Medical ultrasonic image de-noising method based on normal inverse Gaussian model

A normal inverse Gaussian, ultrasound image technology, applied in the field of medical ultrasound image denoising, can solve the problems of bilateral filter gradient distortion, loss of high frequency coefficients, etc.

Inactive Publication Date: 2016-11-09
ZHEJIANG COLLEGE OF ZHEJIANG UNIV OF TECHOLOGY
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to provide a medical ultrasonic image denoising method based on a normal inverse Gaussian model. On the one hand, the present invention improves the Laplace model based on a generalized Gaussian distribution, and proposes a new normal inverse Gaussian model. This model solves the problem of missing too many high-frequency coefficients. Bas...

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
  • Medical ultrasonic image de-noising method based on normal inverse Gaussian model
  • Medical ultrasonic image de-noising method based on normal inverse Gaussian model
  • Medical ultrasonic image de-noising method based on normal inverse Gaussian model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0098] Such as figure 1 As shown, a kind of medical ultrasonic image denoising method based on normal inverse Gaussian model of the present embodiment, such as figure 1 shown, including the following steps:

[0099] 1) Utilize the noise imaging system to collect the envelope signal of the noise image, and establish a medical ultrasound image model through logarithmic transformation; obtain the two-dimensional discrete shearlet coefficient after the two-dimensional discrete shearlet transformation, and the two-dimensional discrete shearlet coefficient includes noise-free Image two-dimensional discrete shearlet coefficient and speckle noise image two-dimensional discrete shearlet coefficient;

[0100] 2) the medical ultrasound image model after the logarithmic transformation obtained in the step 1) utilizes a pyramid filter bank to carry out multi-scale and multi-directional decomposition, and obtains k+1 subband images equal in size to the medical ultrasound image model, so D...

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 method for denoising a medical ultrasonic image based on a normal inverse Gaussian model, comprising the following steps: 1) using a noise imaging system to collect the envelope signal of the noise image, and establishing a medical ultrasonic image model; Step 1) The medical ultrasound image model obtained after the logarithmic transformation utilizes a pyramid filter bank to perform multi-scale and multi-directional decomposition, 3) For the two-dimensional discrete shearlet of the high-frequency part in each sub-band image obtained in the step 2) The transformation coefficients are subjected to threshold method adaptive shrinkage processing; 4) use the trilateral filter to filter the shearlet coefficients in the low-frequency part of step 2); 5) perform shearlet inverse transformation on all coefficients after step 3) and step 4) processing After processing, the medical ultrasound image after denoising is obtained. The invention can well suppress the speckle noise, and at the same time can better help doctors to analyze the condition.

Description

technical field [0001] The invention relates to a method for denoising medical ultrasonic images based on a normal inverse Gaussian model. The invention belongs to the field of medical ultrasonic image denoising, especially a shearlet transform medical image denoising method based on a normal inverse Gaussian model suitable for medical ultrasonic images. Background technique [0002] With the development of science and technology, in the field of medical imaging, imaging technologies such as ultrasound imaging, CT, and MRI have been applied in medical clinical diagnosis. Due to the rapid development of ultrasound imaging technology due to its advantages of high resolution, simple operation, instantaneity, etc., it has the characteristics of non-invasive, no radiation damage, fast and convenient, and has become a widely used and highly safe medical diagnostic technology. Especially for the examination of human body organs and tumor tissue, the use of ultrasound imaging techn...

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): G06T5/00
CPCG06T5/002G06T2207/10132G06T2207/20024G06T2207/30056
Inventor 张聚程义平刘敏超柴金良
Owner ZHEJIANG COLLEGE OF ZHEJIANG UNIV OF TECHOLOGY
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