A method for constructing corpus callosum segmentation prediction images for corpus callosum state assessment

A technology for predicting images and constructing methods, which is applied in the fields of medical image segmentation and deep learning, and can solve problems such as inability to accurately calculate the volume of the corpus callosum, low detection rate of fetal corpus callosum abnormalities, and high error rate

Active Publication Date: 2022-07-19
WEST CHINA HOSPITAL SICHUAN UNIV
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the measurement of the size and position of the corpus callosum still relies on medical imaging technicians to provide it according to the fetal brain ultrasound image annotation, which requires high requirements for the operator's experience and technology, and the ultrasound image cannot accurately calculate the volume of the corpus callosum. It also cannot provide an effective basis for the judgment of the sonographer
Therefore, the abnormal detection rate of fetal corpus callosum is low and the error rate is high

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
  • A method for constructing corpus callosum segmentation prediction images for corpus callosum state assessment
  • A method for constructing corpus callosum segmentation prediction images for corpus callosum state assessment
  • A method for constructing corpus callosum segmentation prediction images for corpus callosum state assessment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Example 1 Construction of deep neural network model for fetal ultrasound image state analysis of the present invention

[0037] (1) Image preprocessing

[0038] a. Collect fetal brain ultrasound images and corpus callosum segmentation label images

[0039] Ultrasound images of the fetal brain were collected using a luminance-modulated ultrasound section imager and a TRT33 variable-frequency dual-plane trans-cerebral probe; the segmented and labeled images of the corpus callosum were provided by medical imaging technicians based on the fetal brain ultrasound images.

[0040] b. Image data preprocessing

[0041]Translate, enhance, and elastically deform the acquired fetal brain ultrasound images, and perform corner point detection and center point detection on the segmentation label image of the corpus callosum. The specific methods are as follows:

[0042] ①Use the horizontal and vertical difference operators to filter all the pixels of the image to obtain to obtain ...

Embodiment 2

[0069] Embodiment 2 Fetal ultrasound image state analysis of the present invention

[0070] Take a fetal brain ultrasound image data to be evaluated and input it into the deep neural network model constructed in Example 1. The segmentation map of the corpus callosum of the brain can be constructed through the output initial contour line and the offset of the active contour, and the state of the corpus callosum of the fetal brain can be evaluated. , see the framework structure of corpus callosum state analysis of fetal ultrasound images based on deep neural network image 3 .

[0071] To sum up, the present invention transforms the corpus callosum of the brain into the initial contour line establishment and the active contour convergence, uses the coding and decoding module to obtain multi-scale image feature information, predicts the corpus callosum state code and initial contour line of the fetal ultrasound image, and distributes the vector through the key points. And the co...

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 method for constructing a corpus callosum segmentation prediction image for corpus callosum state assessment. According to the initial outline of the corpus callosum and the offset of the key point, the segmentation prediction image of the corpus callosum of the brain is cropped from the ultrasound image of the fetal brain. The deep neural network model of the fetal ultrasound image state analysis of the present invention fills the blank of the brain corpus callosum state analysis of the brain ultrasound image, and pioneers a method for evaluating the brain corpus callosum state by using the brain ultrasound image.

Description

technical field [0001] The present invention relates to the field of medical image segmentation and deep learning, in particular to a method for constructing a corpus callosum segmentation prediction image for corpus callosum state assessment. Background technique [0002] The corpus callosum is located at the base of the interhemispheric fissure and is the largest commissural fiber in the cerebral hemisphere. Agenesis of Corpus Callosum (ACC) is a congenital developmental abnormality in the fetal central nervous system, which refers to the partial or complete absence of the corpus callosum during development. effect. [0003] At present, the measurement of the size and position of the corpus callosum still relies on medical imaging technicians to provide annotations based on the ultrasound images of the fetal brain, which requires high requirements on the operator's experience and technology, and ultrasound images cannot accurately calculate the volume of the corpus callos...

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 Patents(China)
IPC IPC(8): G06T7/187G06T7/11G06N3/04G06N3/08G16H30/20
CPCG06T7/187G06T7/11G06N3/08G16H30/20G06T2207/20221G06T2207/20016G06N3/045
Inventor 曹桂群何长涛程建陈玉兰郑文刘鑫周柱玉宋思思
Owner WEST CHINA HOSPITAL SICHUAN 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