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

Children congenital heart disease intelligent diagnosis system based on echocardiography

A technology of congenital heart disease and echocardiography, applied in the field of medical image intelligent processing, to reduce diagnostic errors, improve auxiliary diagnosis and education and training levels

Pending Publication Date: 2022-07-22
FUDAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is no research report on the intelligent diagnosis model of congenital heart disease based on echocardiography.

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 congenital heart disease intelligent diagnosis system based on echocardiography
  • Children congenital heart disease intelligent diagnosis system based on echocardiography
  • Children congenital heart disease intelligent diagnosis system based on echocardiography

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The embodiments of the present invention will be described in detail below, but the protection scope of the present invention is not limited to the examples.

[0048] use figure 1 The network structure in , uses the GeForce RTX 2080Ti GPU to train the classification model and the detection model, and uses the Pytorch framework to build the model of the present invention. For classification models, the classification model is trained by minimizing the cross-entropy loss between the predicted class and the true class. During the optimization process, Adam optimizer and learning rate decay strategy are used. For the detection model, its classification branch is trained by minimizing the cross-entropy loss between the predicted and ground-truth classes, and its regression branch is trained by minimizing the difference between the ground-truth and predicted bounding boxes. Similar to the classification model, the Adam optimizer is also used with an initial learning rate of...

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 congenital heart disease intelligent diagnosis system based on echocardiography. The system comprises an echocardiography video key frame selection module for automatically predicting whether a patient has a heart defect or not, and a congenital heart defect positioning detection module for providing an accurate position of the heart defect of the patient, wherein the echocardiography video key frame selection module is a classification network designed based on ResNet; the latter is a detection network designed based on Faster-RCNN; the gray ultrasound image and the color ultrasound image of the echocardiogram serve as input of the system at the same time; the method further comprises a large-scale echocardiogram set of 5025 children, and an established deep learning model based on echocardiograms can diagnose common congenital heart defects at the same time. Experimental results show that when a standard section of a single echocardiogram is input, 100% of sensitivity and specificity are achieved in diagnosis of three common congenital heart diseases on an external independent verification set.

Description

technical field [0001] The invention belongs to the technical field of medical image intelligent processing, and in particular relates to an intelligent diagnosis system for children's congenital heart disease. Background technique [0002] Congenital heart disease (CHD) is abbreviated as congenital heart disease, which refers to the abnormal cardiac anatomy caused by the formation disorder or abnormal development of the heart and great blood vessels during embryonic development, or the failure of the channels that should be automatically closed after birth. A disease resulting from closure (normal in fetal life). CHD ranks first in birth defects in my country and is the leading cause of neonatal and child mortality, with an incidence of about 9‰ in live births. Among all the subtypes of CHD, Ventricular Septal Defect (VSD), Atrial Septal Defect (ASD) and Patent Ductus Arteriosus (PDA) are the three most common types. [0003] ASD refers to the abnormal development of 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): A61B8/06
CPCA61B8/06A61B8/488A61B8/48
Inventor 李健颜波曹银银谭伟敏林青黄国英
Owner FUDAN UNIV
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