CN110517780A - A kind of aneurysm rupture methods of risk assessment and system - Google Patents
A kind of aneurysm rupture methods of risk assessment and system Download PDFInfo
- Publication number
- CN110517780A CN110517780A CN201910821341.8A CN201910821341A CN110517780A CN 110517780 A CN110517780 A CN 110517780A CN 201910821341 A CN201910821341 A CN 201910821341A CN 110517780 A CN110517780 A CN 110517780A
- Authority
- CN
- China
- Prior art keywords
- data
- aneurysm
- learning sample
- risk evaluation
- rupture
- 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
- 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
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Abstract
This specification embodiment discloses a kind of aneurysm rupture methods of risk assessment and system, passes through and obtains pending data, wherein the pending data includes the first data and/or the second data;The pending data is inputted into aneurysm risk evaluation model, obtain the aneurysm risk evaluation result of the pending data, wherein, the aneurysm risk evaluation model is the model being obtained ahead of time based on neural network method, and the aneurysm rupture risk evaluation result includes aneurysm rupture probability and/or the important feature factor;The aneurysm risk evaluation result of the pending data is exported.The aneurysm rupture methods of risk assessment and system that this specification embodiment provides, can exclude or reduce the participation of human factor, shorten time-consuming, realize simple and fast carry out aneurysm rupture risk assessment, provide Objective support for aneurysm rupture risk assessment.
Description
Technical field
This specification is related to medical image and field of computer technology more particularly to a kind of aneurysm rupture risk assessment side
Method and system.
Background technique
Intracranial aneurysm is mostly the abnormal bulging occurred on entocranial artery tube wall, it was reported that encephalic Unruptured aneurysm
Illness rate may be up to 7% in China adult, causes subarachnoid hemorrhage after rupture, can lead to handicap or death.Cranium
Treatment mainly removes intracranial hematoma and blood is prevented to continue to flow to encephalic after internal aneurysm rupture;Encephalic Unruptured aneurysm needs
Personal management scheme is formulated according to aneurysm rupture risk evaluation result and the state of an illness of observed person, carry out conservative observation
Or surgical intervention.Therefore, aneurysm rupture risk assessment has great importance.
Currently, by observer according to three-dimensional DSA (Digital subtraction angiography, Digital Subtraction blood vessel
Radiography) contrastographic picture or MRA (Magnetic Resonance Angiography, Magnetic Resonance Angiography) image viewing artery
Tumor form, and the state of an illness of observed person is combined, aneurysm rupture risk is assessed, this method often relies on the experience of observer,
It is influenced by subjective judgement, lacks Objective support, it is time-consuming long.
Therefore, it is necessary to a kind of new methods, can exclude or reduce the participation of human factor, shorten time-consuming, realize simple
Aneurysm rupture risk assessment is efficiently carried out, provides Objective support for aneurysm rupture risk assessment.
Summary of the invention
This specification embodiment provides a kind of aneurysm rupture methods of risk assessment and system, asks for solving following technology
Topic: the prior art, by observer according to three-dimensional DSA (Digital subtraction angiography, Digital Subtraction blood vessel
Radiography) contrastographic picture or MRA (Magnetic Resonance Angiography, Magnetic Resonance Angiography) image viewing artery
Tumor form, and the state of an illness of observed person is combined, aneurysm rupture risk is assessed, this method often relies on the experience of observer,
It is influenced by subjective judgement, lacks Objective support, it is time-consuming long.
This specification embodiment provides a kind of aneurysm rupture methods of risk assessment, comprising the following steps:
Obtain pending data, wherein the pending data includes the first data and/or the second data;
The pending data is inputted into aneurysm risk evaluation model, obtains the aneurysm risk of the pending data
Assessment result, wherein the aneurysm risk evaluation model is the model being obtained ahead of time based on neural network method, the artery
Tumor risk of rupture assessment result includes aneurysm rupture probability and/or the important feature factor;
The aneurysm risk evaluation result of the pending data is exported.
Further, the acquisition of the aneurysm risk evaluation model specifically includes:
Obtain the aneurysm data of known sample, wherein the aneurysm data include the first data and/or the second number
According to;
The aneurysm data of the known sample are pre-processed, as learning sample data;
Operation is normalized in the learning sample data, obtains normalized learning sample data;
The normalized learning sample data are inputted into neural network model, according to the normalized learning sample number
According to being trained, aneurysm risk evaluation model is obtained, wherein the neural network model includes full Connection Neural Network mould
Type.
