CN110037718A - Hardware state analysis method, device, computer equipment and storage medium - Google Patents
Hardware state analysis method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110037718A CN110037718A CN201910333538.7A CN201910333538A CN110037718A CN 110037718 A CN110037718 A CN 110037718A CN 201910333538 A CN201910333538 A CN 201910333538A CN 110037718 A CN110037718 A CN 110037718A
- Authority
- CN
- China
- Prior art keywords
- data
- radiation
- radiation counter
- pet system
- counter data
- 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.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/02—Devices for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computerised tomographs
- A61B6/037—Emission tomography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/58—Testing, adjusting or calibrating apparatus or devices for radiation diagnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/58—Testing, adjusting or calibrating apparatus or devices for radiation diagnosis
- A61B6/581—Remote testing of the apparatus or devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/58—Testing, adjusting or calibrating apparatus or devices for radiation diagnosis
- A61B6/586—Detection of faults or malfunction of the device
Abstract
This application involves a kind of hardware state analysis methods, device, computer equipment and storage medium, radiation counter data under the different conditions that computer equipment will acquire are input in preset neural network, the hardware state of available PET system analyzes data, it is used to predict the radiation counter data after default operating time due to the hardware state analysis data of the PET system, the radiation counter data of original state and the uniformity data of scan image, it is equivalent to from hardware state of many aspects to PET system and is analyzed, the case where effective concentrated expression PET system hardware state.
Description
Technical field
This application involves medicine technology fields, more particularly to a kind of hardware state analysis method, device, computer equipment
And storage medium.
Background technique
Positron e mission computed tomography (Positron Emission Computed Tomography, PET)
It is the more advanced clinical examination image technology of the field of nuclear medicine.In clinical application, the hardware state of PET system needs daily
It is monitored, to guarantee the accuracy of the image data of acquisition.
The process being monitored generally for the hardware state of PET system is to acquire the radiometer of PET system hardware daily
Number data, for example, single, coincidence data, then analyze the hard of current PET system according to the radiation counter data
Part state.In practical applications, the hardware state of PET system can generate variation over time, to influence acquisition
Image data accuracy, when monitoring PET system hardware state, need from comprehensive factor consider PET system hardware shape
State bring influences, that is, just knows that the current state of current PE T system hardware is inadequate.
Therefore, the case where reflection PET system hardware state that current PET hardware state analysis method cannot integrate.
Summary of the invention
Based on this, it is necessary to which the reflection PET system that cannot be integrated for above-mentioned current PET hardware state analysis method is hard
The technical issues of the case where part state, provides a kind of hardware state analysis method, device, computer equipment and storage medium.
In a first aspect, the embodiment of the present application provides a kind of hardware state analysis method, this method comprises:
Obtain the first radiation counter data under PET system original state；
The second radiation counter data after obtaining PET system work preset duration；
First radiation counter data and the second radiation counter data are input in preset neural network, PET is obtained
The hardware state of system analyzes data；The hardware state analysis data of the PET system are used to predict after default operating time
Radiation counter data, the radiation counter data of original state and the uniformity data of scan image.
Above-mentioned neural network includes the first sub-neural network and the second sub-neural network in one of the embodiments,；
It is then above-mentioned that first radiation counter data and the second radiation counter data are input in preset neural network, it obtains
Hardware state to PET system analyzes data, comprising:
First radiation counter data are input to the first sub-neural network, it is corresponding default to obtain the first radiation counter data
Radiation counter data after operating time；
Second radiation counter data are input to the first sub-neural network, obtain the corresponding standard of the second radiation counter data
Radiation counter data；
Second radiation counter data are input to the second sub-neural network, obtain the corresponding scanning of the second radiation counter data
The uniformity data of image.
The above method in one of the embodiments, further include:
After obtaining the multiple first sample radiation counter data and multiple work preset durations of PET system in the initial state
The second sample radiation enumeration data；
Using each first sample radiation counter data as input, each second sample radiation enumeration data as output, and will
Each second sample radiation enumeration data is as input, each first sample radiation counter data as output, training the first son nerve
Network initial network model, obtains first nerves network.
This method in one of the embodiments, further include:
Obtain multiple second sample radiation enumeration datas and each second sample spoke of the PET system after the preset duration that works
Penetrate the uniformity data that enumeration data corresponds to scan image；
Using each second sample radiation enumeration data as input, each second sample radiation enumeration data corresponds to scan image
Uniformity data obtains the second sub-neural network as output, the second sub-neural network initial network model of training.
Each second sample radiation enumeration data of above-mentioned acquisition corresponds to the uniformity of scan image in one of the embodiments,
Data, comprising:
Obtain the corresponding bucket source data of each second sample radiation enumeration data；
Bucket source data progress image reconstruction is obtained into the uniformity data of scan image.
