DAC-GAN model construction method and application in mammary gland MR image

A construction method and model technology, which is applied in the field of medical image applications, can solve the problems that the image quality cannot meet the clinical needs, and achieve the effects of avoiding contrast agent allergy, shortening the examination time of patients, and improving quality

Pending Publication Date: 2020-12-25
西安国际医学中心有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the research progress of GAN in the field of medical imaging is gratifying, most of them focus on the transformation between imaging modalities, and the quality of some generated images still cannot meet the clinical needs; in addition, the related research on GAN algorithm in the derivation of breast MR sequence images is still at an advanced stage. initial stage

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
  • DAC-GAN model construction method and application in mammary gland MR image
  • DAC-GAN model construction method and application in mammary gland MR image
  • DAC-GAN model construction method and application in mammary gland MR image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further elaborated below according to the drawings and specific embodiments.

[0048] Such as figure 1 As shown, the DAC-GAN model for breast MR image deduction is constructed using Python3.7 version, and the specific implementation is as follows:

[0049] Step 1: Breast MRI Image Acquisition

[0050] Taking each patient's T1WI sequence, DWI sequence, T2WI sequence and DCE dynamic enhanced sequence image and the patient's diagnosis result as a sample, M patient sample information is extracted to form a data set D.

[0051] The sample sequence images in dataset D are specifically collected through the following steps:

[0052] The prone position images of breast MR examinations of patients were collected retrospectively. All subjects were examined using Siemens MAGNETOM Prisma 3.0TMR. The routine breast MR scan sequences collected included: axial SE T1WI, T1WI; axial Dixon T2WI; acquisition Breast MR dynamic enhanced scan (DCE-MRI) sequen...

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 DAC-GAN model construction method and application in a mammary gland MR image, and the method comprises the following steps: 1, obtaining a mammary gland MR image data set D,and enabling the data in the data set D to comprise the T1WI sequences, DWI sequences, T2WI sequences and DCE dynamic enhancement sequence images of M patients and the diagnosis results of the patients; 2, setting M T1WI sequence images in the data set D obtained in the step 1 as a T1 data set, and setting a DCE dynamic enhancement sequence image as a DCE data set; 3, performing gray value normalization on the T1 data set and the DCE data set obtained in the step 2; 4, improving an existing GAN model by introducing a Non-local attention network and a Channel-attention network to obtain a constructed DAC-GAN model, and performing deduction on a mammary gland MR image to be measured through the DAC-GAN model.

Description

technical field [0001] The invention belongs to the technical field of medical image applications, and in particular relates to a DAC-GAN model construction method, and also relates to the application of the above-mentioned DAC-GAN model in breast MR images. Background technique [0002] At present, breast cancer has become the main cause of cancer death in women worldwide. Early detection, early diagnosis, and early treatment can significantly improve the 5-year survival rate of breast cancer patients. Dynamic contrast-enhanced MRI (DCE-MRI) as a A very valuable quantitative MRI technology has played a huge role in the early detection and diagnosis of breast cancer. However, traditional breast MR examinations are time-consuming and expensive, and there is a risk of patients being allergic to contrast media and related adverse reactions caused by contrast media, such as gadolinium deposition in the brain and abnormal renal function. With the advent of the "Internet + medica...

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): G06T7/00G06K9/46G06N3/04G06N3/08
CPCG06T7/0012G06N3/08G06T2207/10088G06T2207/30068G06V10/40G06N3/045
Inventor 陈宝莹王苹苹聂品李铁柱党艳丽王丽芳朱开国马小伟
Owner 西安国际医学中心有限公司
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