Gastric mucosa cleanliness evaluation method and system based on deep learning

A technology of deep learning and evaluation methods, applied in image data processing, instruments, calculations, etc., can solve the problems of increasing misdiagnosis, missed diagnosis, low quality of gastroscope preparation, poor cleanliness of gastric mucosa, etc.

Active Publication Date: 2020-05-08
SHANDONG UNIV QILU HOSPITAL +1
View PDF12 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to poor cleanliness of the gastric mucosa often occurs during gastroscopy, for example, gastroscopy shows that the stomach is filled with a large number of air bubbles, a large amount of mucus attached, a large amount of regurgitated bile plaques attached, and food retention, etc., resulting in low quality of gastroscopy preparation and affecting gastric The detection, diagnosis and treatment...

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
  • Gastric mucosa cleanliness evaluation method and system based on deep learning
  • Gastric mucosa cleanliness evaluation method and system based on deep learning
  • Gastric mucosa cleanliness evaluation method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 As shown, this embodiment discloses a method for evaluating the cleanliness of gastric mucosa based on deep learning, comprising the following steps:

[0049] Step 1: Construct the evaluation model of gastric mucosal cleanliness. The step 1 specifically includes:

[0050] Step 1.1: Obtain the gastroscope training image set.

[0051] Such as figure 2 As shown, the patient’s gastroscope is projected to the UI interface of the gastric mucosa cleanliness evaluation system by using a video capture card to obtain the frame rate and resolution of the video source of the gastroscope, and based on the video capture card development interface, real-time acquisition of a single frame image or per minute Collect n frames (5-10 frames are recommended).

[0052] Step 1.2: Establish an evaluation system for gastric mucosal cleanliness.

[0053] As an implementation, the grades and scores in the gastric mucosal cleanliness evaluation system are all formulated by ...

Embodiment approach

[0072] As an implementation, the gastric mucosa cleanliness evaluation model construction method includes:

[0073] Based on the same training set, verification set, and test set, AlexNet, SqueezeNet, MobileNet V1-V3, ShuffleNetV1-V2, and Xception deep convolutional networks were trained simultaneously, and group convolution was used in the network (group convolution in AlexNet, not only Optimize the speed of model training, and improve the diversity of features extracted by convolution), depth separable convolution (MobileNet V1-V2, depth separable convolution is used in Xception, while reducing the amount of training parameters, Increased inference speed), residual block (MobileNet V2, residual block is used in Xception, which avoids gradient explosion and enhances multi-level feature extraction), NAS (MobileNet V3 uses NAS to select the network independently) The optimal network structure ensures the prediction accuracy while reducing the size of the model), File Module (in...

Embodiment 2

[0087] The purpose of this embodiment is to provide a gastric mucosa cleanliness evaluation system based on deep learning.

[0088] In order to achieve the above purpose, this embodiment provides a gastric mucosa cleanliness evaluation system based on deep learning, including:

[0089] The training data set acquisition module obtains the gastroscope training image set;

[0090] The scoring and labeling module marks and scores each training image according to the preset gastroscope cleanliness evaluation system;

[0091] The evaluation model building block uses the training image set to train the gastric mucosa cleanliness evaluation model based on the deep learning network;

[0092] Real-time data acquisition module, real-time acquisition of gastroscope video frames;

[0093] The cleanliness evaluation module is based on the pre-built gastric mucosal cleanliness evaluation model, and performs cleanliness evaluation frame by frame.

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 gastric mucosa cleanliness evaluation method and system based on deep learning. The method comprises the following steps: acquiring a gastroscope video frame in real time; performing cleanliness evaluation frame by frame based on a pre-constructed gastric mucosa cleanliness evaluation model; wherein a method for creating the gastric mucosa cleanliness evaluation model comprises the following steps of acquiring a gastroscope training image set; marking and scoring each training image according to a preset gastroscope cleanliness evaluation system; and training the gastric mucosa cleanliness evaluation model based on a deep learning network by adopting the training image set. The gastric mucosa cleanliness can be accurately evaluated, and a positive effect is achieved for diagnosis of gastric diseases and preparation and quality control before endoscopy.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method and system for evaluating the cleanliness of gastric mucosa based on deep learning. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Due to poor cleanliness of the gastric mucosa often occurs during gastroscopy, for example, gastroscopy shows that the stomach is filled with a large number of air bubbles, a large amount of mucus attached, a large amount of regurgitated bile plaques attached, and food retention, etc., resulting in low quality of gastroscopy preparation and affecting gastric The detection, diagnosis and treatment of mucosal lesions increase the possibility of misdiagnosis and missed diagnosis, thus affecting the effectiveness of gastroscopy. [0004] Existing gastroscope image evaluation mainl...

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): G06T7/00
CPCG06T7/0012G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30092
Inventor 左秀丽冯建李延青李广超邵学军李真杨晓云季锐赖永航
Owner SHANDONG UNIV QILU HOSPITAL
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