A method and system for extracting body surface from CT images

Abstract

The invention discloses a CT image surface extraction method and system. A coarse-fine combined surface segmentation method is adopted; in coarse segmentation, isolated connection-based region growth is adopted to discriminate a surface interior and a surface exterior, so as to approximately obtain a surface structure; and in a fine segmentation process, repair and detail preserving smoothing are carried out on an axial view contour of a coarsely segmented three-dimensional surface, so as to realize the rapid, accurate and robust segmentation and extraction of the three-dimensional surface.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method and system for extracting body surface from CT images. Background technique [0002] Body surface segmentation belongs to the category of image segmentation. Commonly used image segmentation methods mainly include the following categories: region-based methods, edge-based methods, classifier-based, clustering, and statistical methods. According to the different characteristics of the objects to be segmented, the segmentation methods adopted or designed are also varied. For the segmentation of the body surface, under ideal conditions, the edge of the body surface area can be obtained by using methods such as boundary tracking or reasonable threshold segmentation. However, in clinical medical imaging, due to the heterogeneity of the internal and external structures of the human body, the distortion of the CT imaging process or the influence of noise, and ...

AI Technical Summary

Problems solved by technology

[0004] The main shortcomings of the threshold segmentation or edge gray segmentation methods above are: (1) The complexity and shape of the human body surface structure, the signal attenuation, noise, distortion and other factors in the CT imaging process can make the body The difference in surface imaging is large, which makes it very difficult to determine the precise threshold and obtain a satisfactory body surface segmentation effect

(2) If the skin segmentation result has holes or includes adhesion tissue structures other than the skin, how to automatically finely repair the body surface and remove impurities outside the body surface is an important factor affecting the body surface segmentation effect, but the existing Literature and invention patents do not consider or state

Images