Above-mentioned first radiation counter data and the second radiation counter data include PET system in one of the embodiments,
Meet event data in single event data and bucket source on system stick source；Single event data include strength distributing information and energy point
Cloth information；Meeting event data includes strength distributing information and flight time distributed intelligence.
In one of the embodiments, when the single event data in acquisition rod source, stick source is located at the visual field center of PET system.
When meeting event data of bucket source is acquired in one of the embodiments, and bucket source is located at the visual field in PET system axle center
Center；PET system axle center is overlapped with the axle center in stick source.
Second aspect, the embodiment of the present application provide a kind of hardware state analytical equipment, which includes:
First data acquisition module, for obtaining the first radiation counter data under PET system original state；
Second data acquisition module, for obtain PET system work preset duration after the second radiation counter data；
Data prediction module is analyzed, it is preset for being input to the first radiation counter data and the second radiation counter data
In neural network, the hardware state analysis data of PET system are obtained；The hardware state analysis data of PET system are for predicting
Radiation counter data, the radiation counter data of original state and the uniformity data of scan image after default operating time.
The third aspect, the embodiment of the present application provide a kind of computer equipment, including memory and processor, memory storage
There is computer program, processor realizes the step for any one method that above-mentioned first aspect embodiment provides when executing computer program
Suddenly.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer program,
The step of any one method that above-mentioned first aspect embodiment provides is realized when computer program is executed by processor.
A kind of hardware state analysis method, device, computer equipment and storage medium provided by the embodiments of the present application calculate
Radiation counter data under the different conditions that machine equipment will acquire are input in preset neural network, available PET system
Hardware state analyze data, since the hardware state analysis data of the PET system are for after predicting default operating time
Radiation counter data, the radiation counter data of original state and the uniformity data of scan image, are equivalent to from many aspects pair
The case where hardware state of PET system is analyzed, effective concentrated expression PET system hardware state.
Detailed description of the invention
Fig. 1 is a kind of hardware state analysis method application environment that one embodiment provides；
Fig. 2 is a kind of flow diagram for hardware state analysis method that one embodiment provides；
Fig. 3 is a kind of flow diagram for hardware state analysis method that one embodiment provides；
Fig. 4 is a kind of flow diagram for hardware state analysis method that one embodiment provides；
Fig. 5 is a kind of flow diagram for hardware state analysis method that one embodiment provides；
Fig. 6 is a kind of flow diagram for hardware state analysis method that one embodiment provides；
Fig. 7 is a kind of data acquisition environment top view for hardware state analysis method that one embodiment provides；
Fig. 8 is a kind of structural block diagram for hardware state analytical equipment that one embodiment provides；
Fig. 9 is a kind of structural block diagram for hardware state analytical equipment that one embodiment provides；
Figure 10 is a kind of structural block diagram for hardware state analytical equipment that one embodiment provides；
Figure 11 is a kind of structural block diagram for hardware state analytical equipment that one embodiment provides；
Figure 12 is a kind of structural block diagram for hardware state analytical equipment that one embodiment provides.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
A kind of hardware state analysis method provided by the present application, can be applied in application environment as shown in Figure 1, this is
System includes emission computerized tomography imaging (Positron Emission Computed Tomogr aphy, PET) system
Hardware device and computer equipment, the radiation counter data that wherein computer equipment is acquired by the hardware device of PET system,
In, computer equipment includes processor, memory, network interface and the database connected by system bus.Wherein, the calculating
The processor of machine equipment is for providing calculating and control ability.The memory of the computer equipment includes that non-volatile memories are situated between
Matter, built-in storage.The non-volatile memory medium is stored with operating system, computer program and database.The built-in storage is
The operation of operating system and computer program in non-volatile memory medium provides environment.The database of the computer equipment is used
In storage flow velocity measurement data.The network interface of the computer equipment is used to communicate with external terminal by network connection.It should
To realize a kind of hardware state analysis method when computer program is executed by processor.
Embodiments herein provides a kind of hardware state analysis method, device, computer equipment and storage medium, it is intended to
The technical issues of solving the reflection PET system hardware state situation that current PET hardware state analysis method cannot integrate.Below
Embodiment will be passed through and specifically how the technical solution of the technical solution of the application and the application is solved in conjunction with attached drawing
Technical problem is stated to be described in detail.These specific embodiments can be combined with each other below, for the same or similar general
Thought or process may repeat no more in certain embodiments.It should be noted that a kind of hardware state analysis provided by the present application
Method, the executing subject of Fig. 2-Fig. 6 are computer equipment, wherein its executing subject can also be hardware state analytical equipment,
In the device part or complete of hardware state analysis can be implemented as by way of software, hardware or software and hardware combining
Portion.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.