Further, described to pre-process the aneurysm data of the known sample, as learning sample data, tool
Body includes:
First data and/or second data are fitted, third data are obtained;
Using first data, second data and the third data as learning sample data, wherein
The data for belonging to aneurysm rupture in habit sample data are identical with the accounting for belonging to the uncracked data of aneurysm.
Further, the learning sample data have digital label, for marking whether aneurysm ruptures, wherein 0 table
Show that aneurysm does not rupture, 1 indicates aneurysm rupture.
Further, described to be fitted first data and/or second data, obtain third data, tool
Body includes:
The data for belonging to ruptured aneurysm are obtained from first data and/or second data;
Based on the data for belonging to ruptured aneurysm, searched and the ruptured aneurysm that belongs to using K- nearest neighbor algorithm
Data on numerical distance similar numerical value as third data.
Further, described that operation is normalized in the learning sample data, obtain normalized learning sample number
According to specifically including:
The mean value and variance for obtaining the data for each feature that the learning sample data are included, are normalized behaviour
Make, the data distribution of each feature is made to meet normal distribution.
Further, first data include the aneurysm morphology parameter of observed person, and second data include
The information parameter of observed person.
A kind of aneurysm rupture risk evaluating system that this specification embodiment provides, comprising:
Input module obtains pending data, wherein the pending data includes the first data and/or the second data;
The pending data is inputted aneurysm risk evaluation model, obtains the pending data by evaluation module
Aneurysm risk evaluation result, wherein the aneurysm risk evaluation model is the mould being obtained ahead of time based on neural network method
Type, the aneurysm rupture risk evaluation result include aneurysm rupture probability and/or the important feature factor;
Output module exports the aneurysm risk evaluation result of the pending data.
Further, the acquisition of the aneurysm risk evaluation model specifically includes:
Obtain the aneurysm data of known sample, wherein the aneurysm data include the first data and/or the second number
According to;
The aneurysm data of the known sample are pre-processed, as learning sample data;
Operation is normalized in the learning sample data, obtains normalized learning sample data;
The normalized learning sample data are inputted into neural network model, according to the normalized learning sample number
According to being trained, aneurysm risk evaluation model is obtained, wherein the neural network model includes full Connection Neural Network mould
Type.
Further, described to pre-process the aneurysm data of the known sample, as learning sample data, tool
Body includes:
First data and/or second data are fitted, third data are obtained;
Using first data, second data and the third data as learning sample data, wherein
The data for belonging to aneurysm rupture in habit sample data are identical with the accounting for belonging to the uncracked data of aneurysm.
Further, the learning sample data have digital label, for marking whether aneurysm ruptures, wherein 0 table
Show that aneurysm does not rupture, 1 indicates aneurysm rupture.
Further, described to be fitted first data and/or second data, obtain third data, tool
Body includes:
The data for belonging to ruptured aneurysm are obtained from first data and/or second data;
Based on the data for belonging to ruptured aneurysm, searched and the ruptured aneurysm that belongs to using K- nearest neighbor algorithm
Data on numerical distance similar numerical value as third data.
Further, described that operation is normalized in the learning sample data, obtain normalized learning sample number
According to specifically including:
The mean value and variance for obtaining the data for each feature that the learning sample data are included, are normalized behaviour
Make, the data distribution of each feature is made to meet normal distribution.
Further, first data include the aneurysm morphology parameter of observed person, and second data include
The information parameter of observed person.
This specification embodiment use at least one above-mentioned technical solution can reach it is following the utility model has the advantages that
This specification embodiment by obtain pending data, wherein the pending data include the first data and/or
Second data;The pending data is inputted into aneurysm risk evaluation model, obtains the aneurysm wind of the pending data
Dangerous assessment result, wherein the aneurysm risk evaluation model is the model being obtained ahead of time based on neural network method, described dynamic
Arteries and veins tumor risk of rupture assessment result includes aneurysm rupture probability and/or the important feature factor;By the dynamic of the pending data
Arteries and veins tumor risk evaluation result is exported, and the participation of human factor can be excluded or reduce, and is shortened time-consuming, is realized simple and fast
Aneurysm rupture risk assessment is carried out, provides Objective support for aneurysm rupture risk assessment.
Detailed description of the invention
In order to illustrate more clearly of this specification embodiment or technical solution in the prior art, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
The some embodiments recorded in this specification, for those of ordinary skill in the art, in not making the creative labor property
Under the premise of, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow diagram for aneurysm rupture methods of risk assessment that this specification embodiment provides;
Fig. 2 is the building flow diagram for the aneurysm risk evaluation model that this specification embodiment provides;
Fig. 3 is a kind of schematic diagram for aneurysm rupture risk evaluating system that this specification embodiment provides.
