CN110364256A - A kind of disease forecasting system and method for the blood-vessel image identification based on big data - Google Patents
A kind of disease forecasting system and method for the blood-vessel image identification based on big data Download PDFInfo
- Publication number
- CN110364256A CN110364256A CN201910542132.XA CN201910542132A CN110364256A CN 110364256 A CN110364256 A CN 110364256A CN 201910542132 A CN201910542132 A CN 201910542132A CN 110364256 A CN110364256 A CN 110364256A
- Authority
- CN
- China
- Prior art keywords
- blood
- vessel
- data
- image data
- vessel image
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
Abstract
The present invention relates to Internet technical field more particularly to the field of image recognition of artificial intelligence, and in particular to a kind of disease forecasting method, apparatus of the blood-vessel image identification based on big data.The disease forecasting method for the blood-vessel image identification based on big data that the invention discloses a kind of, this method may include: by the corresponding blood-vessel image data of acquisition unit acquisition target user, pass through image pre-processing unit blood-vessel image data according to pre-set image processing rule process and generate the corresponding blood vessel identification report of the target user, be compared numerical value standard figures corresponding at least one described blood vessel physical signs by described image analytical unit, and codomain corresponding to difference of the determining numerical value with the standard figures and etc..The present invention can be by big data technology to the disease forecasting of patient, so that medical worker further can judge the disease of patient based on prediction result, to improve the medical diagnosis on disease efficiency of medical worker.
Description
Technical field
The present invention relates to Internet technical field more particularly to the field of image recognition of artificial intelligence, and in particular to a kind of
Based on big data blood-vessel image identification disease forecasting system and applied to the blood-vessel image based on big data in the system
The disease forecasting method of identification.
Background technique
With the development of economy, user increasingly pays close attention to health, in particular, the people want to that itself is known in advance
Potential risk, and then prevention and treatment in advance is carried out to the potential disease.For example, this year comes, caused by cervical carcinoma
The number of casualties is more next more, and usual human patients just perceive the lesion of itself in the cervical carcinoma middle and later periods, so, just shortens
The treatment time of human patients thereby reduces a possibility that human patients cure, therefore, aobvious to the potential risk of itself
It obtains particularly important.In the prior art, the prediction of the potential risk of personnel be usually doctor according to its personal experience and
The inside and outside physiological characteristic of personnel judges, and the prediction result that this mode is formed relies on the ability of doctor itself very much, and this
The inefficiency that kind mode needs to spend a large amount of energy of doctor, and then diseases analysis is caused to be predicted.
Summary of the invention
The technical problem to be solved by the embodiment of the invention is that provide it is a kind of based on big data blood-vessel image identification
Disease forecasting method and device, for solving the problems, such as that medical worker predicts that the accuracy of potential risk is unstable.
In order to solve the above-mentioned technical problem, first aspect present invention disclose it is a kind of based on big data blood-vessel image identification
Disease forecasting method is applied in electronic device wherein, and the electronic device includes acquisition unit, image pre-processing unit, figure
As analytical unit, correspondingly, the disease forecasting method of the blood-vessel image identification based on big data includes:
The corresponding blood-vessel image data of target user are acquired by acquisition unit;
Pass through described in image pre-processing unit blood-vessel image data according to pre-set image processing rule process and generation
The corresponding blood vessel of target user identifies report, wherein the blood vessel identification report includes at least one blood vessel physical signs and institute
State at least one corresponding numerical value of blood vessel physical signs;
By described image analytical unit by numerical value criterion numeral corresponding at least one of described blood vessel physical signs
Value is compared, and determines codomain corresponding to the difference of the numerical value and the standard figures;
Judge whether the codomain is reasonable value field according to preset rules by described image analytical unit, if it is not, institute
It states image analyzing unit and at least one corresponding potential disease item of the target user is determined according to the disease collection of the codomain.
In some alternative embodiments, through image pre-processing unit according to pre-set image processing rule process
Blood-vessel image data simultaneously generate the corresponding blood vessel identification report of the target user, comprising:
According to the corresponding relationship of blood vessel physical signs and data area, by the blood-vessel image data be divided into it is described at least
The corresponding objective analysis data of one blood vessel physical signs;
The objective analysis data is analyzed according to according to preset data analysis rule, wherein preset data analysis rule packet
Include data discrete analysis, data linear analysis;
Determine that at least one of described blood vessel physical signs is corresponding described according to the analysis result of the objective analysis data
Numerical value;
The corresponding blood vessel identification report of the target user is exported according to default generation format.
In some alternative embodiments, the corresponding relationship according to blood vessel physical signs and data area, by institute
It states blood-vessel image data and is divided at least one of described corresponding objective analysis data of blood vessel physical signs, comprising:
Parted pattern is formed according to the corresponding relationship based on history blood vessel physical signs and data area, wherein described point
Cutting model includes at least one blood vessel physiological reference index and at least one described corresponding data field of blood vessel physiological reference index
Domain;
It is raw according to blood vessel physiological reference index at least one of described in the parted pattern and at least one of described blood vessel
The blood-vessel image data are divided at least one of described blood by the corresponding relationship between the corresponding data area of reason reference index
The corresponding objective analysis data of pipe physical signs.
