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

Enteroscopy quality inspection control system based on deep learning

A quality inspection and deep learning technology, applied in the field of medical image processing, can solve the problem of high image quality, achieve good accuracy and improve effectiveness

Active Publication Date: 2019-07-16
FUDAN UNIV
View PDF7 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above studies have high requirements on the quality of images for training and verification, relying on the data obtained from high-quality colonoscopy

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
  • Enteroscopy quality inspection control system based on deep learning
  • Enteroscopy quality inspection control system based on deep learning
  • Enteroscopy quality inspection control system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The embodiments of the present invention will be described in detail below, but the protection scope of the present invention is not limited to the examples.

[0028] use figure 2 network structure in . Among them, it includes 5 convolutional layers, 3 pooling layers, and 3 fully connected layers; in order: convolutional layer 1, convolution kernel: 11×11×64, step size: 4, activation function: RELU;

[0029] Pooling layer 1, window size: 3×3, step size: 2;

[0030] Convolution layer 2, convolution kernel: 5×5×256, step size: 1, activation function: RELU;

[0031] Pooling layer 2, window size: 3×3, step size: 2;

[0032] Convolution layer 3, convolution kernel: 3×3×256, step size: 1, activation function: RELU;

[0033] Convolution layer 4, convolution kernel: 3×3×256, step size: 1, activation function: RELU;

[0034] Convolution layer 5, convolution kernel: 3×3×256, step size: 1, activation function: RELU;

[0035] Pooling layer 3, window size: 3×3, step size: 2; ...

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 belongs to the technical field of medical image processing, and particularly relates to an enteroscopy quality inspection control system based on deep learning. The system comprises an ileocecal valve recognition model used for classifying images according to ileocecal valves and non-ileocecal valves; an intestinal tract quality scoring model used for classifying the images accordingto Boston Bowel Preparation Scale (BBPS) (0-3); wherein the two models are obtained by taking enteroscopy images and tags, namely ileocecal valve tags or scores, as input through an image classification convolutional neural network and carrying out end-to-end training. And the intestinal tract preparation quality is scored by identifying the ileocecal valve and according to the BBPS, and the enteroscopy quality is evaluated. Experimental results show that the enteroscopy quality control system has good specificity and sensitivity when being used for enteroscopy quality control, and can assistendoscopic physicians in clinical examination and improve the enteroscopy quality.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and in particular relates to a colonoscope quality inspection control system. Background technique [0002] Colonoscopy is the gold standard for colorectal cancer screening[1]. Early detection of tumors and resection of precancerous lesions can reduce the risk of death from colorectal cancer[2]. The missed diagnosis of adenoma may lead to tumor progression and delay the timing of treatment. The detection rate of adenoma largely depends on the quality of bowel preparation, and the detection rate of adenoma in high-quality bowel preparation is 41% higher than that of low-quality bowel preparation [3]. Therefore, bowel preparation has become a key indicator for judging the quality control of colonoscopy [4]. There is also evidence that a low rate of cecal cannulation is associated with a high incidence of septal proximal colon cancer [5]. Therefore, as two important indicators fo...

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): G06K9/00G06K9/62G06N3/04G06T7/00
CPCG06T7/0002G06T2207/30028G06T2207/30168G06V40/10G06N3/045G06F18/24G06F18/214
Inventor 颜波钟芸诗牛雪静蔡世伦谭伟敏阿依木克地斯·亚力孔
Owner FUDAN 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