Human skeleton three-dimensional model acquisition method and system based on two-dimensional medical image

Abstract

The invention discloses a human skeleton three-dimensional model acquisition method and system based on a two-dimensional medical image, and the method comprises the steps: carrying out the discretization of a three-dimensional model of a skeleton, obtaining a point cloud file describing the surface shape of the skeleton, and enabling the point cloud file and information obtained in a corresponding X-ray plain film to form a training set; all the point cloud files in the training set are converted into the same coordinate system through a registration process, the corresponding relation among all the point cloud file points in the training set is established, and the training set is updated; deformation vectors between the remaining point cloud files and the reference shape corresponding points are calculated, the deformation vectors of all points in the point cloud form a point cloud deformation domain, and an average deformation domain between the point cloud and the reference shape point cloud is calculated; establishing a posterior probability model by using Bayesian inference; and inputting information which is not included in the X-ray plain film in the training set, then outputting a point cloud file of the reconstruction model, and generating a skeleton three-dimensional model. The time and economic cost for acquiring the skeleton three-dimensional model are reduced, and rapid three-dimensional reconstruction of the skeleton is realized.

Description

technical field [0001] The invention belongs to the technical field of orthopedic imaging modeling, and in particular relates to a method and system for acquiring a three-dimensional model of a human skeleton based on two-dimensional medical images. Background technique [0002] In orthopedic clinics, for bone and joint diseases such as osteoarthritis, fractures, bone defects and bone tumors, in order to achieve the purpose of precise treatment, the establishment of a three-dimensional geometric model of the bone or joint disease area is conducive to helping doctors observe diagnosis and surgical planning , device customization and biomechanical mechanism research. Traditionally, the geometric three-dimensional model of bone is mainly obtained through computerized tomography (CT), and then based on Mimics and other modeling software for extraction and segmentation modeling. However, the cost of CT scanning is high, the radiation dose is large, and the traditional Mimics ext...

AI Technical Summary

Problems solved by technology

This technology requires multiple iterations to obtain a small 3D reconstruction error, which may cause the result to fall into a local optimal solution, and in order to maintain a high-precision 3D reconstruction, it is necessary to generate hundreds or thousands of digitally reconstructed ray images, resulting in time-consuming Longer, and the reconstruction process is more complex

Images