In some alternative embodiments, described to join according to blood vessel physiology at least one of described in the parted pattern
Corresponding relationship between index and at least one of described corresponding data area of blood vessel physiological reference index is examined by the vessel graph
As data be divided into described at least one of before the corresponding objective analysis data of blood vessel physical signs, the method also includes:
Receive revision directive, wherein the revision directive is used to correct the parted pattern and the revision directive includes
At least one is for correcting repairing for the corresponding relationship between at least one of described corresponding data area of blood vessel physiological reference index
Positive parameter;
The parted pattern is corrected based on the corrected parameter.
In some alternative embodiments, the blood-vessel image data include the first blood-vessel image data and/or second
Blood-vessel image data.
In some alternative embodiments, described that the corresponding blood-vessel image number of target user is acquired by acquisition unit
According to, comprising:
Acquire the first blood-vessel image data corresponding in the daytime, and/or acquisition night corresponding second blood
Pipe image data;
And after the corresponding blood-vessel image data of the acquisition target user, described handled according to pre-set image is advised
Before then handling the blood-vessel image data and generating the corresponding blood vessel identification report of the target user, the method is also wrapped
It includes:
Photoplethysmogra is generated according to the first blood-vessel image data and/or the second blood-vessel image data
Data set.
In some alternative embodiments, according to the first blood-vessel image data and/or second vessel graph
Before generating photoplethysmogra data set as data, the method also includes:
The first blood-vessel image data and/or the second blood-vessel image data are filtered using filter, with
Filter out the noise in the first blood-vessel image data and/or the second blood-vessel image data.
In some alternative embodiments, at least one of described blood vessel physical signs include blood flowing speed, blood pressure,
Platelet content, the oxygen content of blood, erythrocyte color, content of hemoglobin.
Second aspect of the present invention discloses a kind of disease forecasting system, wherein the system includes:
It is stored with the memory of executable program code;
The processor coupled with the memory;
The processor calls the executable program code stored in the memory, executes such as first party of the present invention
The disease forecasting method of blood-vessel image identification described in face based on big data.
Third aspect present invention provides a kind of computer readable storage medium, stores in the computer readable storage medium
There is blood-vessel image recognizer, when the blood-vessel image recognizer is executed by processor, executes such as first aspect present invention base
In the disease forecasting method that the blood-vessel image of big data identifies.
Compared with prior art, the present invention has the following technical effect that
The present invention can lead to the blood-vessel image data of acquisition user, and then analyze blood-vessel image number using presupposition analysis method
According to, and then the potential risk of user is predicted based on the analysis results.In the present invention, due to using instrument to blood-vessel image number
According to being handled and analyzed, and then it can predict the potential risk of user, so as to reduce the workload of medical worker,
Improve the diagnosis speed of medical worker.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the process of the disease forecasting method of the disclosed blood-vessel image identification based on big data of the embodiment of the present invention one
Schematic diagram;
Fig. 2 is the structure of the disease forecasting system of the disclosed blood-vessel image identification based on big data of the embodiment of the present invention two
Schematic diagram;
Fig. 3 is the structure of the disease forecasting system of the disclosed blood-vessel image identification based on big data of the embodiment of the present invention three
Schematic diagram.
Specific embodiment
In order to better understand and implement, following will be combined with the drawings in the embodiments of the present invention, in the embodiment of the present invention
Technical solution be clearly and completely described, it is clear that the described embodiment is only a part of the embodiment of the present invention, without
It is whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall within the protection scope of the present invention.
Embodiment one
Referring to Fig. 1, Fig. 1 is the disease forecasting side of the blood-vessel image identification shown in the embodiment of the present invention based on big data
The flow diagram of method, wherein the disease forecasting method of the blood-vessel image identification based on big data is identified applied to blood-vessel image
Disease forecasting system in.As shown in Figure 1, the disease forecasting method that should be identified based on the blood-vessel image of big data may include step
It is rapid:
101, the corresponding blood-vessel image data of target user are acquired by acquisition unit.
102, by image pre-processing unit according to pre-set image handle rule process described in blood-vessel image data and generate
The corresponding blood vessel identification report of the target user, wherein the blood vessel identification report at least one of includes blood vessel physical signs
And at least one of described corresponding numerical value of blood vessel physical signs.
103, pass through described image analytical unit for numerical value mark corresponding at least one described blood vessel physical signs
Quasi- numerical value is compared, and determines codomain corresponding to the difference of the numerical value and the standard figures.
104, judge whether the codomain is reasonable value field according to preset rules by described image analytical unit, if not
It is that described image analytical unit determines at least one corresponding potential disease of the target user according to the disease collection of the codomain
?.
In some alternative embodiments, through image pre-processing unit according to pre-set image processing rule process
Blood-vessel image data simultaneously generate the corresponding blood vessel identification report of the target user, comprising:
According to the corresponding relationship of blood vessel physical signs and data area, by the blood-vessel image data be divided into it is described at least
The corresponding objective analysis data of one blood vessel physical signs;
The objective analysis data is analyzed according to according to preset data analysis rule, wherein preset data analysis rule packet
Include data discrete analysis, data linear analysis;
Determine that at least one of described blood vessel physical signs is corresponding described according to the analysis result of the objective analysis data
Numerical value;
The corresponding blood vessel identification report of the target user is exported according to default generation format.
In some alternative embodiments, the corresponding relationship according to blood vessel physical signs and data area, by institute
It states blood-vessel image data and is divided at least one of described corresponding objective analysis data of blood vessel physical signs, comprising:
Parted pattern is formed according to the corresponding relationship based on history blood vessel physical signs and data area, wherein described point
Cutting model includes at least one blood vessel physiological reference index and at least one described corresponding data field of blood vessel physiological reference index
Domain;
It is raw according to blood vessel physiological reference index at least one of described in the parted pattern and at least one of described blood vessel
The blood-vessel image data are divided at least one of described blood by the corresponding relationship between the corresponding data area of reason reference index
The corresponding objective analysis data of pipe physical signs.
