Disease auxiliary diagnosis method based on image identification

An auxiliary diagnosis and image recognition technology, applied in the computer field, can solve the problems of low prevalence, trouble doctors and patients, lack of experience in rare disease diagnosis and treatment, etc., and achieve the effect of saving time and easy operation

Inactive Publication Date: 2017-09-22
深圳美佳基因科技有限公司
View PDF0 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The vast majority of rare diseases are congenital, and the course of the disease develops slowly. Its prevalence rate is low, but patients are often life-threatening
[0003] At present, the way to diagnose rare diseases is to establish disease research and treatment centers. Such institutions have obvious regional characteristics, and patients’ conditions cannot be diagnosed in time. For most doctors, due to the lack of rare disease diagnosis and Treatment experience, greatly prol

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
  • Disease auxiliary diagnosis method based on image identification
  • Disease auxiliary diagnosis method based on image identification
  • Disease auxiliary diagnosis method based on image identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0049] see figure 1

[0050] A method for aided disease diagnosis based on image recognition, including:

[0051] Step 101: receiving the uploaded symptom image of the patient to be diagnosed;

[0052] The symptom image of the waiting patient uploaded by the user is a typical feature image or image set of the waiting patient. The symptom image of the waiting patient can be collected or stored by the user in the early stage, or it can be collected by the user directly using the mobile terminal device in real time. In the present invention, the definition requirement of the symptom image of the patient to be treated only needs to be able to distinguish the specific symptom of the patient to be diagnosed by the human eye, and there is no technical requirement for photography for the image collector, thus reducing the technical requirements for the user in photography Require.

[0053] Step 102: Utilize the convolutional neural network in the deep learning algorithm to analyze ...

Embodiment approach 2

[0061] see figure 2

[0062] A method for aided disease diagnosis based on image recognition, including:

[0063] Step 201: collect standard symptom images of diagnosed diseases, and build a training library.

[0064] The standard symptom images are clinical standard symptom images of diagnosed patients with various diseases, and the training images include the standard symptom image sets of each disease.

[0065] The convolutional neural network in the deep learning algorithm is used to analyze and extract the standard features of each standard symptom image of each disease in the training gallery to establish a standard feature set.

[0066] Step 202: Receive the uploaded symptom image of the patient to be diagnosed.

[0067] The symptom image of the waiting patient uploaded by the user is a typical feature image or image set of the waiting patient. The symptom image of the waiting patient can be collected or stored by the user in the early stage, or it can be collected ...

Embodiment approach 3

[0098] see image 3

[0099] Correspondingly, in order to solve the above technical problems, another technical solution adopted by the embodiment of the present invention is to provide an image recognition-based aided disease diagnosis device 30, including: an image receiving module 301, an image similarity acquisition module 302 and a probability determination Module 303.

[0100] An image receiving module 301, configured to receive uploaded symptom images of patients to be diagnosed;

[0101] Obtain image similarity module 302, for utilizing the deep learning algorithm to extract the waiting feature of the symptom image of the patient to be diagnosed, set up the waiting feature set, and combine the waiting feature set with the standard symptom image of each disease in the training gallery Compare the standard feature set to obtain the image similarity between the symptom image of the patient to be diagnosed and the standard symptom image of each disease;

[0102] The pro...

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 embodiment of the invention relates to the field of computers and discloses a disease auxiliary diagnosis method based on image identification. The method comprises the steps of receiving an uploaded symptom image of a to-be-diagnosed patient; extracting to-be-diagnosed characteristics of the symptom image of the to-be-diagnosed patient by use of a deep learning algorithm; establishing a to-be-diagnosed characteristics set; comparing the to-be-diagnosed characteristics set with a standard characteristics set of a standard symptom image of each disease in a training gallery to acquire an image similarity between the symptom image of the to-be-diagnosed patient and the standard symptom image of each disease, and determining the probability of the to-be-diagnosed patient who suffers from each disease according to the image similarity. Through the above-mentioned mode, the embodiment can rapidly associate the to-be-diagnosed patient with one or more diseases and saves a lot of time for further definite diagnosis.

Description

technical field [0001] The embodiments of the present invention relate to the field of computers, in particular to a method for aided disease diagnosis based on image recognition. Background technique [0002] Rare diseases are also called orphan diseases. The World Health Organization defines diseases or lesions that affect 0.065% to 0.1% of the population as rare diseases. The vast majority of rare diseases are congenital, and the course of the disease develops slowly. Its prevalence rate is low, but patients are often life-threatening. [0003] At present, the way to diagnose rare diseases is to establish disease research and treatment centers. Such institutions have obvious regional characteristics, and patients’ conditions cannot be diagnosed in time. For most doctors, due to the lack of rare disease diagnosis and Treatment experience greatly prolongs the time required for diagnosis. Doctors mainly diagnose the type of rare disease based on the patient's clinical mani...

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): G06F19/00
Inventor 柳青慕袁平李梦熊郑玉玲
Owner 深圳美佳基因科技有限公司
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