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

Ultrasonic cardiogram contraction/relaxation end-stage frame automatic identification method based on deep learning

A technology of echocardiography and end-diastole, applied in the directions of ultrasound/sonic/infrasonic image/data processing, ultrasound/sonic/infrasonic diagnosis, ultrasound/sonic/infrasonic Permian technology, etc. Missing, time-consuming and other problems, to achieve the effect of reducing the cost of manual participation

Active Publication Date: 2021-02-09
JILIN UNIV +1
View PDF20 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Echocardiography often has a lot of noise, artifacts, and information on contour boundaries is easily lost during imaging, so the process of manual labeling requires high expert knowledge and experience, and must be completed by specially trained medical staff or medical experts, and very time consuming

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
  • Ultrasonic cardiogram contraction/relaxation end-stage frame automatic identification method based on deep learning
  • Ultrasonic cardiogram contraction/relaxation end-stage frame automatic identification method based on deep learning
  • Ultrasonic cardiogram contraction/relaxation end-stage frame automatic identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0033] Such as figure 1 As shown, a deep learning-based echocardiogram end-systolic / diastolic frame automatic identification method of the present invention includes the following steps:

[0034] Step 1, image preprocessing, the specific steps are as follows:

[0035] Retrospective analysis of echocardiographic images (Philips echocardiography system), a total of 49 samples of apical two-chamber, a total of 52 samples of apical four-chamber, each sample contains 2-4 heartbeat cycles, each Each sample contains 78-101 frames, and each frame image is extracted from all the echocardiographic videos collected, and the image size is 600×800 pixels. Convert DICOM (dcm) into bitmap images with lossless compression algorithm in batches through the pydicom library in python. Each sample has the end-stage frame intercepted by the doctor. Since each sample basic...

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 ultrasonic cardiogram systolic / diastolic end-stage frame automatic identification method based on deep learning. The method specifically comprises the following steps: 1, image preprocessing; 2, network construction and training; 3, test set data positioning; and 4, test set data automatic positioning. The ultrasonic cardiogram contraction / relaxation end-stage frame automatic identification method based on deep learning has the beneficial effects that the maximum systolic end-stage frame and the maximum diastolic end-stage frame in all frames of the echocardiogram are automatically predicted, the manual participation cost is reduced, the evaluation of the function of the left ventricle by a doctor is facilitated, and a basis is provided for heart disease diagnosis.

Description

technical field [0001] The present invention relates to a method for automatic identification of systolic / diastolic end-stage frames of echocardiography, in particular to an automatic identification method for echocardiographic systolic / diastolic end-stage frames based on deep learning. Background technique [0002] At present, the commonly used imaging methods for heart disease diagnosis mainly include echocardiography, computed tomography imaging, and magnetic resonance imaging. The function of the left ventricle contributes a lot to the function of the heart, so the automatic positioning and function evaluation of the left ventricle plays a vital role in the clinical quantification and diagnosis of cardiac images. [0003] Echocardiography is a dynamic image that uses ultrasound imaging principles to reflect the movement of the heart in real time, and has the advantages of non-invasive, low-cost, dynamic observation, no radiation, and good repeatability, so it is widely u...

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
IPC IPC(8): A61B8/08
CPCA61B8/0883A61B8/5215A61B8/523
Inventor 孙铭蔚周柚佘燕达洪可欣宋春莉闫冰时小虎王镠璞
Owner JILIN 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com