In some alternative embodiments, corresponding with data area based on history blood vessel physical signs in the basis
Relationship is formed after parted pattern, described according to blood vessel physiological reference index and institute at least one of described in the parted pattern
The corresponding relationship stated between at least one corresponding data area of blood vessel physiological reference index divides the blood-vessel image data
Before at least one of described corresponding objective analysis data of blood vessel physical signs, the method also includes:
Receive revision directive, wherein the revision directive is used to correct the parted pattern and the revision directive includes
At least one is for correcting repairing for the corresponding relationship between at least one of described corresponding data area of blood vessel physiological reference index
Positive parameter;
The parted pattern is corrected based on the corrected parameter.
In some alternative embodiments, the blood-vessel image data include the first blood-vessel image data and/or second
Blood-vessel image data.
In some alternative embodiments, described that the corresponding blood-vessel image number of target user is acquired by acquisition unit
According to, comprising:
Acquire the first blood-vessel image data corresponding in the daytime, and/or acquisition night corresponding second blood
Pipe image data;
And after the corresponding blood-vessel image data of the acquisition target user, described handled according to pre-set image is advised
Before then handling the blood-vessel image data and generating the corresponding blood vessel identification report of the target user, the method is also wrapped
It includes:
Photoplethysmogra is generated according to the first blood-vessel image data and/or the second blood-vessel image data
Data set.
In some alternative embodiments, according to the first blood-vessel image data and/or second vessel graph
Before generating photoplethysmogra data set as data, the method also includes:
The first blood-vessel image data and/or the second blood-vessel image data are filtered using filter, with
Filter out the noise in the first blood-vessel image data and/or the second blood-vessel image data.
In some alternative embodiments, at least one of described blood vessel physical signs include blood flowing speed, blood pressure,
Platelet content, the oxygen content of blood, erythrocyte color, content of hemoglobin.
The present invention can lead to the blood-vessel image data of acquisition user, and then analyze blood-vessel image number using presupposition analysis method
According to, and then the potential risk of user is predicted based on the analysis results.In the present invention, due to using instrument to blood-vessel image number
According to being handled and analyzed, and then it can predict the potential risk of user, so as to reduce the workload of medical worker,
Improve the diagnosis speed of medical worker.
Embodiment two
Referring to Fig. 2, Fig. 2 is the disease forecasting system of the blood-vessel image identification shown in the embodiment of the present invention based on big data
The structural schematic diagram of system, as shown in Fig. 2, the system includes acquisition unit 201, image pre-processing unit 202, image analyzing unit
203, wherein
Acquisition unit 201, for the corresponding blood-vessel image data of acquisition unit acquisition target user;
Image pre-processing unit 202 for the blood-vessel image data according to pre-set image processing rule process and generates
The corresponding blood vessel identification report of the target user, wherein the blood vessel identification report at least one of includes blood vessel physical signs
And at least one of described corresponding numerical value of blood vessel physical signs;
Image analyzing unit 203 is used for numerical value criterion numeral corresponding at least one described blood vessel physical signs
Value is compared, and determines codomain corresponding to the difference of the numerical value and the standard figures;
Image analyzing unit 203 is also used to judge whether the codomain is reasonable value field according to preset rules, if it is not,
Described image analytical unit determines at least one corresponding potential disease item of the target user according to the disease collection of the codomain.
In some alternative embodiments, image pre-processing unit 202 is according to pre-set image processing rule process
Blood-vessel image data simultaneously generate the corresponding blood vessel identification of the target user reports to include sub-step:
According to the corresponding relationship of blood vessel physical signs and data area, by the blood-vessel image data be divided into it is described at least
The corresponding objective analysis data of one blood vessel physical signs;
The objective analysis data is analyzed according to according to preset data analysis rule, wherein preset data analysis rule packet
Include data discrete analysis, data linear analysis;
Determine that at least one of described blood vessel physical signs is corresponding described according to the analysis result of the objective analysis data
Numerical value;
The corresponding blood vessel identification report of the target user is exported according to default generation format.
In some alternative embodiments, described image pretreatment unit 202 is according to blood vessel physical signs and data field
The blood-vessel image data are divided at least one of described corresponding target analysis number of blood vessel physical signs by the corresponding relationship in domain
According to including sub-step:
Parted pattern is formed according to the corresponding relationship based on history blood vessel physical signs and data area, wherein described point
Cutting model includes at least one blood vessel physiological reference index and at least one described corresponding data field of blood vessel physiological reference index
Domain;
It is raw according to blood vessel physiological reference index at least one of described in the parted pattern and at least one of described blood vessel
The blood-vessel image data are divided at least one of described blood by the corresponding relationship between the corresponding data area of reason reference index
The corresponding objective analysis data of pipe physical signs.
In some alternative embodiments, according to raw based on history blood vessel described in described image pretreatment unit 202
The corresponding relationship for managing index and data area is formed after parted pattern, and described image pretreatment unit is according to the parted pattern
In at least one of described blood vessel physiological reference index and at least one of described corresponding data area of blood vessel physiological reference index
Between corresponding relationship the blood-vessel image data are divided at least one of described corresponding target analysis of blood vessel physical signs
Before data, described image pretreatment is also used to:
Receive revision directive, wherein the revision directive is used to correct the parted pattern and the revision directive includes
At least one is for correcting repairing for the corresponding relationship between at least one of described corresponding data area of blood vessel physiological reference index
Positive parameter;
The parted pattern is corrected based on the corrected parameter.
