Method and system for medical image segmentation based on full-representation semi-supervised fast spectral clustering
A medical image and semi-supervised technology, applied in the field of intelligent medical image segmentation, can solve the problems of insufficient fast processing ability and incompatibility with multiple reference situations for medical image segmentation at the same time.
Active Publication Date: 2016-03-16
JIANGNAN UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] The purpose of the present invention is to provide a medical image segmentation method based on full-expression semi-supervised fast spectral clustering, which solves the problems in the prior art that cannot be compatible with multiple reference situations of medical image segmentation at the same time, and the fast processing capacity is not enough
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0055] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0056] For convenience of description, the terms involved in the method of the present invention are defined as follows:
[0057] Definition 1: Dataset X = {x 1 ,x 2 ,...,x N} is a collection of feature data formed by extracting features from all pixels in a medical image and arranging them row by row, where N represents the capacity of the data set;
[0058] Definition 2: The reference set CS is all the data points contained in all the areas circled by the medical personnel in a certain medical image, CS={...,x i ,...,x k ,...,x q ,...}, where i, k, q are the subscripts of the data points in the original collected data set X;
[0059] Definition 3: ,definition for all the x in CS i A collection of data points belonging to the same area;
[0060] Definition 4: ,definition for all the x in CS i A collection of data points belo...
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
Login to View More Abstract
The invention discloses a medical image segmentation method and a medical image segmentation system for fully-represented semi-supervised fast spectral clustering. The method comprises the following steps: obtaining a to-be-treated medical image; circling in the medical image by a touch screen; extracting grey level of pixel, a spatial position and Gabor textural characteristics of the whole medical image, and carrying out characteristic normalization and characteristic dimension reduction treatment; carrying out All-In-One form representation onto reference information of a circled area; generating a graph-based relaxed clustering model based on a full-presenting semi-supervising mechanism; rearranging a quadratic term of the clustering model into a novel positive definite matrix; rewriting as a constraint type minimal enclosing ball form; estimating a final solution based on a rapid approximation strategy of the core set minimal enclosing ball; determining actual category number of clustering segmentation by a graph-based clustering indication vector; and dividing clustering indication components into different subsets based on a K means algorithm according to the category number. The system comprises an FPGA (Field Programmable Gate Array) module and an external device. The method and the system disclosed by the invention are simple to operate, good in real-time performance and high in accuracy.
Description
technical field [0001] The invention belongs to the technical field of intelligent medical image segmentation, and relates to a medical image segmentation method based on full-expression semi-supervised fast spectrum clustering, and also relates to a medical image segmentation system for realizing the method. Background technique [0002] The rapid development of medical imaging technologies such as CT, MRI, and PET continues to promote the progress of modern medicine. Its role has been further developed from the non-invasive inspection and visualization of the anatomical structure of human tissues and organs to the use of disease diagnosis, treatment plan design and treatment effect. basic tool for evaluation. Medical clinical practice and research often need to measure the shape, boundary, cross-sectional area and volume of certain tissues and organs in the human body, so as to obtain important information about the pathology or function of the tissue. Here the medical im...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
Inventor 钱鹏江王士同邓赵红王骏蒋亦樟
Owner JIANGNAN UNIV