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

By Steven C. Mitchell, Boudewijn P. F. Lelieveldt, R. Geest, J. Bosch, Johan Hans C. Reiber, Milan Sonka. IEEE Transactions on Medical Imaging, 2001

393 citations recorded by the source corpus.

Subfields: Cardiology and Cardiovascular Medicine, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/dfafa8f76325ac25754fdfbd106b8a904d797481

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Segmentation of 4D Cardiac MR Images Using a Probabilistic Atlas and the EM Algorithm (2003, methodology): “These last results are comparable to (Mitchell et al., 2001)where the correlation for the LV, RV andmyocardium is r 1⁄4 0:96, r 1⁄4 0:96 and r 1⁄4 0:90, respectively.”
FAME-a flexible appearance modeling environment (2003, background): “[9], [10] demonstrated the applicability of AAMs on single-slice cardiac MRI and later on time series of cardiac MRI [11], [12], [13].”
Automatic segmentation of echocardiographic sequences by active appearance motion models (2002, methodology): “The AAM approach has been extensively described [17]–[19].”
Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach (2006, methodology): “Again, the frequently used iterative gradient descent methods may end at a local optimum [56].”
Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI (2008, methodology): “This model incorporates knowledge about cardiac structure and, thus, provides a robust methodology for performing the segmentation (Mitchell et al., 2001, 2002).”
A review of segmentation methods in short axis cardiac MR images (2011, background): “In (Mitchell et al., 2001), the authors introduce a multistage hybrid model, arguing that AAM are optimized on global appearance but provide imprecise border locations, whereas ASM have a great ability to find local structures.”
Automated Segmentation of the Left Ventricle in Cardiac MRI (2003, methodology): “feature (Section 3). Statistical profile matching based on training data [1, 8 ] models variable grey value appearance, but is computationally expensive in 3D and achieves low specificity (and robustness) if the inter-subject profile variance is high (Fig. 1(c,d)).”
Automatic Model-Based Segmentation of the Heart in CT Images (2008, background): “[22] in a multistage framework for the segmentation of the ventricles in 2-D MR images.”