In some alternative embodiments, the blood-vessel image data include the first blood-vessel image data and/or second
Blood-vessel image data.
In some alternative embodiments, the acquisition unit 201 acquires the corresponding blood-vessel image data of target user,
Including sub-step:
Acquire the first blood-vessel image data corresponding in the daytime, and/or acquisition night corresponding second blood
Pipe image data;
It is described that rule is handled according to pre-set image and after the corresponding blood-vessel image data of the acquisition target user
Before handling the blood-vessel image data and generating the corresponding blood vessel identification report of the target user, described image pretreatment is single
Member 202 is also used to:
Photoplethysmogra is generated according to the first blood-vessel image data and/or the second blood-vessel image data
Data set.
In some alternative embodiments, according to the first blood-vessel image data and/or second vessel graph
Before generating photoplethysmogra data set as data, described image pretreatment unit 202 is also used to:
The first blood-vessel image data and/or the second blood-vessel image data are filtered using filter, with
Filter out the noise in the first blood-vessel image data and/or the second blood-vessel image data.
In some alternative embodiments, at least one of described blood vessel physical signs include blood flowing speed, blood pressure,
Platelet content, the oxygen content of blood, erythrocyte color, content of hemoglobin.
System of the invention can lead to the blood-vessel image data of acquisition user, and then analyze blood vessel using presupposition analysis method
Image data, and then the potential risk of user is predicted based on the analysis results.In the present invention, due to using instrument to blood vessel
Image data is handled and is analyzed, and then can predict the potential risk of user, so as to reduce medical worker's
Workload improves the diagnosis speed of medical worker.
Embodiment three
Referring to Fig. 3, Fig. 3 is the structural schematic diagram of another disease forecasting system disclosed by the embodiments of the present invention.Such as Fig. 3
Shown, which may include:
It is stored with the memory 301 of executable program code;
The processor 302 coupled with memory 301;
Processor 302 calls the executable program code stored in memory 301, executes step:
The corresponding blood-vessel image data of target user are acquired by acquisition unit;
Pass through described in image pre-processing unit blood-vessel image data according to pre-set image processing rule process and generation
The corresponding blood vessel of target user identifies report, wherein the blood vessel identification report includes at least one blood vessel physical signs and institute
State at least one corresponding numerical value of blood vessel physical signs;
By described image analytical unit by numerical value criterion numeral corresponding at least one of described blood vessel physical signs
Value is compared, and determines codomain corresponding to the difference of the numerical value and the standard figures;
Judge whether the codomain is reasonable value field according to preset rules by described image analytical unit, if it is not, institute
It states image analyzing unit and at least one corresponding potential disease item of the target user is determined according to the disease collection of the codomain.
In some embodiments, processor 302 calls the executable program code stored in memory 301, also executes
Step:
In some alternative embodiments, through image pre-processing unit according to pre-set image processing rule process
Blood-vessel image data simultaneously generate the corresponding blood vessel identification report of the target user, comprising:
According to the corresponding relationship of blood vessel physical signs and data area, by the blood-vessel image data be divided into it is described at least
The corresponding objective analysis data of one blood vessel physical signs;
The objective analysis data is analyzed according to according to preset data analysis rule, wherein preset data analysis rule packet
Include data discrete analysis, data linear analysis;
Determine that at least one of described blood vessel physical signs is corresponding described according to the analysis result of the objective analysis data
Numerical value;
The corresponding blood vessel identification report of the target user is exported according to default generation format.
In some alternative embodiments, the corresponding relationship according to blood vessel physical signs and data area, by institute
It states blood-vessel image data and is divided at least one of described corresponding objective analysis data of blood vessel physical signs, comprising:
Parted pattern is formed according to the corresponding relationship based on history blood vessel physical signs and data area, wherein described point
Cutting model includes at least one blood vessel physiological reference index and at least one described corresponding data field of blood vessel physiological reference index
Domain;
It is raw according to blood vessel physiological reference index at least one of described in the parted pattern and at least one of described blood vessel
The blood-vessel image data are divided at least one of described blood by the corresponding relationship between the corresponding data area of reason reference index
The corresponding objective analysis data of pipe physical signs.
In some alternative embodiments, corresponding with data area based on history blood vessel physical signs in the basis
Relationship is formed after parted pattern, described according to blood vessel physiological reference index and institute at least one of described in the parted pattern
The corresponding relationship stated between at least one corresponding data area of blood vessel physiological reference index divides the blood-vessel image data
Before at least one of described corresponding objective analysis data of blood vessel physical signs, the method also includes:
Receive revision directive, wherein the revision directive is used to correct the parted pattern and the revision directive includes
At least one is for correcting repairing for the corresponding relationship between at least one of described corresponding data area of blood vessel physiological reference index
Positive parameter;
The parted pattern is corrected based on the corrected parameter.
In some alternative embodiments, the blood-vessel image data include the first blood-vessel image data and/or second
Blood-vessel image data.
