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

Ultrasonic image hashimoto thyroiditis identification method based on deep neural network

A deep neural network, ultrasound image technology, applied in the field of thyroiditis recognition, can solve the problems of poor generalization performance, not fully automatic method, low accuracy, etc. improved effect

Inactive Publication Date: 2021-01-26
脉得智能科技(无锡)有限公司 +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, the main disadvantages of methods based on manually designed image features and some relatively simple linear classifiers include low accuracy, poor generalization performance, and most of them are not fully automatic methods, etc.

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 image hashimoto thyroiditis identification method based on deep neural network
  • Ultrasonic image hashimoto thyroiditis identification method based on deep neural network
  • Ultrasonic image hashimoto thyroiditis identification method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0038] Please refer to figure 1 , figure 2 with image 3 ,in, figure 1 Segmentation network structure diagram used for the present invention; figure 2 It is a schematic diagram of a separable convolution block in the present invention; image 3 It is a schematic diagram of the structure of the classification model in the present invention.

[0039] The method for identifying Hashimoto's thyroiditis in ultrasound images based on deep neural networks includes: a. using the thyroid ultrasound image data set with label information to train the relevant CNN model;

[0040] b. Using the segmentation model to segment the thyroid region from the original thyroid ultrasound image;

[0041] c. Then input to the classification model to obtain the final classification label of Hashimoto's thyroiditis.

[0042] Need to explain: the structure of the classifi...

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 provides an ultrasonic image hashimoto thyroiditis recognition method based on a deep neural network, and relates to the technical field of thyroiditis recognition. The ultrasonic imagehashimoto thyroiditis recognition method based on the deep neural network comprises the following steps: a, training a related CNN model by utilizing a thyroid ultrasonic image data set with annotation information; b, segmenting a thyroid region from the original thyroid ultrasound image by using a segmentation model; and c, inputting into the classification model to obtain a final hashimoto thyroiditis classification label. The ultrasonic image hashimoto thyroiditis recognition method based on the deep neural network has the advantages of being high in accuracy and good in generalization performance.

Description

technical field [0001] The invention relates to the technical field of thyroiditis identification, in particular to a method for identifying Hashimoto's thyroiditis in ultrasonic images based on a deep neural network. Background technique [0002] Hashimoto's thyroiditis is the most common type of thyroiditis, an autoimmune disease, because it was first discovered and reported by Japanese surgeon Hashimoto Takumi in 1912, also known as Hashimoto's disease or chronic lymphocytic thyroiditis, It is manifested by the appearance of characteristic inflammatory changes in the thyroid gland. According to statistics, the global incidence of Hashimoto's thyroiditis is 0.3-1.5 / 1000 per year, and it shows a growing trend. [0003] Hashimoto's thyroiditis occurs more frequently in middle-aged people, and the number of female patients is significantly more than that of male patients, with a ratio of about 20:1. The symptoms of Hashimoto's thyroiditis are hidden and almost asymptomatic ...

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): G06T7/00G06T7/11G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/084G06T2207/20081G06T2207/20084G06T2207/30004G06N3/045G06F18/24
Inventor 康清波赵婉君王宇石一磊朱精强
Owner 脉得智能科技(无锡)有限公司
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