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

A processing method for classifying brain abnormalities

A processing method and brain technology, applied in computer parts, instruments, characters, and pattern recognition, etc., can solve problems such as large computational complexity, reduce medical pressure, and improve accuracy and objectivity.

Inactive Publication Date: 2019-01-08
BEIJING ANDE YIZHI TECH CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of algorithm usually needs to solve a generalized eigenvector problem. When the image is relatively large, this type of algorithm will encounter the problem of high computational complexity.

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 processing method for classifying brain abnormalities
  • A processing method for classifying brain abnormalities
  • A processing method for classifying brain abnormalities

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] Below in conjunction with accompanying drawing, the present invention is explained in detail.

[0018] Such as figure 1 As shown, the method of the present invention is a processing method for brain abnormality classification, including the following steps: (1) Marking the possible locations of known abnormalities in the brain to generate a priori distribution of possible distribution locations of brain abnormalities, The prior distribution is a set of four-dimensional arrays; (2) Obtain the segmented slice image of brain abnormality, process the slice image and extract the image, obtain a three-dimensional array, mark the position of brain abnormality, and record the number of brain abnormality as X; (3) compare the abnormal position marked in step (2) with the prior distribution in step (1), and obtain X vectors of 1*N, where N is the probability of a certain brain abnormality at this position; ( 4) Average X 1*N vectors to obtain a 1*N' vector, which is the probabil...

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 provides a processing method for classifying brain abnormalities, which comprises the following steps: (1) in a plurality of images containing brain abnormalities, marking the positionsof the brain abnormalities by a three-dimensional array, and recording the quantity of the brain abnormalities; (2) determining the occurrence probability of one or more kinds of brain abnormalities corresponding to the brain abnormalities in each image according to the position and according to a priori distribution of a predetermined brain position and the occurrence probability of a specific kind of brain abnormalities; and (3) calculating an average of the determined plurality of occurrence probabilities as one or more kinds of occurrence probabilities corresponding to the brain abnormalities in the plurality of images. The method of the present application is capable of inferring the type of brain abnormality solely from the location.

Description

technical field [0001] The invention relates to the technical field of magnetic resonance image segmentation of brain abnormalities, in particular to a processing method for classification of brain abnormalities. Background technique [0002] Accurate segmentation of multimodal MR images is critical for diagnosis, surgical planning, postoperative analysis, and chemotherapy / radiation therapy planning. [0003] At present, many researchers at home and abroad have proposed a variety of segmentation methods for GBM multimodal magnetic resonance images, which are mainly divided into pixel or voxel-based segmentation algorithms and graphics-based segmentation algorithms. The basic idea of ​​the pixel-based or voxel-based segmentation algorithm is to classify the pixel into the corresponding category according to the brightness information and texture information of each pixel on the multi-modal image. [0004] Classification algorithms include unsupervised clustering and supervis...

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): G06K9/62
CPCG06V2201/03G06F18/2415
Inventor 吴振洲
Owner BEIJING ANDE YIZHI TECH CO LTD