In some alternative embodiments, described that the corresponding blood-vessel image number of target user is acquired by acquisition unit
According to, comprising:
Acquire the first blood-vessel image data corresponding in the daytime, and/or acquisition night corresponding second blood
Pipe image data;
And after the corresponding blood-vessel image data of the acquisition target user, described handled according to pre-set image is advised
Before then handling the blood-vessel image data and generating the corresponding blood vessel identification report of the target user, the method is also wrapped
It includes:
Photoplethysmogra is generated according to the first blood-vessel image data and/or the second blood-vessel image data
Data set.
In some alternative embodiments, according to the first blood-vessel image data and/or second vessel graph
Before generating photoplethysmogra data set as data, the method also includes:
The first blood-vessel image data and/or the second blood-vessel image data are filtered using filter, with
Filter out the noise in the first blood-vessel image data and/or the second blood-vessel image data.
In some alternative embodiments, at least one of described blood vessel physical signs include blood flowing speed, blood pressure,
Platelet content, the oxygen content of blood, erythrocyte color, content of hemoglobin.
System of the invention can lead to the blood-vessel image data of acquisition user, and then analyze blood vessel using presupposition analysis method
Image data, and then the potential risk of user is predicted based on the analysis results.In the present invention, due to using instrument to blood vessel
Image data is handled and is analyzed, and then can predict the potential risk of user, so as to reduce medical worker's
Workload improves the diagnosis speed of medical worker.
Example IV
The embodiment of the present invention four discloses a kind of computer readable storage medium, stores based on electronic data interchange
Calculation machine program, wherein the computer program makes computer executed step:
The corresponding blood-vessel image data of target user are acquired by acquisition unit;
Pass through described in image pre-processing unit blood-vessel image data according to pre-set image processing rule process and generation
The corresponding blood vessel of target user identifies report, wherein the blood vessel identification report includes at least one blood vessel physical signs and institute
State at least one corresponding numerical value of blood vessel physical signs;
By described image analytical unit by numerical value criterion numeral corresponding at least one of described blood vessel physical signs
Value is compared, and determines codomain corresponding to the difference of the numerical value and the standard figures;
Judge whether the codomain is reasonable value field according to preset rules by described image analytical unit, if it is not, institute
It states image analyzing unit and at least one corresponding potential disease item of the target user is determined according to the disease collection of the codomain.
In some embodiments, computer readable storage medium also executes step:
In some alternative embodiments, through image pre-processing unit according to pre-set image processing rule process
Blood-vessel image data simultaneously generate the corresponding blood vessel identification report of the target user, comprising:
According to the corresponding relationship of blood vessel physical signs and data area, by the blood-vessel image data be divided into it is described at least
The corresponding objective analysis data of one blood vessel physical signs;
The objective analysis data is analyzed according to according to preset data analysis rule, wherein preset data analysis rule packet
Include data discrete analysis, data linear analysis;
Determine that at least one of described blood vessel physical signs is corresponding described according to the analysis result of the objective analysis data
Numerical value;
The corresponding blood vessel identification report of the target user is exported according to default generation format.
In some alternative embodiments, the corresponding relationship according to blood vessel physical signs and data area, by institute
It states blood-vessel image data and is divided at least one of described corresponding objective analysis data of blood vessel physical signs, comprising:
Parted pattern is formed according to the corresponding relationship based on history blood vessel physical signs and data area, wherein described point
Cutting model includes at least one blood vessel physiological reference index and at least one described corresponding data field of blood vessel physiological reference index
Domain;
It is raw according to blood vessel physiological reference index at least one of described in the parted pattern and at least one of described blood vessel
The blood-vessel image data are divided at least one of described blood by the corresponding relationship between the corresponding data area of reason reference index
The corresponding objective analysis data of pipe physical signs.
In some alternative embodiments, corresponding with data area based on history blood vessel physical signs in the basis
Relationship is formed after parted pattern, described according to blood vessel physiological reference index and institute at least one of described in the parted pattern
The corresponding relationship stated between at least one corresponding data area of blood vessel physiological reference index divides the blood-vessel image data
Before at least one of described corresponding objective analysis data of blood vessel physical signs, the method also includes:
Receive revision directive, wherein the revision directive is used to correct the parted pattern and the revision directive includes
At least one is for correcting repairing for the corresponding relationship between at least one of described corresponding data area of blood vessel physiological reference index
Positive parameter;
The parted pattern is corrected based on the corrected parameter.
In some alternative embodiments, the blood-vessel image data include the first blood-vessel image data and/or second
Blood-vessel image data.
In some alternative embodiments, described that the corresponding blood-vessel image number of target user is acquired by acquisition unit
According to, comprising:
Acquire the first blood-vessel image data corresponding in the daytime, and/or acquisition night corresponding second blood
Pipe image data;
And after the corresponding blood-vessel image data of the acquisition target user, described handled according to pre-set image is advised
Before then handling the blood-vessel image data and generating the corresponding blood vessel identification report of the target user, the method is also wrapped
It includes:
Photoplethysmogra is generated according to the first blood-vessel image data and/or the second blood-vessel image data
Data set.
In some alternative embodiments, according to the first blood-vessel image data and/or second vessel graph
Before generating photoplethysmogra data set as data, the method also includes:
The first blood-vessel image data and/or the second blood-vessel image data are filtered using filter, with
Filter out the noise in the first blood-vessel image data and/or the second blood-vessel image data.
In some alternative embodiments, at least one of described blood vessel physical signs include blood flowing speed, blood pressure,
Platelet content, the oxygen content of blood, erythrocyte color, content of hemoglobin.
