Assisted identification and positive feedback system for digestive tract lesions based on cloud platform

A technology for lesion identification and digestive tract, applied in image analysis, image enhancement, instruments, etc., can solve the problems of difficulty in data sharing, low data identification accuracy, missed diagnosis and misdiagnosis, etc. The effect of detection rate

Active Publication Date: 2021-02-05
SHANDONG UNIV QILU HOSPITAL +1
View PDF17 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, the analysis and recognition of digestive tract images is often achieved through the doctor's naked eye observation and manual marking of the lesion location. However, since the models and products recognized by artificial intelligence are distributed in multiple departments of many hospitals, the daily The number of digestive endoscopic images is huge, and the data is private data. At the same time, the data needs to be collected in a unified location, which makes data sharing difficult, and the accuracy of data identification is low, which easily leads to missed and misdiagnosed

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
  • Assisted identification and positive feedback system for digestive tract lesions based on cloud platform
  • Assisted identification and positive feedback system for digestive tract lesions based on cloud platform
  • Assisted identification and positive feedback system for digestive tract lesions based on cloud platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] In one or more embodiments, the embodiment of the present invention provides a cloud platform-based auxiliary identification and positive feedback system for gastrointestinal lesions, including:

[0034] (1) The data collection device is configured to collect the image of the digestive tract to be identified and transmit it to the cloud platform;

[0035] Specifically, the doctor collects the image of the digestive tract to be identified through the graphics and text workstation. The graphic workstation is the software for recording the inspection process, and collects the images of the endoscope through the video acquisition card;

[0036] The graphic workstation calls the Web API interface of the cloud platform through the computer network, and submits the digestive tract image to the cloud platform.

[0037] (2) The cloud platform is configured to establish an inference model, construct a training set to optimize the training of the inference model; use the inferenc...

Embodiment 2

[0082] In one or more embodiments, a terminal device is disclosed, which includes a processor and a computer-readable storage medium, the processor is used to implement instructions; the computer-readable storage medium is used to store multiple instructions, refer to figure 2 , the instructions are adapted to be loaded by the processor and perform the following process:

[0083] Collect images of the digestive tract to be identified and send them to the cloud platform;

[0084] The cloud platform establishes an inference model, constructs a training set, and performs optimized training on the inference model; uses the inference model to infer gastrointestinal lesions from the received images, and saves the images and the identification results of gastrointestinal lesions respectively;

[0085] The doctor client can view the inference results online, and mark and correct the inference results;

[0086] Add the error-corrected images to the training set and retrain the infere...

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 system for auxiliary identification and positive feedback of digestive tract lesions based on a cloud platform, comprising: a data collection device configured to collect images of the digestive tract to be identified and transmit them to the cloud platform; Inferring the model, constructing a training set to optimize the training of the inference model; using the inference model to infer the position of the digestive tract and the type of focus on the received image, and saving the image and the identification result of the focus of the digestive tract respectively; online The error correction module is configured as a doctor client to view the inference results online, and mark and correct the inference results; the online optimization module is configured to add the error-corrected images to the training set and retrain the inference model . The invention can improve the accuracy of identifying lesions in the digestive tract and improve the detection rate of diseases in the digestive system.

Description

technical field [0001] The invention relates to the technical field of cloud platform data processing, in particular to a cloud platform-based auxiliary identification and positive feedback system for digestive tract lesions. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Gastrointestinal diseases are usually judged by obtaining images of the digestive tract through gastrointestinal endoscopy, and then analyzing and identifying the images to determine whether there are lesions. [0004] At present, the analysis and recognition of digestive tract images is often achieved through the doctor's naked eye observation and manual marking of the lesion location. However, since the models and products recognized by artificial intelligence are distributed in multiple departments of many hospitals, the daily The number of digestive endoscopic image...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06N5/04
CPCG06N5/041G06T7/0012G06T2207/20081G06T2207/30096
Inventor 冯健李延青周如琛赖永航左秀丽杨晓云李真邵学军辛伟
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