Human body three-dimensional skeleton model marking method based on data driving and template guiding

A skeletal model, data-driven technology, applied in the field of digital medicine, can solve the problems of time-consuming and labor-intensive, low degree of automation, inability to meet the actual needs of 3D, and achieve the effect of effective integration and processing with high degree of automation.

Pending Publication Date: 2021-01-08
HOHAI UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Under the existing conditions, the processing of bone CT data is generally done manually by doctors based on existing medical knowledge and clinical experience, with the help of 3D

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Human body three-dimensional skeleton model marking method based on data driving and template guiding
  • Human body three-dimensional skeleton model marking method based on data driving and template guiding
  • Human body three-dimensional skeleton model marking method based on data driving and template guiding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] A data-driven and template-guided human 3D bone model labeling method, combining figure 1 The flowchart shown includes the following steps:

[0059] Step 1: Transform CT medical scan data into a 3D skeletal mesh model in Mimics software, and manually segment and mark the obtained 3D skeletal mesh model (such as figure 2 shown);

[0060] Step 2: Utilize the mapping algorithm (such as image 3 As shown), the normal vector of each point in the marked three-dimensional skeletal mesh model obtained in step 2 and the three-dimensional coordinates of the label information combination point are output to a text file;

[0061] The specific steps are:

[0062] S2.1 Use file IO operations to list all data file names under pieces

[0063] S2.2 Store the data in the AnnoyIndex data structure in sequence

[0064] S2.3 Use the label information in the file name to extract the label

[0065] S2.4 read the data under the all folder into mesh

[0066] S2.5 For each point in the m...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a human body three-dimensional skeleton model marking method based on data driving, and the method comprises the steps: firstly converting skeleton CT scanning data into a skeleton grid model, carrying out the manual segmentation marking, and outputting a normal vector of each point and a three-dimensional coordinate of a label information combination point to a text file through employing a mapping algorithm; and training the mapped data through a multi-level PointNet++ network model to obtain a coarse-to-fine skeleton region segmentation network model, inputting the corresponding data into the hierarchically segmented PointNet++ network model to obtain a rough skeleton model segmentation result, and performing graph segmentation on the rough skeleton model segmentation result to optimize a boundary segmentation result; further extracting an anatomical mark of the skeleton template through a PointNet++ network, fitting the skeleton template to an outer surfacearea by matching the anatomical mark, mapping the anatomical mark on the template to a target skeleton, and finally obtaining a skeleton classification result and the corresponding anatomical mark.

Description

technical field [0001] The invention belongs to the field of digital medical treatment, and in particular relates to a method for marking a three-dimensional skeleton model of a human body based on data drive and template guidance. Background technique [0002] With the development of digital medical care and big data, digital orthopedic technology and clinical research models have been deeply integrated, gradually developing from empirical, fuzzy, and manual to standardization, precision, and automation, and providing the next generation of preoperative planning technology As a powerful tool, digital 3D preoperative planning can help doctors effectively overcome visual limitations, improve the accuracy of data measurement, and make diagnosis more accurate and efficient. Among them, the data-driven and template-guided human 3D bone model marking method can effectively help doctors solve common orthopedic case types, accurately plan the scope of surgery, and provide reference...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/11G06T7/55G06T17/20G06T7/00G06K9/62G06N3/04G06N3/08
CPCG06T7/11G06T7/55G06T7/0012G06T17/20G06N3/08G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30008G06T2200/04G06N3/045G06F18/241
Inventor 陈子凌郭松源
Owner HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products