scholarly journals Quantitative Assessment of Right Ventricular Size and Function with Multiple Parameters from Artificial Intelligence-Based Three-Dimensional Echocardiography: A Comparative Study with Cardiac Magnetic Resonance

2021 ◽  
Author(s):  
Ying Zhu ◽  
Yuwei bao ◽  
Kangchao Zheng ◽  
Wei Zhou ◽  
Zhang Jun ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Three Dimensional ◽  
Systolic Volume ◽  
Multiple Parameters ◽  
End Systolic Volume ◽  
Dimensional Echocardiography ◽  
Three Dimensional Echocardiography ◽  
And Function

Abstract Aims: This study aimed to explore the validation and the diagnostic value of multiple right ventricle (RV) volumes and functional parameters parameters derived from a novel artificial intelligence (AI)-based three-dimensional echocardiography (3DE) algorithm compared to cardiac magnetic resonance (CMR). Methods and Results: 51 patients with a broad spectrum of clinical diagnoses were finally included in this study. AI-based RV 3DE was performed in a single-beat HeartModel mode within 24 hours after CMR. Whether in the entire population or the patients with moderate and poor image quality, RV volumes and right ventricular ejection fraction (RVEF) measured by AI-based 3DE showed a statistically significant correlation with the corresponding CMR analysis (P<0.05 for all). The Bland-Altman plots indicated that these parameters were slightly underestimated by AI-based 3DE. Based on CMR derived RVEF<45% as RV dysfunction, end-systolic volume (ESV), end-systolic volume index (EDVi), stroke volume (SV), and RVEF showed great diagnostic performance in identifying RV dysfunction, as well as some non-volumetric parameters, including tricuspid annular systolic excursion (TAPSE), fractional area change (FAC), RV septum and free-wall longitudinal strains (LS) (P<0.05 for all). The cutoff value was 43% for RVEF with a sensitivity of 94% and specificity of 67%. Conclusion: AI-based 3DE provide rapid and accurate quantitation of the RV volumes and function with multiple parameters. Both volumetric and non-volumetric measurements derived from AI-based 3DE contributed to the identification of the RV dysfunction, even in the patients without excellent image quality of RV 3DE. Keywords: artificial intelligence, three-dimensional echocardiography, right ventricle, multiple parameters

scholarly journals Feasibility and Accuracy of a Fully Automated Right Ventricular Quantification Software With Three-Dimensional Echocardiography: Comparison With Cardiac Magnetic Resonance

2021 ◽  
Vol 8 ◽  
Author(s):  
Ashfaq Ahmad ◽  
He Li ◽  
Xiaojing Wan ◽  
Yi Zhong ◽  
Yanting Zhang ◽  
...  
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Right Ventricular ◽  
Three Dimensional ◽  
Frame Rate ◽  
The Novel ◽  
Systolic Volume ◽  
Dimensional Echocardiography ◽  
Three Dimensional Echocardiography ◽  
Rv Function

Background: A novel, fully automated right ventricular (RV) software for three-dimensional quantification of RV volumes and function was developed. The direct comparison of the software performance with cardiac magnetic resonance (CMR) was limited. Therefore, the aim of this study was to test the feasibility, accuracy, and reproducibility of a fully automated RV quantification software against CMR imaging as a reference.Methods: A total of 170 patients who underwent both CMR and three-dimensional echocardiography were enrolled. RV end-diastolic volume (RVEDV), RV end-systolic volume (RVESV), and RV ejection fraction (RVEF) were obtained using fully automated three-dimensional RV quantification software and compared with a CMR reference. For inter-technical agreement, Spearman correlation and Bland–Altman analysis were used.Results: The fully automated RV quantification software was feasible in 149 patients. RVEDV and RVESV were underestimated, and RVEF was overestimated compared with CMR values. RV measurements obtained from the manual editing method correlated better with CMR values than that without manual editing (RVEDV, 0.924 vs. 0.794: RVESV, 0.955 vs. 0.854; RVEF, 0.941 vs. 0.781 respectively, all p &lt; 0.0001) with less bias and narrower limit of agreement (LOA). The bias and LOA for RV volumes and EF using the automated software without and with manual editing were greater in patients with severely impaired RV function or low frame rate than those with normal and mild impaired RV function, or high frame rate. The fully automated RV three-dimensional measurements were highly reproducible.Conclusion: The novel fully automated RV software shows good feasibility and reproducibility, and the measurements had a high correlation with CMR values. These findings support the routine application of the novel 3D automated RV software in clinical practice.

Cardiac magnetic resonance imaging for assessment of mitral stenosis before and after percutaneous balloon valvuloplasty in comparison to two- and three-dimensional echocardiography

2020 ◽  
Vol 61 (9) ◽  
pp. 1176-1185
Author(s):  
Hanaa MM Abdelaziz ◽  
Ahmed M Tawfik ◽  
Ayman A Abd-Elsamad ◽  
Sherif A Sakr ◽  
Abdulsalam M Algamal
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Mitral Regurgitation ◽  
Mitral Stenosis ◽  
Three Dimensional ◽  
Percutaneous Balloon ◽  
Before And After ◽  
Dimensional Echocardiography ◽  
Three Dimensional Echocardiography ◽  
2D And 3D

Background The experience with cardiac magnetic resonance (CMR) in mitral stenosis (MS) is limited in contrast to mitral regurgitation. Purpose To compare CMR versus 2D and 3D transthoracic (TTE) and 3D transesophgeal (TEE) echocardiography in assessment of rheumatic MS before and after percutaneous balloon mitral valvuloplasty (PBMV). Material and Methods Twenty consecutive symptomatic patients with MS were evaluated prospectively and independently by CMR, TTE, and TEE pre-PBMV, and by CMR and TTE post-PBMV. Mitral valve area (MVA) was assessed by CMR planimetry, TTE and TEE planimetry, and pressure half time (PHT). Further assessment included trans-mitral velocity, mitral regurgitation (MR), and left atrial (LA) volume. Results PBMV was successful in 18 patients and failed in two patients (one with MVA <1.5 cm2, one developed severe MR). Pre-PBMV and MVA by CMR, 2D TTE, biplane, 3D TTE, 3D TEE, and PHT were 1.16, 1.16, 1.10, 1.02, 1.05, and 0.99 cm2, respectively. Post-PBMV, a significant increase in MVA was observed (2.15, 2.06, 2.07, 2.04, and 2.03 cm2, respectively). High agreement was observed between CMR and echocardiography before and after PBMV, except for PHT method. CMR significantly underestimated trans-mitral velocity and gradients compared to echocardiography (P<0.001). Before PBMV, mild MR was observed in 11, 12, and 19 patients by 2D TTE, 3D TTE, and CMR. After PBMV, MR was observed in all patients (19 mild, one severe) by all modalities. Echocardiography significantly underestimated LA volume compared to CMR (P<0.001). LA volume decreased significantly after PBMV (P<0.001). Conclusion CMR provides comprehensive assessment of several parameters in MS patients before and after intervention. Agreement with echocardiography is acceptable.

Sign in / Sign up

Export Citation Format

Share Document