Region segmentation method and device for three-dimensional medical model data and storage medium

Abstract

The invention provides a region segmentation method and device for three-dimensional medical model data and a storage medium, and the method comprises the following steps: obtaining a medical image ofa patient, carrying out the three-dimensional reconstruction of the medical image through a contour surface algorithm, and obtaining three-dimensional medical grid model data; converting the three-dimensional medical grid model data into a corresponding dual graph form, and setting the edge weight of the graph according to the distance between the triangular patches on the three-dimensional medical grid model data; performing approximate farthest point sampling on the dual graph to obtain a plurality of seed points; operating a clustering algorithm based on pruning on the dual graph, and determining an area controlled by each seed point; and merging the adjacent classes one by one according to a minimum merging cost principle, and determining a segmentation result according to the numberof the remaining classes selected by the user. The method is faster, more efficient, accurate in segmentation effect, easy and convenient to operate, simple in used equipment, low in cost and high inpractical value.

Description

technical field [0001] The invention relates to the field of digital medical technology, in particular to a method for segmenting three-dimensional medical model data, a device for segmenting three-dimensional medical model data, and a non-temporary computer-readable storage medium. Background technique [0002] In the process of surgical operation design, doctors usually need to carefully observe certain tissues and organs of the patient in order to design an accurate surgical plan. For images obtained by high-precision electronic computer tomography or nuclear magnetic resonance technology, the three-dimensional structure of the tissue and organ of interest can be reconstructed according to the isosurface, or the volume rendering algorithm can be used to present the user with the area they want to observe. However, none of these methods can enable doctors to observe the substructure of a certain tissue and organ in an all-round way, so that it is impossible to design an ac...

AI Technical Summary

Problems solved by technology

However, these methods are sensitive to noise and have low efficiency, so the above-mentioned techniques are difficult to be directly applied clinically.

Images