Abstract
The work deals with the segmentation of the image data using the
algorithm based on the numerical solution of the geometrical
evolution partial differential equation of the Allen-Cahn type. This
equation has origin in the description of motion by mean curvature
and has diffusive character. The diffusion process can be controlled
by the input intensity signal, so that edges of the objects or
areas can be found. The method is applied to the problem of
automatic segmentation of the left heart ventricle from the images
obtained by magnetic resonance (cardiac MRI). The segmentation is a
necessary step for estimation of significant indicators of the
myocardial function from dynamic MR images such as the ejection
fraction or the kinetic parameters of the wall thickening during the
cardiac cycle. These parameters describe clinical situation of the
myocardium.
algorithm based on the numerical solution of the geometrical
evolution partial differential equation of the Allen-Cahn type. This
equation has origin in the description of motion by mean curvature
and has diffusive character. The diffusion process can be controlled
by the input intensity signal, so that edges of the objects or
areas can be found. The method is applied to the problem of
automatic segmentation of the left heart ventricle from the images
obtained by magnetic resonance (cardiac MRI). The segmentation is a
necessary step for estimation of significant indicators of the
myocardial function from dynamic MR images such as the ejection
fraction or the kinetic parameters of the wall thickening during the
cardiac cycle. These parameters describe clinical situation of the
myocardium.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Czech–Japanese Seminar in Applied Mathematics 2006 |
| Pages | 37-49 |
| Number of pages | 13 |
| Volume | 6 |
| Publication status | Published - 2007 |
Publication series
| Name | COE Lecture Note |
|---|---|
| Publisher | Faculty of Mathematics, Kyushu University Fukuoka |
| Volume | 6 |
| ISSN (Print) | 1881-4042 |