Method for segmenting anatomical structures from 3d image data by using topological information

Abstract

A method is disclosed for segmenting anatomical structures, in particular the coronary vessel tree, from 3D image data. In the method, a starting point is initially set in the 3D image data, and at least one known anatomically significant point and / or at least one known anatomically significant surface are / is identified in the 3D image data. Subsequently, proceeding from the starting point the structure is subsequently segmented pixel by pixel with the aid of a multiplicity of segmentation steps in such a way that an instantaneous distance is determined automatically relative to the anatomically significant point and / or to the anatomically significant surface in each segmentation step. Further, segmentation parameters and / or a selection of adjacent pixels for continuing the segmentation are / is established as a function of the distance, taking account of a model topology. The method enables an accurate and reliable segmentation of the anatomical structure.

Description

technical field [0001] The invention relates to a method for segmenting anatomical structures, in particular coronary vascular trees, from three-dimensional image data, for example generated in CT angiography (CTA). [0002] The method according to the invention is firstly used in the field of computed tomography when recording vascular structures. Background technique [0003] Compared with other imaging techniques such as Magnetic Resonance Tomography (MR), PET (Positron Emission Tomography), SPECT (Single Photon Emission Computed Tomography) or 3D ultrasound techniques, the great advantage of CT angiography is e.g. The entire vascular tree of the heart can be documented with only one CT scan in the absence of drugs. The three-dimensional image data obtained here can be visualized using different techniques. [0004] For quantitative analysis, especially for measuring stenosis or plaque deposition, it is necessary to segment the corresponding regions of the vascular stru...

AI Technical Summary

Problems solved by technology

[0005] Known "region growing" techniques work satisfactorily in many cases, but do not reach all blood vessels visible to the viewer in the display of the 3D image photograph

In proper 3D visualization techniques, the human eye is still able to identify the smallest blood vessels as part of the structure, whereas segmentation algorithms can only detect specific uniform, relevant parts of the examined volume

In addition, if the segmented structure has similar HU values ​​and is located very closely on the vessel structure, the segmented structure may also grow into adjacent image regions

Images