In one embodiment, Fig. 2 provides a kind of hardware state analysis method, and what is involved is computers to set for the present embodiment
The standby radiation counter data first obtained after PET system original state and work preset duration, then by both radiation counter numbers
According to being input in preset neural network model, the detailed process of the hardware state analysis data of PET system is obtained, such as Fig. 2 institute
Show, which comprises
S101 obtains the first radiation counter data under PET system original state.
In the present embodiment, the system that the original state of PET system indicates correction of just having installed is finished, and is not devoted oneself to work also
State, wherein what radiation counter data indicated is the data of PET system hardware state, for example, strength distributing information, Energy distribution
Information or flight time distributed intelligence etc..Then in practical applications, computer equipment obtains the under PET system original state
One radiation counter data can be and finish in PET system correction of just having installed, and when not devoting oneself to work also, acquire PET system hardware
Radiation counter data.It should be noted that PET system original state and PET system work mentioned by the embodiment of the present application
Made the states such as preset duration, expression be all PET system the state that integrally combines of software and hardware.
S102, the second radiation counter data after obtaining PET system work preset duration.
In this step, what is indicated after PET system work preset duration is that the PET system has worked a period of time, this
Without limitation to the specific duration of preset duration, in practical applications, computer equipment obtains the second radiation counter number to embodiment
According to when, can be with weekly when a length of period acquisition PET system radiation counter data, be also possible to the acquisition of other operations
Data, the present embodiment do not limit this.
First radiation counter data and the second radiation counter data are input in preset neural network, obtain by S103
Hardware state to PET system analyzes data；The hardware state analysis data of the PET system are for predicting default operating time
Radiation counter data, the radiation counter data of original state and the uniformity data of scan image later.
Based on the first radiation counter data and the second spoke that in above-mentioned S101 step and S102 step, computer equipment is obtained
Enumeration data is penetrated, in this step, the first radiation counter data and the second radiation counter data are input to preset nerve
In network, the hardware state analysis data of PET system can be obtained, wherein the neural network is trained in advance, is used for root
The network model of the hardware state analysis data of PET system is determined according to the radiation counter data of PET system, therefore in the present embodiment
In, directly it can determine that the hardware state of PET system analyzes data using the neural network model, for the instruction of the neural network
Practice process will do it detailed description in subsequent embodiment.Wherein, the hardware state for the PET system which determines
Data are analyzed to be used to predict the radiation counter number after the default operating time of PET system according to the radiation counter data of PET system
According to what is predicted is the PET system state that system hardware is likely to occur in following a period of time after a certain starting point, wherein
The hardware state analysis data for the PET system that the neural network model determines are also used for the radiation counter data according to PET system
The radiation counter data for predicting default original state, that is, predict be when PET system after a period of work, when original state
Radiation counter data, which can assist the self of PET system hardware state, to guarantee the hardware package of PET system
Hold best condition.Wherein, the hardware state analysis data for the PET system that neural network model determines are also used to according to PET system
Radiation counter data prediction scan image uniformity data, that is, predict be current PET system hardware state its correspondence
The uniformity data of the image scanned can determine PET system hardware state according to the uniformity data of the scan image
Contacting between scan image uniformity.
Hardware state analysis method provided in this embodiment, the radiation counter under the different conditions that computer equipment will acquire
Data are input in preset neural network, and the hardware state of available PET system analyzes data, due to the PET system
Hardware state analysis data are for radiation counter data, the radiation counter data of original state after predicting default operating time
With the uniformity data of scan image, it is equivalent to from hardware state of many aspects to PET system and is analyzed, it is effective comprehensive
Conjunction reflects the case where PET system hardware state.
For above-mentioned neural network, the embodiment of the present application also provides a kind of hardware state analysis method, in this method on
Stating neural network includes the first sub-neural network and the second sub-neural network, then based on the above embodiment, what the present embodiment was related to
It is computer equipment with specific reference to the first radiation counter data and the second radiation counter data, obtains PET system hardware state point
The detailed process for analysing data, as shown in figure 3, above-mentioned S103 step includes:
First radiation counter data are input to the first sub-neural network by S201, and it is corresponding to obtain the first radiation counter data
Default operating time after radiation counter data.
In this step, the first radiation counter data obtained in above-mentioned S101 step are input to the first sub-neural network
In, obtained output is the radiation counter data after the corresponding default operating time of the first radiation counter data, wherein this reality
Applying the first sub-neural network in example is preparatory trained network model.It is understood that the first radiometer in this step
Radiation counter data after the corresponding default operating time of number data, expression is the hardware state of PET system to acquire this
First radiation counter data time is starting point, and the radiation counter data after presetting operating time can predict PET according to the data
The state that system is likely to occur from acquisition the first radiation counter data for system hardware in a period of time following after starting point.
Second radiation counter data are input to the first sub-neural network by S202, and it is corresponding to obtain the second radiation counter data
Standard Ratio enumeration data.