The disease forecasting that computer readable storage medium of the invention is identified by executing the blood-vessel image based on big data
Step in side can lead to the blood-vessel image data of acquisition user, and then analyze blood-vessel image data using presupposition analysis method,
And then the potential risk of user is predicted based on the analysis results.In the present invention, due to using instrument to blood-vessel image data
It is handled and is analyzed, and then can predict that the potential risk of user mentions so as to reduce the workload of medical worker
The diagnosis speed of high medical worker.
Embodiment five
The embodiment of the invention discloses a kind of computer program product, which includes storing computer
The non-transient computer readable storage medium of program, and the computer program is operable to that computer is made to execute one institute of embodiment
Step in the disease forecasting method of the blood-vessel image identification based on big data of description.
In the disease forecasting side of computer program product of the invention by executing the blood-vessel image identification based on big data
The step of, the blood-vessel image data of acquisition user can be led to, and then analyze blood-vessel image data using presupposition analysis method, in turn
The potential risk of user is predicted based on the analysis results.In the present invention, due to being carried out using instrument to blood-vessel image data
Processing and analysis, and then can predict the potential risk of user, so as to reduce the workload of medical worker, improve doctor
The diagnosis speed of business personnel.
Installation practice described above is only illustrative, wherein the unit as illustrated by the separation member can be with
It is or may not be and be physically separated, component shown as a unit may or may not be physical unit,
Can be in one place, or may be distributed over multiple network units.It can select according to the actual needs wherein
Some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
In the case where labour, it can understand and implement.
By the specific descriptions of above embodiment, those skilled in the art can be understood that each embodiment
It can realize by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding,
Substantially the part that contributes to existing technology can be embodied in the form of software products above-mentioned technical proposal in other words,
The computer software product may be stored in a computer readable storage medium, and storage medium includes read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), programmable read only memory
(Programmable Read-only Memory, PROM), Erasable Programmable Read Only Memory EPROM (Erasable
Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-time
Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
Finally, it should be noted that a kind of disease of blood-vessel image identification based on big data disclosed by the embodiments of the present invention is pre-
Surveying disclosed by method and device is only present pre-ferred embodiments, is only used to illustrate the technical scheme of the present invention, rather than
It is limited;Although the present invention is described in detail referring to the foregoing embodiments, those skilled in the art should
Understand;It can still modify to technical solution documented by aforementioned every embodiment, or special to part of technology
Sign is equivalently replaced;And these modifications or substitutions, so that the essence of corresponding technical solution is detached from bold and unrestrained every embodiment
The spirit and scope of technical solution.
Claims (10)
1. a kind of disease forecasting method of the blood-vessel image identification based on big data, is applied in electronic device, the electronics dress
It sets including acquisition unit, image pre-processing unit, image analyzing unit, which is characterized in that the described method includes:
The corresponding blood-vessel image data of target user are acquired by acquisition unit;
By image pre-processing unit blood-vessel image data according to pre-set image processing rule process and generate the target
User's corresponding blood vessel identification report, wherein the blood vessel identification report at least one of include blood vessel physical signs and it is described extremely
The corresponding numerical value of one item missing blood vessel physical signs;
By described image analytical unit by numerical value standard figures corresponding at least one of described blood vessel physical signs into
Row compares, and determines codomain corresponding to the difference of the numerical value and the standard figures;
Judge whether the codomain is reasonable value field according to preset rules by described image analytical unit, if it is not, the figure
As analytical unit determines at least one corresponding potential disease item of the target user according to the disease collection of the codomain.
2. the method as described in claim 1, which is characterized in that described to be handled by image pre-processing unit according to pre-set image
Blood-vessel image data described in rule process simultaneously generate the corresponding blood vessel identification report of the target user, comprising:
According to the corresponding relationship of blood vessel physical signs and data area, the blood-vessel image data are divided at least one of described
The corresponding objective analysis data of blood vessel physical signs;
The objective analysis data is analyzed according to according to preset data analysis rule, wherein preset data analysis rule includes number
According to discrete analysis, data linear analysis;
At least one of described corresponding numerical value of blood vessel physical signs is determined according to the analysis result of the objective analysis data;
The corresponding blood vessel identification report of the target user is exported according to default generation format.
3. method according to claim 2, which is characterized in that described to be closed according to blood vessel physical signs is corresponding with data area
The blood-vessel image data are divided at least one of described corresponding objective analysis data of blood vessel physical signs by system, comprising:
Parted pattern is formed according to the corresponding relationship based on history blood vessel physical signs and data area, wherein the segmentation mould
Type includes at least one blood vessel physiological reference index and at least one described corresponding data area of blood vessel physiological reference index;
According to blood vessel physiological reference index at least one of described in the parted pattern and at least one of described blood vessel physiology ginseng
The blood-vessel image data are divided at least one of described blood vessel raw by the corresponding relationship examined between the corresponding data area of index
Manage the corresponding objective analysis data of index.
4. method as claimed in claim 3, which is characterized in that described according to blood at least one of described in the parted pattern
Corresponding relationship between pipe physiological reference index and at least one of described corresponding data area of blood vessel physiological reference index is by institute
It states blood-vessel image data to be divided into before at least one of described corresponding objective analysis data of blood vessel physical signs, the method is also
Include:
Receive revision directive, wherein the revision directive is used to correct the parted pattern and the revision directive includes at least
One for correcting the amendment ginseng of the corresponding relationship between at least one of described corresponding data area of blood vessel physiological reference index
Number;
The parted pattern is corrected based on the corrected parameter.