Specific embodiment
Intracranial aneurysm Morphologic Parameters are of great significance for the diagnosis of intracranial aneurysm, intracranial aneurysm morphology
Parameter can be obtained by medical image, including but not limited to DSA, MRA.
The basic principle of DSA is that the two frame X-ray images shot before and after injecting contrast agent are digitized input picture calculating
Machine obtains clearly pure blood vessel image by subtracting shadow, enhancing and reimaging process, while showing blood vessel shadow in real time.DSA tool
Have that contrast resolution is high, the review time is short, contrast agent dosage is few, concentration is low, patient's x-ray uptake is substantially reduced and saves
The advantages that film, has a very important significance in the clinical diagnosis of vascular disorder.DSA becomes encephalic because of its imaging characteristics
The goldstandard of arteries deformity and Diagnosis of Aneurysm.
MRA basic principle is to remove phase effect based on saturation effect, inflow enhancement effect, flowing.MRA is by presaturation band
The head end of 3D layers of block is placed in be saturated venous blood flow, the arterial blood of reverse flow enters 3D layers of block, because not being saturated to produce
Raw MR signal.It is divided into multiple thin layers to excite a thicker volume when scanning, reduces excitation volume thickness to reduce to flow into and satisfy
And effect, and can guarantee scanning volume range, obtain the thin layer image of several layers of adjacent level, make image clearly, blood vessel it is subtle
Structure shows that spatial resolution improves.MRA is also gradually used for the diagnosis of intracranial aneurysm because of the imaging characteristics of its high quality.
In this application, the information parameter of aneurysm morphology parameter and observed person based on observed person, Ke Yishi
Now to the assessment of the aneurysm rupture risk of evaluated value.
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with this explanation
Attached drawing in book embodiment is clearly and completely described the technical solution in this specification embodiment, it is clear that described
Embodiment be merely a part but not all of the embodiments of the present application.Based on this specification embodiment, this field
Those of ordinary skill's every other embodiment obtained without creative efforts, all should belong to the application
The range of protection.
Below in conjunction with attached drawing, the technical scheme provided by various embodiments of the present application will be described in detail.
Fig. 1 is a kind of flow diagram for aneurysm rupture methods of risk assessment that this specification embodiment provides.The party
Method specifically includes the following steps:
Step S101: pending data is obtained, wherein the pending data includes the first data and/or the second data.
In this application, the first data include the aneurysm morphology parameter of observed person, including but not limited to: aneurysm
Volume, the ratio for carrying tumor blood vessel average diameter, knurl length and tumor neck diameter ratio (SR), knurl length and tumor neck breadth degree
(AR), aneurysm major diameter, aneurysm height, aneurysm width, aneurysm neck width, inflow angle.Second data include being seen
The information parameter for the person of examining, including but not limited to: the age of observed person, gender, smoking history, hypertension, family history.
In one embodiment of the application, it is based on three-dimensional DSA image, obtains the aneurysm morphology ginseng of observed person
Number.After DSA image is converted to STL image, the aneurysm morphology parameter of observed person is measured.First data can also be based on three
It ties up the medical image except DSA image to obtain, such as MRA image.The aneurysm morphology parameter of observed person is dynamic including belonging to
The data and belong to the uncracked data of aneurysm that arteries and veins tumor ruptures.
In one embodiment of the application, the information parameter of observed person is that the case information based on observed person obtains
's.
Since observed person may have one or more aneurysms, pending data includes one or more
The corresponding data of aneurysm.
In this application, observed person is the object of aneurysm rupture risk assessment in the application.
Step S103: the pending data is inputted into aneurysm risk evaluation model, obtains the pending data
Aneurysm risk evaluation result, wherein the aneurysm rupture risk evaluation result includes aneurysm rupture probability and/or important
Characterization factor.
In this application, aneurysm risk evaluation model is the aneurysm data using known sample, is based on machine learning
The model of acquisition.For the acquisition for understanding aneurysm risk evaluation model, Fig. 2 is a kind of aneurysm that this specification embodiment provides
The acquisition flow diagram of risk evaluation model, specifically includes:
Step S201: the aneurysm data of known sample are obtained, wherein the aneurysm data include the first data and/
Or second data.
In this application, the first data and/or the second data are the corresponding data of each aneurysm sample, and each artery
Whether aneurysm ruptures known to tumor sample standard deviation, and is marked with digital label, wherein 0 expression aneurysm does not rupture, and 1 indicates
Aneurysm rupture.
Step S203: the aneurysm data of the known sample are pre-processed, as learning sample data.
Due in the aneurysm data of the abovementioned steps S201 known sample obtained, it is understood that there may be belong to aneurysm rupture
Data are well below the uncracked data of aneurysm are belonged to, and in order to guarantee the accuracy of subsequent aneurysm rupture model, therefore, need
Will the aneurysm data to known sample pre-process.
In this application, first data and second data are fitted, obtain third data;
Using first data, second data and the third data as learning sample data, wherein
The data for belonging to aneurysm rupture in habit sample data are identical with the accounting for belonging to the uncracked data of aneurysm.
In this application, learning sample data can be form, for subsequent step use.
In this application, the aneurysm data of the abovementioned steps S201 known sample obtained are pre-processed, it is specific to wrap
It includes:
The data for belonging to ruptured aneurysm are obtained from first data and/or second data;
Based on the data for belonging to ruptured aneurysm, searched and the ruptured aneurysm that belongs to using K- nearest neighbor algorithm
Data on numerical distance similar numerical value as third data.
In one embodiment of the application, using ADASYN algorithm, the first data and/or the second data are intended
It closes, obtains third data.Specific steps include:
(1) degree of unbalancedness is calculated.
Note minority class sample be ms, most classes be ml, then degree of unbalancedness be d=ms/ml, then d ∈ (0,1].
(2) sample size for needing to synthesize is calculated.
G=(ml-ms) * b, b ∈ [0,1], as b=1, i.e. G is equal to the difference of minority class and most classes, at this time composite number
Most class numbers and minority class data after just balance.
(3) k neighbours are calculated to each sample for belonging to minority class Euclidean distance, △ is to belong to majority in k neighbours
The number of samples of class, note ratio r are r=△/k, r ∈ [0,1].
(4) ri that each minority class sample is obtained in (3) calculates the feelings of most classes around each minority class sample
Condition.
(5) number of synthesis sample is calculated each minority class sample.
(6) 1 minority class sample is selected around each minority class sample to be synthesized in k neighbours, according to following etc.
Formula is synthesized.
Synthesis is repeated until meeting the number for needing step (5) to synthesize.
Step S205: operation is normalized in the learning sample data, obtains normalized learning sample data.
Since the abovementioned steps S203 learning sample data obtained are input neural network model, data distribution meeting
Directly affect the training effect and stability of neural network model, therefore, in order to guarantee neural network model training effect and
Stability, learning sample data need further progress normalization operation, obtain normalized learning sample data.
In this application, operation is normalized to the data sample data, specifically included:
The mean value and variance for obtaining the data for each feature that the learning sample data are included, are normalized behaviour
Make, the data distribution of each feature is made to meet normal distribution.Specifically, pair for belonging to each feature in study sample data is calculated
The mean value and variance of data are answered, then subtracts the mean value with each data of the corresponding data of each feature, then divided by variance, thus
Realize that normalization operation, mean value 0, the variance of the data distribution for each feature for making learning sample data be included are 1 just
State distribution.In this application, feature refers to the title of each index included in learning sample data, in such as the first data
Aneurysm volume, the ratio for carrying tumor blood vessel average diameter, knurl length and tumor neck diameter ratio (SR), knurl length and tumor neck breadth degree
It is worth (AR), aneurysm major diameter, aneurysm height, aneurysm width, aneurysm neck width, flows into angle, each index represents
One feature, for another example age of the observed person in the second data, gender, smoking history, hypertension, family history, each index
Also a feature is represented.The data of each feature refer to the corresponding numerical value of each feature, if the age 21,21 is the number at age
According to.
Step S207: the normalized learning sample data are inputted into neural network model, according to described normalized
Learning sample data are trained, and obtain aneurysm risk evaluation model, wherein the neural network model includes full connection mind
Through network model.
In this application, aneurysm risk evaluation model is the model being obtained ahead of time based on neural network method, preferably entirely
Connection Neural Network model, based on the similar thinking of the present invention, by neural metwork training, the method for realizing aneurysm risk assessment
Also belong to protection scope of the present invention.
Neural network model uses two layers of neural network in the application, and two layers of neuron is connected with each other, wherein second layer mind
Number through member is twice of second layer neuron.The neural network model includes input layer, middle layer and output layer, wherein
Middle layer and output layer are computation layer.
