CN110037718B - Hardware state analysis method and device, computer equipment and storage medium - Google Patents
Hardware state analysis method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110037718B CN110037718B CN201910333538.7A CN201910333538A CN110037718B CN 110037718 B CN110037718 B CN 110037718B CN 201910333538 A CN201910333538 A CN 201910333538A CN 110037718 B CN110037718 B CN 110037718B
- Authority
- CN
- China
- Prior art keywords
- data
- radiation
- pet system
- neural network
- radiation count
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 89
- 230000005855 radiation Effects 0.000 claims abstract description 233
- 238000013528 artificial neural network Methods 0.000 claims abstract description 89
- 238000002600 positron emission tomography Methods 0.000 claims description 133
- 238000000034 method Methods 0.000 claims description 42
- 238000012549 training Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 16
- 238000002591 computed tomography Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 230000002457 bidirectional effect Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009206 nuclear medicine Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/037—Emission tomography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/58—Testing, adjusting or calibrating thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/58—Testing, adjusting or calibrating thereof
- A61B6/581—Remote testing
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/58—Testing, adjusting or calibrating thereof
- A61B6/586—Detection of faults or malfunction of the device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Engineering & Computer Science (AREA)
- Radiology & Medical Imaging (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Optics & Photonics (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- High Energy & Nuclear Physics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Nuclear Medicine (AREA)
- Measurement Of Radiation (AREA)
Abstract
The computer device inputs the acquired radiation count data in different states into a preset neural network to obtain hardware state analysis data of the PET system, and the hardware state analysis data of the PET system are used for predicting the radiation count data after preset working time, the radiation count data in an initial state and uniformity data of a scanned image, so that the hardware state of the PET system is analyzed from multiple aspects, and the condition of the hardware state of the PET system is effectively and comprehensively reflected.
Description
Technical Field
The present application relates to the field of medical technology, and in particular, to a method and an apparatus for hardware state analysis, a computer device, and a storage medium.
Background
Positron Emission Tomography (PET) is a relatively advanced clinical examination imaging technique in the field of nuclear medicine. In clinical applications, the hardware status of the PET system needs to be monitored daily to ensure the accuracy of the acquired image data.
The monitoring of the hardware status of the PET system is usually performed by acquiring radiation count data of the PET system hardware, for example, single, coincidence data, every day, and then analyzing the current hardware status of the PET system according to the radiation count data. In practical application, the hardware state of the PET system changes along with the time, so that the accuracy of the acquired image data is affected, and when the hardware state of the PET system is monitored, the influence caused by the hardware state of the PET system needs to be considered from comprehensive factors, namely, only the current state of the current PET system hardware is not sufficient.
Therefore, the current PET hardware state analysis method cannot comprehensively reflect the hardware state of the PET system.
Disclosure of Invention
In view of the above, it is necessary to provide a hardware status analysis method, apparatus, computer device and storage medium for solving the technical problem that the existing PET hardware status analysis method cannot comprehensively reflect the hardware status of the PET system.
In a first aspect, an embodiment of the present application provides a hardware state analysis method, where the method includes:
acquiring first radiation counting data of a PET system in an initial state;
acquiring second radiation counting data of the PET system after working for a preset time;
inputting the first radiation counting data and the second radiation counting data into a preset neural network to obtain hardware state analysis data of the PET system; and the hardware state analysis data of the PET system is used for predicting radiation count data after preset working time, radiation count data in an initial state and uniformity data of a scanned image.
In one embodiment, the neural network includes a first sub-neural network and a second sub-neural network;
inputting the first radiation count data and the second radiation count data into a preset neural network to obtain hardware state analysis data of the PET system, including:
inputting the first radiation counting data into a first sub-neural network to obtain radiation counting data after preset working time corresponding to the first radiation counting data;
inputting the second radiation counting data into the first sub-neural network to obtain standard radiation counting data corresponding to the second radiation counting data;
and inputting the second radiation counting data into a second sub-neural network to obtain uniformity data of the scanned image corresponding to the second radiation counting data.
In one embodiment, the method further includes:
acquiring a plurality of first sample radiation count data and a plurality of second sample radiation count data after working for a preset time length of a PET system in an initial state;
and training a first sub neural network initial network model by taking the radiation counting data of each first sample as input and the radiation counting data of each second sample as output, taking the radiation counting data of each second sample as input and the radiation counting data of each first sample as output to obtain a first neural network.
In one embodiment, the method further comprises:
acquiring a plurality of second sample radiation counting data of the PET system after working for a preset time length and uniformity data of a scanned image corresponding to each second sample radiation counting data;
and taking the radiation count data of each second sample as input, taking the uniformity data of the scanned image corresponding to the radiation count data of each second sample as output, and training a second sub-neural network initial network model to obtain a second sub-neural network.