5. the method as described in claim 1, which is characterized in that the blood-vessel image data include the first blood-vessel image data,
And/or the second blood-vessel image data.
6. the method as described in claim 1, which is characterized in that described to acquire the corresponding blood vessel of target user by acquisition unit
Image data, comprising:
Acquisition corresponding first blood-vessel image data, and/or acquisition night corresponding second blood-vessel image data in the daytime;
It is described to be handled at rule according to pre-set image and after the corresponding blood-vessel image data of the acquisition target user
Before managing the blood-vessel image data and generating the corresponding blood vessel identification report of the target user, the method also includes:
Photoplethysmogra data are generated according to the first blood-vessel image data and/or the second blood-vessel image data
Collection.
7. method as claimed in claim 6, which is characterized in that according to the first blood-vessel image data and/or described
Before two blood-vessel image data generate photoplethysmogra data set, the method also includes:
The first blood-vessel image data and/or the second blood-vessel image data are filtered using filter, to filter out
Noise in the first blood-vessel image data and/or the second blood-vessel image data.
8. the method according to claim 1 to 7, which is characterized in that at least one of described blood vessel physical signs includes blood
Liquid flowing velocity, blood pressure, platelet content, the oxygen content of blood, erythrocyte color, content of hemoglobin.
9. in a kind of electronic device, the electronic device includes acquisition unit, image pre-processing unit, image analyzing unit,
It is characterized in that, the electronic device further include:
It is stored with the memory of executable program code;
The processor coupled with the memory;
The processor calls the executable program code stored in the memory, executes as claim 1-8 is any
The disease forecasting method of the blood-vessel image identification based on big data described in.
10. a kind of computer readable storage medium, which is characterized in that be stored with vessel graph in the computer readable storage medium
As recognizer, when the blood-vessel image recognizer is executed by processor, such as the described in any item bases of claim 1-8 are executed
In the disease forecasting method that the blood-vessel image of big data identifies.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910542132.XA CN110364256A (en) | 2019-06-21 | 2019-06-21 | A kind of disease forecasting system and method for the blood-vessel image identification based on big data |
PCT/CN2020/093613 WO2020253510A1 (en) | 2019-06-21 | 2020-05-30 | Big data blood vessel image identification-based disease prediction system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910542132.XA CN110364256A (en) | 2019-06-21 | 2019-06-21 | A kind of disease forecasting system and method for the blood-vessel image identification based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110364256A true CN110364256A (en) | 2019-10-22 |
Family
ID=68216453
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910542132.XA Pending CN110364256A (en) | 2019-06-21 | 2019-06-21 | A kind of disease forecasting system and method for the blood-vessel image identification based on big data |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110364256A (en) |
WO (1) | WO2020253510A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020253510A1 (en) * | 2019-06-21 | 2020-12-24 | 平安科技(深圳)有限公司 | Big data blood vessel image identification-based disease prediction system and method |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005023086A2 (en) * | 2003-08-25 | 2005-03-17 | University Of North Carolina At Chapel Hill | Systems, methods, and computer program products for analysis of vessel attributes for diagnosis, disease staging, and surgical planning |
CN102014731A (en) * | 2008-04-08 | 2011-04-13 | 新加坡国立大学 | Retinal image analysis systems and methods |
KR20130028484A (en) * | 2011-09-09 | 2013-03-19 | 스타링포스 주식회사 | Method for diagnosis of diseases using nail capillary image |
CN103458772A (en) * | 2011-04-07 | 2013-12-18 | 香港中文大学 | Method and device for retinal image analysis |
CN105103163A (en) * | 2013-03-07 | 2015-11-25 | 火山公司 | Multimodal segmentation in intravascular images |
CN106874663A (en) * | 2017-01-26 | 2017-06-20 | 中电科软件信息服务有限公司 | Cardiovascular and cerebrovascular disease Risk Forecast Method and system |
CN107516019A (en) * | 2017-10-20 | 2017-12-26 | 世好(贵州)健康管理有限公司 | Noninvasive health forecast system and method |
CN107847156A (en) * | 2015-06-15 | 2018-03-27 | 维塔尔实验室公司 | The method and system assessed and managed for angiocardiopathy |
CN108257674A (en) * | 2018-01-24 | 2018-07-06 | 龙马智芯(珠海横琴)科技有限公司 | Disease forecasting method and apparatus, equipment, computer readable storage medium |
CN108742566A (en) * | 2018-04-16 | 2018-11-06 | 北京京大律业知识产权代理有限公司 | A kind of risk of cardiovascular diseases control method based on big data |
CN109009009A (en) * | 2018-07-26 | 2018-12-18 | 方顺丽 | Blood vessel appraisal procedure, device and intelligent terminal |
CN109741344A (en) * | 2018-12-28 | 2019-05-10 | 上海联影智能医疗科技有限公司 | Blood vessel segmentation method, apparatus, medical imaging equipment and storage medium |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1631316A (en) * | 2005-01-10 | 2005-06-29 | 上海德安生物医学工程有限公司 | Cerebrovascular system function and brain recirculation dynamic analysis method and apparatus thereof |
