A method and system for feature extraction of diffusion tensor images

Abstract

The invention belongs to the technical field of medical image processing, and particularly relates to a method and a system for extracting image characteristics of diffusion tensor. The method for extracting the image characteristics of the diffusion tensor comprises the steps of a, calculating a tensor eigenvalue of a DTI (diffusion tensor imaging) image in the principal direction, and analyzing distribution characteristics of tensor eigenvalues of all images; b, constructing a weight matrix according to the distribution characteristics of the tensor eigenvalues, and establishing and optimizing a weight matrix based target function so as to construct a new characteristic space; and c, solving the target function to acquire a multi-linear projection matrix, projecting a DTI tensor eigenvalue based matrix space to multiple linear sub-spaces, and carrying out characteristic extraction and dimensionality reduction on DTI images of the sub-spaces. The method provided by the invention not only can effectively reflect various sample characteristics, but also can reduce the calculation cost, diffusion characteristics of the diffusion tensor image on three principal directions are fully dug on the basis of keeping the original image structure information, purposes of dimensionality reduction and characteristic extraction are realized, and a dimensionality curse is avoided effectively.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, in particular to a method and system for extracting diffusion tensor image features. Background technique [0002] Diffusion Tensor Imaging (DTI) is a new method to describe the structure of the brain and is a special form of Magnetic Resonance Imaging (MRI). Unlike MRI, which tracks hydrogen atoms in water molecules, diffusion tensor imaging maps the direction in which water molecules are moving. Diffusion tensor imaging (presented differently than previous images) could reveal how brain tumors affect nerve cell connections, guide medical staff in performing brain surgery, and reveal links to stroke, multiple sclerosis, schizophrenia, dyslexia and more Subtle abnormal changes in the brain and spinal cord. [0003] Diffusion tensor imaging data is essentially a second-order tensor structure, and each voxel of it contains the three-dimensional spatial information of the diffusio...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method and system for extracting features of a diffusion tensor image, aiming at solving the problem that the existing vector mode learning algorithm processing and analysis of the diffusion tensor image destroys the original data structure, and the calculation amount is large and the calculation cost is high. question

Images