In this step, the second radiation counter data obtained in above-mentioned S102 step are input to the first sub-neural network
In, obtained output is the corresponding Standard Ratio enumeration data of the second radiation counter data, it is to be understood that in this step
The corresponding Standard Ratio enumeration data of second radiation counter data, what which indicated is PET system first
The radiation counter data of beginning state, in this way, what the radiation counter data of the acquisition according to PET system after a period of work obtained
After Standard Ratio enumeration data, the self of PET system hardware state can be assisted, to guarantee that the hardware of PET system is kept
Best condition.It should be noted that the first sub-neural network in this step and the first sub- nerve net in above-mentioned S201 step
Network is the same neural network, which is two way blocks, and first sub-neural network is in step S201
With outputting and inputting just on the contrary in this step.
Second radiation counter data are input to the second sub-neural network by S203, and it is corresponding to obtain the second radiation counter data
Scan image uniformity data.
In this step, the second radiation counter data obtained in above-mentioned S102 step are input to the second sub-neural network
In, obtained output is the uniformity data of the corresponding scan image of the second radiation counter data, wherein in the present embodiment
Second sub-neural network is preparatory trained network model.The corresponding scan image of second radiation counter data in this step
Uniformity data, expression is the image of the corresponding scanning of the hardware state of current PET system when acquiring the second radiation counter data
Uniformity data, can determine that PET system hardware state and scan image are equal according to the uniformity data of the scan image
Connection between even property.
Hardware state analysis method provided in this embodiment, respectively by the first radiation counter data and the second radiation counter number
According to being input in preparatory trained first sub-neural network and preparatory trained second sub-neural network, first is respectively obtained
Radiation counter data, the corresponding Standard Ratio of the second radiation counter data after the corresponding default operating time of radiation counter data
The uniformity data of enumeration data and the corresponding scan image of the second radiation counter data, is obtained by different neural networks in this way
It to above three data, is analyzed from hardware state of many aspects to PET system, effective concentrated expression PET system
The case where system hardware state.
In addition, the embodiment of the present application also provides the first sub-neural network and the second sub-neural network be trained it is specific
Process, as shown in figure 4, being then based on above embodiments, present invention also provides a kind of hardware analysis method, this method further include:
S301, obtains PET system multiple first sample radiation counter data in the initial state and multiple work are default
The second sample radiation enumeration data after duration.
When this step is computer equipment training above-mentioned first nerves network initial network model, training sample data are obtained
Process, then in practical applications, computer equipment obtains PET system multiple radiation counter data in the initial state, i.e.,
For first sample radiation counter data, radiation counter data after multiple work preset durations, as the second sample radiation is counted
Data.
S302, using each first sample radiation counter data as input, each second sample radiation enumeration data as export,
, as input, each first sample radiation counter data as output, the first son is trained with using each second sample radiation enumeration data
Neural network initial network model, obtains first nerves network.
Based on the first sample radiation counter data and the second sample radiation enumeration data obtained in above-mentioned S301 step, meter
Calculate machine equipment using each first sample radiation counter data as input, each second sample radiation enumeration data as export and will be each
Second sample radiation enumeration data is as input, each first sample radiation counter data as output, the first sub- nerve net of training
Network initial network model, obtains first nerves network.Since the first nerves network is two way blocks, when training,
It needs first sample radiation counter data as input, the second sample radiation enumeration data as exporting and by the second sample spoke
Penetrate enumeration data as input, first sample radiation counter data as output after, as have trained it is primary, with such sequence
After training repeatedly, first sub-neural network can be obtained.Because of first sample radiation counter data and the second sample radiation meter
Difference between number data is only that corresponding hardware state is different, therefore the first sub-neural network is actually to find PET
System initial hardware state is to the connection between PET system hardware state after a period of work and at one section of job search
Between after PET system hardware state be transformed into the rule of its initial hardware state.
Hardware state analysis method provided in this embodiment, computer equipment is according to multiple first sample radiation counter data
Two-way training is carried out to the first sub-neural network with the second sample radiation enumeration data after multiple work preset durations, so that should
First sub-neural network has the radiation counter data of radiation counter data and original state after predicting default operating time
Function, ensure that significantly to the realization of the function of scanning device hardware state comprehensive analysis.
Equally, in another embodiment, as shown in figure 5, this application provides a kind of hardware state analysis method,
This method further include:
S401 obtains multiple second sample radiation enumeration datas and each second sample of the PET system after the preset duration that works
Background radiation enumeration data corresponds to the uniformity data of scan image.
