Breast ultrasound imaging quality monitoring system and method based on deep neural network

A technology of deep neural network and ultrasound imaging, applied in neural learning methods, biological neural network models, neural architecture, etc., can solve the problems that ultrasound images depend on radiologists and cannot evaluate the quality of ultrasound images, so as to promote standardization and standardization , reduce subjective factors, reduce the effect of subjective factors

Active Publication Date: 2021-06-01
SICHUAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Based on the above problems, the present invention provides an ultrasound imaging quality monitoring system and method based on a deep neural network, which is used to solve the problem that the evaluation of ultrasound image quality in the prior art relies too much on radiologists, and cannot timely monitor the quality of ultrasound images. evaluation question

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
  • Breast ultrasound imaging quality monitoring system and method based on deep neural network
  • Breast ultrasound imaging quality monitoring system and method based on deep neural network
  • Breast ultrasound imaging quality monitoring system and method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 Shown, a kind of ultrasonic imaging quality monitoring method based on deep neural network, comprises the following steps:

[0065] Step 1: Data preparation, including collecting ultrasound images, and marking whether the imaging quality is up to standard for the ultrasound images, marking the features of the imaging problems for the ultrasound images, and marking the text of the prompt information for the ultrasound images; the deep neural network needs to learn from a large number of From the original data of breast ultrasound images, learn the features of different indicators that can affect the image quality, and combine the existing classification labels to train and optimize the model. Therefore, before training the deep neural network, it is necessary to carry out a large amount of breast ultrasound image data. Manual labeling.

[0066] Among them, for the image data labeling of the classification model, 300,000 ultrasound images from different...

Embodiment 2

[0095] Such as Figure 4-Figure 6 As shown, an ultrasound imaging quality monitoring system based on deep neural network, including classification model, generation model and language model;

[0096] The classification model is used to preliminarily judge whether the ultrasonic image meets the quality standard, if the quality standard is not met, then it is sent into the generation model, and if the quality standard is met, the ultrasonic image is output and printed;

[0097] The generation model is used to judge the factors that cause the ultrasound image quality to be substandard, generate a feature matrix describing different factors that affect the imaging quality, and then send the feature matrix to the language model;

[0098] The language model is used to give operation suggestions for the problems in the feature matrix, adjust the operation of the monitoring system according to the operation suggestions, optimize the imaging quality, and continue to send the pre-output...

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 relates to the technical field of breast ultrasound imaging quality monitoring, in particular to a breast ultrasound imaging quality monitoring system and method based on a deep neural network, which is used to solve the problem that the evaluation of ultrasound image quality in the prior art is too dependent on radiologists and cannot be timely Ultrasound image quality for evaluation issues. The invention includes a classification model, a generation model and a language model; the classification model is used to preliminarily judge whether the ultrasound image meets the quality standard; the generation model is used to judge the factors that cause the quality of the ultrasound image to fail to meet the standard, and the generated description affects the imaging quality feature matrix of different factors, and then send the feature matrix to the language model; the language model is used to give operation suggestions for the problems in the feature matrix. The present invention can reduce the subjective factors of manual judgment, and at the same time avoid the problem that the user finds that there is a problem with the imaging quality after getting the ultrasound report but has lost the best adjustment time.

Description

technical field [0001] The present invention relates to the technical field of breast ultrasound imaging quality monitoring, and more particularly relates to a deep neural network-based ultrasound imaging quality monitoring system and method. Background technique [0002] Female breasts are composed of skin, fibrous tissue, breast glands and fat. Breast cancer is a malignant tumor that occurs in the glandular epithelial tissue of the breast. With the unhealthy lifestyle of contemporary society and the increase of mental pressure, more and more women Suffering from breast cancer, the incidence of breast cancer increases with age. According to the 2009 breast cancer incidence data released by the National Cancer Center and the Ministry of Health's Center for Disease Control and Prevention in 2012, the incidence of breast cancer in the national tumor registration area is at the It ranks first among female malignant tumors. Compared with other important organs in the body such a...

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): G06T7/00G16H30/20G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06N3/084G16H30/20G06T2207/10132G06T2207/20081G06T2207/20084G06T2207/30068G06T2207/30168G06N3/045G06F18/24G06F18/214
Inventor 章毅戚晓峰张潇之郭泉李浩陈怡
Owner 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

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