CN107977958A - A kind of image diagnosing method and device - Google Patents
A kind of image diagnosing method and device Download PDFInfo
- Publication number
- CN107977958A CN107977958A CN201711164256.6A CN201711164256A CN107977958A CN 107977958 A CN107977958 A CN 107977958A CN 201711164256 A CN201711164256 A CN 201711164256A CN 107977958 A CN107977958 A CN 107977958A
- Authority
- CN
- China
- Prior art keywords
- image
- feature
- disease location
- described image
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4854—Diagnosis based on concepts of traditional oriental medicine
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
Abstract
The invention discloses a kind of image diagnosing method and device.It is related to intelligent measure technology；Solve the problems, such as that prior art detection means can not handle complex application context.This method includes：Gather disease location image；The image collected is pre-processed, extracts the feature of described image；According to the feature, with reference to user information file, judge and the matched histological type of described image.Technical solution provided by the invention is suitable for automated diagnostic detection device, realizes the intelligent diagnostics based on image procossing.
Description
Technical field
The present invention relates to intelligent measure technology, espespecially a kind of image diagnosing method and device.
Background technology
Inferior health is very universal in modern society, only has 5% according to statistics, in population in the world and meets the United Nations and defends
The health standards that raw tissue (WHO) is promulgated, 20% is in morbid state, and remaining 75% puzzlement for all suffering from inferior health.So
And inferior health does not have significant clinical symptoms, therefore it is difficult to be discovered by individual, while also is difficult to be detected by routine inspection
Come.
In theory of traditional Chinese medical science, inferior health is defined as health and the intermediateness in disease.Theory of traditional Chinese medical science thinks, health
The quality of state can emerge from the external feature of human body, therefore can use the four methods of diagnosis (four methods of diagnosis) diagnosis to people
Body is detected.However, the four methods of diagnosis are at the same time there is also great subjectivity, due to doctor, can not to obtain patient by the four methods of diagnosis each
The comprehensive information of aspect, the diagnosis based on local message often have uncertain and unstability.
As inferior health is paid attention to be subject to more and more people, become using computer technology to carry out the research for the use of inferior health
It must become more and more popular, but not remove to solve the related article of inferior health problem still not using image technique or other multimedia technologies
It is more.The achievement of overwhelming majority inferior health context of detection is depended in sensor technology and blood testing at present, it is impossible to covers diagnosis
During existing a variety of symptom forms (such as visual signature), so as to have impact on practical application.
The content of the invention
In order to solve the above technical problem, the present invention provides a kind of image diagnosing method and device.Based on artificial intelligence
Technology, using deep learning neutral net, artificial intelligence technology is introduced into such as TCM tongue diagnosis diagnosis practice, by disease
Station diagram picture is pre-processed, feature extraction, diagnosis and etc., complicated applications can not be handled by solving prior art detection means
The problem of scene, the image information for maximally utilising artificial intelligence technology and collecting improve diagnostic accuracy, contract significantly
Short Diagnostic Time.
In order to reach the object of the invention, the present invention provides a kind of image diagnosing method, including：
Gather disease location image；
The image collected is pre-processed, extracts the feature of described image；
According to the feature, with reference to user information file, judge and the matched histological type of described image.
Preferably, the pretreatment carried out to the image collected includes at least any one of following processing mode or appoints
Anticipate multinomial：
Denoising, enhancing, size adjustment, brightness adjustment, contrast normalization, image are ajusted, disease location detection and localization.
Preferably, the step of gathering disease location image includes：
Shoot disease location image；
The environmental information shot according to described image, the image that shooting obtains standard color gamut figure is compared, is collected
The image at the stem position of standardization.
Present invention also offers a kind of image diagnosing system, including：
Image capture module, for gathering disease location image；
Characteristic extracting module, for being pre-processed to the image collected, extracts the feature of described image；
Matching module is diagnosed, for according to the feature, with reference to user information file, judging and the matched disease of described image
Manage type.
Preferably, the characteristic extracting module, specifically for using any one of following processing mode or any multinomial
The image collected is pre-processed：
Denoising, enhancing, size adjustment, brightness adjustment, contrast normalization, image are ajusted, disease location detection and localization.
Preferably, described image acquisition module includes：
Camera unit, for shooting disease location image；
Image generation unit, for the environmental information shot according to described image, the image reference colour that shooting is obtained
Domain figure compares, and collects the image at the stem position of standardization.
The present invention provides a kind of image diagnosing method and device, disease location image is gathered, to the image collected
Pre-processed, extract the feature of described image, further according to the feature, with reference to user information file, judgement and described image
Matched histological type.The intelligent diagnostics based on image procossing are realized, solving prior art detection means can not be handled again
The problem of miscellaneous application scenarios.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by specification, rights
Specifically noted structure is realized and obtained in claim and attached drawing.
