The authors propose 3D (2D + time) novel, fast, robust, bidirectional coupled parametric deformable models that are capable of segmenting left ventricle (LV) wall borders using first- and second-order visual appearance features. The authors examine the effect of the proposed segmentation method on the estimation of global cardiac performance indexes.Methods:
First-order visual appearance of the cine cardiac magnetic resonance (CMR) signals (inside and outside the boundary of the deformable model) is modeled with an adaptive linear combination of discrete Gaussians (LCDG). Second-order visual appearance of the LV wall is accurately modeled with a translational and rotation-invariant second-order Markov-Gibbs random field (MGRF). The LCDG parameters are estimated using our previously proposed modification of the EM algorithm, and the potentials of rotationally invariant MGRF are computed analytically.Results:
The authors tested the proposed segmentation approach on 15 cine CMR data sets using the Dice similarity coefficient (DSC) and the average distance (AD) between the ground truth and automated segmentation contours. The authors documented an average DSC value of 0.926 ± 0.022 and an average AD value of 2.16 ± 0.60 mm compared to two other level set methods that achieve an average DSC values of 0.904 ± 0.033 and 0.885 ± 0.02; and an average AD values of 2.86 ± 1.35 mm and 5.72 ± 4.70 mm, respectively.Conclusions:
The proposed segmentation approach demonstrated superior performance over other methods. Specifically, the comparative results on the publicly available MICCAI 2009 Cardiac MR Left Ventricle Segmentation database documented superior performance of the proposed approach over published methods. Additionally, the high accuracy of our segmentation approach leads to accurate estimation of the global performance indexes, as evidenced by the Bland-Altman analyses of the end-systolic volume (ESV), end-diastolic volume (EDV), and the ejection fraction (EF) ratio.