In one embodiment, the acquiring uniformity data of the scanned image corresponding to each second sample radiation count data includes:
acquiring barrel source data corresponding to the radiation count data of each second sample;
and carrying out image reconstruction on the bucket source data to obtain uniformity data of the scanned image.
In one embodiment, the first and second radiation count data each comprise single event data on a PET system rod source and coincidence event data on a barrel source; the single event data comprises intensity distribution information and energy distribution information; the coincidence event data includes intensity distribution information and time-of-flight distribution information.
In one embodiment, the rod source is centered in the field of view of the PET system when acquiring single event data for the rod source.
In one embodiment, when acquiring coincidence event data of a barrel source, the barrel source is positioned in the center of the visual field of the axis of the PET system; the axis of the PET system is superposed with the axis of the rod source.
In a second aspect, an embodiment of the present application provides a hardware status analysis apparatus, including:
the first data acquisition module is used for acquiring first radiation counting data of the PET system in an initial state;
the second data acquisition module is used for acquiring second radiation counting data after the PET system works for a preset time;
the analysis data prediction module is used for inputting the first radiation count data and the second radiation count data into a preset neural network to obtain hardware state analysis data of the PET system; the hardware state analysis data of the PET system is used to predict radiation count data after a preset operating time, radiation count data of an initial state, and uniformity data of a scanned image.
In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of any one of the methods provided in the embodiments of the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any one of the methods provided in the foregoing embodiments of the first aspect.
According to the hardware state analysis method and device, the computer device inputs the acquired radiation count data in different states into the preset neural network, and hardware state analysis data of the PET system can be obtained.
Drawings
FIG. 1 is an application environment of a hardware state analysis method according to an embodiment;
FIG. 2 is a flowchart illustrating a hardware status analysis method according to an embodiment;
FIG. 3 is a flowchart illustrating a hardware status analysis method according to an embodiment;
FIG. 4 is a flowchart illustrating a hardware status analysis method according to an embodiment;
FIG. 5 is a flowchart illustrating a hardware status analysis method according to an embodiment;
FIG. 6 is a flowchart illustrating a hardware state analysis method according to an embodiment;
FIG. 7 is a top view of a data collection environment for a hardware state analysis method, according to an embodiment;
fig. 8 is a block diagram illustrating a hardware status analysis apparatus according to an embodiment;
fig. 9 is a block diagram of a hardware status analysis apparatus according to an embodiment;
fig. 10 is a block diagram illustrating a hardware status analysis apparatus according to an embodiment;
fig. 11 is a block diagram illustrating a hardware status analysis apparatus according to an embodiment;
fig. 12 is a block diagram of a hardware status analysis apparatus according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The hardware state analysis method provided by the present application can be applied to an application environment as shown in fig. 1, where the system includes a hardware device of a transmission Computed tomography (PET) system and a computer device, where the computer device acquires radiation count data through the hardware device of the PET system, and the computer device includes a processor, a memory, a network interface, and a database which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store flow rate measurement data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a hardware state analysis method.
The embodiment of the application provides a hardware state analysis method, a hardware state analysis device, computer equipment and a storage medium, and aims to solve the technical problem that the existing PET hardware state analysis method cannot comprehensively reflect the hardware state condition of a PET system. The following describes in detail the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems by embodiments and with reference to the drawings. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. It should be noted that in the hardware state analysis method provided in the present application, the execution main body in fig. 2 to fig. 6 is a computer device, where the execution main body may also be a hardware state analysis apparatus, and the apparatus may be implemented as part or all of the hardware state analysis by software, hardware, or a combination of software and hardware.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
In an embodiment, fig. 2 provides a hardware state analysis method, where the embodiment relates to a specific process in which a computer device first acquires radiation count data of a PET system in an initial state and after a preset duration of operation, and then inputs the two types of radiation count data into a preset neural network model to obtain hardware state analysis data of the PET system, as shown in fig. 2, the method includes:
s101, first radiation counting data of the PET system in an initial state are acquired.
In this embodiment, the initial state of the PET system represents a state in which the system has not been put into operation immediately after the installation and calibration are completed, and the radiation count data represents data of the hardware state of the PET system, such as intensity distribution information, energy distribution information, or time-of-flight distribution information. In practical application, the computer device acquires the first radiation count data of the PET system in the initial state, and may acquire the radiation count data of the PET system hardware when the PET system is just installed and corrected and is not put into operation. It should be noted that, in the embodiments of the present application, the initial state of the PET system and the state of the PET system operating for the preset time duration represent the state of the PET system in which software and hardware are integrated.
