Template guiding and data driving three-dimensional broken bone segmentation and splicing method

A data-driven, bone-crushing technology, applied in the field of digital medicine, can solve problems such as difficult calculation of corresponding relationships and insignificant curvature of fracture boundaries, so as to improve the efficiency and degree of automation of preoperative planning, reduce the time of preoperative planning, and improve the degree of automation and the effect of efficiency

Pending Publication Date: 2021-01-08
HOHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (2) Sometimes the curvature of the fracture boundary is not significant
Among them, the key problem is to construct the corresponding relationship between the outer surface of the broken bone and the template, especially when the area of ​​the broken bone is small or the characteristics of the outer surface of the broken bone are not obvious, the calculation of the corresponding relationship is very difficult

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
  • Template guiding and data driving three-dimensional broken bone segmentation and splicing method
  • Template guiding and data driving three-dimensional broken bone segmentation and splicing method
  • Template guiding and data driving three-dimensional broken bone segmentation and splicing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0066] A template-guided and data-driven method for 3D bone fragment segmentation and assembly, combining figure 1 The flowchart shown includes the following steps:

[0067] Step 1: Combine figure 2 As shown in the training data processing flow chart, Mimics and 3-matic software are used to realize the three-dimensional reconstruction and preprocessing of the broken bone and the contralateral bone template, and the three-dimensional mesh model of the broken bone and the template is constructed (such as image 3 shown in a);

[0068] Step 2: Convert the 3D bone fragment mesh model obtained in step 1 into a point cloud model, input it into the PointNet++ segmentation neural network, and output the probability of the inner and outer surface of the bone fragment vertex;

[0069] Step 3: From step 2, extract points whose outer surface probability range is [0.9,1.0] as the point cloud model M of the outer surface of the broken bone; (such as image 3 as shown in c);

[0070] St...

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 template-guided and data-driven three-dimensional broken bone segmentation and splicing method, and the method comprises the following steps: taking a broken bone three-dimensional model generated by a CT image as an information input source, carrying out the preliminary extraction of broken bone outer surface information through neural network training, and calculating the features of the broken bone outer surface; matching the outer surface of each broken bone with an opposite side healthy bone template based on the features; determining a fracture boundary according to the distance between the broken bone and the template and the surface curvature information of the broken bone, and realizing broken bone repairing and splicing; carrying out the loop iteration in the process, and realizing the broken bone feature extraction, fragment boundary determination and fragment reset gradual refinement. According to the invention, the basic requirements of broken bone extraction and broken bone splicing are followed, and the broken bone splicing requirement of medical requirements is met; through a small amount of man-machine interaction, efficient fracture repair is completed, the requirement for preoperative planning of medical staff is met, and the working efficiency is improved.

Description

technical field [0001] The invention belongs to the field of digital medical treatment, and in particular relates to a template-guided and data-driven three-dimensional broken bone segmentation and splicing method. Background technique [0002] With the rapid development of digital medicine, the application of digital technology in surgery is becoming more and more important. As an interdisciplinary field of computer science and biomedicine, extracting broken bones from a 3D bone model and realizing splicing repair is a special application in digital medicine and plays an important role in computer-aided 3D preoperative planning. Digital 3D preoperative planning can help doctors effectively overcome visual limitations, improve the accuracy of data measurement, and make diagnosis more accurate and efficient. There is an urgent need for preoperative planning to extract broken bones and achieve splicing and repair. It can help doctors correctly extract medical semantic paramet...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G16H30/20G16H30/40G06T7/10G06T7/55G06T19/00G06N3/04G06N3/08
CPCG16H30/20G16H30/40G06T7/10G06T7/55G06T19/00G06N3/08G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30008G06T2210/41G06T2200/04G06N3/045
Inventor 郭松源陈子凌
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap