CN108171272A - A kind of evaluation method and device of Medical Imaging Technology - Google Patents
A kind of evaluation method and device of Medical Imaging Technology Download PDFInfo
- Publication number
- CN108171272A CN108171272A CN201810030984.6A CN201810030984A CN108171272A CN 108171272 A CN108171272 A CN 108171272A CN 201810030984 A CN201810030984 A CN 201810030984A CN 108171272 A CN108171272 A CN 108171272A
- Authority
- CN
- China
- Prior art keywords
- medical
- imaging technology
- medical imaging
- evaluation
- medical 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
- G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The embodiment of the present application discloses a kind of evaluation method of Medical Imaging Technology, and this method is based on advance trained Medical Imaging Technology evaluation model and Medical Imaging Technology is evaluated.Because Medical Imaging Technology evaluation model is to train to obtain according to multiple medical diagnostic information fidelity evaluation results of parameter index and medical image training sample for weighing Medical Imaging Technology of medical image training sample, thus by measured from medical image it is multiple be input in Medical Imaging Technology evaluation model for the parameter index of weighing Medical Imaging Technology after, it can obtain the output result of reflection medical diagnostic information fidelity, the evaluation result of the output result as Medical Imaging Technology, the evaluation result of reflection medical diagnostic information fidelity can be obtained, the diagnostic value of medical image can be weighed.The embodiment of the present application also discloses a kind of evaluating apparatus of Medical Imaging Technology.
Description
Technical field
This application involves Medical Imaging Technology field more particularly to a kind of evaluation method and device of Medical Imaging Technology.
Background technology
Medical Imaging is the subject for covering a variety of image technologies based on radiodiagnosis medicine.As common X-ray is taken the photograph
Shadow, digital photography (CR, DR), digital subtraction angiography (DSA), CR scanning (CT), magnetic resonance imaging
(MRI), ultrasonic technique (B ultrasound etc.) and radionuclide scanning (SPECT, PET etc.) etc..
Since image documentation equipment acquires and handle the difference of aspect and the difference in perception of human vision etc., finally connect
The medical image information received there is various kinds difference, therefore how from diagnostic value angle, cure by comprehensive comprehensively evaluation
Image technology (including medical imaging device and method) is learned, it is most important to the development of Medical Imaging.
From diagnostic value angle, the core aspect for evaluating Medical Imaging Technology is the evaluation to its precision, i.e.,
The evaluation of picture quality.Due to the image-forming principle and tissue of the medical image property difference of itself so that medical image has multiple
Polygamy and diversity, the evaluation of picture quality must be to provide accurate diagnostic message as cardinal principle, and evaluation result will
Reflect fidelity of the image to diagnostic message.
However the evaluation of existing picture quality is all based on image specific physical quantity and picture quality is evaluated, example
Such as, the Y-PSNR of image, mean square error, entropy etc..These are based on the specific physical quantity of image to the evaluation side of picture quality
Method completely can only can not really reflect fidelity of the image to diagnostic message from one-sided evaluation image quality, can not
Provide the evaluation result with diagnostic value.For example, peak value signal-to-noise ratio but diagnostic value comprising a little artifacts may not
Lower peak value signal-to-noise ratio but artifact-free image can be higher than.In fact, radiologist is artifact-free from low peak signal-to-noise ratio
More effective diagnostic messages can be often obtained in figure.Therefore, there are one for the method for existing one-sided evaluation image quality
It settles finally sex-limited, and this limitation is increasingly emphasized by academia.
Therefore, how from medical image final purpose --- the angle of medical diagnosis on disease is provided with diagnostic value
The evaluation result of Medical Imaging Technology be that industry is continually striving to solve the problems, such as.
Invention content
In view of this, this application provides a kind of evaluation method and device of Medical Imaging Technology, have diagnosis to provide
The evaluation result of the Medical Imaging Technology of value.
In order to achieve the above-mentioned object of the invention, the application employs following technical solution：
A kind of evaluation method of Medical Imaging Technology, including：
Obtain the medical image obtained by Medical Imaging Technology to be evaluated；
It is measured from the medical image and obtains multiple parameter indexes for being used to weigh Medical Imaging Technology；The multiple use
Include multiple images mass parameter in the parameter index for weighing Medical Imaging Technology；
By multiple Medical Imaging Technology evaluation trained in advance is input to for weighing the parameter index of Medical Imaging Technology
In model；
The output of the Medical Imaging Technology evaluation model is obtained as a result, the output result is as medical image to be evaluated
The evaluation result of technology；
The Medical Imaging Technology evaluation model is used to weigh medical image skill according to the multiple of medical image training sample
The parameter index of art and the medical diagnostic information fidelity evaluation result of medical image training sample train to obtain.
Optionally, the method further includes：
Advance training of medical image technology evaluation model.
Optionally, the advance training of medical image technology evaluation model, specifically includes：
N number of medical image training sample is obtained, N is positive integer；
Obtain respectively each medical image training sample it is multiple for weigh Medical Imaging Technology parameter indexes and
Medical diagnostic information fidelity evaluation result；
Multiple parameter index and medical diagnosis for being used to weigh Medical Imaging Technology of the N number of medical image training sample of training
Correspondence between fidelity of information evaluation result, so as to obtain Medical Imaging Technology evaluation model.
Optionally, the Medical Imaging Technology evaluation model is one kind in linear function model and BP network models.
Optionally, Y-PSNR of the described multiple images mass parameter index including image, mean square error, structure are similar
At least two in degree, difference in perception model, entropy.
Optionally, the multiple cost that medical imaging device is further included for the parameter index of weighing Medical Imaging Technology
At least one of parameter, the robustness parameter of medical image imaging method and medical image sweep time parameter.
A kind of evaluating apparatus of Medical Imaging Technology, including:
First acquisition unit, for obtaining the medical image obtained by Medical Imaging Technology to be evaluated；
Measuring unit obtains multiple parameters for weighing Medical Imaging Technology and refers to for being measured from the medical image
Mark, it is the multiple to include multiple images mass parameter for weighing the parameter index of Medical Imaging Technology；
Input unit, for being input to medicine trained in advance by multiple for weighing the parameter index of Medical Imaging Technology
In image technology evaluation model；
Second acquisition unit, for obtaining the output of the Medical Imaging Technology evaluation model as a result, the output result
Evaluation result as Medical Imaging Technology to be evaluated；
Wherein, the Medical Imaging Technology evaluation model is used to weigh medicine shadow according to the multiple of medical image training sample
As the parameter index of technology and the medical diagnostic information fidelity evaluation result of medical image training sample train to obtain.
Optionally, described device further includes training unit, for advance training of medical image technology evaluation model.
Optionally, the training unit includes：
First obtains subelement, and for obtaining N number of medical image training sample, N is positive integer；
Second obtains subelement, is used to weigh medical image for obtaining the multiple of each medical image training sample respectively
The parameter index of technology and medical diagnostic information fidelity evaluation result；
Training subelement, for training multiple ginsengs for being used to weigh Medical Imaging Technology of N number of medical image training sample
Correspondence between number index and medical diagnostic information fidelity evaluation result, so as to obtain Medical Imaging Technology evaluation mould
Type.
A kind of terminal device, the terminal device include：
Processor and memory；
Said program code for storing program code, and is transferred to the processor by the memory；
The processor, for the instruction perform claim in memory to be called to require the medicine shadow described in 1-6 any one
As the evaluation method of technology.
Compared to the prior art, the application has the advantages that：
Based on above technical scheme it is found that the evaluation method of Medical Imaging Technology provided by the embodiments of the present application is based in advance
Trained Medical Imaging Technology evaluation model evaluates Medical Imaging Technology.Because Medical Imaging Technology evaluation model is root
Multiple according to medical image training training sample train sample for weighing the parameter index of Medical Imaging Technology and medical image
This medical diagnostic information fidelity evaluation result trains to obtain, and therefore, the embodiment of the present application will be measured from medical image
To it is multiple be input in Medical Imaging Technology evaluation model for the parameter index of weighing Medical Imaging Technology after, can obtain
Reflect the output of medical diagnostic information fidelity as a result, the evaluation result of the output result as Medical Imaging Technology.Thus
It is obtained with the evaluation result of reflection medical diagnostic information fidelity.The evaluation result of the reflection medical diagnostic information fidelity
The diagnostic value of medical image can be weighed.Therefore, the evaluation method of Medical Imaging Technology provided by the embodiments of the present application
Can be from the final purpose of medical image --- the angle of medical diagnosis on disease provides the Medical Imaging Technology with diagnostic value
Evaluation result.
Description of the drawings
In order to which the specific implementation of the application is expressly understood, used when the application specific implementation is described below
Attached drawing do a brief description.
Fig. 1 show a kind of flow of the training method of Medical Imaging Technology evaluation model provided by the embodiments of the present application
Figure；
Fig. 2 show a kind of flow chart of Medical Imaging Technology evaluation method provided by the embodiments of the present application；
Fig. 3 show a kind of Medical Imaging Technology for motion artifacts correcting technology provided by the embodiments of the present application and evaluates
The flow chart of the training method of model；
Fig. 4 show a kind of Medical Imaging Technology for motion artifacts correcting technology provided by the embodiments of the present application and evaluates
The flow chart of method；
Fig. 5 show a kind of flow of Medical Imaging Technology evaluation method for CT technologies provided by the embodiments of the present application
Figure；
Fig. 6 show a kind of structure of control device for Medical Imaging Technology evaluation provided by the embodiments of the present application
Figure；
Fig. 7 show a kind of structure chart of the evaluating apparatus of Medical Imaging Technology provided by the embodiments of the present application.
Specific embodiment
As recorded in background technology, existing Medical Imaging Technology evaluation is normally based on the calculating of specific physical quantity,
Such as calculated for the specific physical quantity such as Y-PSNR, mean square error or entropy, the imaging however, as medical image is former
The property difference of reason and tissue itself so that medical image has complexity and diversity, this to be based on specific physical quantity
Evaluation method on the one hand have one-sidedness, completely can not really reflect fidelity of the image to diagnostic message, can not give
The evaluation result of diagnostic value is provided, is inaccurate as medicine is weighed as the evaluation criterion of equipment or method, on the other hand,
This method is not in evaluation from the final purpose of medical image, i.e. the angle of medical diagnosis on disease goes to consider, only from the angle of engineering
Degree goes to weigh, and does not embody the particularity of medical image so that evaluation result accuracy is not high.
In view of this, the embodiment of the present application provides a kind of based on advance trained Medical Imaging Technology evaluation model pair
The method that Medical Imaging Technology is evaluated.Medical Imaging Technology evaluation model is multiple use according to medical image training sample
In the medical diagnostic information fidelity evaluation result for the parameter index and medical image training sample for weighing Medical Imaging Technology
Training obtains, compared to medical diagnostic information fidelity evaluation result is obtained by specific Physical Quantity Calculation in the prior art, originally
Application embodiment traditional Chinese medicine technology evaluation model has fully considered the multiple parameters index for weighing Medical Imaging Technology, the letter of acquisition
It ceases more comprehensively, after the multiple parameters index measured from medical image is input in Medical Imaging Technology evaluation model,
Obtained output result can more accurately react medical diagnostic information fidelity, can be used for weighing the clinic of medical image
Diagnostic value.
It is to be appreciated that the Medical Imaging Technology described in the embodiment of the present application includes medical imaging device and medical image is imaged
At least one of method.
In order to be easier to understand Medical Imaging Technology evaluation method provided by the embodiments of the present application, below first with reference to attached drawing
To the Medical Imaging Technology evaluation model introduction in the embodiment of the present application.
Fig. 1 show the embodiment of the present application and provides a kind of flow chart of the training method of Medical Imaging Technology evaluation model,
Fig. 1 is please referred to, this method includes：
S101：Obtain N number of medical image training sample.
Medical image training sample can be understood as the medical image sample for training pattern.Medical image training sample
Can be obtained from medical imaging device, for example, from medical x-ray machine, digital image apparatus, x-ray computer tomography equipment,
Acquired ordinary x-ray photography, computer x-ray in MR imaging apparatus, supersonic imaging apparatus and/or nuclear medical imaging device
It photographs (Computed Radiography, CR), digital radiography (Digital Radiography, DR), Digital Subtraction blood
Pipe radiography (Digital Substraction Angiography, DSA), computer x line tomoscans (Computed
Tomography, CT), magnetic resonance imaging (Magnetic Resource Imaging, MRI), ultrasonic technique (B ultrasound, B-scan
Ultrasonography) and/or positive electron sends tomography technology (Positron Emission Tomography, PET)
Deng.Wherein, medical image training sample can be the historical data of above-mentioned medical imaging device, can also be by medical imaging device
It obtains in real time.
N is the quantity of medical image training sample, it will be understood that for trained medical image training samples number at least
It it is one, that is to say, that N is positive integer.The quantity N of medical image training sample is bigger, to Medical Imaging Technology evaluation model
Training is more advantageous, is particularly advantageous for improving the accuracy rate of Medical Imaging Technology evaluation model.
S102：Multiple parameter indexes for being used to weigh Medical Imaging Technology of each medical image training sample are obtained respectively
And medical diagnostic information fidelity evaluation result.
Industry usually weighs Medical Imaging Technology using picture quality.Moreover, doctor is carried out from medical image
Condition-inference.Therefore, in order to from the angle of medical diagnosis on disease, provide the evaluation knot of the Medical Imaging Technology with diagnostic value
Fruit weighs the parameter index that Medical Imaging Technology parameter index includes at least the picture quality for weighing medical image.
In the embodiment of the present application in some possible realization methods, the parameter index packet of the picture quality of medical image is weighed
Include Y-PSNR, mean square error, structural similarity, difference in perception model and entropy of image etc., can obtain it is therein extremely
Few two training for being used for Medical Imaging Technology evaluation model.
In addition, in order to comprehensively evaluate Medical Imaging Technology, promote the improvement and development of Medical Imaging Technology, remove
It, can also from medicine outside the precision aspect of i.e. Medical Imaging Technology evaluates Medical Imaging Technology in terms of the picture quality
Image documentation equipment cost, the robustness of imaging method, sweep time length etc. evaluate Medical Imaging Technology.Therefore,
In the embodiment of the present application in some possible realization methods, multiple parameters for being used to weigh Medical Imaging Technology of this step acquisition
Index can also include the cost parameter of medical imaging device, the robustness parameter of medical image imaging method and medical image and sweep
Retouch at least one of time parameter.
Multiple parameter indexes for weighing Medical Imaging Technology are got using this, can picture be cured to medicine from many aspects
Technology carries out overall merit, and overcoming traditional one-sided evaluation method has the shortcomings that one-sidedness, thus can be more accurate, complete
Evaluate Medical Imaging Technology to face.
Medical diagnostic information fidelity evaluation result is a kind of knot evaluated from medical diagnosis on disease angle medical image
Fruit.The evaluation method of traditional calculating based on specific physical quantity, evaluation result is to go to weigh from the angle of engineering, and this Shen
Medical diagnostic information fidelity that please be in embodiment is from final purpose, that is, medical diagnosis on disease of medical image, according to medical image
The diagnostic message included evaluates medical image, medical diagnostic information fidelity evaluation result is obtained, due to fully examining
The particularity of medical image is considered so that more accurate to the evaluation of Medical Imaging Technology.As an example, medical diagnostic information is protected
True degree evaluation result can be evaluated medical image to obtain by clinical expert according to experience.For example, it can incite somebody to action
One clinical expert as medical diagnostic information fidelity evaluation result, evaluates the evaluation of medical image to further improve
As a result accuracy can also determine medical diagnostic information fidelity according to multidigit clinical expert to the evaluation result of medical image
Evaluation result.As more specific example, medical diagnostic information fidelity evaluation result can be clinical expert according to experience
Medical image is assessed to being conducive to the scoring given by the value of medical diagnosis on disease.
In order to make it easy to understand, it is illustrated with reference to specific example.
Getting 2 kinds of images respectively from medical imaging device, one kind has peak value signal-to-noise ratio but comprising a little artifact,
One kind has low peak signal-to-noise ratio but not comprising artifact.If according to traditional evaluation method based on specific physical quantity, such as
The evaluation method of Y-PSNR based on image, then tool is higher than for the evaluation result of the image with peak value signal-to-noise ratio
There is the evaluation result of the image of low peak signal-to-noise ratio.However, medical image is put often for doctor to be assisted to carry out medical diagnosis on disease
The doctor for penetrating section is more likely to using low peak signal-to-noise ratio, artifact-free image, from low peak signal-to-noise ratio but artifact-free figure
More effective diagnostic messages can be obtained as in, that is to say, that from the point of view of diagnosing the illness, for low peak signal-to-noise ratio,
The evaluation result of artifact-free image is better than the evaluation result of peak value signal-to-noise ratio, the image for having artifact.It is this from medical diagnosis on disease
The evaluation result that angle is set out can more accurately react the diagnostic value of medical image, and then can be more accurately to medicine shadow
As technology is evaluated.
S103：Multiple parameter index and doctors for being used to weigh Medical Imaging Technology of the N number of medical image training sample of training
The correspondence between diagnostic message fidelity evaluation result is learned, so as to obtain Medical Imaging Technology evaluation model.
In the multiple parameter indexes and medicine for being used to weigh Medical Imaging Technology for getting medical image training sample
After diagnostic message fidelity evaluation result, the parameter index of Medical Imaging Technology and medical diagnostic information fidelity can will be weighed
Degree evaluation result is trained, and obtains commenting with medical diagnostic information fidelity for weighing the parameter index of Medical Imaging Technology
Correspondence between valency result, and then obtain Medical Imaging Technology evaluation model.
It is corresponding between the parameter index of Medical Imaging Technology and medical diagnostic information fidelity evaluation result for weighing
Relationship can be indicated by function, the multiple parameter indexes and medical diagnostic information for being used to weigh Medical Imaging Technology of training
Correspondence between fidelity evaluation result is equivalent to determining medical diagnostic information fidelity evaluation result and is used to weigh with multiple
The coefficient of parameters in the function expression of the parameter index of size medical image technology namely determining function expression.
It is appreciated that according to the difference of correspondence, the Medical Imaging Technology evaluation model that training obtains also differs.
In some possible realization methods of the embodiment of the present application, Medical Imaging Technology evaluation model can be linear function model and artificial
One kind in neural network (artificial neural networks, ANN) model.Wherein, linear function model can be compared with
It easily realizes, the linear of parameter index that medical diagnostic information evaluation result can be expressed as to multiple characterization picture qualities adds
Then weight function passes through the parameter of multiple measurement medical image qualities in priori, that is, medical image training sample
Index and corresponding medical diagnostic information fidelity evaluation result, obtain the weights of parameters index in linear weighting function
(also referred to as coefficient).Artificial nerve network model can approach arbitrary continuation function, have very strong non-linear mapping capability, flexibly
Property is very big, can more accurately describe medical diagnostic information fidelity.It can be by multiple phenograms of medical image training sample
The parameter index of image quality amount is input in artificial neural network with medical diagnostic information fidelity evaluation result and is trained, with
To corresponding network model.
As the specific example of the application, the specific implementation of this step can be as follows：
Multiple parameter indexes for being used to weigh Medical Imaging Technology are pre-designed to tie with the evaluation of medical diagnostic information fidelity
Then the function expression of fruit refers to according to the multiple of N number of medical image training sample for weighing the parameter of Medical Imaging Technology
Correspondence between mark and medical diagnostic information fidelity evaluation result, is calculated the unknown parameter in function expression.
In this way, it obtains multiple for weighing between the parameter index of Medical Imaging Technology and medical diagnostic information fidelity evaluation result
Functional relation expression formula, the functional relation expression formula is as Medical Imaging Technology evaluation model.
It is illustrated below：
Design multiple parameter indexes for being used to weigh Medical Imaging Technology and medical diagnostic information fidelity evaluation result
Function is linear function, which is：Y=a1*x1+a2*x2+a3*x3, in the function expression, y is each
The medical diagnostic information fidelity evaluation result of medical image training sample, x1, x2, x3For each medical image training sample
For weighing the parameter index of Medical Imaging Technology.
It is used to weigh with corresponding according to the medical diagnostic information fidelity evaluation result of each medical image training sample
The correspondence of the parameter index of Medical Imaging Technology calculates the parameter a in the linear function expression1, a2, a3, treat parameter
a1, a2, a3After obtaining, you can obtain accurately multiple parameter indexes and medical diagnostic information for being used to weigh Medical Imaging Technology
Functional relation between fidelity evaluation result, so as to obtain Medical Imaging Technology evaluation model.
It is a kind of specific implementation of the training method of Medical Imaging Technology evaluation model provided by the embodiments of the present application above
Mode is believed by obtaining the multiple of medical image training sample for weighing the parameter index of Medical Imaging Technology with medical diagnosis
Cease fidelity evaluation result, multiple parameter index and doctors for being used to weigh Medical Imaging Technology of training of medical image training sample
The correspondence between diagnostic message fidelity evaluation result is learned, so as to obtain Medical Imaging Technology evaluation model.Due to obtaining
Multiple parameter indexes for weighing Medical Imaging Technologies so as to the evaluation of medical image more fully, overcome traditional comment
The shortcomings of one-sidedness of valency mode, and Medical Imaging Technology is commented by medical diagnostic information fidelity evaluation result
Valency can embody the particularity of medical image so that the evaluation for Medical Imaging Technology from the angle to diagnose the illness
It is more accurate.
