Prostate multi-modal image non-rigid registration method based on mixed model

A multi-modal image, non-rigid registration technology, applied in the field of non-rigid registration of prostate images, can solve the problems of uncertain direction of image deformation, inability to obtain effects, and insufficient Effects of Improving Registration Accuracy

Active Publication Date: 2016-12-07
XIDIAN UNIV
View PDF5 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Demons algorithm based on the optical flow field model uses the gray gradient information of the reference image to determine the movement of each pixel of the floating image, but this method of only relying on the grad

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
  • Prostate multi-modal image non-rigid registration method based on mixed model
  • Prostate multi-modal image non-rigid registration method based on mixed model
  • Prostate multi-modal image non-rigid registration method based on mixed model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] refer to figure 1 , the implementation steps of the present invention are as follows:

[0027] Step 1. Input prostate CT image and prostate MRI image for segmentation.

[0028] Prostate CT image and prostate MRI image are obtained from a certain hospital. The resolution of prostate CT image is 256×256, and the resolution of prostate MRI image is 256×256. They are segmented by Level Set method respectively. The segmented target image is as follows: figure 2 shown, where figure 2 (a) is the target image of prostate MRI, figure 2 (b) is the target image of prostate CT.

[0029] Step 2. Preprocess the target image.

[0030] Perform Gaussian low-pass filtering on the target image of prostate CT to make the image smoother and clearer, and use the filtered image as a reference image r,

[0031] Gaussian low-pass filtering is performed on the target image of the prostate MRI to make the image smoother and clearer, and the filtered image is used as the floating image f. ...

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 prostate multi-modal image non-rigid registration method based on a mixed model, and mainly solves the problem in the prior art that registration of prostate CT and MRI images is not good. The method is realized by steps of 1) inputting prostate CT and MRI images and segmenting the prostate CT and MRI images to obtain targets respectively; 2) taking filtered prostate CT and MRI images as a reference image and a floating image respectively, and subjecting the two images to pyramid multi resolving; 3) subjecting the floating image to offset and layer-by-layer iteration to obtain a crude registration image; 4) dividing the reference image and the crude registration image in a control point mesh manner, moving control points of the crude registration image, and obtaining a post-transformation image according to displacement of the control points; 5) continuously carrying out iteration until the similarity between the post-transformation image and the reference image is maximal, so as to obtain final displacement; and 6) obtaining a registration image according to the final displacement. The invention improves the registration precision between complex deformation and a multi-mode image, and can be used for medical CT and MRI image processing.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a non-rigid registration method for prostate images, which can be used for processing medical CT images and nuclear magnetic resonance MRI images. Background technique [0002] The prostate is the largest accessory gonad in men and one of the exocrine glands in the human body, located between the bladder and the original genital diaphragm. Genetic mutations in cells can cause uncontrolled proliferation and cause cancer. Prostate cancer is a malignant tumor from the prostate gland. In addition to expanding in size and invading adjacent organs, malignant cells may also metastasize to other parts of the body, especially bones and lymph nodes. Prostate cancer can cause pain, difficulty urinating, erectile dysfunction and other symptoms, seriously endangering people's health. In Western countries, prostate cancer is the second most common cancer in men, killing ...

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): G06T7/00
CPCG06T7/0012G06T2207/10081G06T2207/10088G06T2207/20024G06T2207/30081
Inventor 缑水平徐腾焦李成马文萍刘芳盛柯马晶晶
Owner XIDIAN 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