods and Results One hundred and sixty-nine healthy subjects (age 44 ± 13 years, M/F: 96/73) free of cardiovascular disease were recruited in a prospective study (NCT03217240) and underwent CMR, including 2D PC at an orthogonal plane just above the sinotubular junction, and CPET (cycle ergometer) within one week. The following AO flow parameters were derived: AO forward and backward flow indexed to body surface area (FFi, BFi), average flow displacement during systole (FDsavg), late systole (FDlsavg), diastole (FDdavg), systolic retrograde flow (SRF), systolic flow reversal ratio (sFRR), and pulse wave velocity (PWV). Exercise capacity was assessed by peak oxygen uptake (PVO2) from CPET. The mean values of FDsavg, FDlsavg, FDdavg, SRF, sFRR, and PWV were 17 ± 6%, 19 ± 8%, 29 ± 7%, 4.4 ± 4.2 mL, 5.9 ± 5.1%, and 4.3 ± 1.6 m/s, respectively. They all increased with age (r = 0.623, 0.628, 0.353, 0.590, 0.649, 0.598, all P < 0.0001), and decreased with PVO2 (r = −0.302, −0.270, −0.253, −0.149, −0.219, −0.161, all P < 0.05). A stepwise multivariable linear regression analysis using left ventricular ejection fraction (LVEF), FFi, and FDsavg showed an area under the curve of 0.769 in differentiating healthy subjects with high-risk exercise capacity (PVO2 ≤ 14 mL/kg/min). Conclusion AO flow haemodynamics change with aging and predict exercise capacity. Registration NCT03217240

show abstract

Section: Methodsmentioning

confidence: 99%

Aortic flow is associated with aging and exercise capacity

Zhao,

Garg,

Assadi

et al. 2023

European Heart Journal Open

Self Cite

View full text Add to dashboard Cite

show abstract

“…A semi-automated method based on artificial intelligence (AI) and subsequent manual inspection and corrections where needed was used to segment endocardial and epicardial borders in stacks of LV and RV short-axis images [ 21 ]. In our study cohort, manual adjustments of AI segmented contours in heart apex were performed in 32/163 (19.6%) cases.…”

Section: Methodsmentioning

confidence: 99%

Age- and sex-specific reference values of biventricular flow components and kinetic energy by 4D flow cardiovascular magnetic resonance in healthy subjects

Zhao,

Tan,

Garg

et al. 2023

Journal of Cardiovascular Magnetic Resonance

Self Cite

View full text Add to dashboard Cite

Background Advances in four-dimensional flow cardiovascular magnetic resonance (4D flow CMR) have allowed quantification of left ventricular (LV) and right ventricular (RV) blood flow. We aimed to (1) investigate age and sex differences of 4D flow CMR-derived LV and RV relative flow components and kinetic energy (KE) parameters indexed to end-diastolic volume (KEiEDV) in healthy subjects; and (2) assess the effects of age and sex on these parameters. Methods We performed 4D flow analysis in 163 healthy participants (42% female; mean age 43 ± 13 years) of a prospective registry study (NCT03217240) who were free of cardiovascular diseases. Relative flow components (direct flow, retained inflow, delayed ejection flow, residual volume) and multiple phasic KEiEDV (global, peak systolic, average systolic, average diastolic, peak E-wave, peak A-wave) for both LV and RV were analysed. Results Compared with men, women had lower median LV and RV residual volume, and LV peak and average systolic KEiEDV, and higher median values of RV direct flow, RV global KEiEDV, RV average diastolic KEiEDV, and RV peak E-wave KEiEDV. ANOVA analysis found there were no differences in flow components, peak and average systolic, average diastolic and global KEiEDV for both LV and RV across age groups. Peak A-wave KEiEDV increased significantly (r = 0.458 for LV and 0.341 for RV), whereas peak E-wave KEiEDV (r = − 0.355 for LV and − 0.318 for RV), and KEiEDV E/A ratio (r = − 0.475 for LV and − 0.504 for RV) decreased significantly, with age. Conclusion These data using state-of-the-art 4D flow CMR show that biventricular flow components and kinetic energy parameters vary significantly by age and sex. Age and sex trends should be considered in the interpretation of quantitative measures of biventricular flow. Clinical trial registration https://www.clinicaltrials.gov. Unique identifier: NCT03217240.

show abstract

Automated Three-Dimensional Liver Reconstruction with Artificial Intelligence for Virtual Hepatectomy

Takamoto

Ban

Nara

et al. 2022

Journal of Gastrointestinal Surgery

View full text Add to dashboard Cite

Validation of Artificial Intelligence Cardiac MRI Measurements: Relationship to Heart Catheterization and Mortality Prediction

Abstract: This is a repository copy of Validation of artificial intelligence cardiac MRI measurements: relationship to heart catheterization and mortality prediction.

Cited by 8 publications

References 25 publications

Aortic flow is associated with aging and exercise capacity

Aortic flow is associated with aging and exercise capacity

Age- and sex-specific reference values of biventricular flow components and kinetic energy by 4D flow cardiovascular magnetic resonance in healthy subjects

Automated Three-Dimensional Liver Reconstruction with Artificial Intelligence for Virtual Hepatectomy

Contact Info

Product

Resources

About