Brain nuclear magnetic resonance image-based multi-dimensional feature classification algorithm

Abstract

The invention discloses a brain MR image-based multi-dimensional feature classification algorithm. The algorithm comprises the steps of performing regional division on brain MR images and extracting a plurality of ROI characteristics; selecting a mark characteristic, establishing a correlation among the ROI characteristics about the mark characteristic, and forming related characteristics; extracting the ROI characteristics and the related characteristics from the brain MR images to form an ROI characteristic set and a related characteristic set; selecting an optimal ROI characteristic subset and an optimal related characteristic subset from the ROI characteristic set and the related characteristic set through a mixed characteristic algorithm; and setting a weight factor of a function proportion of the ROI characteristics in a classifier, and integrating the optimal ROI characteristic subset and the optimal related characteristic subset through the weight factor and a multi-kernel SVM model to form a multi-kernel classifier. According to the algorithm, high-dimensional characteristics are obtained; local change and function connection change caused by related diseases can be analyzed at the same time; the classification accuracy is high; and the algorithm can assist in diagnosis of different diseases.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, the present invention relates to a multidimensional feature classification algorithm based on brain magnetic resonance images. Background technique [0002] Medical imaging refers to the technology and processing process of obtaining internal tissue images of the human body or a certain part of the human body in a non-invasive manner for medical treatment or medical research. It includes the following two relatively independent research directions: medical imaging system and medical image processing. The former refers to the process of image formation, including the research on imaging mechanism, imaging equipment, imaging system analysis and other issues; the latter refers to the further processing of the obtained image, the purpose of which is to make the original image that is not clear enough Restoration, or to highlight certain feature information in ...

AI Technical Summary

Problems solved by technology

The existing features based on brain magnetic resonance images are mainly based on voxel-based morphological features. The classification algorithm established by using this feature can only find out the structural changes of specific parts, but cannot analyze the changes of functional connections of specific parts. At present, there is no good classification algorithm for clinical use that can simultaneously analyze the changes in human body structure and the structure-functional connection on the basis of brain MRI images, which requires extracting higher-dimensional information from brain MRI images. feature and establish a classifier to realize the classification algorithm of related diseases

Images