Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Brain glioma segmentation model and segmentation method based on deep learning

A technique for brain glioma and segmentation models, which is applied in neural learning methods, biological neural network models, image analysis, etc., can solve problems such as high difficulty and time-wasting, and achieve the effect of improving the ability and improving the segmentation effect

Pending Publication Date: 2021-02-26
QILU UNIV OF TECH
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In clinical practice, the diagnosis of glioma is usually divided manually by experts, which is time-consuming and difficult, and the separation of glioma is the key to clinical treatment

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
  • Brain glioma segmentation model and segmentation method based on deep learning
  • Brain glioma segmentation model and segmentation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] A brain glioma segmentation model based on deep learning of the present invention includes an encoding model and a decoding model. The encoding model includes a convolutional layer and N encoding modules. The encoding includes a hole dense unit and a pool located at the output of the hole dense unit. The above-mentioned N encoding modules are connected in sequence and located at the output end of the convolutional layer, the encoding module located at the end of the transmission is the end encoding module, and the other encoding modules are intermediate encoding modules, and N is greater than or equal to 3; the decoding module includes sequentially connected first An end decoding module, an intermediate decoding module, and an end decoding module; the head end decoding module includes sequentially connected hole dense units and upsampling convolutional layers, the head end decoding module is located at the output end of the end encoding module, and the output end of the h...

Embodiment 2

[0042] The glioma segmentation method based on deep learning of the present invention comprises the following steps:

[0043] S100. Acquiring various three-dimensional nuclear magnetic resonance images as input images, where the above nuclear magnetic resonance images include various MRI modalities and brain glial regions marked by experts;

[0044] S200. Perform normalization processing on the above-mentioned input image, so that the input image conforms to a normal distribution;

[0045] S300. Construct the glioma segmentation model based on deep learning disclosed in Example 1;

[0046]S400. Based on the normalized input image, train the above-mentioned glioma segmentation model to obtain a trained glioma segmentation model;

[0047] S500. Acquiring a nuclear magnetic resonance image to be detected as a test image, the nuclear magnetic resonance image including various MRI modalities and brain glial regions marked by experts;

[0048] S600. Perform normalization processin...

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 a brain glioma segmentation model and segmentation method based on deep learning, belongs to the technical field of brain glioma segmentation, and aims to solve the technical problem of how to accurately segment brain glioma. The segmentation model comprises: a coding model which comprises a convolution layer and N coding modules, wherein the coding model comprises a hole dense unit and a pooling layer located at the output end of the hole dense unit; a decoding module, wherein the decoding module comprises a head end decoding module, a middle decoding module and a tailend decoding module which are connected in sequence, the output end of the head-end decoding module is in jump connection with the output end of the hole dense unit in the tail-end encoding module through a jump connection layer, the output end of each intermediate decoding module is in jump connection with the output end of the hole dense unit in the corresponding intermediate coding module through a jump connection layer, the tail end decoding module comprises a convolution layer, a hole dense unit and a convolution layer which are connected in sequence, and the tail end decoding module islocated at the output end of the related jump layer of the previous decoding module.

Description

technical field [0001] The present invention relates to the technical field of glioma segmentation, in particular to a glioma segmentation model and segmentation method based on deep learning. Background technique [0002] In today's society, people are paying more and more attention to their own living conditions and medical conditions, and health has become a topic of great concern in people's lives. Therefore, medicine must continue to develop, and medical imaging, which is an important means of diagnosis and treatment for doctors, must also be obtained. develop accordingly. Today, medical images play an important role that cannot be underestimated in medical diagnosis. [0003] In medical images, there are magnetic resonance scans (MRI) and computed tomography (CT), etc. Medical image segmentation has a wide range of research values ​​in medical research, disease analysis, and surgical planning. Intelligent segmentation of glioma is of great significance for disease di...

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): G06T7/00G06T7/11G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/08G06T2207/10088G06T2207/30096G06N3/045
Inventor 任晓强赵越
Owner QILU UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com