A 3D Statistical Shape Model for the Left Ventricle of the Heart
MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
STACOM'10/CESC'10 Proceedings of the First international conference on Statistical atlases and computational models of the heart, and international conference on Cardiac electrophysiological simulation challenge
Cardiac anchoring in MRI through context modeling
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Construction of a 4D statistical atlas of the cardiac anatomy and its use in classification
MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Left ventricular segmentation challenge from cardiac MRI: a collation study
STACOM'11 Proceedings of the Second international conference on Statistical Atlases and Computational Models of the Heart: imaging and modelling challenges
| Hi-index | 0.00 |
We demonstrate that large legacy databases of manually segmented cardiac MR images can be used to build a shape atlas based on 3D left-ventricular finite-element models. We make use of the Cardiac Atlas Project database to build an atlas of 2,045 asymptomatic cases from the MESA study. Manually placed anatomical landmarks on long-axis and short-axis magnetic resonance images were combined with manually drawn contours on the short axis images which were corrected for breath-hold mis-registration using an automated method. The contours were then fitted by the model using linear least squares optimisation. The fitting error was 0.5 ±0.4 mm at end-diastole and 0.5 ±0.6 mm at end-systole (mean ± std. dev.). Results were validated against 3D models created by experts in a sub-sample of 253 cases using manual breath-hold registration. The atlas surface error was 1.3 ±0.8 mm at end-diastole and 1.2 ±0.9 mm at end-systole. The end-diastolic volume error was 9.0 ±8.7 ml; the end-systolic volume error was 0.8 ±6.3 ml; and the mass error 5.9 ±12.9 g. These differences arose mainly at the base and apex because long-axis images were used in the validation models, but were only used in the automated models to define basal fiducial markers. All models were aligned and scaled, and finally analysed by principal component analysis. Significant differences were found in the first mode shape (sphericity) by gender, smoking, and hypertension.