MRI segmentation method based on reinforcement learning multi-scale neural network

A multi-scale segmentation and reinforcement learning technology, applied in the field of image processing, can solve the problems of inconsistent judgment severity, difference in MRI data quality, and inability to quantify, and achieve the effect of improving segmentation effect, improving segmentation accuracy, and enhancing learning.

Pending Publication Date: 2020-10-16
XIDIAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Because the inflammatory area is irregular in shape, size, and distribution on the MRI data, there are problems such as inability to quantify and inconsistency in judging the severity when clinicians use MRI data to analyze patients. The difference in the quality of MRI data caused by the difference of different equipment increases the difficulty of reading images for clinicians
[0005] Existing medical image segmentation algorithms have serious missing and mis-segmented problems when segmenting inflammatory regions, which seriously affects doctors'

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • MRI segmentation method based on reinforcement learning multi-scale neural network
  • MRI segmentation method based on reinforcement learning multi-scale neural network
  • MRI segmentation method based on reinforcement learning multi-scale neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0024] Example 1

[0025] With the development of science and technology, human beings have more knowledge about spondyloarthritis. More information about inflammatory areas of spondyloarthritis can be found through single-modality magnetic resonance image MRI. During regional segmentation, the segmentation effect is often poor due to the large difference in the shape and size of the inflammatory region in the MRI image data. In view of the current situation, the present invention proposes an MRI segmentation method based on reinforcement learning multi-scale neural network after exploration and experimentation, which is used for segmentation of inflammatory regions of single-modality image MRI.

[0026] The invention is an MRI segmentation method based on reinforcement learning multi-scale neural network.

[0027] see figure 1 , including the following steps:

[0028] (1) Divide training, validation and test sample sets: First, the MRI raw data of AS patients are obtained ...

Example Embodiment

[0038] Example 2

[0039] The MRI segmentation method based on the reinforcement learning multi-scale neural network is the same as the embodiment 1, and the voxel constraint strategy described in the step (2) of the present invention sets the label value of the MRI inflammation area. The voxel constraint strategy proposed by the present invention is aimed at the problem that the distribution of voxel values ​​in the inflammatory area is very different, resulting in poor segmentation effect. Adjust according to the size of the voxel value of the inflammatory area:

[0040]

[0041]

[0042] The label value of the original inflammation area is modified according to the voxel value of the MRI data by the above formula, where y n is the original label value, y′ n is the modified label value, σ is the weighted value, p max is the maximum voxel value of the current MRI data, p n is the value of the voxel of the nth MRI data, and ρ is a hyperparameter to ensure that the de...

Example Embodiment

[0045] Example 3

[0046] The MRI segmentation method based on the reinforcement learning multi-scale neural network is the same as the embodiment 1-2, and the MRI based on the reinforcement learning multi-scale neural network is constructed to deal with the large difference in shape and size and the diffuse blurred inflammation area described in the step (3) of the present invention. The segmentation model LGR-Net, which addresses the segmentation of multi-scale and diffusely ambiguous inflammatory regions. It includes the following steps:

[0047] (3.1) Building a multi-scale segmentation sub-network: First, for the problem of large differences in the shape and scale of the inflammatory area, a multi-scale convolution module GMS is constructed to extract multi-scale information. Considering the network size limitation and the commonly used convolution kernel size, the design Nine common convolution kernels with different dilation rates d and different sizes k are connected ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an MRI segmentation method based on a reinforcement learning multi-scale neural network, and solves the problems of error-prone segmentation and missing segmentation of multi-scale, fuzzy and diffuse MRI inflammatory regions in the existing method. According to the method, the voxel constraint strategy of modifying the inflammatory region label value according to the voxelvalue is adopted, and the segmentation effect of the segmentation model on the inflammatory region with large voxel value difference is improved; according to the method, a multi-scale convolution module GMS is designed for inflammatory regions with large shape and size differences, and the segmentation effect of the segmentation model on the multi-scale inflammatory regions is improved; in orderto solve the problem that the segmentation model is difficult to identify the diffusion blurred inflammatory region, the reinforcement learning network is used for data enhancement, and the discrimination performance of the segmentation model for the diffusion blurred inflammatory region is improved. According to the method, wrong segmentation and missing segmentation of the multi-scale fuzzy diffusion inflammatory region are reduced, and the segmentation effect of the MRI inflammatory region is improved. The method can be used for MRI inflammatory region segmentation and quantitative analysisautomatic processing.

Description

technical field [0001] The invention belongs to the technical field of image processing, and mainly relates to the single-mode image segmentation of nuclear magnetic resonance inflammatory lesions, specifically an MRI segmentation method based on reinforcement learning multi-scale neural network, which can be used for the inflammation area in hip joint nuclear magnetic resonance image MRI Data partitioning. Background technique [0002] Ankylosing spondylitis (AS) comprises a group of related disorders characterized by inflammation of the sacroiliac joints and at sites such as the spine, peripheral joints, and tendon attachments. The etiology of AS is complex, the pathogenesis is unclear, the early clinical manifestations of patients are not typical, the traditional radiological examination is not sensitive, and the lack of specific laboratory indicators has caused great obstacles for clinicians to accurately judge AS in the early stage. In time, it will often cause serious...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/00G06T7/11
CPCG06T7/0012G06T7/11G06T2207/10088G06T2207/20084G06T2207/20081G06T2207/30012
Inventor 缑水平卢云飞刘宁涛曹思颖路凯童诺刘波毛莎莎焦昶哲
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap