Method and device for segmenting brain white matter high signal based on deep learning method

Abstract

The invention provides a method of segmenting a brain white matter high signal based on a deep learning method. The method comprises the following steps of: constructing an original input image, carrying out preprocessing operation on the original input image, the preprocessing operation comprising image registration, first extraction of a brain contour, second extraction of the brain contour, image data standardization and image size unification, carrying out white matter high signal segmentation processing on the original input image after the preprocessing operation, and performing binarization processing on the brain white matter high signal probability graph generated after segmentation processing through a preset threshold to obtain a brain white matter high signal graph, and restoring the brain white matter high signal graph to an original size. The method has no limitation on the size of an input image, and is extremely high in segmentation speed, high in generalization and easy to use. The invention further provides a device for segmenting the brain white matter high signal based on the deep learning method.

Description

technical field [0001] The present disclosure relates to the technical field of biological computers, in particular, to a method and device for segmenting brain white matter hyperintensities based on deep learning methods. Background technique [0002] In the prior art, white matter hyperintensity is a kind of multiple punctate, patchy or confluent hyperintensities in white matter manifested on fluid-attenuated inversion recovery sequence (FLAIR), which is common in the elderly and stroke patients, especially Common in subcortical ischemic cerebrovascular disease caused by small vessel disease. White matter hyperintensity is an important imaging feature to measure white matter abnormalities, and it is a high-risk risk factor for stroke, dementia, depression and other diseases. In addition, some studies have shown that there is a close relationship between the volume and location of white matter hyperintensity and cognitive impairment. Therefore, the evaluation of white mat...

AI Technical Summary

Problems solved by technology

Most current white matter hyperintensity segmentation methods are designed for specific studies or for samples with specific parameters, have not been evaluated in samples with different parameters, are not publicly available as user-friendly software packages, and usually do not provide different brain parameters. Details of areas of white matter hyperintensity

Images