Children brain MRI demyelination focus positioning method based on deep semi-supervised segmentation

A positioning method and a semi-supervised technology, applied in the field of deep learning and image processing, can solve the problems of blurred ADEM lesions, the inability of doctors to effectively identify the boundaries of lesions, and the inability to label data, achieving good robust performance, good edge learning ability, Overcome the effect of blurred edges

Pending Publication Date: 2022-06-28
ZHEJIANG UNIV +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The inventive introduced supervision model of the present invention is mainly to solve the following two difficult problems existing in the current ADEM lesion localization analysis: As a result, it is impossible to accurately and effectively label the data, so the use of full supervision will invalidate the final model

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
  • Children brain MRI demyelination focus positioning method based on deep semi-supervised segmentation
  • Children brain MRI demyelination focus positioning method based on deep semi-supervised segmentation
  • Children brain MRI demyelination focus positioning method based on deep semi-supervised segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The method of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0061] like figure 1 As shown, a deep semi-supervised segmentation method for localization of demyelinating lesions in children's brain MRI includes the following steps:

[0062] Step 1. Data set construction, data enhancement and annotation. The original data set was constructed by backtracking hospital cases, and the data was annotated using 3Dslicer annotation software. And based on the data characteristics, the image data is cropped, cut, cleaned, and data enhanced.

[0063] Specific steps are as follows:

[0064] 1-1. Collect brain MRI image data of patients with acute disseminated encephalomyelitis.

[0065] 1-2. Use 3D slicer labeling software to label the lesions in the original data pixel by pixel. For the original brain MRI image data in dicom format, the extracted image is saved in nrrd format, the image is a single-channel 1...

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 children brain MRI demyelination focus positioning method based on deep semi-supervised segmentation, and the method comprises the steps: firstly constructing a data set, and then constructing a segmentation model which comprises a Student network and a Teacher network; carrying out Student network training by utilizing the constructed data set, and carrying out parameter drift according to the Student network parameters after back propagation to obtain Teamer network parameters; according to the method, a pre-processing mode is designed in a targeted manner, so that the method has good compensation for possible problems in the imaging process. By means of image enhancement, image plus noise and semi-supervision, the model can obtain good segmentation performance only through a small number of annotated images, good robustness is obtained for noise and artifacts, and the problems that the annotation process is large in difficulty, inaccurate and time-consuming and labor-consuming are solved.

Description

technical field [0001] The invention relates to the fields of image processing and deep learning, in particular to a lesion segmentation and positioning method based on a brain magnetic resonance image of a child suffering from acute disseminated encephalomyelitis. Background technique [0002] Acute disseminated encephalomyelitis (ADEM) is an inflammatory demyelinating disease of the central nervous system (CNS) that often involves multiple parts of the brain and polio and white top, and is prevalent in children and young adults. In the prime of life, it can also cause severe neurological dysfunction in patients, often secondary to infection or after vaccination, and a small number of cases have no obvious incentives. ADEM has the characteristics of acute onset, rapid progression, and monophasic course. In recent years, the understanding of ADEM has changed, and ADEM is considered to be a clinical syndrome caused by multiple etiologies, rather than a specific disease. The ...

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): G06T7/11G06T7/00G06V10/774G06V10/778G06V10/72G06V10/82G06N3/04G06N3/08G06K9/62A61B5/055
CPCG06T7/11G06T7/0012G06N3/084A61B5/055G06T2207/10088G06T2207/20081G06T2207/20084G06T2207/30016G06N3/047G06N3/048G06N3/045G06F18/2155G06F18/217G06F18/10
Inventor 高峰徐璐魏劭农王天磊蒋铁甲张洪锡刘珂舟曹九稳
Owner ZHEJIANG 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