White matter fiber brain map construction method by means of diffusion tensor imaging medical image

Abstract

Provided is a white matter fiber brain map construction method by means of a diffusion tensor imaging medical image. The method comprises the steps that an original diffusion tensor imaging image is input (101); image preprocessing is conducted on a diffusion tensor image (106), wherein the substeps of data format conversion (102), 4D image converting (103), anisotropy value computing (104) and bone removing operation (105) are included; a registration technology is utilized (107), reflection transformation (108) and a large-deformation differential homomorphic mapping algorithm (109) are used, and different tested diffusion tensor images are registrated to the same standardized space (107); diffusion weighted imaging analysis is conducted (113), wherein the substeps of analyzing a deformation field by means of a diffusion tensor model (110), conducting diffusion weighted imaging redirection (111) and estimating diffusion tensor (112) are included; two brain white matter maps are constructed for patients and normal people (115); machine learning is conducted (114), wherein feature extraction (116) and feature selection (117) are conducted on tested pictures, data sets are divided into a training set and a test set, machine learning is conducted according to the maps (118), and training is conducted to generate a classifier (121).

Description

Background technique [0001] The invention relates to a method for constructing a white matter fiber brain atlas using diffusion tensor imaging medical images, which is used for clinical medical auxiliary diagnosis of brain diseases. Background technique [0002] Diffusion tensor imaging, as a special magnetic resonance imaging method, is widely used to explore the structural characteristics of white matter fibers in living brains. This imaging technology indirectly describes the geometric shape and spatial direction of the brain white matter fiber structure by detecting the diffusion characteristics of brain water molecules, which plays a very important role in the study of brain white matter development and some neurological diseases. [0003] For the currently commonly used public brain atlas templates, structural information about the white matter of the brain is relatively missing. This is because in traditional MRI images, white matter information is relatively singl...

AI Technical Summary

Problems solved by technology

This is because in traditional MRI images, white matter information is relatively single

The anatomical information reflected in the traditional MRI template is a single gray value information, which is very difficult to identify the characteristic white matter region

Images