Since the essence of neural network is exactly by parameter and activation primitive come the true letter between fit characteristic and target
Number relationships the case where in order to reduce model over-fitting, using the method for giving up neuron at random, enable training every time all from all minds
Through giving up a certain amount of neuron in member at random.
Globally optimal solution in order to obtain calculates the gradient value of each step, and obtains each step most using gradient descent method
Small value, makes loss function reach minimum.
The neuron that neural network model finally exports passes through sigmoid classification function, obtains what the model was classified automatically
As a result, obtaining aneurysm risk evaluation model.Sigmoid classification function is also Logistic function, can be used for neural network mould
Hidden neuron exports in type, and value range is (0,1).Therefore, in this application, by the place of sigmoid classification function
Reason, it is ensured that the data of output are located in (0,1), carry out the assessment of aneurysm rupture risk.
In aneurysm risk evaluation model training process, the neural network of preferably end-to-end training, not end-to-end training
Neural network be also considered as same mode.
It should be strongly noted that aneurysm risk evaluation model is in the training process, it is to be carried out using the feature of sample
Trained, including but not limited to: whether aneurysm ruptures between the first data and/or the second data and/or third data
Mapping relations.
Using aneurysm rupture risk evaluation model provided by the present application, the aneurysm data of observed person are inputted into artery
Tumor risk evaluation model, aneurysm risk evaluation model can be exported including aneurysm rupture probability and/or the important feature factor.In
In the application, the aneurysm data of observed person include but is not limited to: the first data and/or the second data, that is, observed person
Aneurysm morphology parameter and/or observed person information parameter.In this application, the important feature factor has been reacted and artery
The coherence of tumor risk of rupture.The important feature factor can be a kind of feature, or various features.The important feature factor is
Based on aneurysm risk evaluation model, from the partial information parameter of the extraction in the second data, such as hypertension, smoking history.
In one embodiment of the application, using aneurysm risk evaluation model provided by the present application, by number to be processed
According to input aneurysm risk evaluation model, the probability for obtaining the aneurysm rupture risk of observed person is 70%, after can be used as
The auxiliary reference of continuous diagnoses and treatment, decides whether operative treatment.
One or more groups of aneurysm data input aneurysm risk assessment may be implemented in method provided by the embodiments of the present application
Model obtains the assessment result of aneurysm rupture risk.In this application, one group of aneurysm data is corresponding to an aneurysm
Data, including the first data and/or the second data.
The method that this specification embodiment provides can exclude or reduce the participation of human factor, shorten time-consuming, realization letter
It is single efficiently to carry out aneurysm rupture risk assessment, Objective support is provided for aneurysm rupture risk assessment.
The appraisal procedure that this specification embodiment provides is used for auxiliary observation in practical application, software can be encapsulated as
Person quickly obtains rationally reliable prediction result and/or to influence the aneurysm broken when carrying out Unruptured aneurysm Treatment decsion
Split the great influence factor of risk.
Based on same thinking, this specification embodiment additionally provides a kind of aneurysm rupture risk evaluating system, and Fig. 3 is
A kind of schematic diagram for aneurysm rupture risk evaluating system that this specification embodiment provides, the system include:
Input module 301 obtains pending data, wherein the pending data includes the first data and/or the second number
According to;
The pending data is inputted aneurysm risk evaluation model, obtains the pending data by evaluation module 303
Aneurysm risk evaluation result, wherein the aneurysm risk evaluation model is obtained ahead of time based on neural network method
Model, the aneurysm rupture risk evaluation result include aneurysm rupture probability and/or the important feature factor;
Output module 305 exports the aneurysm risk evaluation result of the pending data.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be according to different from sequentially holding in embodiment
It goes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily requires the particular order shown
Or consecutive order is just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can be with
Or may be advantageous.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device,
For electronic equipment, nonvolatile computer storage media embodiment, since it is substantially similar to the method embodiment, so description
It is fairly simple, the relevent part can refer to the partial explaination of embodiments of method.
Device that this specification embodiment provides, electronic equipment, nonvolatile computer storage media with method are corresponding
, therefore, device, electronic equipment, nonvolatile computer storage media also have the Advantageous effect similar with corresponding method
Fruit, since the advantageous effects of method being described in detail above, which is not described herein again corresponding intrument,
The advantageous effects of electronic equipment, nonvolatile computer storage media.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " is patrolled
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed is most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method process can be readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and insertion microcontroller, the example of controller includes but is not limited to following microcontroller
Device: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320 are deposited
Memory controller is also implemented as a part of the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained to come in fact in the form of logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc.