In addition, the method evaluated using the Medical Imaging Technology evaluation model Medical Imaging Technology, it can be very clever
The parameter index of measurement Medical Imaging Technology is selected livingly.And working as has the new parameter index for being used to weigh Medical Imaging Technology to go out
After now, the new parameter index for being used to weigh Medical Imaging Technology may be used and carry out model training, it is corresponding so as to obtain
Evaluation model.
Based on above-mentioned Medical Imaging Technology evaluation model, the embodiment of the present application additionally provides a kind of commenting for Medical Imaging Technology
Valency method.
Fig. 2 show a kind of flow chart of the evaluation method of Medical Imaging Technology provided by the embodiments of the present application, please refers to
Fig. 2, this method include：
S201：Obtain the medical image obtained by Medical Imaging Technology to be evaluated.
Medical Imaging Technology to be evaluated can be applied to the Medical Imaging Technology of medical domain or newly opened
Hair, not yet clinical practice Medical Imaging Technology.For example, Medical Imaging Technology to be evaluated can be DSA, CT or MRI etc..
Obtaining the medical image obtained by Medical Imaging Technology to be evaluated can be by a variety of realization method, such as doctor to be evaluated may be used
The medical imaging device for learning image technology directly shoots acquisition, can also be obtained from the historical data of above-mentioned medical imaging device
It takes.
S202：It is measured from medical image and obtains multiple parameter indexes for being used to weigh Medical Imaging Technology.
Include many indexes for weighing the parameter index of Medical Imaging Technology.Wherein, for the weighing apparatus of medical image quality
It measures most important, that is to say, that the parameter that the parameter index for weighing Medical Imaging Technology can include characterization picture quality refers to
Mark, such as the parameter of the characterization picture quality such as Y-PSNR, mean square error, entropy, difference in perception model and structural similarity
Index, multiple images mass parameter can be therein at least two.In this step, can be measured from medical image obtain it is more
The parameter index of a characterization picture quality, the parameter index of these characterization picture qualities can be used for from the angle pair to diagnose the illness
Medical image is evaluated.
In addition to picture quality, there are many more the application of other factors medical imaging image technology, and then affect to medicine
The evaluation of image technology.For example, the cost of image documentation equipment, the robustness of imaging method and sweep time etc., to medicine shadow
As the evaluation of technology plays an important role.The medical image obtained by Medical Imaging Technology to be evaluated can be obtained, from medicine
It is measured in image and obtains image parameter quality index, obtain the cost parameter of medical imaging equipment, medical imaging imaging method
At least one of robustness parameter and medical imaging sweep time parameter, to be input to Medical Imaging Technology evaluation model,
Obtain comprehensive Medical Imaging Technology evaluation result.
It should be noted that the Medical Imaging Technology parameter index that is used to weigh that this step measures is included in training doctor
It learns in the measurement Medical Imaging Technology parameter index that image technology evaluation model uses.Specifically, what this step measured
For weighing the measurement Medical Imaging Technology that Medical Imaging Technology parameter index is used with training of medical image technology evaluation model
Parameter index can be identical.For example, employed in training of medical image technology evaluation model image quality parameter Y-PSNR,
The cost parameter of mean square deviation and image documentation equipment, then the medical image that the measurement of this step is obtained by Medical Imaging Technology to be evaluated
The cost parameter of image quality parameter Y-PSNR, mean square error and image documentation equipment.If training of medical image technology is evaluated
The robustness of the image quality parameters such as entropy, structural similarity and imaging method is employed in model, then this step measure by
The Shandong of the image quality parameters such as entropy, the structural similarity of medical image that Medical Imaging Technology to be evaluated obtains and imaging method
Stick.
S203：By multiple Medical Imaging Technology trained in advance is input to for weighing the parameter index of Medical Imaging Technology
In evaluation model.
Medical Imaging Technology evaluation model in this step can embodiment illustrated in fig. 1 is trained according to medicine shadow
As technology evaluation model.The parameter index for being used to weigh Medical Imaging Technology and the medicine in this step inputted in this step
The parameter index of image technology evaluation model used medical image training sample in training is identical.
S204：The output of the Medical Imaging Technology evaluation model is obtained as a result, the output result is as doctor to be evaluated
Learn the evaluation result of image technology.
It is commented when the parameter index by multiple for weighing Medical Imaging Technology is input to Medical Imaging Technology trained in advance
After in valency model, by the operation of Medical Imaging Technology evaluation model, evaluation result and the output of Medical Imaging Technology are obtained, from
And the output result of Medical Imaging Technology evaluation model can be got.
The output result can be considered as the evaluation result to the medical image.Since the medical image is by medicine to be evaluated
What image technology obtained, the evaluation result of the medical image is equivalent to a certain extent to Medical Imaging Technology to be evaluated
Evaluation result, therefore can be using the output result as the evaluation result of Medical Imaging Technology to be evaluated.
When the parameter of input Medical Imaging Technology evaluation model further includes the cost parameter of medical imaging device, medical image
When the robustness parameter of imaging method and/or medical image sweep time parameter, the output knot of Medical Imaging Technology evaluation model
Fruit, when can be while Medical Imaging Technology precision be reflected, can also reflect the cost of Medical Imaging Technology, robustness and/
Or efficiency, it is thus possible to than more fully, quantitatively evaluating Medical Imaging Technology to be evaluated.
Specific implementation for the evaluation method of Medical Imaging Technology provided by the embodiments of the present application above.The specific reality
Existing mode is based on advance trained Medical Imaging Technology evaluation model and Medical Imaging Technology is evaluated.Because of medical image skill
Art evaluation model is multiple parameter indexes and medicine for being used to weigh Medical Imaging Technology according to medical image training sample
The medical diagnostic information fidelity evaluation result of image training sample trains to obtain, and therefore, the embodiment of the present application will be from medicine figure
The multiple parameter indexes for being used to weigh Medical Imaging Technology measured as in are input in Medical Imaging Technology evaluation model
Afterwards, the output of reflection medical diagnostic information fidelity can be obtained as a result, the evaluation of the output result as Medical Imaging Technology
As a result.Thus also it is obtained with the evaluation result of reflection medical diagnostic information fidelity.The reflection medical diagnostic information fidelity
The evaluation result of degree can weigh the diagnostic value of medical image.Therefore, medical image skill provided by the embodiments of the present application
The evaluation method of art can be from the final purpose of medical image --- and the angle of medical diagnosis on disease is provided with diagnostic value
The evaluation result of Medical Imaging Technology.
Medical Imaging Technology is evaluated in addition, multiple parameters index may be used in the specific implementation, evaluation knot
The characteristics of fruit can more fully reflect the Medical Imaging Technology relative to traditional evaluation method.It is this comprehensive, quantitative
Medical Imaging Technology evaluation method can more precisely evaluate various Medical Imaging Technologies, as a result of unified measurement mark
Standard goes to weigh the superiority-inferiority of each technology, and various Medical Imaging Technologies effectively can be screened, can be by evaluation result
Preferable Medical Imaging Technology is applied in clinic.
In order to make it easy to understand, with reference to motion artifacts correcting technology in MRI to medicine shadow provided by the embodiments of the present application
As technology evaluation model and Medical Imaging Technology evaluation method are introduced.
Fig. 3 show a kind of flow of the training method of Medical Imaging Technology evaluation model provided by the embodiments of the present application
Figure, please refers to Fig. 3, this method includes：
S301：Obtain N number of image pattern scanned by motion artifacts correcting technology.
