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

Mobile terminal disease intelligent auxiliary diagnosis system based on deep learning

A deep learning and auxiliary diagnosis technology, applied in the field of mobile medicine, can solve the problems of low repeatability, high subjectivity of manual reading, time-consuming and labor-intensive knowledge and experience inheritance difficulties, etc., to improve efficiency and accuracy, and improve disease diagnosis. Precise results

Pending Publication Date: 2020-10-30
DONGGUAN UNIV OF TECH
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the use of AI to assist radiologists in diagnosis will meet the rigid needs of the market. Manual film reading has problems such as high subjectivity, low repeatability, insufficient quantification and information utilization, time-consuming and labor-intensive and difficult inheritance of knowledge and experience.

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
  • Mobile terminal disease intelligent auxiliary diagnosis system based on deep learning
  • Mobile terminal disease intelligent auxiliary diagnosis system based on deep learning
  • Mobile terminal disease intelligent auxiliary diagnosis system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] figure 1 , 2As shown, the system is used to distinguish between benign and malignant pulmonary nodules in CT images. First, collect DICOM images of the lungs with pathological results, analyze the DICOM images, and obtain the grayscale information of the file and the included image pixel information with a single template. The gray value of the image is normalized. At the same time, in order to prevent the phenomenon of network overfitting, it is necessary to increase the number of training images, randomly rotate, flip, distort, adjust the contrast, brightness and other enhancements and disturbance data preprocessing operations on the image; secondly , extract the two-dimensional features of pulmonary nodules under the multi-scale view from the underlying pixel-level information. According to the size of the image, the size of the convolution kernel and the depth of the network are reasonably selected. In order to enhance the performance of the model and reduce the num...

Embodiment 2

[0072] figure 1 , 2 As shown, the system is used for pathological analysis of CT images of lung tumors. First, collect DICOM images of lungs with pathological results, analyze the DICOM images of lungs, obtain file grayscale information with multiple templates, and select the lesion area to determine Image serial number, in order to reduce the phenomenon of network over-fitting, it is necessary to increase the number of training images, perform image rotation, mirroring, increase white noise and other enhancements and disturb data preprocessing operations; secondly, in order to solve the problem of training sample images due to human intervention. Few and deep learning models require a large number of contradictions between samples. A transfer learning (Transfer Learning) network model is proposed to extract features from training samples, and then encode them into low-dimensional feature vectors while retaining feature information as much as possible and greatly reduce the de...

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 a mobile terminal disease intelligent auxiliary diagnosis system based on deep learning. The system is provided with a mobile medical terminal and a mobile medical cloud server. The mobile medical terminal comprises a voice recognition module, a character input module and a mobile medical cloud server connection interface. The mobile medical cloud server comprises an imageprocessing module, a medical knowledge base and a knowledge reasoning module; and the knowledge reasoning module in the mobile medical cloud server receives a text chief statement, performs knowledgereasoning on the text chief statement by utilizing the medical knowledge base to obtain a disease diagnosis result and a judgment result, and feeds back the disease diagnosis result and the judgmentresult to the mobile medical terminal through the mobile medical cloud server connection interface. Diseases are input through the mobile medical terminal and transmitted to the mobile medical cloud server, a medical common sense, a clinical guideline and a medical knowledge base are established through the cloud storage technology and used for fuzzy matching, a patient is guided to supplement disease description according to the optimal judgment result, and therefore the efficiency and accuracy of disease diagnosis are improved.

Description

technical field [0001] The invention relates to the field of mobile medical technology, in particular to provide an intelligent diagnosis auxiliary system by using the mobile Internet. Background technique [0002] At present, "artificial intelligence + medical care" is developing rapidly. Medicine is a discipline that relies on inductive logic, empirical learning, and evidence-based application. Artificial intelligence can play an important role in this industry. At the same time, my country's medical resources are in short supply and the supply is seriously insufficient. The application of artificial intelligence in the medical industry can improve the work efficiency of doctors and improve the supply of medical resources in disguise. Driven by policies and algorithm dividends, "artificial intelligence + medical care" is developing rapidly. At present, the annual growth rate of medical imaging data in my country is about 30%, while the annual growth rate of the number of ...

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 Applications(China)
IPC IPC(8): G16H50/20G16H80/00G16H10/60G16H30/20G16H30/40G06K9/62G06F40/289
CPCG16H50/20G16H80/00G16H10/60G16H30/20G16H30/40G06F40/289G06F18/24155G06F18/24323
Inventor 梁经伦叶国良陈立甲吴佳鑫黄冠淋张木荣
Owner DONGGUAN UNIV OF TECH
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