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when specification one or more embodiment.
It should be understood by those skilled in the art that, this specification embodiment can provide as method, system or computer program
Product.Therefore, this specification embodiment can be used complete hardware embodiment, complete software embodiment or combine software and hardware
The form of the embodiment of aspect.Moreover, it wherein includes that computer is available that this specification embodiment, which can be used in one or more,
It is real in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form for the computer program product applied.
This specification is referring to the method, equipment (system) and computer program product according to this specification embodiment
Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram
The combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computers
Processor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices
To generate a machine, so that generating use by the instruction that computer or the processor of other programmable data processing devices execute
In the dress for realizing the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram
It sets.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
This specification can describe in the general context of computer-executable instructions executed by a computer, such as journey
Sequence module.Generally, program module include routines performing specific tasks or implementing specific abstract data types, programs, objects,
Component, data structure etc..Specification can also be practiced in a distributed computing environment, in these distributed computing environments,
By executing task by the connected remote processing devices of communication network.In a distributed computing environment, program module can
To be located in the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The foregoing is merely this specification embodiments, are not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (14)
1. a kind of aneurysm rupture methods of risk assessment characterized by comprising
Obtain pending data, wherein the pending data includes the first data and/or the second data;
The pending data is inputted into aneurysm risk evaluation model, obtains the aneurysm risk assessment of the pending data
As a result, wherein the aneurysm risk evaluation model is the model being obtained ahead of time based on neural network method, and the aneurysm is broken
Splitting risk evaluation result includes aneurysm rupture probability and/or the important feature factor;
The aneurysm risk evaluation result of the pending data is exported.
2. the method as described in claim 1, which is characterized in that the acquisition of the aneurysm risk evaluation model specifically includes:
Obtain the aneurysm data of known sample, wherein the aneurysm data include the first data and/or the second data;
The aneurysm data of the known sample are pre-processed, as learning sample data;
Operation is normalized in the learning sample data, obtains normalized learning sample data;
The normalized learning sample data are inputted into neural network model, according to the normalized learning sample data into
Row training, obtains aneurysm risk evaluation model, wherein the neural network model includes full Connection Neural Network model.
3. method as claimed in claim 3, which is characterized in that described to be located the aneurysm data of the known sample in advance
Reason, as learning sample data, specifically includes:
First data and/or second data are fitted, third data are obtained;
Using first data, second data and the third data as learning sample data, wherein the study sample
The data for belonging to aneurysm rupture in notebook data are identical with the accounting for belonging to the uncracked data of aneurysm.
4. method as claimed in claim 2 or claim 3, which is characterized in that the learning sample data have digital label, for marking
Whether note aneurysm ruptures, wherein 0 expression aneurysm does not rupture, and 1 indicates aneurysm rupture.
5. method as claimed in claim 3, which is characterized in that it is described by first data and/or second data into
Row fitting, obtains third data, specifically includes:
The data for belonging to ruptured aneurysm are obtained from first data and/or second data;
Based on the data for belonging to ruptured aneurysm, searched and the data for belonging to ruptured aneurysm using K- nearest neighbor algorithm
Similar numerical value is as third data on numerical distance.
6. method according to claim 2, which is characterized in that it is described that operation is normalized in the learning sample data,
It specifically includes:
The mean value and variance for obtaining the data for each feature that the learning sample data are included, are normalized operation, make
The data distribution of each feature meets normal distribution.
7. the method as described in claim 1, which is characterized in that first data include the aneurysm morphology of observed person
Parameter, second data include the information parameter of observed person.
8. a kind of aneurysm rupture risk evaluating system characterized by comprising
Input module obtains pending data, wherein the pending data includes the first data and/or the second data;
The pending data is inputted aneurysm risk evaluation model, obtains the artery of the pending data by evaluation module
Tumor risk evaluation result, wherein the aneurysm risk evaluation model is the model being obtained ahead of time based on neural network method, institute
Stating aneurysm rupture risk evaluation result includes aneurysm rupture probability and/or the important feature factor;
Output module exports the aneurysm risk evaluation result of the pending data.
9. system as claimed in claim 7, which is characterized in that the acquisition of the aneurysm risk evaluation model specifically includes:
Obtain the aneurysm data of known sample, wherein the aneurysm data include the first data and/or the second data;
The aneurysm data of the known sample are pre-processed, as learning sample data;
Operation is normalized in the learning sample data, obtains normalized learning sample data;
The normalized learning sample data are inputted into neural network model, according to the normalized learning sample data into
Row training, obtains aneurysm risk evaluation model, wherein the neural network model includes full Connection Neural Network model.