In MRI system, for the motion artifacts being difficult to avoid that in scanning process, there are many motion artifacts correcting technology,
In order to therefrom filter out effective motion artifacts correcting technology, unified standard may be used, each technology is evaluated.Tool
Body can train a unified Medical Imaging Technology evaluation model to various motion artifacts correcting technologies to the embodiment of the present application
It is evaluated.
Training of medical image technology evaluation model, it is necessary first to obtain medical image training sample.It in this step, can be with
N number of image pattern scanned by motion artifacts correcting technology is obtained, wherein, N is positive integer.This N number of sample can be by
Different types of motion artifacts correcting technology scans to obtain.
S302：The index for being used to weigh Medical Imaging Technology of each image pattern is measured, uses Y respectively1、Y2…YmIt represents.
In this step, index of each image pattern at m aspect can be measured, since the quantity of image pattern is N,
Therefore the index Y of various aspects1、Y2…YmN-dimensional vector may be used to be indicated.
As an example, m can be 3, Y1、Y2、Y3Y-PSNR, entropy and structural similarity can be represented respectively.
S303：It obtains the medical diagnostic information fidelity that clinical expert assesses each image pattern and evaluates knot
Fruit S.
Since the quantity of image pattern is N, the medical diagnostic information fidelity assessed each image pattern
Evaluation result S may be used N-dimensional vector and be indicated.
The form that marking may be used in medical diagnostic information fidelity evaluation result S is embodied, and is included in image pattern
Diagnostic message it is more, score is higher, and medical diagnostic information fidelity evaluation result S is higher.
S304：The training of medical diagnostic message fidelity evaluation result S and index Y for weighing Medical Imaging Technology1、Y2…Ym
Between function model.
In this step, first order linear function training of medical diagnostic message fidelity evaluation result S may be used with weighing
The index Y of Medical Imaging Technology1、Y2…YmBetween function model.For example, function model can be expressed as follows：
S=b1·Y1+b2·Y2+…bm·Ym (1)
Wherein, b1、b2And bmDeng the coefficient or weights for indices, b in this step1、b2And bmFor unknown number.
It should be noted that the embodiment of the present application does not limit the execution sequence of S302, S303, S304, it can basis
It needs to be configured.For example, may be performed simultaneously S302, S303 and S304, S303 or S304 can also be first carried out.
S305：The indices Y that will be measured in S3021、Y2…YmIt is commented with the medical diagnostic information fidelity obtained in S303
The unknown parameter of function model is calculated in valency result S input function models, and the parameter value after calculating is substituted into function model,
Obtain Medical Imaging Technology evaluation model.
Due to Y1、Y2…YmIt is that N-dimensional is vectorial with S, the indices Y that will be measured in S3021、Y2…YmWith being obtained in S303
Medical diagnostic information fidelity evaluation result S input function models, N number of unknown parameter about function model can be obtained
Equation can obtain the value of unknown parameter in function model to this N number of solving simultaneous equation.Obtained value substitution letter will be solved
Exponential model can obtain Medical Imaging Technology evaluation model.
As an example, when function model is the first order linear function model shown in formula (1), by Y1、Y2…YmWith S
Model is input to, can be obtained N number of about b1、b2……bmEquation, by being solved to equation, b can be obtained1、
b2……bmValue, by b1、b2……bmSubstitution formula (1) obtains Medical Imaging Technology evaluation model.
It is real shown in processes of the above-mentioned S301~S305 for training of medical image technology evaluation model, specific implementation and Fig. 1
Apply that example is similar, the specific implementation process of correlation step may refer to embodiment illustrated in fig. 1, and which is not described herein again.
After Medical Imaging Technology evaluation model of the training for motion artifacts correcting technology, the medical image can be passed through
Technology evaluation model respectively evaluates different motion artifacts correcting technologies.Next, with reference to motion artifacts correcting technology,
The evaluation method of Medical Imaging Technology provided by the embodiments of the present application is introduced.
Fig. 4 show a kind of evaluation method of Medical Imaging Technology provided by the embodiments of the present application, for motion artifacts
Correcting technology is evaluated, and this method includes：
S401：Obtain the medical image obtained by motion artifacts correcting technology to be evaluated.
Motion artifacts correcting technology to be evaluated can be at least one of motion artifacts correcting technology.It obtains by be evaluated
The medical image that motion artifacts correcting technology obtains can be obtained by motion artifacts correcting technology real time scan to be evaluated.
S402：Measure the medical image that motion artifacts correcting technology to be evaluated obtains for weighing Medical Imaging Technology
Parameter index y1、y2…ym。
The implementation procedure of S402 is identical with S302, and which is not described herein again.
S403：The parameter index y that will be measured in S4021、y2…ymMedical Imaging Technology evaluation model is input to, will be exported
As a result the evaluation result as motion artifacts correcting technology to be evaluated.
S401~S403 is pseudo- to movement to be evaluated for the Medical Imaging Technology evaluation model trained by S301~S305
The process that shadow correcting technology is evaluated implements, the specific implementation process of correlation step similar with embodiment illustrated in fig. 2
Embodiment illustrated in fig. 2 can be referred to.
Motion artifacts correcting technology in the embodiment of the present application combination MRI system provides a kind of motion artifacts correcting technology
Evaluation method.N number of image pattern scanned by motion artifacts correcting technology is obtained, obtains the multiple of each image pattern
Believe for weighing the medical diagnosis that the index of Medical Imaging Technology and clinical expert assess each image pattern
Fidelity evaluation result is ceased, according to medical diagnostic information fidelity evaluation result and multiple fingers for being used to weigh Medical Imaging Technology
Target functional relation, training of medical image technology evaluation model.The medicine that motion artifacts correcting technology to be evaluated is scanned
The parameter index for being used to weigh Medical Imaging Technology of image, is input to the Medical Imaging Technology evaluation model, obtains to be evaluated
The evaluation result of motion artifacts correcting technology.Since the Medical Imaging Technology evaluation model is based on motion artifacts correcting technology figure
Decent it is multiple for weigh the indexs of Medical Imaging Technology and clinical expert to the diagnostic value of each image pattern into
Row assessment obtain medical diagnostic information fidelity evaluation result training, on the one hand overcome in conventional method be based only upon it is specific
Physical Quantity Calculation one-sidedness it is specific, the particularity of medical image has on the other hand been fully considered, from the angle to diagnose the illness
Degree evaluates medical image so that evaluation result is closer to reality.By using evaluation side provided by the embodiments of the present application
Formula can combine the diagnostic value of the medical image of motion artifacts correcting technology, from many aspects using unified standard to each
Motion artifacts correcting technology is weighed, so as to filter out effective motion artifacts correcting technology.
Above-described embodiment mainly evaluates Medical Imaging Technology from picture quality level, it is possible to understand that a medicine
Can image technology clinically be widely used also is influenced by many other factors.For example, Medical Imaging Technology
Clinical practice can be restricted by factors such as cost, efficiency, cost is excessively high, sweep time long can influence user
Experience.Therefore, can also be on the basis of based on image quality evaluation for the evaluation of Medical Imaging Technology, integrative medicine image
The cost of equipment, the robustness of medical image image-forming principle and/or medical image sweep time parameter etc. are evaluated.