Brief description of the drawings
Attached drawing is used for providing further understanding technical solution of the present invention, and a part for constitution instruction, with this
The embodiment of application is used to explain technical scheme together, does not form the limitation to technical solution of the present invention.
Fig. 1 is a kind of flow diagram for image diagnosing method that the embodiment of the present invention two provides；
Fig. 2 is a kind of structure diagram for image diagnosing system that the embodiment of the present invention three provides；
Fig. 3 is the structure diagram of image capture module 201 in Fig. 2.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the case where there is no conflict, in the embodiment and embodiment in the application
Feature can mutually be combined.
Step shown in the flowchart of the accompanying drawings can be in the computer system of such as a group of computer-executable instructions
Perform.Also, although logical order is shown in flow charts, in some cases, can be with suitable different from herein
Sequence performs shown or described step.
As inferior health is paid attention to be subject to more and more people, become using computer technology to carry out the research for the use of inferior health
It must become more and more popular, but not remove to solve the related article of inferior health problem still not using image technique or other multimedia technologies
It is more.The achievement of overwhelming majority inferior health context of detection is depended in sensor technology and blood testing at present, it is impossible to covers diagnosis
During existing a variety of symptom forms (such as visual signature), so as to have impact on practical application.
To solve the above-mentioned problems, the embodiment provides a kind of image diagnosing method and device.Using depth
Learning neural network, the characteristics of making full use of artificial intelligence technology accuracy rate high, realizes that whole system efficiency is substantially improved, and solves
It is current to lack the problem of automatic technology means of (such as lingual diagnosis) are diagnosed by visual signature.
The embodiment of the present invention one is illustrated first.
The present invention provides a kind of image diagnosing system, including：
Image capturing system, is acquired the tongue image of patient；
Image preprocessing system, carries out the image collected in denoising, enhancing, size, brightness, contrast normalization, figure
As ajusting, the pretreatment such as tongue image detection；
The pathological characters in the tongue image of pretreatment are passed through in Feature Extraction System, extraction；
Diagnostic system, according to the feature extracted, with reference to the age of patient, gender, occupation, conventional medical history, family's medical history
Etc. other information, diagnosed.
Below in conjunction with the accompanying drawings, the embodiment of the present invention two is illustrated.
An embodiment of the present invention provides a kind of image diagnosing method, uses flow such as Fig. 1 of this method completion diagnostic imaging
It is shown, including：
Step 101, collection disease location image；
Preferably, the image not shot in this step to imaging first-class capture apparatus directly uses, but herein
On the basis of gather disease location image, specifically, after disease location image shoot, the environment letter that is shot according to described image
Breath, the image that shooting obtains standard color gamut figure is compared, collects the image at the stem position of standardization.
Step 102, pre-process the image collected, extracts the feature of described image；
In this step, the pretreatment includes at least any one of following processing mode or any multinomial：
Denoising, enhancing, size adjustment, brightness adjustment, contrast normalization, image are ajusted, disease location detection and localization.
Step 103, according to the feature, with reference to user information file, judge and the matched histological type of described image；
In this step, with reference to the feature of image, according to patient age, gender, occupation, conventional medical history, family's medical history etc. its
His information, realizes pathological diagnosis.
Below in conjunction with the accompanying drawings, the embodiment of the present invention three is illustrated.
An embodiment of the present invention provides a kind of image diagnosing system, the structure of the device as shown in Fig. 2, including：
Image capture module 201, for gathering disease location image；
Characteristic extracting module 202, for being pre-processed to the image collected, extracts the feature of described image；
Matching module 203 is diagnosed, for according to the feature, with reference to user information file, judgement to be matched with described image
Histological type.
Preferably, the characteristic extracting module 202, specifically for using any one of following processing mode or any more
Item pre-processes the image collected：
Denoising, enhancing, size adjustment, brightness adjustment, contrast normalization, image are ajusted, disease location detection and localization.
Preferably, described image acquisition module 201 structure as shown in figure 3, including：
Camera unit 2011, for shooting disease location image；
Image generation unit 2012, for the environmental information shot according to described image, the image that shooting is obtained is marked
Quasi- gamut map compares, and collects the image at the stem position of standardization.
The embodiment provides a kind of image diagnosing method and device, disease location image is gathered, to gathering
To image pre-processed, extract the feature of described image, further according to the feature, with reference to user information file, judge with
The matched histological type of described image.Realize the intelligent diagnostics based on image procossing, solve prior art detection means without
Method handles the problem of complex application context.
