Segmentation of a calcified blood vessel

A method for segmentation of a calcified blood vessel in image data, comprising:

• providing a vesseltree representation of the blood vessel;
• providing a number of preliminary boundary representations of a number of cross-sections of the blood vessel;
• providing a number of intensity profiles in the image data in the number of cross-sections;
• determining a calcification in at least one of the cross-sections based on the corresponding intensity profile;
• correcting each preliminary boundary representation into a corrected boundary representation which excludes the calcification from an inner part of the blood vessel;
• providing an image representation of the calcified blood vessel;
• providing a start surface model, including a mesh with a plurality of vertices connected by edges;
• defining, for each vertex, a ray normal to the surface model at the position of the vertex;
• assigning more than two labels to each vertex, each label representing a candidate position of the vertex on the ray;
• providing, based in the corrected boundary representation, a representation of likelihoods for each candidate position the likelihood referring to whether the candidate position corresponds to a surface point of the blood vessel in the image representation;
• defining a first order Markov Random Field with discrete multivariate random variables, the random variables comprising the labels of the candidate positions and the representation of likelihoods;
• and
• finding an optimal segmentation of the calcified blood vessel by using a maximum a posteriori estimation in this Markov Random Field.

A segmentation system for segmentation of a calcified blood vessel in image data, comprising:

• an input interface for the image data;
• a first provision unit configured to provide a vesseltree representation of the blood vessel,
• a second provision unit configured to provide a number of preliminary boundary representations of a number of cross-sections of the blood vessel;
• a third provision unit configured to provide a number of intensity profiles in the image data in the number of cross-sections;
• a determination unit configured to,
• obtain the threshold intensity level based on ranges of an intensity distribution of the intensity profile corresponding to at least one cross-section of the number of cross-sections, and
• determine a calcification in the at least one cross-section based on the threshold intensity level;
• and
• a correction unit configured to correct each preliminary boundary representation into a corrected boundary representation which excludes the calcification from an inner part of the blood vessel.