For below using CT technologies as Medical Imaging Technology to be evaluated, it is situated between to the evaluation method of Medical Imaging Technology
It continues.The embodiment of the present application emphasis is to the cost of integrative medicine image documentation equipment, the robustness and medicine of medical image image-forming principle
The process that image scan time parameter etc. is evaluated is introduced, and other parts are referred to previous embodiment.
Fig. 5 show a kind of flow chart of Medical Imaging Technology evaluation method provided by the embodiments of the present application, please refers to figure
5, this method includes：
S501：Obtain the medical image obtained by CT technologies.
S502：The index for being used to weigh Medical Imaging Technology of the medical image obtained by CT technologies is measured, including peak value
Signal-to-noise ratio, mean square error, entropy, structural similarity, the cost of medical imaging device, the robustness of medical image image-forming principle and
Medical image sweep time.
Wherein, Y-PSNR, mean square error, entropy, structural similarity are image quality parameter index, are mainly used for from figure
Medical Imaging Technology is evaluated in terms of image quality amount etc., the cost of medical imaging device, the robust of medical image image-forming principle
Property and medical image sweep time mainly from Medical Imaging Technology in itself such as cost, robustness, efficiency etc. to medicine
Image technology is evaluated.Can be to Medical Imaging Technology to be evaluated using These parameters, such as the CT in the embodiment of the present application
Technology carries out many-sided, multi-angle quantitative overall merit, while evaluation image quality, also to the cost of equipment, imaging
Time efficiency etc. evaluated.
S503：Multiple indexs for being used to weigh Medical Imaging Technology that measurement obtains are input to medicine shadow trained in advance
As technology evaluation model.
In order to facilitate expression, can by Y-PSNR, mean square error, entropy, structural similarity, medical imaging device into
Originally, y is respectively adopted in the robustness of medical image image-forming principle and medical image sweep time1、y2…y7It is indicated.In advance
Trained Medical Imaging Technology evaluation model can be expressed as：
S=f (y1,y2,y3,y4,y5,y6,y7) (2)
Wherein, S represents the medical diagnostic information fidelity evaluation result for medical image.By formula (2) it is found that for doctor
Learning the medical diagnostic information fidelity evaluation result of image can be expressed as about Y-PSNR y1, mean square error y2, entropy y3、
Structural similarity y4, medical imaging device cost y5, medical image image-forming principle robustness y6And during medical image scanning
Between y7Function.
As a result of Y-PSNR y1, mean square error y2, entropy y3, structural similarity y4, can from image-forming principle and
The various aspects such as property difference of tissue itself are evaluated the picture quality of Medical Imaging Technology, and employ medical image
The cost y of equipment5, medical image image-forming principle robustness y6And medical image sweep time y7It can be except picture quality
Other levels in addition evaluate Medical Imaging Technology so that evaluation result is more comprehensively, more accurately.
S504：The output of Medical Imaging Technology evaluation model is obtained as a result, using the output result as the evaluation of CT technologies
As a result.
Due to the output the result is that by the various aspects such as picture quality, equipment cost, imaging efficiency, multi-angle to CT technologies
It is that the medical image of acquisition is evaluated as a result, therefore, can using for the evaluation result of the medical image as to be evaluated
The evaluation result of CT technologies.
The embodiment of the present application provides a kind of Medical Imaging Technology evaluation method, passes through the medicine figure that will be obtained by CT technologies
As in multiple indexs such as picture quality level, equipment cost level, image-forming principle robustness level, imaging efficiency level, input
To Medical Imaging Technology evaluation model trained in advance, the Medical Imaging Technology evaluation model can from picture quality, equipment into
The many levels such as sheet, robustness, imaging efficiency evaluate Medical Imaging Technology, using the output result of the model as CT skills
The evaluation result of art can fully reflect diagnostic value, cost, robustness and the imaging efficiency of CT technologies, this evaluation side
Formula relative to traditional evaluation method based on specific physical quantity more fully, it is also more accurate.
Above-described embodiment provide Medical Imaging Technology evaluation method can be as shown in Figure 6 control device perform.Fig. 6
Shown control device include processor (processor) 610, communication interface (Communications Interface) 620,
Memory (memory) 630, bus 640.Processor 610, communication interface 620, memory 630 are completed mutually by bus 640
Between communication.
Wherein, the evaluation instruction of Medical Imaging Technology can be stored in memory 630, which for example can be with right and wrong
Volatile memory (non-volatile memory).Processor 610 can call the medical image performed in memory 630
The logical order of technology evaluation, to perform the evaluation method of above-mentioned Medical Imaging Technology.As embodiment, the medical image skill
The logical order of the evaluation of art can the corresponding program of software in order to control, when processor performs the instruction, control device can be with
The corresponding function interface of the instruction is accordingly shown on display interface.
If the function of the logical order of the evaluation of Medical Imaging Technology realized in the form of SFU software functional unit and as
Independent product is sold or in use, can be stored in a computer read/write memory medium.Based on such understanding, sheet
The part or the part of the technical solution that disclosed technical solution substantially in other words contributes to the prior art can be with
The form of software product embodies, which is stored in a storage medium, including some instructions to
(can be personal computer, server or the network equipment etc.) performs each implementation of the present invention so that computer equipment
The all or part of step of example method.And aforementioned storage medium includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with
Store the medium of program code.
The logical order of the evaluation of above-mentioned Medical Imaging Technology is properly termed as " evaluating apparatus of Medical Imaging Technology ",
The device can be divided into each function module.Referring specifically to following embodiment.
The specific embodiment of the evaluating apparatus of Medical Imaging Technology provided by the embodiments of the present application is described below.
Fig. 7 show a kind of structure chart of the evaluating apparatus of Medical Imaging Technology provided by the embodiments of the present application, please refers to
Fig. 7, the device include first acquisition unit 701, measuring unit 702, input unit 703 and second acquisition unit 704,
In：
First acquisition unit 701, for obtaining the medical image obtained by Medical Imaging Technology to be evaluated；
Measuring unit 702 obtains multiple parameters for weighing Medical Imaging Technology and refers to for being measured from medical image
Mark, it is multiple to include multiple images mass parameter for weighing the parameter index of Medical Imaging Technology；
Input unit 703, for being input to training in advance by multiple for weighing the parameter index of Medical Imaging Technology
In Medical Imaging Technology evaluation model；
Second acquisition unit 704, for obtaining the output of Medical Imaging Technology evaluation model as a result, output result is used as and treats
Evaluate the evaluation result of Medical Imaging Technology；
Wherein, Medical Imaging Technology evaluation model is used to weigh medical image skill according to the multiple of medical image training sample
The parameter index of art and the medical diagnostic information fidelity evaluation result of medical image training sample train to obtain.
Optionally, which further includes training unit, for advance training of medical image technology evaluation model.
Optionally, training unit includes：
First obtains subelement, and for obtaining N number of medical image training sample, the number of medical image training sample is N,
N is positive integer；
Second obtains subelement, is used to weigh medical image for obtaining the multiple of each medical image training sample respectively
The parameter index of technology and medical diagnostic information fidelity evaluation result；
Training subelement, for training multiple ginsengs for being used to weigh Medical Imaging Technology of N number of medical image training sample
Correspondence between number index and medical diagnostic information fidelity evaluation result, so as to obtain Medical Imaging Technology evaluation mould
Type.
