Three-dimensional broken bone segmentation method and device based on deep learning
A technology of deep learning and bone crushing, applied in the field of digital medicine, can solve the problems of low degree of automation, time-consuming and labor-intensive, unable to meet the actual needs of 3D, and achieve the effect of saving manpower, reducing difficulty, and reducing preoperative planning time
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0048] combine figure 1 The present embodiment shown provides an overall flow chart of a three-dimensional bone fragment segmentation method based on deep learning, including:
[0049] Step 1: Build a PointNet++ deep neural network, which includes:
[0050] S1.1 The feature extraction part consists of a sampling layer, a combination layer and a feature extraction layer. Each layer extracts point sets of multiple neighborhood ranges. PointNet is used as the feature extraction structure to extract local correlation features. As the layers increase, the perception The field increases, the number of feature points decreases, and each feature point contains more and more information.
[0051] The principle of PointNet++ is as follows: the point set is divided into overlapping local areas by the distance measure of the underlying space, and the local features of the captured fine geometric structure are extracted from the small area; these local features are further grouped into la...
Embodiment 2
[0088] On the basis of the above embodiments, a 3D bone fragment segmentation method based on deep learning includes: extracting vertex coordinates and vertex normal vectors based on the acquired 3D bone fragment mesh model, and generating a bone fragment point cloud model; The cloud model is input to the pre-trained PointNet++ deep neural network to predict the vertex bone fragment label probability of the bone fragment point cloud model, which includes the label probability of cortical bone and the label probability of cancellous bone; the obtained The label probability of the vertex cortical bone and the label probability of the cancellous bone are mapped to the corresponding three-dimensional bone fragment mesh model, and the graph cut method is used to further optimize the bone fragment segmentation results.
[0089] A specific embodiment includes constructing a CT medical scan image to be subjected to three-dimensional bone fragment segmentation into a three-dimensional b...
Embodiment 3
[0099] Embodiment 3, a three-dimensional bone fragment segmentation device based on deep learning, including a bone fragment point cloud model generation module, a label probability output module, and a bone fragment segmentation module; wherein
[0100] The point cloud model generation module is used for extracting vertex coordinates and vertex normal vectors based on the acquired three-dimensional bone fragment mesh model to generate a bone fragment point cloud model;
[0101] The PointNet++ deep neural network module is used to input the generated bone fragment point cloud model to the pre-trained PointNet++ deep neural network to predict the probability of the vertex bone fragment label of the bone fragment point cloud model, and the bone fragment label probability includes cortical bone The label probability of and the label probability of cancellous bone;
[0102] The bone fragment segmentation module is configured to map the obtained label probability of the vertex cort...
PUM
Login to view more Abstract
Description
Claims
Application Information
Login to view more - R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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