When training the second sub-neural network in this step for computer equipment, the process of training data is obtained, then in reality
In, computer equipment obtains multiple second sample radiation enumeration datas of the PET system after the preset duration that works, He Ge
Two sample radiation enumeration datas correspond to the uniformity data of scan image, wherein multiple second sample radiation enumeration datas here
Can be identical as the second sample radiation enumeration data of above-mentioned the first sub-neural network of training, and for computer equipment according to
The second sample radiation enumeration data obtains the process of the uniformity data of corresponding scan image, as follows, present embodiments provides
A kind of way of example:
Optionally, as shown in fig. 6, " uniformity data that each second sample radiation enumeration data of acquisition corresponds to scan image "
Include:
S501 obtains the corresponding bucket source data of each second sample radiation enumeration data.
In this step, computer equipment first obtains the corresponding bucket source data of the second sample radiation enumeration data, and expression is
When obtaining the second sample radiation enumeration data of acquisition, the bucket source data of PET system, wherein this barrel of source data is that one kind meets thing
Part, in practical applications, computer equipment meet all data that bucket source is analyzed in event from this.
Bucket source data progress image reconstruction is obtained the uniformity data of scan image by S502.
Based on the bucket source data of above-mentioned S501 step, this barrel of source data is carried out image reconstruction by computer equipment, is obtained pair
Then the scan image answered obtains the uniformity data of scan image.
S402, using each second sample radiation enumeration data as input, the corresponding scanning of each second sample radiation enumeration data
The uniformity data of image obtains the second sub-neural network as output, the second sub-neural network initial network model of training.
It is counted based on the multiple second sample radiation enumeration datas obtained in above-mentioned S401 step and each second sample radiation
Data correspond to the uniformity data of scan image, and computer equipment is using each second sample radiation enumeration data as input, and each the
Two sample radiation enumeration datas correspond to the uniformity data of scan image as output, the second sub-neural network initial network of training
Model, obtains the second sub-neural network, and the function of trained second sub-neural network is the radiation counter according to PET system
Data predict the uniformity data of scan image, can determine PET system hardware according to the uniformity data of the scan image
Contacting between state and scan image uniformity.
Hardware state analysis method provided in this embodiment, computer equipment is according to multiple second sample radiation enumeration datas
As input correspond to multiple second sample radiation enumeration datas the uniformity data of scan image to the second sub-neural network into
Row training is ensure that significantly so that second sub-neural network has the function of the uniformity data of prediction scan image to sweeping
The function of retouching device hardware state comprehensive analysis is realized.
Below by specific embodiment by the collection process of the radiation counter data referred in the embodiment of the present application, and adopt
Collection environment is illustrated, then optionally, above-mentioned first radiation counter data and the second radiation counter data include PET system stick
Meet event data in single event data and bucket source on source；Single event data include strength distributing information, Energy distribution letter
Breath；Meeting event data includes strength distributing information and flight time distributed intelligence.Optionally, the single event data in acquisition rod source
When, stick source is located at the visual field center of PET system.Optionally, when meeting event data of bucket source is acquired, bucket source is located at PET system
The visual field center in axle center；PET system axle center is overlapped with the axle center in stick source.
Wherein, computer equipment first radiation counter data, the second radiation counter data in acquisition above-described embodiment, with
And first sample radiation counter data and the second sample radiation enumeration data, illustratively, environment when these data may include
One stick source and a bucket source, wherein the stick source and homologous top view can be as shown in fig. 7, the circumferential direction in the stick source and bucket source be same
The heart, respective length can be 30cm, and stick source internal diameter can be 0.5cm, and the diameter in bucket source can be 20cm, which is connection
's.Based on the environment, when computer equipment acquires data, penetrating property drug (such as 1mciFDG) is injected first into stick source and is shaken
Uniformly, which can be divided into two beds in the acquisition of subsequent radiation counter data and carry out, by the axle center in stick source and system
(PET system) axle center is overlapped, and, stick source is axially parallel with PET system, then by the visual field center for moving on to PET system in stick source
Single event data are acquired, and analyze strength distributing information, energy distribution information information from the single event data；Wherein, it counts
It calculates machine equipment and bucket source is moved on into PET system axle center visual field centric acquisition, event data that acquisition bucket source issued meet, and from the symbol
Flight time distributed intelligence information is analyzed in conjunction event, wherein flight time distributed intelligence information can be by sinogram
Tof sonogram symmetry obtain, the lor across stick source as unit of block meet event data the flight time divide
There is symmetry in cloth information；The data are subjected to the uniformity data that image reconstruction obtains image simultaneously.Wherein, the present embodiment
During middle neural network model is readily applicable to the daily state monitoring of CT, MR and other image systems, assesses.Certainly above-mentioned to make
Stick source diameter and three-dimensional dimension size can change in a certain range, and the present embodiment is not specifically limited in this embodiment.Wherein,
It is above-mentioned establish the method contacted between radiation counter data and image conformity can also be used in establish other images such as CRC it
Between get in touch with, the present embodiment also without limitation, can specifically be changed this according to the actual situation.