Optionally, Medical Imaging Technology evaluation model is one kind in linear function model and BP network models.
Optionally, the Y-PSNR of multiple images mass parameter index including image, mean square error, structural similarity,
At least two in difference in perception model, entropy.
Optionally, multiple costs that medical imaging device is further included for weighing the parameter index of Medical Imaging Technology are joined
At least one of number, the robustness parameter of medical image imaging method and medical image sweep time parameter.
It is to be appreciated that the evaluating apparatus of Medical Imaging Technology provided by the embodiments of the present application with it is provided by the embodiments of the present application
The evaluation method of Medical Imaging Technology is corresponding, and the technique effect reached is also opposite with the technique effect that evaluation method reaches
It should.For the sake of brevity, it is not described in detail herein, refers to the corresponding technique effect of acquisition methods of above-mentioned example.
The foregoing description of the disclosed embodiments enables professional and technical personnel in the field to realize or using the application.
A variety of modifications of these embodiments will be apparent for those skilled in the art, it is as defined herein
General Principle can in other embodiments be realized in the case where not departing from spirit herein or range.Therefore, the application
The embodiments shown herein is not intended to be limited to, and is to fit to and the principles and novel features disclosed herein phase one
The most wide range caused.
Claims (10)
1. a kind of evaluation method of Medical Imaging Technology, which is characterized in that including：
Obtain the medical image obtained by Medical Imaging Technology to be evaluated；
It is measured from the medical image and obtains multiple parameter indexes for being used to weigh Medical Imaging Technology；It is the multiple to be used to weigh
The parameter index of size medical image technology includes multiple images mass parameter；
By multiple Medical Imaging Technology evaluation model trained in advance is input to for weighing the parameter index of Medical Imaging Technology
In；
The output of the Medical Imaging Technology evaluation model is obtained as a result, the output result is as Medical Imaging Technology to be evaluated
Evaluation result；
The Medical Imaging Technology evaluation model is used to weigh Medical Imaging Technology according to the multiple of medical image training sample
The medical diagnostic information fidelity evaluation result of parameter index and medical image training sample trains to obtain.
2. according to the method described in claim 1, it is characterized in that, the method further includes：
Advance training of medical image technology evaluation model.
3. according to the method described in claim 2, it is characterized in that, the advance training of medical image technology evaluation model, tool
Body includes：
N number of medical image training sample is obtained, N is positive integer；
Multiple parameter indexes and medicine for being used to weigh Medical Imaging Technology of each medical image training sample are obtained respectively
Diagnostic message fidelity evaluation result；
Multiple parameter indexes and medical diagnostic information for being used to weigh Medical Imaging Technology of the N number of medical image training sample of training
Correspondence between fidelity evaluation result, so as to obtain Medical Imaging Technology evaluation model.
4. according to claim 1-3 any one of them evaluation methods, which is characterized in that the Medical Imaging Technology evaluation model
For one kind in linear function model and BP network models.
5. according to the evaluation method described in claim 1-3, which is characterized in that described multiple images mass parameter index includes figure
At least two in the Y-PSNR of picture, mean square error, structural similarity, difference in perception model, entropy.
6. according to claim 1-3 any one of them evaluation methods, which is characterized in that the multiple to be used to weigh medical image
The parameter index of technology further includes the robustness parameter and medicine of the cost parameter of medical imaging device, medical image imaging method
At least one of image scan time parameter.
7. a kind of evaluating apparatus of Medical Imaging Technology, which is characterized in that including:
First acquisition unit, for obtaining the medical image obtained by Medical Imaging Technology to be evaluated；
Measuring unit obtains multiple parameter indexes for being used to weigh Medical Imaging Technology for being measured from the medical image,
It is the multiple to include multiple images mass parameter for weighing the parameter index of Medical Imaging Technology；
Input unit, for being input to medical image trained in advance by multiple for weighing the parameter index of Medical Imaging Technology
In technology evaluation model；
Second acquisition unit, for obtaining the output of the Medical Imaging Technology evaluation model as a result, the output result conduct
The evaluation result of Medical Imaging Technology to be evaluated；
Wherein, the Medical Imaging Technology evaluation model is used to weigh medical image skill according to the multiple of medical image training sample
The parameter index of art and the medical diagnostic information fidelity evaluation result of medical image training sample train to obtain.
8. device according to claim 7, which is characterized in that described device further includes training unit, for training in advance
Medical Imaging Technology evaluation model.
9. device according to claim 8, which is characterized in that the training unit includes：
First obtains subelement, and for obtaining N number of medical image training sample, N is positive integer；
Second obtains subelement, is used to weigh Medical Imaging Technology for obtaining the multiple of each medical image training sample respectively
Parameter index and medical diagnostic information fidelity evaluation result；
Training subelement, for the multiple of N number of medical image training sample to be trained to refer to for weighing the parameter of Medical Imaging Technology
Correspondence between mark and medical diagnostic information fidelity evaluation result, so as to obtain Medical Imaging Technology evaluation model.
10. a kind of terminal device, which is characterized in that the terminal device includes：
Processor and memory；
Said program code for storing program code, and is transferred to the processor by the memory；
The processor, for the instruction perform claim in memory to be called to require the medical image skill described in 1-6 any one
The evaluation method of art.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810030984.6A CN108171272A (en) | 2018-01-12 | 2018-01-12 | A kind of evaluation method and device of Medical Imaging Technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810030984.6A CN108171272A (en) | 2018-01-12 | 2018-01-12 | A kind of evaluation method and device of Medical Imaging Technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108171272A true CN108171272A (en) | 2018-06-15 |
Family
ID=62514548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810030984.6A Pending CN108171272A (en) | 2018-01-12 | 2018-01-12 | A kind of evaluation method and device of Medical Imaging Technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108171272A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109350100A (en) * | 2018-09-27 | 2019-02-19 | 上海联影医疗科技有限公司 | Medical imaging procedure, medical imaging devices and computer readable storage medium |
| CN109785944A (en) * | 2018-12-13 | 2019-05-21 | 平安医疗健康管理股份有限公司 | Hospital evaluation method and Related product based on data analysis |
| CN109919912A (en) * | 2019-01-28 | 2019-06-21 | 平安科技（深圳）有限公司 | A kind of quality evaluating method and device of medical image |
