Brain magnetic resonance image segmentation method based on improved fuzzy C-means

A magnetic resonance image, blurring technology, applied in the field of medical image processing, can solve the problems of complex objective function and fitness function, no consideration of pixel spatial information, and slow optimization speed

Pending Publication Date: 2020-10-23
ZHONGYUAN ENGINEERING COLLEGE
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The document "An Image Segmentation Algorithm Based on Improved PSO and FCM" proposes an image segmentation algorithm combining PSO and FCM. Compared with the present invention, this method only uses the gray level information of the data, and the target selected during optimization The function and the fitness function are more complex and require a large amount of calculation
[0007] Chinese patent (application number: 201610038254.1) discloses a brain MRI image segmentation method. Compared with the present invention, although the method also uses the particle swarm optimization algorithm to optimize the set of cluster centers, the source image of its optimization process The data only uses grayscale information, without considering the spatial information of pixels, and in order to avoid premature convergence, the optimization algorithm adopts a chaotic search method, which increases the complexity of the algorithm, thereby reducing the speed of optimization (image segmentation)

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
  • Brain magnetic resonance image segmentation method based on improved fuzzy C-means
  • Brain magnetic resonance image segmentation method based on improved fuzzy C-means
  • Brain magnetic resonance image segmentation method based on improved fuzzy C-means

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0092] The test parameters of embodiment 1 and 2 (the value of these test parameters is the routine value in this area, can also obtain in conjunction with the research of relevant algorithm and a large amount of simulation experiments) settings are: population size (p=100), constant ( σ=40), ambiguity (m=2), maximum number of iterations (t max =500), error threshold (β=0.00001) and learning factor (c1=c2=2), in addition, for embodiment 1, division class number c=3, for embodiment 2, division class number c=4 .

[0093] 2. Simulation content:

[0094] Embodiment 1: adopt general FCM, GAFCM (genetic algorithm combined with fuzzy C mean value), FGFCM (fast generalized fuzzy C mean value), FRFCM (fast robustness fuzzy C mean value) and segmentation method of the present invention to image not containing cerebrospinal fluid respectively Carry out segmentation processing, the result is as follows figure 2 , where 2(a) is the source image containing noise, figure 2 (b1), 2(b2)...

Embodiment 2

[0095] Embodiment 2: respectively adopt general FCM, GAFCM, FGFCM, FRFCM and the method of the present invention to carry out segmentation processing to the image containing cerebrospinal fluid, the result is as follows image 3 , where 3(a) is the source image containing noise, image 3 (b1), 3(b2) and 3(b3) are the gray matter, white matter and cerebrospinal fluid results obtained by the general FCM segmentation method, respectively, image 3 (c1), 3(c2) and 3(c3) are the gray matter, white matter and cerebrospinal fluid images obtained by GAFCM segmentation method respectively, image 3 (d1), 2(d2) and 3(d3) are the result images of gray matter, white matter and cerebrospinal fluid obtained by FGFCM segmentation method respectively, image 3 (e1), 3(e2) and 3(e3) are the result images of gray matter, white matter and cerebrospinal fluid obtained by FRFCM segmentation method respectively, image 3 (f1), 3(f2) and 3(f3) are gray matter, white matter and cerebrospinal fluid ...

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 provides a brain magnetic resonance image segmentation method based on an improved fuzzy C mean value. Segmentation method, a novel gray scale reconstruction method is provided; spatialinformation and gray scale information between two pixel points can be fully utilized; an adaptive particle swarm optimization algorithm is combined with the fuzzy C-means model; according to the combination strategy, an optimization mode of a particle swarm algorithm is used for replacing a gradient descent updating mode of a clustering center in a fuzzy C-means algorithm, and in the iterative updating process of the particle speed and position, a self-adaptive weight factor is used, so that the image segmentation speed is increased firstly and then decreased, and the segmentation layout is integrated firstly and then locally. The medical image segmentation method is simple, has extremely high robustness for noise, and can effectively improve the segmentation precision of the medical image.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a brain magnetic resonance image segmentation method based on improved fuzzy C-means. Background technique [0002] With the rapid development of computer and visualization technology, medical imaging technology has shown a new look, and the information processing of medical images has become more and more popular, which has made a qualitative leap in the development of modern medicine. Currently, MRI, CT and Medical imaging represented by B-ultrasound has become an indispensable medical tool in clinical diagnosis. Medical image segmentation is an important part of medical image analysis, and it is the basis and key to realize the registration, fusion, recognition, quantitative analysis and image-guided surgery of medical equipment images. In the field of medical image segmentation, the most representative The most important and clinically valuable is the segmentation of ...

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): G06T7/11G06T7/90G06K9/62G06N3/00
CPCG06T7/11G06T7/90G06N3/006G06T2207/10088G06T2207/30016G06F18/23Y02T10/40
Inventor 李召温鹏伟周同驰卞芳方李征付凯柴旭朝瞿博阳郭倩倩朱小培
Owner ZHONGYUAN ENGINEERING COLLEGE
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