It should be understood that although each step in the flow chart of Fig. 2-6 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-6
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 8, providing a kind of hardware state analytical equipment, which includes: the first number
According to acquisition module 10, the second data acquisition module 11 and analysis data prediction module 12, wherein
First data acquisition module 10, for obtaining the first radiation counter data under PET system original state；
Second data acquisition module 11, for obtain PET system work preset duration after the second radiation counter data；
Data prediction module 12 is analyzed, it is default for being input to the first radiation counter data and the second radiation counter data
Neural network in, obtain PET system hardware state analysis data；The hardware state analysis data of PET system are for pre-
The uniformity number of radiation counter data, the radiation counter data of original state and scan image after the default operating time of survey
According to.
A kind of hardware state analytical equipment provided by the above embodiment, implementing principle and technical effect and the above method are real
It is similar to apply example, details are not described herein.
In one embodiment, above-mentioned neural network includes the first sub-neural network and the second sub-neural network, then such as Fig. 9
It is shown, a kind of hardware state analytical equipment is provided, above-mentioned analysis data prediction module 12 includes: that the first analysis data determine list
Member 121, second analyzes data determination unit 122 and third analyzes data determination unit 123, wherein
First analysis data determination unit 121 is obtained for the first radiation counter data to be input to the first sub-neural network
Radiation counter data to after the corresponding default operating time of the first radiation counter data；
Second analysis data determination unit 122 is obtained for the second radiation counter data to be input to the first sub-neural network
To the corresponding Standard Ratio enumeration data of the second radiation counter data；
Third analysis data determination unit 123 is obtained for the second radiation counter data to be input to the second sub-neural network
To the uniformity data of the corresponding scan image of the second radiation counter data.
A kind of hardware state analytical equipment provided by the above embodiment, implementing principle and technical effect and the above method are real
It is similar to apply example, details are not described herein.
In one embodiment, as shown in Figure 10, a kind of hardware state analytical equipment, the device are provided further include: the
One training data obtains module 13 and first network training module 14, wherein
First training data obtains module 13, for obtaining the multiple first samples radiation of PET system in the initial state
The second sample radiation enumeration data after enumeration data and multiple work preset durations；
First network training module 14, for using each first sample radiation counter data as input, each second sample spoke
Enumeration data is penetrated as output, and using each second sample radiation enumeration data as input, each first sample radiation counter data
As output, the first sub-neural network initial network model of training obtains first nerves network.
A kind of hardware state analytical equipment provided by the above embodiment, implementing principle and technical effect and the above method are real
It is similar to apply example, details are not described herein.
In one embodiment, as shown in figure 11, a kind of hardware state analytical equipment, the device are provided further include: the
Two training datas obtain module 15 and the second network training module 16, wherein
Second training data obtains module 15, for obtaining multiple second samples of the PET system after the preset duration that works
Radiation counter data and each second sample radiation enumeration data correspond to the uniformity data of scan image；
Second network training module 16, for using each second sample radiation enumeration data as input, each second sample spoke
The uniformity data conduct output that enumeration data corresponds to scan image is penetrated, the second sub-neural network initial network model of training obtains
To the second sub-neural network.
A kind of hardware state analytical equipment provided by the above embodiment, implementing principle and technical effect and the above method are real
It is similar to apply example, details are not described herein.
In one embodiment, as shown in figure 12, a kind of hardware state analytical equipment, above-mentioned second training data are provided
Obtaining module 15 includes: training data acquiring unit 151 and data reconstruction unit 152, wherein
Training data acquiring unit 151, for obtaining the corresponding bucket source data of each second sample radiation enumeration data；
Data reconstruction unit 152, for bucket source data progress image reconstruction to be obtained the uniformity data of scan image.
A kind of hardware state analytical equipment provided by the above embodiment, implementing principle and technical effect and the above method are real
It is similar to apply example, details are not described herein.
In one embodiment, above-mentioned first radiation counter data and the second radiation counter data include PET system stick
Meet event data in single event data and bucket source on source；Single event data include strength distributing information, Energy distribution letter
Breath；Meeting event data includes flight time distributed intelligence.In one embodiment, when the single event data in acquisition rod source, stick
Source is located at the visual field center of PET system.In one embodiment, when meeting event data of bucket source is acquired, bucket source is located at PET system
The visual field center in system axle center；PET system axle center is overlapped with the axle center in stick source.
A kind of hardware state analytical equipment provided by the above embodiment, implementing principle and technical effect and the above method are real
It is similar to apply example, details are not described herein.
