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

Thyroid nodule grading identification system and method

A technology for thyroid nodules and identification methods, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve the problems of lack of interpretability for patients and radiologists, and achieve the effect of improving the consistency of interpretation

Pending Publication Date: 2022-02-18
SHANDONG UNIV QILU HOSPITAL
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, most of the computer-aided diagnosis systems for ultrasound images of thyroid nodules focus on the diagnosis of benign and malignant images, but the simple diagnosis of benign and malignant lacks certain interpretability for patients and radiologists

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 grading identification system and method
  • Thyroid nodule grading identification system and method
  • Thyroid nodule grading identification system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] A thyroid nodule grading identification system is provided in Embodiment 1, the system includes:

[0042] An acquisition module, configured to acquire an ultrasound image of the thyroid gland to be detected;

[0043] The extraction module is used to extract the image features of the thyroid ultrasound image;

[0044] The identification module is used to obtain the classification and identification results of thyroid nodules based on the extracted image features and using a pre-trained classification model;

[0045] The decision-making module is used to select and determine the generation mode of the thyroid nodule status description report according to the extracted image features;

[0046] The generating module is configured to generate a thyroid nodule status description report according to the determined generating mode.

[0047] Wherein, the decision-making module is composed of multiple fully-connected layer networks, and the last fully-connected layer uses an ac...

Embodiment 2

[0060] In Example 2, a model based on the fusion of a multi-task convolutional neural network and a template database is provided, which realizes the identification and classification of thyroid nodules and the evaluation of benign and malignant based on thyroid ultrasound images, and obtains an evaluation report.

[0061] Such as figure 1 As shown, the model mainly implements the diagnosis of benign and malignant thyroid nodules on ultrasound images, and at the same time generates a report for the ultrasound images. The model inputs a set of thyroid ultrasound images For each ultrasound image The benign and malignant diagnosis of the image corresponding to the model output Simultaneously output a coherent and smooth diagnostic report Among them, each section of ultrasonic diagnosis report consists of several words w t composition.

[0062] In this model, the report generation module consists of a generation model and a template database. In the generation model, a mu...

Embodiment 3

[0097] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the above-mentioned thyroid gland A section classification identification method, the method comprising:

[0098] Obtain an ultrasound image of the thyroid gland to be detected;

[0099] extracting image features of thyroid ultrasound images;

[0100] Based on the extracted image features, use the pre-trained classification model to obtain the classification and recognition results of thyroid nodules;

[0101] According to the extracted image features, select and determine the generation mode of the thyroid nodule status description report;

[0102] According to the determined generation mode, a thyroid nodule status description report is generated.

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 a thyroid nodule grading identification method and system, and belongs to the technical field of thyroid nodule detection. An acquisition module acquires a thyroid ultrasound image to be detected; the extraction module extracts image features of the thyroid ultrasound image; the identification module obtains a thyroid nodule grading identification result by using a pre-trained classification model based on the extracted image features; the decision-making module selects and determines a generation mode of a thyroid nodule condition description report according to the extracted image features; and the generation module generates a thyroid nodule condition description report according to the determined generation mode. The problems that in the prior art, ultrasonic result interpretation doctors are uneven in level, thyroid ultrasonic results are difficult to summarize, and consequently diagnosis results are inconsistent are solved, and the ultrasonic result interpretation consistency is improved; the thyroid ultrasound interpretation result is summarized, doctors are helped to judge whether a patient is subjected to observation follow-up visit, operative treatment or referral treatment, and the thyroid ultrasound interpretation method has important practical significance for primary clinic.

Description

technical field [0001] The invention relates to the technical field of thyroid nodule detection, in particular to a thyroid nodule grading recognition system and method for judging the classification of thyroid nodules and evaluating benign and malignant based on thyroid ultrasound images. Background technique [0002] Thyroid nodules refer to abnormal masses in thyroid nodules, which are very common in clinical practice. The rate of malignant thyroid nodules has been on the rise in recent years. At present, the two most commonly used diagnostic methods for distinguishing benign from malignant thyroid nodules are ultrasonography and fine needle aspiration biopsy (FNA). Among them, B-ultrasound technology is widely used in the clinical diagnosis of thyroid nodules because of its convenience, simplicity, quickness, and non-radiation characteristics. [0003] However, radiologists usually base their diagnosis on the ultrasound features of nodules on ultrasound images, which i...

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): G06V10/764G06V10/774G06V10/82G06K9/62G06N3/04G16H15/00
CPCG16H15/00G06N3/045G06F18/241G06F18/214
Inventor 陈丽侯新国刘磊梁凯郭星宏
Owner SHANDONG UNIV QILU HOSPITAL
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