Improved mammary gland MRI segmentation method based on U-Net network

A DCE-MRI, breast technology, applied in the field of medical science and technology, can solve problems such as time-consuming and error-prone, and achieve the effect of reducing workload and improving segmentation accuracy

Pending Publication Date: 2021-07-30
HARBIN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Analyzing such a large amount of data is a very time-consuming and error-prone task

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
  • Improved mammary gland MRI segmentation method based on U-Net network
  • Improved mammary gland MRI segmentation method based on U-Net network
  • Improved mammary gland MRI segmentation method based on U-Net network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] A specific embodiment of the present invention will be described in detail below in conjunction with the figures, but it should be understood that the protection scope of the present invention is not limited by the specific embodiment.

[0019] Such as figure 1 As shown, an improved breast MRI segmentation method based on the U-Net network, based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), the specific steps are as follows:

[0020] Step 1: In view of the fact that the 3D convolutional neural network occupies too much resources in terms of model parameters and data volume, and the 3D data set is limited. The 2D convolutional neural network performs better in terms of model parameters, accuracy, speed and data volume, and the data set is sufficient. The present invention uses a 2D convolutional neural network to segment 3D breast DCE-MRI data. First, build a 2D convolutional neural network for mammary gland segmentation (attached Figure 4 ), th...

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 improved mammary gland MRI segmentation method based on a U-Net network. At present, dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) is proved to be an effective auxiliary diagnosis tool and can be used for early discovery and diagnosis of breast cancer. However, there is no CAD (Computer Aided Detection) system, manual DCE-MRI examinations are relatively difficult and error-prone. In typical CAD, in the early stage of breast tissue segmentation, the number of voxels used for analysis is reduced by removing external tissue and air, thereby improving reliability and reducing computational effort. On the basis, the improved mammary gland MRI segmentation method based on the U-Net network is provided to improve the segmentation precision of mammary gland tissues, improve the reliability of subsequent segmentation of mammary gland tumors and reduce the calculated amount.

Description

technical field [0001] The invention relates to the technical field of medical science and technology, in particular to an improved breast MRI segmentation method based on a U-Net network. Background technique [0002] According to World Health Organization (WHO) estimates, the incidence of breast cancer in 2012 was 1.67 million cases (788,000 cases in more developed countries), 522,000 deaths (198,000 cases in more developed countries), during 2007-2012 There are 6.2 million cases worldwide (3.2 million in more developed countries). According to WHO, early detection is a key factor in reducing cancer mortality. Although the World Health Organization advocates mammography as a reference screening tool, dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become increasingly popular due to the safety, high 3D resolution, and dynamic information of MRI (non-ionizing radiation). It is increasingly used as a clinical imaging procedure to assess response to neoadj...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/12G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06T7/12G06N3/08G06T2207/10088G06T2207/20081G06T2207/30068G06N3/045
Inventor 王波童守迪范红宾袁鹏王狄
Owner HARBIN UNIV OF SCI & TECH
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