Specific about hardware state analytical equipment limits the limit that may refer to above for hardware state analysis method
Fixed, details are not described herein.Modules in above-mentioned hardware state analytical equipment can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in the computer equipment part in figure 1 above.The computer equipment include by system bus connect processor,
Memory, network interface, display screen and input unit.Wherein, the processor of the computer equipment is calculated and is controlled for providing
Ability.The memory of the computer equipment includes non-volatile memory medium, built-in storage.Non-volatile memory medium storage
There are operating system and computer program.The built-in storage is operating system and computer program in non-volatile memory medium
Operation provides environment.The network interface of the computer equipment is used to communicate with external terminal by network connection.The computer
To realize a kind of hardware state analysis method when program is executed by processor.The display screen of the computer equipment can be liquid crystal
Display screen or electric ink display screen, the input unit of the computer equipment can be the touch layer covered on display screen, can also
To be the key being arranged on computer equipment shell, trace ball or Trackpad, external keyboard, Trackpad or mouse can also be
Deng.
It will be understood by those skilled in the art that structure shown in Fig. 1, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
Obtain the first radiation counter data under PET system original state；
The second radiation counter data after obtaining PET system work preset duration；
First radiation counter data and the second radiation counter data are input in preset neural network, PET is obtained
The hardware state of system analyzes data；The hardware state analysis data of the PET system are used to predict after default operating time
Radiation counter data, the radiation counter data of original state and the uniformity data of scan image.
A kind of computer equipment provided by the above embodiment, implementing principle and technical effect and above method embodiment class
Seemingly, details are not described herein.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain the first radiation counter data under PET system original state；
The second radiation counter data after obtaining PET system work preset duration；
First radiation counter data and the second radiation counter data are input in preset neural network, PET is obtained
The hardware state of system analyzes data；The hardware state analysis data of the PET system are used to predict after default operating time
Radiation counter data, the radiation counter data of original state and the uniformity data of scan image.
A kind of computer readable storage medium provided by the above embodiment, implementing principle and technical effect and the above method
Embodiment is similar, and details are not described herein.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of hardware state analysis method, which is characterized in that the described method includes:
Obtain the first radiation counter data under positron e mission computed tomography PET system original state；
The second radiation counter data after obtaining the PET system work preset duration；
The first radiation counter data and the second radiation counter data are input in preset neural network, institute is obtained
State the hardware state analysis data of PET system；The hardware state analysis data of the PET system are for predicting default operating time
Radiation counter data, the radiation counter data of original state and the uniformity data of scan image later.
2. the method according to claim 1, wherein the neural network includes the first sub-neural network and second
Sub-neural network；
It is then described that first radiation counter data and the second radiation counter data are input in preset neural network, it obtains
The hardware state of PET system analyzes data, comprising:
The first radiation counter data are input to first sub-neural network, obtain the first radiation counter data pair
Radiation counter data after the default operating time answered；
The second radiation counter data are input to first sub-neural network, obtain the second radiation counter data pair
The Standard Ratio enumeration data answered；
The second radiation counter data are input to second sub-neural network, obtain the second radiation counter data pair
The uniformity data for the scan image answered.
3. according to the method described in claim 2, it is characterized in that, the method also includes:
After obtaining the more first sample radiation counter data and multiple work preset durations of the PET system in the initial state
Second sample radiation enumeration data；
Using each first sample radiation counter data as input, each second sample radiation enumeration data as export,
It, as input, each first sample radiation counter data as output, is instructed with using each second sample radiation enumeration data
Practice the first sub-neural network initial network model, obtains the first nerves network.
4. according to the method described in claim 2, it is characterized in that, the method also includes:
Obtain multiple second sample radiation enumeration datas and each second sample of the PET system after the preset duration that works
Background radiation enumeration data corresponds to the uniformity data of scan image；
Using each second sample radiation enumeration data as input, each second sample radiation enumeration data corresponds to scanning figure
The uniformity data of picture obtains second sub-neural network as output, the second sub-neural network initial network model of training.
5. according to the method described in claim 4, it is characterized in that, each second sample radiation enumeration data pair of acquisition
Answer the uniformity data of scan image, comprising:
Obtain the corresponding bucket source data of each second sample radiation enumeration data；
Bucket source data progress image reconstruction is obtained into the uniformity data of the scan image.
6. method described in -5 according to claim 1, which is characterized in that the first radiation counter data and second radiation
Enumeration data includes meeting event data in single event data and bucket source on PET system stick source；The single event
Data include strength distributing information and energy distribution information；The event data that meets includes strength distributing information and flight time
Distributed intelligence.
7. according to the method described in claim 6, it is characterized in that, when acquiring the single event data in the stick source, the stick source
Positioned at the visual field of PET system center.
8. according to the method described in claim 6, it is characterized in that, acquiring when meeting event data of the bucket source, the bucket
Source is located at the visual field center in the PET system axle center；The PET system axle center is overlapped with the axle center in the stick source.
