Unlock instant, AI-driven research and patent intelligence for your innovation.

Medical ultrasonic image filtering method based on sparse representation

A sparse representation, ultrasound image technology, applied in the field of medical ultrasound image filtering based on sparse representation, which can solve problems such as edge and detail blurring

Inactive Publication Date: 2014-09-03
FUDAN UNIV
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the selection of the threshold is also very critical, the wrong threshold will lead to blurred edges and details

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 filtering method based on sparse representation
  • Medical ultrasonic image filtering method based on sparse representation
  • Medical ultrasonic image filtering method based on sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The simulation image and the actual ultrasonic image test are carried out on the filtering method proposed by the present invention. The method in this paper, KSVD algorithm [5], anisotropic diffusion filter algorithm [3] and wavelet algorithm [4] were used for filtering respectively, and the results were compared. In the method of this paper, after several parameter optimizations and comparisons, b =11, t =80, the filtering effect is the best.

[0056] First, the filtering performance of the simulated images is compared. For a noise-free original image, use the ultrasound model [3] proposed by Yu et al. to simulate and add different degrees of noise to it. image 3 (a) is the original image, image 3 (b) is a noisy image.

[0057] Figure 4 Represents the filtering effects of various algorithms for a noisy image. (a) is the original image, (b) is the noise image, (c)-(e) is the image filtered through KSVD, SRAD and wavelet algorithm respectively, (f) is the filt...

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 belongs to the technical field of image processing, in particular to a medical ultrasound image filtering method based on sparse representation. The present invention uses an over-complete dictionary to decompose the two-dimensional ultrasonic image into the sparsest coefficient representation; adopts the idea of ​​global filtering based on sub-block similarity, and uses global redundant information to find the most similar image in the entire image for each image sub-block According to all the most similar sub-blocks obtained, all the pixels in the atomic block are filtered together; for the pixels with multiple estimates in each overlapping area, the mean value processing is performed on them, so as to realize the filtering of the entire image . The invention is very suitable for filtering medical ultrasonic images, can effectively reduce speckle noise, and better maintain texture information and edge characteristics in ultrasonic images.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a medical ultrasound image filtering method based on sparse representation. Background technique [0002] Ultrasound imaging has important applications in medical clinical diagnosis due to its advantages of non-invasive, real-time, strong repeatability, and low cost of diagnosis and treatment. However, there are a large number of spots in the ultrasound image, which cover up some details, seriously affect the resolution of subtle features and image quality, especially blur the edges and details, and increase the difficulty of medical diagnosis. [0003] Commonly used speckle noise filtering methods include local statistical method [1], median filtering method [2], anisotropic filtering method [3] and wavelet filtering method [4], etc. These methods can reduce the influence of noise to varying degrees, but there are still some problems. For filtering algorithms based on...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00
Inventor 郭翌汪源源
Owner FUDAN UNIV