Gastroscope image auxiliary processing system and method based on ensemble learning

An integrated learning and auxiliary processing technology, applied in medical images, computer-aided medical procedures, informatics, etc., can solve the requirements of clinical auxiliary diagnosis and treatment without considering the influence of training sets, sensitivity, specificity missed diagnosis rate, and misdiagnosis rate and other issues, so as to improve the level of diagnosis and treatment at the grassroots level, improve the quality of medical practice, and improve the overall performance

Active Publication Date: 2018-01-09
HEFEI UNIV OF TECH
View PDF13 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is that a single CNN classifier is often used in the existing gastroscope image-aided diagnosis system, and the influence of the training set on the results is not considered, resulting in the sensitivity, specificity, mi

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
  • Gastroscope image auxiliary processing system and method based on ensemble learning
  • Gastroscope image auxiliary processing system and method based on ensemble learning
  • Gastroscope image auxiliary processing system and method based on ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Embodiment 1, reference figure 1 , this embodiment proposes an integrated learning-based gastroscope image auxiliary processing system, including an image acquisition module, a data preprocessing module, a neural network training module, and an integrated learning module. The image acquisition module is used to collect gastroscope images, and the image data collected is transmitted to the data preprocessing module; the data preprocessing module includes a raw data preparation module and a training data preparation module, and the raw data preparation module is used to realize image data Arranging the training data, including screening and expanding the original image data, and setting different labels for the image data according to whether they are sick or not, so as to be further called in CNN; the training data preparation module further divides the sorted data into Training set, test set and verification set, and the proportion of training set, test set and verifica...

Embodiment 2

[0044] Embodiment 2, based on the system proposed in Embodiment 1, this embodiment proposes a method based on an auxiliary diagnostic processing system, refer to figure 2 ,include:

[0045] Step 201, image data acquisition: acquire gastroscope image data through electronic gastroscope;

[0046] Step 202, image data preprocessing:

[0047] Raw data preparation: filter and expand the collected image data, complete the sorting of image data to training data; filter out invalid data to avoid adverse effects of wrong knowledge on neural network training, and at the same time expand the data set to avoid overfitting The problem, and set different labels for the image according to the diseased and non-disease, to be further called in CNN;

[0048] Training data preparation: After the original data is classified, the network training cannot be performed directly. The prepared data needs to be further divided into training set, test set and verification set, and the proportion of th...

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 gastroscope image auxiliary processing system and method based on ensemble learning. The system includes an image acquisition module, a data preprocessing module, a neural network training module and an ensemble learning module, optimization of processes of screening, data classification and expansion of image data is realized through the data preprocessing module, the neural network training module realizes expansion of an adopted convolutional neural network model, and at the same time, a method for integrating different classifiers that are generated is provided through the ensemble learning module, aiming at obtaining a final decision classifier to improve overall performance of the classifier, thereby meeting requirements of clinical auxiliary diagnosis and treatment in four indexes of sensitivity, specificity, rate of missed diagnosis and misdiagnosis rate, and the method effectively improves recognition efficiency and accuracy, truly playing a role of assisting diagnosis and treatment.

Description

technical field [0001] The invention relates to the field of endoscope image recognition, in particular to a gastroscope image auxiliary processing system and method based on integrated learning. Background technique [0002] With the advancement of endoscopic technology, a variety of image diagnostic systems or methods have been developed in recent years. They are of great clinical significance as a method for screening tumors and diagnosing qualitative changes. Many doctors have performed gastrointestinal endoscopy. However, most diagnoses will be affected by the observer's sensibility and experience. Therefore, a quantitative evaluation of symptoms is needed as a "secondary diagnosis" to assist doctors in diagnosis. For example, the invention patent with the application publication number [CN105979847A] discloses an endoscopic image diagnosis auxiliary system to assist in identifying the pathological type in the identification object area in the endoscopic image; the inve...

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): G16H30/40G16H50/20G06K9/62
Inventor 丁帅杨善林孙晓王浩岳子杰潘金鑫
Owner HEFEI UNIV OF TECH
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