MRI image hippocampus region segmentation method based on various losses and multi-scale features

Abstract

The invention provides an MRI image hippocampus region segmentation method based on various loss and multi-scale features. The method comprises the following steps: step 1, acquiring a plurality of T1-modal brain MRI images and hippocampus tags; step 2, taking the left and right labels of the left and right hippocampus as a reference, cutting the brain MRI image of each T1 mode to obtain a plurality of cut left and right hippocampus cubes; and step 3, performing 3D dicing on each cut left and right hippocampus cubes to obtain 3D dices of all the cut left and right hippocampus cubes, screening out 3D blocks containing hippocampus voxels greater than a set threshold value from the 3D dices of all the cut left and right hippocampus cubes, and performing pretreatment on the screened 3D blocks. According to the invention, the labels of the hippocampus and the background can be accurately segmented, and the segmentation accuracy is improved through the combination of multi-scale information and various losses, so that the segmentation accuracy of the hippocampus in the brain image is remarkably improved.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for segmenting hippocampal regions of MRI images based on multiple losses and multi-scale features. Background technique [0002] In recent years, neuroimaging technology has played a very important role in the diagnosis of many neurological diseases. Studies have shown that Alzheimer's disease (AD) is closely related to the shape and volume of the hippocampus. Through brain magnetic resonance imaging (MRI The correct segmentation of the hippocampus in ) can help doctors to better diagnose neurological diseases such as AD to a certain extent. With the rapid development of various semi-automatic and automatic hippocampus segmentation techniques, a large number of studies have used structural magnetic resonance imaging to segment the hippocampus, especially the deep learning model has achieved great success in the past few years, and the deep learning mode...

AI Technical Summary

Problems solved by technology

[0004] The invention provides a method for segmenting the hippocampus region of MRI images based on multiple losses and multi-scale features, the purpose of which is to solve the poor segmentation performance and low segmentation accuracy of the traditional deep learning hippocampus segmentation method based on brain MRI images The problem

Images