Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images

A fully automated approach to segmentation of the left and right cardiac ventricles from magnetic resonance (MR) images is reported. A novel multistage hybrid appearance model methodology is presented in which a hybrid active shape model/active appearance model (AAM) stage helps avoid local minima of the matching function. This yields an overall more favorable matching result. An automated initialization method is introduced making the approach fully automated. The authors' method was trained in a set of 102 MR images and tested in a separate set of 60 images. In all testing cases, the matching resulted in a visually plausible and accurate mapping of the model to the image data. Average signed border positioning errors did not exceed 0.3 mm in any of the three determined contours-left-ventricular (LV) epicardium, LV and right-ventricular (RV) endocardium. The area measurements derived from the three contours correlated well with the independent standard (r=0.96, 0.96, 0.90), with slopes and intercepts of the regression lines close to one and zero, respectively. Testing the reproducibility of the method demonstrated an unbiased performance with small range of error as assessed via Bland-Altman statistic. In direct border positioning error comparison, the multistage method significantly outperformed the conventional AAM (p<0.001). The developed method promises to facilitate fully automated quantitative analysis of LV and RV morphology and function in clinical setting.

[1]  Alok Gupta,et al.  Dynamic Programming for Detecting, Tracking, and Matching Deformable Contours , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Milan Sonka,et al.  Segmentation and interpretation of MR brain images. An improved active shape model , 1998, IEEE Transactions on Medical Imaging.

[3]  Timothy F. Cootes,et al.  A Unified Framework for Atlas Matching Using Active Appearance Models , 1999, IPMI.

[4]  J. Reiber,et al.  Comparison between manual and semiautomated analysis of left ventricular volume parameters from short-axis MR images. , 1997, Journal of computer assisted tomography.

[5]  J M Bland,et al.  Statistical methods for assessing agreement between two methods of clinical measurement , 1986 .

[6]  Juyang Weng,et al.  Learning-based ventricle detection from cardiac MR and CT images , 1994, Proceedings of IEEE Workshop on Biomedical Image Analysis.

[7]  Timothy F. Cootes,et al.  Statistical models of appearance for computer vision , 1999 .

[8]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[9]  A de Roos,et al.  Left ventricular measurements with cine and spin-echo MR imaging: a study of reproducibility with variance component analysis. , 1993, Radiology.

[10]  Boudewijn P. F. Lelieveldt,et al.  A multiresolution image segmentation technique based on pyramidal segmentation and fuzzy clustering , 2000, IEEE Trans. Image Process..

[11]  Milan Sonka,et al.  Image processing analysis and machine vision [2nd ed.] , 1999 .

[12]  James S. Duncan,et al.  Boundary Finding with Parametrically Deformable Models , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[14]  E L Ritman,et al.  Extraction of left-ventricular chamber from 3-D CT images of the heart. , 1990, IEEE transactions on medical imaging.

[15]  Max A. Viergever,et al.  Geodesic deformable models for medical image analysis , 1998, IEEE Transactions on Medical Imaging.

[16]  James S. Duncan,et al.  Model-based deformable surface finding for medical images , 1996, IEEE Trans. Medical Imaging.

[17]  A de Roos,et al.  Echo planar MRI of the heart on a standard system: validation of measurements of left ventricular function and mass. , 1996, Journal of computer assisted tomography.

[18]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.