Vertebra segmentation and mass center detection method based on clustering

A technology of clustering centers and vertebrae, which is applied in the field of image segmentation and centroid detection based on clustering, can solve the problems of complex organizational structure and difficulty in locating the centroid of a single vertebra, so as to improve the speed, accuracy and accuracy , good feasibility effect

Inactive Publication Date: 2018-09-14
HARBIN UNIV OF SCI & TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The adjacent tissue structure of the spine is complex and the background texture is rich, which also makes

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
  • Vertebra segmentation and mass center detection method based on clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] 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.

[0032] Step S1: Firstly, the spine CT image to be detected is preprocessed, and the Gaussian smoothing filter is used to remove noise, and the gray scale linear transformation is used to enhance the contrast of the region to be detected.

[0033] Step S2: Use the improved FCM image clustering to segment and extract the vertebral region in the spine CT image. First, calculate the histogram of the image information. The number of peak points in the histogram is set as the number of cluster categories, and the number of cluster centers is The maximum number of clustering categories is iterated until it is less than the set threshold or the maximum number of iterations is reached to stop iterating. The result of classification is output, and the interference points are remove...

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 vertebra segmentation and mass center detection method based on clustering. The vertebra image segmentation and mass center detection has a special application value in the diagnosis of the spinal diseases. A spine consists of a vertebra and an intervertebral disc, wherein the vertebra is used for protecting the tissues in a human body, such as visceral organs and nerve and blood vessels, and the intervertebral disc is used for maintaining the flexibility of the human body. Therefore, the tissue structure around the spline is relatively complex, and the diagnosis is more difficult. Based on the above problems, the invention proposes the vertebra segmentation and mass center detection method based on clustering, so as to improve the accuracy of segmentation and mass center location. The method comprises the following steps: A, carrying out the preprocessing of CT data of the spine, and highlighting a region of interest; B, segmenting and extracting a vertebra region in a spine CT image through using improved FCM image clustering; C, performing the extraction and clustering of pixel points of an original vertebra image, and then finding the final mass centerthrough density estimation; D, synthesizing the result of segmentation and the result of mass center localization.

Description

technical field [0001] The invention mainly relates to the field of vertebral image segmentation processing, in particular to methods for image segmentation and centroid detection based on clustering. Background technique [0002] Image processing, also known as digital image processing, refers to the operations and processing steps performed by digital computers on images in order to achieve a certain purpose. Since the invention of X-ray imaging by German physicist Professor Roentgen at the end of the 19th century, the technology of medical imaging has continued to develop, and image processing technology has also been widely used in medical imaging, which has also favorably promoted the application of medical imaging in clinical medicine. In the process of medical imaging, improving the quality of images has always been the goal that people strive for. It not only provides convenience for doctors' observation and judgment, but also completes the segmentation and feature c...

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): G06T7/00G06T7/11G06T7/66G06K9/62
CPCG06T7/0012G06T7/11G06T7/66G06T2207/30012G06T2207/10081G06F18/23
Inventor 刘侠孙艳楠余洪波
Owner HARBIN UNIV OF SCI & TECH
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