By medical image acquisition device, the face-image of patient is saved as into digital information.According to image capture environment
Illumination, background, and the information such as colour gamut of collecting device, the image of collection standard color gamut figure is compared, is reduced due to collection
Image fault caused by environmental difference, improves the standardization level of image information.For the image collected, by denoising,
Enhancing, size, brightness, contrast normalization, image are ajusted, and the pretreatment such as tongue image detection, highlights feature of image, strengthen
The expression ability of image, good basis is laid for subsequent extracted characteristics of image.To the image after pretreatment, carried using feature
Algorithm is taken, extracts the feature of global criteria, improves the standardization level of feature.
Although disclosed herein embodiment as above, the content be only readily appreciate the present invention and use
Embodiment, is not limited to the present invention.Technical staff in any fields of the present invention, is taken off not departing from the present invention
On the premise of the spirit and scope of dew, any modification and change, but the present invention can be carried out in the form and details of implementation
Scope of patent protection, still should be subject to the scope of the claims as defined in the appended claims.
Claims (6)
- A kind of 1. image diagnosing method, it is characterised in that including：Gather disease location image；The image collected is pre-processed, extracts the feature of described image；According to the feature, with reference to user information file, judge and the matched histological type of described image.
- 2. image diagnosing method according to claim 1, it is characterised in that the pretreatment carried out to the image collected Including at least any one of following processing mode or any multinomial：Denoising, enhancing, size adjustment, brightness adjustment, contrast normalization, image are ajusted, disease location detection and localization.
- 3. image diagnosing method according to claim 1, it is characterised in that the step of gathering disease location image includes：Shoot disease location image；The environmental information shot according to described image, the image that shooting obtains standard color gamut figure is compared, collects standard The image at the stem position of change.
- A kind of 4. image diagnosing system, it is characterised in that including：Image capture module, for gathering disease location image；Characteristic extracting module, for being pre-processed to the image collected, extracts the feature of described image；Matching module is diagnosed, for according to the feature, with reference to user information file, judging and the matched pathology class of described image Type.
- 5. image diagnosing system according to claim 4, it is characterised in that the characteristic extracting module, specifically for making Pre-processed with any one of following processing mode or any multinomial image to collecting：Denoising, enhancing, size adjustment, brightness adjustment, contrast normalization, image are ajusted, disease location detection and localization.
- 6. image diagnosing system according to claim 1, it is characterised in that described image acquisition module includes：Camera unit, for shooting disease location image；Image generation unit, for the environmental information shot according to described image, the image standard color gamut figure that shooting is obtained Compare, collect the image at the stem position of standardization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711164256.6A CN107977958A (en) | 2017-11-21 | 2017-11-21 | A kind of image diagnosing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711164256.6A CN107977958A (en) | 2017-11-21 | 2017-11-21 | A kind of image diagnosing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107977958A true CN107977958A (en) | 2018-05-01 |
Family
ID=62010629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711164256.6A Pending CN107977958A (en) | 2017-11-21 | 2017-11-21 | A kind of image diagnosing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107977958A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109259732A (en) * | 2018-10-09 | 2019-01-25 | 广东数相智能科技有限公司 | A kind of identification model construction method and the illness method for early warning based on lingual diagnosis |
| CN109659037A (en) * | 2018-12-29 | 2019-04-19 | 大连君煜信息技术有限公司 | The recommended method and device of regimen |
| CN112908472A (en) * | 2021-03-16 | 2021-06-04 | 南通市第一人民医院 | Chronic ulcer infection risk assessment method and system |
| WO2021203517A1 (en) * | 2020-04-10 | 2021-10-14 | 广州永士达医疗科技有限责任公司 | Oct device and apparatus for detecting spell of sickness of asthma patient, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830380A (en) * | 2006-04-20 | 2006-09-13 | 上海交通大学 | Tongue picture anulgis and diagnosis system of traditional Chinese medicine |
| CN1914617A (en) * | 2004-02-03 | 2007-02-14 | 美国西门子医疗解决公司 | Systems and methods for automated diagnosis and decision support for heart related diseases and conditions |