CN104517015A (en) * | 2013-09-26 | 2015-04-15 | 中国人民解放军第二军医大学 | Mini device for preventing cerebrovascular disease through computer-aided diagnosis for ultrasonic image |
EP3777689A1 (en) * | 2014-12-08 | 2021-02-17 | Koninklijke Philips N.V. | Diagnostic and imaging direction based on anatomical and/or physiological parameters |
CN108095760A (en) * | 2017-11-07 | 2018-06-01 | 广州华科盈医疗科技有限公司 | A kind of appraisal procedure and device for being used to evaluate internal carotid blood vessel index parameter |
CN108670192B (en) * | 2018-04-21 | 2019-08-16 | 重庆贝奥新视野医疗设备有限公司 | A kind of multispectral eyeground imaging system and method for dynamic vision stimulation |
CN110364256A (en) * | 2019-06-21 | 2019-10-22 | 平安科技(深圳)有限公司 | A kind of disease forecasting system and method for the blood-vessel image identification based on big data |
-
2019
- 2019-06-21 CN CN201910542132.XA patent/CN110364256A/en active Pending
-
2020
- 2020-05-30 WO PCT/CN2020/093613 patent/WO2020253510A1/en active Application Filing
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005023086A2 (en) * | 2003-08-25 | 2005-03-17 | University Of North Carolina At Chapel Hill | Systems, methods, and computer program products for analysis of vessel attributes for diagnosis, disease staging, and surgical planning |
CN102014731A (en) * | 2008-04-08 | 2011-04-13 | 新加坡国立大学 | Retinal image analysis systems and methods |
CN103458772A (en) * | 2011-04-07 | 2013-12-18 | 香港中文大学 | Method and device for retinal image analysis |
KR20130028484A (en) * | 2011-09-09 | 2013-03-19 | 스타링포스 주식회사 | Method for diagnosis of diseases using nail capillary image |
CN105103163A (en) * | 2013-03-07 | 2015-11-25 | 火山公司 | Multimodal segmentation in intravascular images |
CN107847156A (en) * | 2015-06-15 | 2018-03-27 | 维塔尔实验室公司 | The method and system assessed and managed for angiocardiopathy |
CN106874663A (en) * | 2017-01-26 | 2017-06-20 | 中电科软件信息服务有限公司 | Cardiovascular and cerebrovascular disease Risk Forecast Method and system |
CN107516019A (en) * | 2017-10-20 | 2017-12-26 | 世好(贵州)健康管理有限公司 | Noninvasive health forecast system and method |
CN108257674A (en) * | 2018-01-24 | 2018-07-06 | 龙马智芯(珠海横琴)科技有限公司 | Disease forecasting method and apparatus, equipment, computer readable storage medium |
CN108742566A (en) * | 2018-04-16 | 2018-11-06 | 北京京大律业知识产权代理有限公司 | A kind of risk of cardiovascular diseases control method based on big data |
CN109009009A (en) * | 2018-07-26 | 2018-12-18 | 方顺丽 | Blood vessel appraisal procedure, device and intelligent terminal |
CN109741344A (en) * | 2018-12-28 | 2019-05-10 | 上海联影智能医疗科技有限公司 | Blood vessel segmentation method, apparatus, medical imaging equipment and storage medium |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020253510A1 (en) * | 2019-06-21 | 2020-12-24 | 平安科技(深圳)有限公司 | Big data blood vessel image identification-based disease prediction system and method |
Also Published As
Publication number | Publication date |
---|---|
WO2020253510A1 (en) | 2020-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ko et al. | 28n19 Ijaet0319396 V7 Iss1 242 254 | |
CN107436993B (en) | Method and server for establishing ICU patient condition evaluation model | |
CN109920540A (en) | Construction method, device and the computer equipment of assisting in diagnosis and treatment decision system | |
CN109864736A (en) | Processing method, device, terminal device and the medium of electrocardiosignal | |
Fritz et al. | Using machine learning techniques to develop forecasting algorithms for postoperative complications: protocol for a retrospective study | |
US20220254486A1 (en) | System and method for a patient dashboard | |
CN111899837A (en) | Operation report coordination method and system based on digital operating room | |
CN110085325B (en) | Method and device for constructing knowledge graph about traditional Chinese medicine experience data | |
JP2014520335A (en) | Evaluation system and evaluation method | |
CN110706769A (en) | Method and device for DRGs grouping of medical insurance data and electronic equipment | |
CN109243546A (en) | The method for building up and device of anticoagulation drug effect Optimized model | |
CN110874409A (en) | Disease grading prediction system, method, electronic device and readable storage medium | |
CN110767316A (en) | Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume | |
CN110364256A (en) | A kind of disease forecasting system and method for the blood-vessel image identification based on big data | |
Kim et al. | Deep learning model for predicting intradialytic hypotension without privacy infringement: a retrospective two-center study | |
CN116524248B (en) | Medical data processing device, method and classification model training device | |
CN108320788A (en) | Hospital business analysis method and device | |
CN110619939A (en) | Blood transfusion closed-loop system, method and computer storage medium | |
Coiera | Automated signal interpretation | |
Eggerth et al. | Comparison of Body Weight Trend Algorithms for Prediction of Heart Failure Related Events in Home Care Setting. | |
Nestola et al. | Novel risk predictor for thrombus deposition in abdominal aortic aneurysms | |
Ratnakar et al. | Smart Innovative Medical Devices Based on Artificial Intelligence | |
WO2019211575A1 (en) | Method and apparatus for classifying subjects based on time series phenotypic data | |
Brancozzi | Mobile cross-platform gesture-guided visual pain tracking for endometriosis | |
Mazid | THE INTEGRATION OF BUSINESS INTELLIGENCE IN COMPANIES |
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 |