| CN109933680A (en) * | 2019-03-19 | 2019-06-25 | 北京大学深圳医院 | Image data screening technique, device, computer equipment and its storage medium |
| CN110619447A (en) * | 2018-06-20 | 2019-12-27 | 广州虎牙信息科技有限公司 | Anchor evaluation method, device, equipment and storage medium |
| CN111192660A (en) * | 2019-12-24 | 2020-05-22 | 上海联影智能医疗科技有限公司 | Image report analysis method, equipment and computer storage medium |
| CN111489409A (en) * | 2020-04-24 | 2020-08-04 | 东软医疗系统股份有限公司 | CT image processing method and device, CT equipment and CT system |
| CN111557681A (en) * | 2020-06-03 | 2020-08-21 | 诸暨市人民医院 | Spiral CT image analysis method |
| CN111598883A (en) * | 2020-05-20 | 2020-08-28 | 重庆工程职业技术学院 | Calibration label equipment for acquiring cloud data medical image and working method |
| CN112669940A (en) * | 2020-12-24 | 2021-04-16 | 中电通商数字技术(上海)有限公司 | Quality control film reading method and system based on AI (Artificial Intelligence) image |
| CN112767307A (en) * | 2020-12-28 | 2021-05-07 | 上海联影智能医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN112862342A (en) * | 2021-02-26 | 2021-05-28 | 复旦大学附属中山医院 | Intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence |
| CN114783558A (en) * | 2022-04-25 | 2022-07-22 | 四川大学华西医院 | CTPA image report generation system for pulmonary embolism patients |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1934589A (en) * | 2004-03-23 | 2007-03-21 | 美国西门子医疗解决公司 | Systems and methods providing automated decision support for medical imaging |
| CN102945552A (en) * | 2012-10-22 | 2013-02-27 | 西安电子科技大学 | No-reference image quality evaluation method based on sparse representation in natural scene statistics |
| CN104424385A (en) * | 2013-08-22 | 2015-03-18 | 上海联影医疗科技有限公司 | Method and device for evaluating medical images |
| CN104463828A (en) * | 2013-09-18 | 2015-03-25 | 株式会社日立医疗器械 | CT image evaluation device and CT image evaluation method |
| US20160174943A1 (en) * | 2013-08-09 | 2016-06-23 | Koninklijke Philips N.V. | Method and system for medical imaging and information display |
-
2018
- 2018-01-12 CN CN201810030984.6A patent/CN108171272A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1934589A (en) * | 2004-03-23 | 2007-03-21 | 美国西门子医疗解决公司 | Systems and methods providing automated decision support for medical imaging |
| CN102945552A (en) * | 2012-10-22 | 2013-02-27 | 西安电子科技大学 | No-reference image quality evaluation method based on sparse representation in natural scene statistics |
| US20160174943A1 (en) * | 2013-08-09 | 2016-06-23 | Koninklijke Philips N.V. | Method and system for medical imaging and information display |
| CN104424385A (en) * | 2013-08-22 | 2015-03-18 | 上海联影医疗科技有限公司 | Method and device for evaluating medical images |
| CN104463828A (en) * | 2013-09-18 | 2015-03-25 | 株式会社日立医疗器械 | CT image evaluation device and CT image evaluation method |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619447A (en) * | 2018-06-20 | 2019-12-27 | 广州虎牙信息科技有限公司 | Anchor evaluation method, device, equipment and storage medium |
| CN110619447B (en) * | 2018-06-20 | 2023-03-24 | 广州虎牙信息科技有限公司 | Anchor evaluation method, device, equipment and storage medium |
| CN109350100A (en) * | 2018-09-27 | 2019-02-19 | 上海联影医疗科技有限公司 | Medical imaging procedure, medical imaging devices and computer readable storage medium |
| CN109785944B (en) * | 2018-12-13 | 2023-02-10 | 平安医疗健康管理股份有限公司 | Hospital evaluation method based on data analysis and related products |
| CN109785944A (en) * | 2018-12-13 | 2019-05-21 | 平安医疗健康管理股份有限公司 | Hospital evaluation method and Related product based on data analysis |
| CN109919912A (en) * | 2019-01-28 | 2019-06-21 | 平安科技（深圳）有限公司 | A kind of quality evaluating method and device of medical image |
| CN109933680A (en) * | 2019-03-19 | 2019-06-25 | 北京大学深圳医院 | Image data screening technique, device, computer equipment and its storage medium |
| CN111192660A (en) * | 2019-12-24 | 2020-05-22 | 上海联影智能医疗科技有限公司 | Image report analysis method, equipment and computer storage medium |
| CN111192660B (en) * | 2019-12-24 | 2023-10-13 | 上海联影智能医疗科技有限公司 | Image report analysis method, device and computer storage medium |
| CN111489409A (en) * | 2020-04-24 | 2020-08-04 | 东软医疗系统股份有限公司 | CT image processing method and device, CT equipment and CT system |
| CN111598883A (en) * | 2020-05-20 | 2020-08-28 | 重庆工程职业技术学院 | Calibration label equipment for acquiring cloud data medical image and working method |
| CN111557681A (en) * | 2020-06-03 | 2020-08-21 | 诸暨市人民医院 | Spiral CT image analysis method |
| CN112669940A (en) * | 2020-12-24 | 2021-04-16 | 中电通商数字技术(上海)有限公司 | Quality control film reading method and system based on AI (Artificial Intelligence) image |
| CN112767307A (en) * | 2020-12-28 | 2021-05-07 | 上海联影智能医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN112862342A (en) * | 2021-02-26 | 2021-05-28 | 复旦大学附属中山医院 | Intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence |
| CN114783558A (en) * | 2022-04-25 | 2022-07-22 | 四川大学华西医院 | CTPA image report generation system for pulmonary embolism patients |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108171272A (en) | A kind of evaluation method and device of Medical Imaging Technology | |
| US11116471B2 (en) | Methods and apparatus for extended low contrast detectability for radiographic imaging systems | |
| CN102871686B (en) | The apparatus and method of physiological parameter are measured based on 3D medical image | |
| CN109035284B (en) | Heart CT image segmentation method, device, equipment and medium based on deep learning | |
| JP2021521993A (en) | Image enhancement using a hostile generation network | |
| CN109166087A (en) | Style conversion method, device, medical supply, image system and the storage medium of medical image | |
| US9652872B2 (en) | System and method of medical imaging | |
| CN107464231B (en) | System and method for determining optimal operating parameters for medical imaging | |
| Hansegård et al. | Semi-automated quantification of left ventricular volumes and ejection fraction by real-time three-dimensional echocardiography | |
| CN100345162C (en) | Method of determining an image from an image sequence | |
| WO2012064986A2 (en) | System and method of ultrasound image processing | |
| CN111666966B (en) | Material decomposition based on artificial intelligence in medical imaging | |
| CN109754397B (en) | Blood vessel section center path extraction method and device, terminal equipment and storage medium | |
| EP3890642A2 (en) | Method, device and system for intracavity probe procedure planning | |
| CN113159040B (en) | Method, device and system for generating medical image segmentation model | |
| Reddy et al. | Video-based deep learning for automated assessment of left ventricular ejection fraction in pediatric patients | |
| JP6888041B2 (en) | How to get a medical sagittal image, how to train a neural network to get a medical sagittal image, and a computer device | |
| Karatas et al. | A deep learning approach to dental restoration classification from bitewing and periapical radiographs | |
| Mansell et al. | Comparison of the within-reader and inter-vendor agreement of left ventricular circumferential strains and volume indices derived from cardiovascular magnetic resonance imaging | |
| WO2020007026A1 (en) | Segmentation model training method and apparatus, and computer-readable storage medium | |
| CN110197472A (en) | A kind of method and system for ultrasonic contrast image stabilization quantitative analysis | |
| EP3597107B1 (en) | Topogram-based fat quantification for a computed tomography examination | |
| CN111325758A (en) | Lung image segmentation method and device and training method of image segmentation model | |
| CN110063739A (en) | Method for correcting image, device and the electronic equipment of SPECT and PET | |
| CN115797252A (en) | Patient anatomy and task specific automatic exposure control in computed tomography |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |
|
| RJ01 | Rejection of invention patent application after publication |