Model-based left ventricle segmentation in 3D ultrasound using phase image

In this paper, we propose a semi-automatic method for left ventricle segmentation. The proposed method utilizes a multi-scale quadrature filter method to enhance the 3D volume, followed by a model-based level set method to segment the endocardial surface of the left ventricle. The phase map from the quadrature filters is also used to weight the influence of contour points when updating the statistical model.

[1]  Ahror Belaid,et al.  Phase based level set segmentation of ultrasound images , 2009, 2009 9th International Conference on Information Technology and Applications in Biomedicine.

[2]  Olivier D. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  Hans Knutsson,et al.  Morphons: segmentation using elastic canvas and paint on priors , 2005, IEEE International Conference on Image Processing 2005.

[4]  Magnus Borga,et al.  Blood vessel segmentation using multi-scale quadrature filtering , 2010, Pattern Recognit. Lett..

[5]  H. Frimmel,et al.  Fast level-set based image segmentation using coherent propagation. , 2014, Medical physics.

[6]  Örjan Smedby,et al.  The efficacy of 2D, non-linear noise reduction filtering in cardiac imaging: a pilot study , 2011, Acta radiologica.

[7]  Örjan Smedby,et al.  Automatic Multi-organ Segmentation in Non-enhanced CT Datasets Using Hierarchical Shape Priors , 2014, 2014 22nd International Conference on Pattern Recognition.

[8]  Örjan Smedby,et al.  Level-set based vessel segmentation accelerated with periodic monotonic speed function , 2011, Medical Imaging.

[9]  Can segmented 3D images be used for stenosis evaluation in coronary CT angiography? , 2012, Acta radiologica.

[10]  Hans Knutsson,et al.  True 4D Image Denoising on the GPU , 2011, Int. J. Biomed. Imaging.