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

Deep learning method for identifying oral squamous cell carcinoma based on visual features

A squamous cell carcinoma and visual feature technology, applied in the field of deep learning technology, can solve problems such as artificial intelligence models for identifying oral squamous cell carcinoma, achieve the effects of reducing the weight of loss values, improving quality of life, and simple methods

Active Publication Date: 2020-07-03
WUHAN UNIV
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So far, no artificial intelligence model for identifying OSCC from visual features has been reported

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
  • Deep learning method for identifying oral squamous cell carcinoma based on visual features
  • Deep learning method for identifying oral squamous cell carcinoma based on visual features
  • Deep learning method for identifying oral squamous cell carcinoma based on visual features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings.

[0047] Step 1. Obtain clear photos of oral squamous cell carcinoma lesions and normal oral photos, including: a development set for model training and parameter adjustment;

[0048] The test set is used for result evaluation.

[0049] The oral photos of patients with oral squamous cell carcinoma and healthy adults were taken with a digital SLR camera. Regardless of the camera brand, the shooting parameters were set as follows: manual mode, depth of field set to f value less than 1 / 18, and exposure time shorter than 1 / 80 Seconds, (converted into a 35mm format camera) macro lens between 100mm-105mm, the shooting camera is equipped with a ring macro flash (the brand is not limited), the flash is set to TTL mode, the camera’s white balance is set to the flash white balance, when taking photos Select the fixed central focus point to focus. Select the flash mode when the m...

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 deep learning method for identifying oral squamous cell carcinoma based on visual features. The method comprises the following steps: 1) establishing a development set and atest set; 2) constructing a data training sample; 3) training a target detection network model; 4) performing batch initial positioning on the oral photos of the development set through the target detection model, and constructing a classification network data sample by using the positioned photo area; 5) expanding classification network data samples; 6) the DenseNet is used as a backbone networkof the classification network, and the DenseNet is improved, so that the model is more concentrated in difficult samples of wrong classification; the oral squamous cell carcinoma detection method hasthe advantages that the oral squamous cell carcinoma can be detected from the oral photos by the aid of the oral squamous cell carcinoma detection method, the oral squamous cell carcinoma detection sensitivity is high, the oral squamous cell carcinoma detection specificity is good, and the oral squamous cell carcinoma detection method is suitable for detecting and screening various oral squamous cell carcinoma.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to the application of deep learning technology to the detection of specific visual feature regions in a certain type of photos. The deep learning neural network obtained from this training has good accuracy, precision and recall for the detection of oral squamous cell carcinoma in photos, and is suitable for the screening of patients with oral squamous cell carcinoma. [0002] technical background [0003] Oral cancer ranks among the top ten malignant tumors in the world. In 2018, there were 354,864 new cases of oral cancer predicted worldwide, and 177,384 deaths due to oral cancer. In terms of pathological classification, more than 90% of oral cancer patients are squamous cell carcinoma, and middle-aged and elderly men who are heavy smokers and alcoholics are high risk groups. Countries and regions where betel nut chewing is prevalent, such as India, Pakistan, Bangladesh, and...

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
IPC IPC(8): G06T7/00G06K9/32G06K9/62G06N3/04G06N3/08A61B5/00
CPCG06T7/0012G06N3/084A61B5/0088A61B5/4542A61B5/7267G06T2207/30096G06V10/25G06N3/045G06F18/214
Inventor 熊学鹏赵怡芳傅秋云李凯雄
Owner WUHAN 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