10. system as claimed in claim 9, which is characterized in that the aneurysm data by the known sample carry out pre-
Processing, as learning sample data, specifically includes:
First data and/or second data are fitted, third data are obtained;
Using first data, second data and the third data as learning sample data, wherein the study sample
The data for belonging to aneurysm rupture in notebook data are identical with the accounting for belonging to the uncracked data of aneurysm.
11. the system as described in claim 9 or 10, which is characterized in that the learning sample data have digital label, are used for
Whether mark aneurysm ruptures, wherein 0 expression aneurysm does not rupture, and 1 indicates aneurysm rupture.
12. system as claimed in claim 10, which is characterized in that described by first data and/or second data
It is fitted, obtains third data, specifically include:
The data for belonging to ruptured aneurysm are obtained from first data and/or second data;
Based on the data for belonging to ruptured aneurysm, searched and the data for belonging to ruptured aneurysm using K- nearest neighbor algorithm
Similar numerical value is as third data on numerical distance.
13. system as claimed in claim 9, which is characterized in that it is described that operation is normalized in the learning sample data,
It specifically includes:
The mean value and variance for obtaining the data for each feature that the learning sample data are included, are normalized operation, make
The data distribution of each feature meets normal distribution.
14. system as claimed in claim 8, which is characterized in that first data include the aneurysm morphology of observed person
Parameter is learned, second data include the information parameter of observed person.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910821341.8A CN110517780A (en) | 2019-09-02 | 2019-09-02 | A kind of aneurysm rupture methods of risk assessment and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910821341.8A CN110517780A (en) | 2019-09-02 | 2019-09-02 | A kind of aneurysm rupture methods of risk assessment and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110517780A true CN110517780A (en) | 2019-11-29 |
Family
ID=68630261
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910821341.8A Pending CN110517780A (en) | 2019-09-02 | 2019-09-02 | A kind of aneurysm rupture methods of risk assessment and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110517780A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111584076A (en) * | 2020-04-08 | 2020-08-25 | 北京市神经外科研究所 | Aneurysm rupture risk assessment method and system |
CN111584077A (en) * | 2020-04-08 | 2020-08-25 | 北京市神经外科研究所 | Aneurysm rupture risk assessment method and system |
CN111671556A (en) * | 2020-04-14 | 2020-09-18 | 北京市神经外科研究所 | Aneurysm stent and method of construction thereof |
CN112617770A (en) * | 2020-12-28 | 2021-04-09 | 首都医科大学附属北京天坛医院 | Intracranial aneurysm risk prediction method based on artificial intelligence and related device |
WO2021098768A1 (en) * | 2019-11-22 | 2021-05-27 | 强联智创(北京)科技有限公司 | Method and system for assessing aneurysm rupture risk |
CN112927815A (en) * | 2021-05-10 | 2021-06-08 | 首都医科大学附属北京天坛医院 | Method, device and equipment for predicting intracranial aneurysm information |
CN113066574A (en) * | 2021-03-29 | 2021-07-02 | 昆明同心医联科技有限公司 | Neural network-based aneurysm rupture prediction method, device and storage medium |
CN113130078A (en) * | 2021-05-11 | 2021-07-16 | 首都医科大学附属北京天坛医院 | Method, device and equipment for predicting intracranial aneurysm occlusion |
CN116525121A (en) * | 2023-07-05 | 2023-08-01 | 昆明同心医联科技有限公司 | Method for establishing primary spring coil recommendation model of embolic aneurysm and application of primary spring coil recommendation model |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016094330A2 (en) * | 2014-12-08 | 2016-06-16 | 20/20 Genesystems, Inc | Methods and machine learning systems for predicting the liklihood or risk of having cancer |
CN109907732A (en) * | 2019-04-09 | 2019-06-21 | 广州新脉科技有限公司 | A kind of appraisal procedure and system of rupture of intracranial aneurysm risk |
CN109961850A (en) * | 2019-03-19 | 2019-07-02 | 肖仁德 | A kind of method, apparatus, computer equipment for assessing rupture of intracranial aneurysm risk |
-
2019
- 2019-09-02 CN CN201910821341.8A patent/CN110517780A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016094330A2 (en) * | 2014-12-08 | 2016-06-16 | 20/20 Genesystems, Inc | Methods and machine learning systems for predicting the liklihood or risk of having cancer |