| US20080139966A1 (en) * | 2006-12-07 | 2008-06-12 | The Hong Kong Polytechnic University | Automatic tongue diagnosis based on chromatic and textural features classification using bayesian belief networks |
| CN105877709A (en) * | 2016-04-07 | 2016-08-24 | 新绎健康科技有限公司 | Health condition data acquisition device, health condition data acquisition analysis system and method |
| CN106725310A (en) * | 2016-11-29 | 2017-05-31 | 深圳市易特科信息技术有限公司 | Evolution of Tongue Inspection of TCM image processing system and method |
| CN106897573A (en) * | 2016-08-01 | 2017-06-27 | 12西格玛控股有限公司 | Use the computer-aided diagnosis system for medical image of depth convolutional neural networks |
-
2017
- 2017-11-21 CN CN201711164256.6A patent/CN107977958A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1914617A (en) * | 2004-02-03 | 2007-02-14 | 美国西门子医疗解决公司 | Systems and methods for automated diagnosis and decision support for heart related diseases and conditions |
| CN1830380A (en) * | 2006-04-20 | 2006-09-13 | 上海交通大学 | Tongue picture anulgis and diagnosis system of traditional Chinese medicine |
| US20080139966A1 (en) * | 2006-12-07 | 2008-06-12 | The Hong Kong Polytechnic University | Automatic tongue diagnosis based on chromatic and textural features classification using bayesian belief networks |
| CN105877709A (en) * | 2016-04-07 | 2016-08-24 | 新绎健康科技有限公司 | Health condition data acquisition device, health condition data acquisition analysis system and method |
| CN106897573A (en) * | 2016-08-01 | 2017-06-27 | 12西格玛控股有限公司 | Use the computer-aided diagnosis system for medical image of depth convolutional neural networks |
| CN106725310A (en) * | 2016-11-29 | 2017-05-31 | 深圳市易特科信息技术有限公司 | Evolution of Tongue Inspection of TCM image processing system and method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109259732A (en) * | 2018-10-09 | 2019-01-25 | 广东数相智能科技有限公司 | A kind of identification model construction method and the illness method for early warning based on lingual diagnosis |
| CN109659037A (en) * | 2018-12-29 | 2019-04-19 | 大连君煜信息技术有限公司 | The recommended method and device of regimen |
| WO2021203517A1 (en) * | 2020-04-10 | 2021-10-14 | 广州永士达医疗科技有限责任公司 | Oct device and apparatus for detecting spell of sickness of asthma patient, and storage medium |
| CN112908472A (en) * | 2021-03-16 | 2021-06-04 | 南通市第一人民医院 | Chronic ulcer infection risk assessment method and system |
| CN112908472B (en) * | 2021-03-16 | 2021-10-08 | 南通市第一人民医院 | Chronic ulcer infection risk assessment method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977958A (en) | A kind of image diagnosing method and device | |
| CN113011485B (en) | Multi-mode multi-disease long-tail distribution ophthalmic disease classification model training method and device | |
| CN109543526B (en) | True and false facial paralysis recognition system based on depth difference characteristics | |
| KR100506085B1 (en) | Apparatus for processing tongue image and health care service apparatus using tongue image | |
| CN110009623A (en) | A kind of image recognition model training and image-recognizing method, apparatus and system | |
| CN106056588A (en) | Capsule endoscope image data redundancy removing method | |
| CN108553081B (en) | Diagnosis system based on tongue fur image | |
| CN111310851A (en) | Artificial intelligence ultrasonic auxiliary system and application thereof | |
| CN106102554A (en) | Image processing apparatus, image processing method and image processing program | |
| CN108670285A (en) | A kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system | |
| CN109411084A (en) | A kind of intestinal tuberculosis assistant diagnosis system and method based on deep learning | |
| CN109615633A (en) | Crohn disease assistant diagnosis system and method under a kind of colonoscopy based on deep learning | |
| CN103975364B (en) | Selection of images for optical examination of the cervix | |
| WO2019098415A1 (en) | Method for determining whether subject has developed cervical cancer, and device using same | |
| CN109508755B (en) | Psychological assessment method based on image cognition | |
| CN112151167A (en) | Intelligent screening method for six-age dental caries of children based on deep learning | |
| CN109241963A (en) | Blutpunkte intelligent identification Method in capsule gastroscope image based on Adaboost machine learning | |
| CN108717872A (en) | Health analysis method and system based on face, hard recognition and big data | |
| CN103735247B (en) | For the palm colour analysis method of health status identification | |
| CN111353326A (en) | In-vivo detection method based on multispectral face difference image | |
| WO2020179950A1 (en) | Deep learning-based method and device for prediction of progression of brain disease | |
| CN109978873A (en) | A kind of intelligent physical examination system and method based on Chinese medicine image big data | |
| Zhang et al. | Computer identification and quantification of fissured tongue diagnosis | |
| CN109949272A (en) | Identify the collecting method and system of skin disease type acquisition human skin picture | |
| Akimov et al. | Methods of COVID-19 Diagnosis Accuracy Improving by Human Head Micromovement Video Processing Using Vibraimage Technology and Artificial Intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180501 |
|
| RJ01 | Rejection of invention patent application after publication |