Thyroid nodule Tirads grading automatic identification model construction method and device

A technology for automatic identification of thyroid nodules, applied in neural learning methods, character and pattern recognition, biological neural network models, etc. Speed, improving generalization ability, the effect of good features

Pending Publication Date: 2021-05-07
北京小白世纪网络科技有限公司
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Judging from the current research status, the application of deep learning in thyroid ultrasound diagnosis is often limited to the automatic identification of benign and malignant, and the research on TI-RADS classification is still vacant, so that more detailed information cannot be given when assisting doctors in diagnosis. The information is not conducive to the judgment of doctors, so this study uses convolutional neural network to study the TI-RADS classification of thyroid

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
  • Thyroid nodule Tirads grading automatic identification model construction method and device
  • Thyroid nodule Tirads grading automatic identification model construction method and device
  • Thyroid nodule Tirads grading automatic identification model construction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] According to an embodiment of the present invention, a Tirads grading automatic identification model building device for thyroid nodules is provided, figure 2 It is a schematic diagram of the Tirads grading automatic identification model building device for thyroid nodules in the embodiment of the present invention, as figure 2 As shown, the thyroid nodule Tirads grading automatic identification model construction device according to the embodiment of the present invention specifically includes:

[0042] Data preprocessing module 20: for performing data preprocessing on thyroid ultrasound images; the data preprocessing module is specifically used for:

[0043] Perform grayscale processing on the thyroid ultrasound image, convert the image to grayscale and then perform normalization processing to complete the image feature processing;

[0044] Segmentation module 22: used to generate a segmentation mask as a training label by adopting ellipse fitting conversion to the...

Embodiment 2

[0052] The embodiment of the present invention provides a Tirads grading automatic identification model building device for thyroid nodules, such as image 3 As shown, it includes: a memory 30, a processor 32, and a computer program stored on the memory 30 and operable on the processor 32. When the computer program is executed by the processor 32, the following method steps are implemented:

[0053] S1. Perform data preprocessing on thyroid ultrasound images;

[0054] Specifically, in the original training data, since each ultrasound image is affected by various factors, the distribution range of the features is very different. When the difference between the test sample and the training sample is large, the model effect will be poor. Therefore, it is necessary to normalize the features of each ultrasound image to the same value interval to eliminate the correlation between different features. The characteristic processing method of ultrasound images; because this research is...

Embodiment 3

[0064] An embodiment of the present invention provides a computer-readable storage medium, where a program for realizing information transmission is stored on the computer-readable storage medium, and when the program is executed by the processor 32, the following method steps are implemented:

[0065] S1. Perform data preprocessing on thyroid ultrasound images;

[0066] Specifically, in the original training data, since each ultrasound image is affected by various factors, the distribution range of the features is very different. When the difference between the test sample and the training sample is large, the model effect will be poor. Therefore, it is necessary to normalize the features of each ultrasound image to the same value interval to eliminate the correlation between different features. The characteristic processing method of ultrasound images; because this research is based on the fact that most of the images generated by ultrasound instruments are grayscale, only a...

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 thyroid nodule Tirads grading automatic identification model construction method and device. The method comprises the following steps: S1, carrying out data preprocessing on a thyroid ultrasound image; s2, performing ellipse fitting conversion on the preprocessed thyroid ultrasound image to generate a segmentation mask as a training label; and S3, building a multi-task model based on a convolutional neural network, inputting the training label into the multi-task model, and performing training by adopting a preset loss function to obtain a trained thyroid nodule Tirads grading automatic identification model. According to the invention, in thyroid nodule TI-RADS grading automatic identification, the latest convolutional neural network framework is used for carrying out automatic identification tasks on thyroid ultrasound images in an end-to-end mode, TI-RADS grading is completed, detection work can be completed in the early stage of thyroid cancer, and therefore expensive work such as puncture does not need to be used; and a doctor is assisted to complete thyroid cancer screening.

Description

technical field [0001] The invention belongs to the field of computer artificial intelligence deep learning, and relates to image automatic recognition technology, in particular to a method and device for constructing a thyroid nodule Tirads classification automatic recognition model. Background technique [0002] The detection rate of thyroid nodules has increased significantly in the past two decades, and more nodules are now detected, showing a clear upward trend. Most nodules are benign or indolent. Accurate judgment of benign and malignant thyroid nodules can be analyzed by fine needle biopsy, and the risk of patients can be reduced by surgery, which can reduce significant healthcare costs. Workup for these incidental thyroid nodules usually includes ultrasonography. Radiologists have found several sonographic features of thyroid nodules suggestive of malignancy, including hypoechoicity, absence of halos, microcalcifications, solidity, intranodular blood flow, and aspe...

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): G06T7/00G06T7/11G06T7/62G06K9/62G06N3/08
CPCG06T7/0012G06T7/11G06T7/62G06N3/08G06T2207/10132G06T2207/20081G06T2207/20084G06T2207/30096G06F18/2431
Inventor 杜强黄丹郭雨晨聂方兴唐超张兴
Owner 北京小白世纪网络科技有限公司
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