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

• Published in: IEEE transactions on medical imaging 2001-05, Vol.20 (5), p.415-423
• Main Authors: Mitchell, S.C., Lelieveldt, B.P.F., van der Geest, R.J., Bosch, H.G., Reiver, J.H.C., Sonka, M.
• Format: Article
• Language: English
• Subjects: Active appearance model; Active shape model; Area measurement; Automation; Biological and medical sciences; Cardiology; Cardiovascular system; Computer Simulation; Computerized tomography; Data Interpretation, Statistical; Error analysis; Heart Ventricles - anatomy & histology; Image Processing, Computer-Assisted - statistics & numerical data; Image segmentation; Investigative techniques, diagnostic techniques (general aspects); Magnetic resonance; Magnetic Resonance Imaging - methods; Magnetic Resonance Imaging - statistics & numerical data; Measurement standards; Medical sciences; Models, Theoretical; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Regression analysis; Reproducibility of Results; Statistical analysis; Studies; Testing
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/42.925294

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