S102, second radiation counting data after the PET system works for a preset time length are obtained.
In this step, after the preset working duration of the PET system, it indicates that the PET system has been working for a period of time, and the specific duration of the preset duration is not limited in this embodiment.
S103, inputting the first radiation count data and the second radiation count data into a preset neural network to obtain hardware state analysis data of the PET system; and the hardware state analysis data of the PET system is used for predicting radiation count data after preset working time, radiation count data in an initial state and uniformity data of a scanned image.
Based on the first radiation count data and the second radiation count data obtained by the computer device in the above steps S101 and S102, in this step, the first radiation count data and the second radiation count data are input into a preset neural network, so that the hardware state analysis data of the PET system can be obtained, where the neural network is a network model trained in advance and used for determining the hardware state analysis data of the PET system according to the radiation count data of the PET system, and therefore in this embodiment, the hardware state analysis data of the PET system can be determined directly using the neural network model, and a training process of the neural network will be described in detail in the following embodiments. The hardware state analysis data of the PET system determined by the neural network model is used for predicting radiation count data after the preset working time of the PET system according to the radiation count data of the PET system, namely predicting the state of the PET system which is possible to appear in system hardware in the next period of time after a certain starting point, wherein the hardware state analysis data of the PET system determined by the neural network model is also used for predicting the radiation count data of a preset initial state according to the radiation count data of the PET system, namely predicting the radiation count data of the PET system in the initial state after the PET system works for a period of time, and the prediction can assist self-correction of the hardware state of the PET system so as to ensure that the hardware of the PET system keeps the best state. The hardware state analysis data of the PET system determined by the neural network model is also used for predicting the uniformity data of the scanned image according to the radiation count data of the PET system, namely predicting the uniformity data of the image scanned corresponding to the current hardware state of the PET system, and determining the relation between the hardware state of the PET system and the uniformity of the scanned image according to the uniformity data of the scanned image.
In the hardware state analysis method provided by this embodiment, the computer device inputs the acquired radiation count data in different states into the preset neural network, so as to obtain the hardware state analysis data of the PET system, and since the hardware state analysis data of the PET system is used to predict the radiation count data after the preset working time, the radiation count data in the initial state, and the uniformity data of the scanned image, the hardware state of the PET system is analyzed in many ways, so that the condition of the hardware state of the PET system is effectively reflected comprehensively.
As to the above neural network, an embodiment of the present application further provides a hardware state analysis method, where in the method, the neural network includes a first sub neural network and a second sub neural network, and based on the above embodiment, this embodiment relates to a specific process in which a computer device obtains PET system hardware state analysis data specifically according to first radiation count data and second radiation count data, as shown in fig. 3, where the step S103 includes:
s201, inputting the first radiation counting data to a first sub-neural network to obtain radiation counting data after preset working time corresponding to the first radiation counting data.
In this step, the first radiation count data obtained in the step S101 is input into a first sub-neural network, and the obtained output is the radiation count data after a preset working time corresponding to the first radiation count data, where the first sub-neural network in this embodiment is a pre-trained network model. It can be understood that, in this step, the radiation count data after the preset operation time corresponding to the first radiation count data represents the hardware state of the PET system starting from the time of acquiring the first radiation count data and the radiation count data after the preset operation time, and according to the radiation count data, the possible state of the system hardware in the next period of time after the PET system starts from acquiring the first radiation count data can be predicted.
S202, inputting the second radiation counting data into the first sub-neural network to obtain standard radiation counting data corresponding to the second radiation counting data.
In this step, the second radiation count data obtained in the step S102 is input into the first sub-neural network, and the obtained output is the standard radiation count data corresponding to the second radiation count data, and it can be understood that, in this step, the standard radiation count data corresponding to the second radiation count data represents the radiation count data of the PET system in the initial state, so that after the standard radiation count data is obtained according to the radiation count data acquired after the PET system works for a period of time, the self-correction of the hardware state of the PET system can be assisted, so as to ensure that the hardware of the PET system maintains the best state. It should be noted that the first sub-neural network in this step is the same neural network as the first sub-neural network in the step S201, the first sub-neural network is a bidirectional neural network, and the input and output of the first sub-neural network in step S201 and this step are just opposite.
And S203, inputting the second radiation counting data to a second sub-neural network to obtain uniformity data of the scanned image corresponding to the second radiation counting data.
