Common colon disease classification method based on deep neural network and auxiliary system

A deep neural network and disease classification technology, applied in the field of common colon disease classification methods and auxiliary systems, can solve the problems of large subjective influencing factors, time-consuming and labor-intensive colonoscopy, high missed detection rate and false detection rate. Improve diagnostic efficiency, improve accuracy, reduce missed detection rate and false detection rate

Inactive Publication Date: 2021-04-02
SICHUAN UNIV
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are still many defects in the manual inspection method of colonoscopy in hospitals. For example, the judgment of lesion location and type depends entirely on the doctor's operation level, knowledge level and clinical experience, and the subjective influence factors are relatively large; at the same time, the inspection of ...

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
  • Common colon disease classification method based on deep neural network and auxiliary system
  • Common colon disease classification method based on deep neural network and auxiliary system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] This embodiment is a method for classifying common colon diseases based on a deep neural network, the flow chart of which is shown in figure 1 , wherein the method includes the following steps:

[0043] S1. Obtain the colonoscopy image data, and mark the name of the lesion contained in the image for the data sample. If there is no lesion in the image, mark it as normal; the lesion types included in this example include cancer, polyp and inflammation. If there is no lesion in the image , it is marked as normal.

[0044]S2. Divide the data samples of the same label into a data set, and divide each data set into a training set, a verification set and a test set, wherein the training set and the verification set are used for model training and saving model parameters respectively, and the test set is used for To verify the final model effect; when training a neural network, too small a training set sample size will cause the network to overfit and affect the training effec...

Embodiment 2

[0058] In this embodiment, on the basis of Embodiment 1, an auxiliary system for common colon diseases based on a deep neural network is proposed. This system is divided into two main modules: a model training module and an auxiliary diagnosis module. The model training modules include:

[0059] (1) The data acquisition module is used to acquire colonoscopy image data, and label the names of the lesions contained in the data sample images; in this example, the images without lesions are marked as normal, and the images with lesions include cancer, polyps , three types of inflammation.

[0060] (2) The model training module is used to train the corresponding colonoscopy image classification model based on data sets of different classification tasks; A lesion type classification model is trained on datasets of , polyps, and inflammation.

[0061] (3) Model identification module, used to input the corresponding classification model to the colonoscope image to be classified to o...

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 relates to the field of image recognition of computer vision and the field of artificial intelligence, and provides a common colon disease classification method based on a deep neural network and an auxiliary system, and the auxiliary system comprises a model training module and an auxiliary diagnosis module. The method comprises the steps of obtaining a multi-classification data setand a binary classification data set; training based on the binary classification data set to obtain a normal abnormal deep neural network classification model; training based on the multi-classification data set to obtain a lesion type deep neural network classification model; fusing the two models to obtain a deep neural network disease classification model of the colonoscope image, in the model, firstly inputting the image in the test set into a normal abnormal deep neural network classification model, if the image is judged to be normal, directly outputting a judgment result, and if the image is judged to be abnormal, inputting into a lesion type deep neural network classification model, further determining the lesion type, and outputting a judgment result.

Description

technical field [0001] The invention relates to the field of image recognition of computer vision and the field of artificial intelligence, in particular to a method for classifying common colonic diseases based on a deep neural network and an auxiliary system. Background technique [0002] Colon cancer is a common malignant tumor of the digestive tract, and its incidence rate ranks third among gastrointestinal tumors. In terms of clinical manifestations, colon cancer usually has no symptoms in the early stage, and symptoms will not appear until the middle and late stages. Colonoscopy is the most intuitive and effective way to find colon cancer. In addition to malignant tumor lesions, there are many types of lesions in the colon, such as inflammation and polyps. Most colon cancers are evolved from polyps. Therefore, in the process of colonoscopy, the timely and accurate detection of intestinal lesions and their correct classification will have an important impact on the ev...

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): G06K9/62G06N3/04G06N3/08G16H50/20
CPCG06N3/08G16H50/20G06V2201/03G06N3/045G06F18/25G06F18/241G06F18/214
Inventor 章毅胡兵吴雨刘伟周尧庞博袁湘蕾甘雨
Owner SICHUAN UNIV
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