Full Quantification of Left Ventricle Using Deep Multitask Network with Combination of 2D and 3D Convolution on 2D + t Cine MRI

Author(s):  
Yeonggul Jang ◽  
Sekeun Kim ◽  
Hackjoon Shim ◽  
Hyuk-Jae Chang
Keyword(s):  
Cine Mri ◽  
Author(s):  
Giovanni Molina ◽  
Jose D. Velazco-Garcia ◽  
Dipan Shah ◽  
Aaron T. Becker ◽  
Ioannis Seimenis ◽  
...  

2020 ◽  
Vol 21 (Supplement_1) ◽  
Author(s):  
F Ericsson ◽  
B Tayal ◽  
K Hay Kragholm ◽  
T Zaremba ◽  
N Holmark Andersen ◽  
...  

Abstract Introduction In standard practice, LV volumes and EF are estimated by 2D technique. 3D echocardiographic assessment seems more reliable; however, this method has not yet been validated in the general population. Purpose To validate 3D echocardiography in a large population sample and investigate differences between 2D and 3D LVEF and volumes Methods In The Copenhagen City Heart Study, 4466 echocardiograms were available for analysis. The echocardiograms were obtained during four consecutive heartbeats in both 2D and 3D with GE Vivid E9. Offline analysis was performed on EchoPac v. 201. LVEF was calculated by the modified Simpsons Biplane Auto EF for 2D and by the 4LVQ method for 3D. Results The study included 2090 echocardiograms. The mean 2D LVEF was 57.3 ± 6.1% (IQR 54 - 61%) and 51.7 ± 7.9% (IQR 47 - 57%) by 3D. The mean end-diastolic volume (EDV) and end-systolic volume (ESV) by 2D and 3D techniques were: EDV 2D 106.1 ± 29.6 ml vs EDV 3D 128.2 ± 32.3 ml , ESV 2D 45.7 ± 15.6 ml vs. ESV 3D 45.7 ± 20.7 , p < 0.05 among all variables. The average difference of means between 2D and 3D LVEF was 5.6 ± 11.2%, -22.1 ± 56.8 ml for EDV, and -16.9 ± 32.9 ml for ESV. The correlation coefficient for LVEF was 0.42, EDV 0.76 and for ESV 0.70. Conclusion In our study, we found a significant difference in both LVEF and ventricular volumes when comparing 2D echocardiograms with 3D. 3DE had, in general, lower LVEF, higher EDV and ESV compared to 2D. Table 1: Summary of results Table 1 - Summary of results n = 2090 Variable Min Max Mean IQR (25-75) p-value LVEF, 2D (%) 18 76 57.3 ± 6.1 54-61 < 0.05 LVEF, 3d (%) 13 77 51.7 ± 7.9 47-57 < 0.05 EDV, 2D (ml) 13 275 106.1 ± 29.6 85-123.8 < 0.05 EDV, 3D (ml) 50 270 128.2 ± 32.3 106-148 < 0.05 ESV, 2D (ml) 15 150 45.7 ± 15.6 35-54 < 0.05 ESV, 3D (ml) 13 185 45.7 ± 20.7 48-74 < 0.05 LVEF: left ventricle ejection fraction, EDV: end-diastolic volume, ESV: end systolic volume, IQR: Inter-quartile range Abstract 1180 Figure 1: Correlation and BA-plot


2017 ◽  
Vol 7 (1) ◽  
Author(s):  
Hong Liu ◽  
Dan Yang ◽  
Ke Wan ◽  
Yong Luo ◽  
Jia-Yu Sun ◽  
...  

AbstractThe cine magnetic resonance imaging based technique feature tracking-cardiac magnetic resonance (FT-CMR) is emerging as a novel, simple and robust method to evaluate myocardial strain. We investigated the distribution characteristics of left-ventricular myocardial strain using a novel cine MRI based deformation registration algorithm (DRA) in a cohort of healthy Chinese subjects. A total of 130 healthy Chinese subjects were enrolled. Three components of orthogonal strain (radial, circumferential, longitudinal) of the left ventricle were analyzed using DRA on steady-state free precession cine sequence images. A distinct transmural circumferential strain gradient was observed in the left ventricle that showed universal increment from the epicardial to endocardial myocardial wall (epiwall: −15.4 ± 1.9%; midwall: −18.8 ± 2.0%; endowall: −22.3 ± 2.3%, P < 0.001). Longitudinal strain showed a similar trend from epicardial to endocardial layers (epiwall: −16.0 ± 2.9%; midwall: −15.6 ± 2.7%; endowall: −14.8 ± 2.4%, P < 0.001), but radial strain had a very heterogeneous distribution and variation. In the longitudinal direction from the base to the apex of the left ventricle, there was a trend of decreasing peak systolic longitudinal strain (basal: −23.3 ± 4.6%; mid: −13.7 ± 7.3%; apical: −13.2 ± 5.5%; P < 0.001). In conclusion, there are distinct distribution patterns of circumferential and longitudinal strain within the left ventricle in healthy Chinese subjects. These distribution patterns of strain may provide unique profiles for further study in different types of myocardial disease.


2009 ◽  
Author(s):  
Christopher Casta ◽  
Patrick Clarysse ◽  
Joël Schaerer ◽  
Jérome Pousin

We introduce a bio-inspired dynamic deformable (DET) model based on the equation of dynamics and including temporal smoothness constraints. The behaviour and characteristics of the dynamic DET model is studied in the context of the semi automatic spatio-temporal segmentation of the left ventricle myocardium in cine-MR images. The segmentation accuracy for endo/epicardium contours at end-diastole and end-systole, and as consequence the performance and limits of the current implementation, is evaluated in the context of the MICCAI LV Segmentation Challenge on a database of 15 multi-slice cine-MRI examinations.


Sign in / Sign up

Export Citation Format

Share Document