Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Contour Smoothing Method Based on Freeman Chain Code in Medical Image Segmentation

A medical image and chain code technology, applied in the field of contour smoothing, can solve problems such as unfavorable image registration and recognition, inconsistent with visual habits, and image processing effects.

Active Publication Date: 2019-12-20
TIANJIN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the existing region of interest extraction process, the contours of tissues or organs in medical images often show abnormal jagged and granulated phenomena, that is, local bulges and concavities in the contours, such artifacts / errors / distortions of the contours Not only does it not conform to people's visual habits, but it usually does not conform to the medical anatomical structure, which will affect the next step of image processing, for example, it is not conducive to image registration and recognition

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
  • A Contour Smoothing Method Based on Freeman Chain Code in Medical Image Segmentation
  • A Contour Smoothing Method Based on Freeman Chain Code in Medical Image Segmentation
  • A Contour Smoothing Method Based on Freeman Chain Code in Medical Image Segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0020] Step 1: For a digitized image, remove the surrounding edge pixels, and each pixel in the middle part has eight "neighboring pixels". These eight "neighboring pixels" start from the right and are marked as {0, 1, 2 counterclockwise. ,3,4,5,6,7}, representing the eight directions around the pixel, such as figure 2 shown. A curve is discretized by the grid to form n chains, and the chain code of this curve can be expressed as {c(i)} n , each chain points to one of these eight directions, c(i)∈{0,1,…7}, i is the index value of the pixel, c(i) is from pixel (i) to pixel (i+1 ) direction chain code. Expressing the curve in this form is the Freeman chain code.

[0021] Such as image 3 As shown, an MRI tomographic image of a human upper limb is taken as an example for illustration. Figure 4 It is the region of interest obtained by using the manual watersh...

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 Freeman chain code-based contour smoothing method in medical image segmentation. The method comprises the steps of extracting a target tissue or organ as a region of interest by utilizing algorithms such as a manual watershed algorithm and the like, and then performing calculation to obtain a single-pixel outer contour curve of the region; performing Freeman chain code encoding; searching for "a to-be-restored chain code segment"; restoring "the to-be-restored chain code segment": firstly determining a relative displacement (dx,dy) of head and tail chain code elements, and then determining two main directions of a new chain code used for restoration in combination with a Freeman chain code trend in front of a rectangular window; performing simultaneous solving according to the two selected main directions and the relative displacement (dx,dy) to obtain the number of main directions of two Freeman chain codes; and finally performing sorting according to a solving result to serve as a new chain code segment used for restoration; and when necessary, performing further restoration.

Description

technical field [0001] The invention relates to a contour smoothing method in the segmentation process of bones, viscera and tissues in medical images, in particular to the contour smoothing operation using Freeman chain codes. Background technique [0002] In the related processing of medical images, it is usually necessary to extract and segment regions of interest, such as the extraction of liver and bone. Commonly used methods include threshold method, watershed algorithm, flood filling method, etc. After obtaining the region of interest, Freeman chain code can be used to store the contour information of the region. However, in the existing region of interest extraction process, the contours of tissues or organs in medical images often show abnormal jagged and granulated phenomena, that is, local bulges and concavities in the contours, such artifacts / errors / distortions of the contours Not only does it not conform to people's visual habits, but it also generally does not...

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): G06T5/00G06T7/00G06T7/13
CPCG06T5/002G06T7/0012G06T2207/10088G06T2207/30004
Inventor 曹玉珍郭怡湘余辉张力新苗春发邓勇时尧
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products