9. a kind of hardware state analytical equipment, which is characterized in that described device includes:
First data acquisition module, for obtaining under positron e mission computed tomography PET system original state
One radiation counter data；
Second data acquisition module, for obtaining the second radiation counter data after PET system work preset duration；
Data prediction module is analyzed, it is pre- for being input to the first radiation counter data and the second radiation counter data
If neural network in, obtain the PET system hardware state analysis data；The hardware state of the PET system is analyzed
Data are used to predict radiation counter data after default operating time, the radiation counter data of original state and scan image
Uniformity data.
10. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 8 the method when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910333538.7A CN110037718B (en) | 2019-04-24 | 2019-04-24 | Hardware state analysis method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910333538.7A CN110037718B (en) | 2019-04-24 | 2019-04-24 | Hardware state analysis method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110037718A true CN110037718A (en) | 2019-07-23 |
| CN110037718B CN110037718B (en) | 2022-11-25 |
Family
ID=67279081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910333538.7A Active CN110037718B (en) | 2019-04-24 | 2019-04-24 | Hardware state analysis method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110037718B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100246919A1 (en) * | 2007-12-20 | 2010-09-30 | Koninklijke Philips Electronics N.V. | Radiation detector for counting or integrating signals |
| CN107976706A (en) * | 2016-10-25 | 2018-05-01 | 上海东软医疗科技有限公司 | A kind of counting loss bearing calibration of PET system and device |
| CN109308728A (en) * | 2018-10-25 | 2019-02-05 | 上海联影医疗科技有限公司 | PET-Positron emission computed tomography scan image processing method and processing device |
| CN109523584A (en) * | 2018-10-26 | 2019-03-26 | 上海联影医疗科技有限公司 | Image processing method, device, multi-mode imaging system, storage medium and equipment |
-
2019
- 2019-04-24 CN CN201910333538.7A patent/CN110037718B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100246919A1 (en) * | 2007-12-20 | 2010-09-30 | Koninklijke Philips Electronics N.V. | Radiation detector for counting or integrating signals |
| CN107976706A (en) * | 2016-10-25 | 2018-05-01 | 上海东软医疗科技有限公司 | A kind of counting loss bearing calibration of PET system and device |
| CN109308728A (en) * | 2018-10-25 | 2019-02-05 | 上海联影医疗科技有限公司 | PET-Positron emission computed tomography scan image processing method and processing device |
| CN109523584A (en) * | 2018-10-26 | 2019-03-26 | 上海联影医疗科技有限公司 | Image processing method, device, multi-mode imaging system, storage medium and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110037718B (en) | 2022-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109754447A (en) | Image generating method, device, equipment and storage medium | |
| Lizier et al. | Multivariate information-theoretic measures reveal directed information structure and task relevant changes in fMRI connectivity | |
| CN109598745B (en) | Image registration method and device and computer equipment | |
| EP3085305B1 (en) | Subject-specific assessment of neurological disorders with biochemical propagation mechanisms | |
| CN109567852B (en) | Method for determining scanning range, method, device and equipment for acquiring medical image | |
| US11229377B2 (en) | System and method for next-generation MRI spine evaluation | |
| CN111161269B (en) | Image segmentation method, computer device, and readable storage medium | |
| CN110570483A (en) | scanning method, scanning device, computer equipment and storage medium | |
| CN111369542A (en) | Blood vessel marking method, image processing system and storage medium | |
| CN110335250A (en) | Network training method, device, detection method, computer equipment and storage medium | |
| CN111028212B (en) | Key point detection method, device, computer equipment and storage medium | |
| CN110584698A (en) | Detector quality control validation method, detector quality control validation device, computer equipment and storage medium | |
| DE112015002935T5 (en) | Reconstruction with multiple photopeaks in quantitative single-photon emission computed tomography | |
| CN110687585B (en) | Method, device, computer equipment and storage medium for obtaining crystal efficiency | |
| CN110037718A (en) | Hardware state analysis method, device, computer equipment and storage medium | |
| Ryczkowski et al. | Tomotherapy archive structure and new software tool for loading and advanced analysis of data contained in it | |
| CN110226942A (en) | Data display method, device, PET scan equipment and storage medium | |
| CN111160441A (en) | Classification method, computer device, and storage medium | |
| Kotina et al. | Digital Image Processing in Nuclear Medicine | |
| CN107016148B (en) | Enterprise protocol management | |
| CN108873047A (en) | Detect method, system, computer equipment and the storage medium of radioactive source activity | |
| Bedoucha et al. | Visual exploration of large normal mode spaces to study protein flexibility | |
| CN110766653B (en) | Image segmentation method and device, computer equipment and storage medium | |
| CN110599560B (en) | Magnetic resonance imaging method, device, storage medium and computer equipment | |
| CN111210414A (en) | Medical image analysis method, computer device and readable storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co.,Ltd. Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |