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

Color image caries recognition method based on deep learning

A deep learning and color image technology, applied in the fields of computer science and medicine, can solve problems such as low efficiency of human diagnosis, slow diagnosis speed, uneven distribution of medical resources, etc.

Active Publication Date: 2021-09-10
HUNAN UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that due to the rapid increase in the number of visits to the stomatology department, the uneven distribution of medical resources, and the slow diagnosis speed caused by the low efficiency of artificial diagnosis, a deep learning-based color Image caries recognition method

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
  • Color image caries recognition method based on deep learning
  • Color image caries recognition method based on deep learning
  • Color image caries recognition method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0023] Refer to attached figure 1 , a color image caries identification method based on deep learning proposed by the present invention is specifically implemented through the following steps:

[0024] Step S1, data sample collection: collect the real oral color images of patients in the hospital's stomatology department by taking pictures, and obtain a sample photo data set;

[0025] Step S2, data labeling: through the diagnosis and marking of the data set by a professional doctor, the specific location and type of caries are classified into five categories according to the severity of caries, namely slight visual changes in enamel, obvious visual changes in enamel, and no teeth Localized enamel destruction with exposed dentin, deep dentin shadows, and prominent cavities with exposed dentin. Use Colabeler to mark the caries area. E...

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 color image caries recognition method based on deep learning, and the method divides the recognition of decayed teeth into two stages, the first stage is target detection, in which a darknet deep neural network of a yolov3 target detection framework is used for training a marked real color image, and an obtained model can recognize a caries focus; in the second stage, the focus recognized in the previous stage is stored as a new image in a matting mode, the new image serves as new deep learning training data, a residual convolutional neural network se_resnet101 with an attention mechanism is used for conducting learning training on the matted rectangular focus area image, and the obtained model can recognize the caries type. Detection and classification are independent from each other in the two stages, so that the classification accuracy is improved.

Description

technical field [0001] The present invention relates to the fields of computer science and medicine, in particular to a color image caries identification method based on deep learning. Background technique [0002] Caries is one of the three major diseases of the oral cavity. People pay more and more attention to dental health, but lack of professional caries diagnosis knowledge, and due to uneven distribution of medical resources and low efficiency of artificial diagnosis, many patients do not receive corresponding treatment. diagnosis and treatment. Therefore, there is a need for an easy-to-use and effective caries identification and diagnosis technology for caries prevention and rapid screening. [0003] Dentists can identify and diagnose dental caries based on the International Caries Detection and Assessment System (icdas) through naked eye observation. In the field of target detection, this WYSIWYG feature is very suitable for deep learning model training. The popula...

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): G06T7/00G06Q10/06G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06Q10/06393G06N3/08G06T2207/10024G06T2207/20081G06T2207/30036G06N3/045G06F18/241
Inventor 彭绍亮崔勇辉许钰涵刘浩
Owner HUNAN 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