CN109961850A (en) * | 2019-03-19 | 2019-07-02 | 肖仁德 | A kind of method, apparatus, computer equipment for assessing rupture of intracranial aneurysm risk |
CN109907732A (en) * | 2019-04-09 | 2019-06-21 | 广州新脉科技有限公司 | A kind of appraisal procedure and system of rupture of intracranial aneurysm risk |
Non-Patent Citations (1)
Title |
---|
J.J. LIU 等: "Prediction of rupture risk in anterior communicating artery aneurysms with a feed-forward artificial neural network", 《EUROPEAN RADIOLOGY》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021098768A1 (en) * | 2019-11-22 | 2021-05-27 | 强联智创(北京)科技有限公司 | Method and system for assessing aneurysm rupture risk |
CN111584076A (en) * | 2020-04-08 | 2020-08-25 | 北京市神经外科研究所 | Aneurysm rupture risk assessment method and system |
CN111584077A (en) * | 2020-04-08 | 2020-08-25 | 北京市神经外科研究所 | Aneurysm rupture risk assessment method and system |
CN111671556A (en) * | 2020-04-14 | 2020-09-18 | 北京市神经外科研究所 | Aneurysm stent and method of construction thereof |
CN112617770A (en) * | 2020-12-28 | 2021-04-09 | 首都医科大学附属北京天坛医院 | Intracranial aneurysm risk prediction method based on artificial intelligence and related device |
CN113066574A (en) * | 2021-03-29 | 2021-07-02 | 昆明同心医联科技有限公司 | Neural network-based aneurysm rupture prediction method, device and storage medium |
CN112927815A (en) * | 2021-05-10 | 2021-06-08 | 首都医科大学附属北京天坛医院 | Method, device and equipment for predicting intracranial aneurysm information |
CN113130078A (en) * | 2021-05-11 | 2021-07-16 | 首都医科大学附属北京天坛医院 | Method, device and equipment for predicting intracranial aneurysm occlusion |
CN116525121A (en) * | 2023-07-05 | 2023-08-01 | 昆明同心医联科技有限公司 | Method for establishing primary spring coil recommendation model of embolic aneurysm and application of primary spring coil recommendation model |
CN116525121B (en) * | 2023-07-05 | 2023-09-26 | 昆明同心医联科技有限公司 | Method for establishing primary spring coil recommendation model of embolic aneurysm and application of primary spring coil recommendation model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110517780A (en) | A kind of aneurysm rupture methods of risk assessment and system | |
CN110534193A (en) | A kind of aneurysm rupture methods of risk assessment and system | |
WO2020083374A1 (en) | Method and system for measuring morphological parameters of an intracranial aneurysm image | |
CN109493348A (en) | A kind of measurement method and system of the Morphologic Parameters of intracranial aneurysm image | |
CN111081378B (en) | Aneurysm rupture risk assessment method and system | |
CN109584997B (en) | Method and system for measuring morphological parameters of intracranial aneurysm image | |
CN110517242A (en) | A kind of aneurysmal analysis method and device | |
CN109472780B (en) | Method and system for measuring morphological parameters of intracranial aneurysm image | |
CN109448004B (en) | Centerline-based intracranial blood vessel image interception method and system | |
CN109671066A (en) | A kind of method and system of the cerebral infarction judgement based on head CT images | |
Oeltze‐Jafra et al. | Generation and visual exploration of medical flow data: Survey, research trends and future challenges | |
CN109472823B (en) | Method and system for measuring morphological parameters of intracranial aneurysm image | |
Hahn et al. | Artificial intelligence and machine learning in aortic disease | |
CN111584077A (en) | Aneurysm rupture risk assessment method and system | |
CN111127428A (en) | Method and system for extracting target region based on brain image data | |
CN109389637A (en) | A kind of measurement method and system of the Morphologic Parameters of intracranial aneurysm image | |
CN111091563B (en) | Method and system for extracting target region based on brain image data | |
CN109447967A (en) | A kind of dividing method and system of intracranial aneurysm image | |
CN111223089B (en) | Aneurysm detection method and device and computer readable storage medium | |
CN111584076A (en) | Aneurysm rupture risk assessment method and system | |
CN110739078B (en) | Aneurysm rupture risk assessment method and system | |
CN112185550A (en) | Typing method, device and equipment | |
CN110503642A (en) | A kind of localization method and system based on DSA image | |
CN109671067A (en) | A kind of measurement method and system of the core Infarction volume based on head CT images | |
Kruse et al. | Glottisnetv2: temporal glottal midline detection using deep convolutional neural networks |
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 |