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

Method for segmenting adrenal tumor of medical CT (computed tomography) image based on sparse representation

An adrenal tumor, sparse representation technology, applied in the field of image processing, can solve problems such as manual delineation, high initial contour requirements, and segmentation results entering local minima.

Active Publication Date: 2015-05-20
FUDAN UNIV
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the level set method has high requirements for the initial contour, and often needs to be drawn manually, and the poor initial contour will easily lead to the segmentation result entering a local minimum.

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
  • Method for segmenting adrenal tumor of medical CT (computed tomography) image based on sparse representation
  • Method for segmenting adrenal tumor of medical CT (computed tomography) image based on sparse representation
  • Method for segmenting adrenal tumor of medical CT (computed tomography) image based on sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] Carry out the actual CT image test on the segmentation method proposed by the present invention. The initial contour obtained by this method and the manually drawn ellipse contour were used as the initial contour of the level set segmentation method to segment 30 tumor images. Taking the tumor outline manually drawn by doctors as the gold standard, the segmentation results of the two methods were compared with the manually drawn tumor outline. In this method, the binary mapping threshold is set to 0.30.

[0079] The segmentation result comparison parameter adopts the area of ​​overlap (area of ​​overlap, AO ) and accuracy (accuracy, AC ).

[0080] Overlap area AO :

[0081]

[0082] Accuracy AC :

[0083]

[0084] in TP is the true positive rate, FP is the false positive rate:

[0085]

[0086]

[0087] GS , SE Respectively represent the point sets of the gold standard segmentation and level set segmentation results, Indicates the number...

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, and particularly relates to a method for segmenting an adrenal tumor of a medical CT (computed tomography) image based on sparse representation. The method comprises the following steps of utilizing a trained over-complete dictionary which is sensitive to a boundary to decompose the interest region of a two-dimensional CT image into image subblocks, and performing sparse representation; for the obvious difference of absolute values of first coefficients obtained by sparse decomposition of a homogeneous region and a non-homogeneous region of the image, selecting a proper threshold value to distinguish the coefficients, and obtaining the corresponding image boundary subblocks and a binary image; utilizing a region growth method to grow a rough profile of the tumor on the binary image, using the rough profile as the initial profile of a horizontal set segmenting method, and performing multiple iteration, so as to obtain the final boundary of the tumor. The method has the advantages that the automation degree of the image segmenting of the adrenal tumor in the image is greatly improved, the reliance degree of the horizontal set segmenting method on the initial profile is reduced, and the segmenting result is more accurate.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for segmenting adrenal gland tumors in medical CT images with sparse representation. Background technique [0002] The adrenal gland is located in the retroperitoneum, and its lower and outer sides are closely attached to the upper and inner sides of the kidneys on both sides. It can secrete adrenaline, corticosteroids and other important hormones that regulate the physiological functions of the human body, and is an important endocrine organ in the body. Once a tumor occurs in a certain part of the adrenal gland, the hormones secreted by the corresponding part will be out of balance, causing some cardiovascular diseases, which can be life-threatening in severe cases. [0003] Because the symptoms caused by adrenal gland tumors are similar to other adrenal gland diseases (such as adrenal hyperplasia), but the treatment options for the two are differ...

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 Applications(China)
IPC IPC(8): G06T7/00
CPCG06T2207/20081G06T2207/30084G06T2207/30096
Inventor 郭翌柴汉超汪源源
Owner FUDAN 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com