Vertebra positioning method based on convolutional neural network
A technology of convolutional neural network and positioning method, which is applied in the direction of neural learning method, biological neural network model, neural architecture, etc., can solve the problems of increasing the difficulty of locating the spine, complex organizational structure, etc., to reduce the detection area and improve the accuracy Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0026] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings.
[0027] Step S1: first preprocess the spine CT image to be detected, remove dryness, and enhance the contrast of the region to be detected.
[0028] Step S2: Train the Faster R-CNN model, which is divided into two steps of training, the training of the RPN network and the training of the Fast R-CNN network. The RPN network obtains the candidate area of the target area, and the Fast R-CNN network is used for target detection. Input the preprocessed spine CT image and the candidate area image of the target area obtained through the RPN network into the Fast R-CNN detector for secondary training of the model, and finally obtain the vertebral positioning model.
[0029] Step S3: Use the kernel density estimation method to find the centroid of the entire region from the fram...
PUM
Abstract
Description
Claims
Application Information
- 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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com