In this step, the second radiation count data obtained in the step S102 is input into a second sub-neural network, and the obtained output is uniformity data of a scanned image corresponding to the second radiation count data, where the second sub-neural network in this embodiment is a pre-trained network model. In this step, the uniformity data of the scanned image corresponding to the second radiation count data indicates that, when the second radiation count data is acquired, the current hardware state of the PET system corresponds to the uniformity data of the scanned image, and the relationship between the hardware state of the PET system and the uniformity of the scanned image can be determined according to the uniformity data of the scanned image.
In the hardware state analysis method provided by this embodiment, the first radiation count data and the second radiation count data are respectively input to the pre-trained first sub-neural network and the pre-trained second sub-neural network, and radiation count data after a preset working time corresponding to the first radiation count data, standard radiation count data corresponding to the second radiation count data, and uniformity data of the scanned image corresponding to the second radiation count data are respectively obtained, so that the three data are obtained through different neural networks, the hardware state of the PET system is analyzed from multiple aspects, and the condition of the hardware state of the PET system is effectively and comprehensively reflected.
In addition, an embodiment of the present application further provides a specific process of training the first sub-neural network and the second sub-neural network, as shown in fig. 4, based on the above embodiment, the present application further provides a hardware analysis method, where the method further includes:
s301, acquiring a plurality of first sample radiation count data and a plurality of second sample radiation count data after working for a preset time length of the PET system in an initial state.
In the present step, when the computer device trains the first neural network initial network model, a process of obtaining training sample data is performed, and in practical application, the computer device obtains a plurality of radiation count data of the PET system in an initial state, that is, a first sample radiation count data, and a plurality of radiation count data after working for a preset time period, that is, a second sample radiation count data.
S302, taking the radiation count data of each first sample as input, taking the radiation count data of each second sample as output, taking the radiation count data of each second sample as input, taking the radiation count data of each first sample as output, and training a first sub-neural network initial network model to obtain a first neural network.
Based on the first sample radiation count data and the second sample radiation count data obtained in the step S301, the computer device trains the first sub-neural network initial network model to obtain the first neural network by using each first sample radiation count data as input, each second sample radiation count data as output, each second sample radiation count data as input, and each first sample radiation count data as output. Because the first neural network is a bidirectional neural network, during training, the first sub-neural network can be obtained after training once by taking the first sample radiation counting data as input, the second sample radiation counting data as output, the second sample radiation counting data as input and the first sample radiation counting data as output. Because the difference between the first sample radiation count data and the second sample radiation count data is only that the corresponding hardware states are different, the first sub-neural network is actually used for searching the relationship between the initial hardware state of the PET system and the hardware state of the PET system after a period of operation, and for searching the rule for the hardware state of the PET system to be converted into the initial hardware state after a period of operation.
In the hardware state analysis method provided by this embodiment, the computer device performs bidirectional training on the first sub-neural network according to the plurality of first sample radiation count data and the plurality of second sample radiation count data after working for the preset time duration, so that the first sub-neural network has a function of predicting the radiation count data after the preset working time duration and the radiation count data in the initial state, and the function of comprehensively analyzing the hardware state of the scanning device is greatly ensured.
Also, in another embodiment, as shown in fig. 5, the present application provides a hardware state analysis method, where the method further includes:
s401, acquiring a plurality of second sample radiation count data of the PET system after working for a preset time length and uniformity data of a scanned image corresponding to each second sample radiation count data.
In this step, when the second sub-neural network is trained for the computer device, a process of obtaining training data is performed, and in practical application, the computer device obtains a plurality of second sample radiation count data after a preset time period of operation of the PET system and uniformity data of a scanned image corresponding to each second sample radiation count data, where the plurality of second sample radiation count data may be the same as the second sample radiation count data used for training the first sub-neural network, and for a process of obtaining the uniformity data of a corresponding scanned image according to the second sample radiation count data, the present embodiment provides an embodiment as follows:
optionally, as shown in fig. 6, "acquiring uniformity data of the scan image corresponding to each second sample radiation count data" includes:
and S501, acquiring barrel source data corresponding to the second sample radiation count data.
In this step, the computer device first obtains barrel source data corresponding to the second sample radiation count data, which indicates that the barrel source data of the PET system is obtained when the second sample radiation count data is acquired, where the barrel source data is a coincidence event, and in practical applications, the computer device analyzes various data of the barrel source from the coincidence event.
And S502, carrying out image reconstruction on the bucket source data to obtain uniformity data of the scanned image.
Based on the bucket source data in the step S501, the computer device performs image reconstruction on the bucket source data to obtain a corresponding scanned image, and then obtains uniformity data of the scanned image.
S402, taking the radiation counting data of each second sample as input, taking the uniformity data of the corresponding scanned image of the radiation counting data of each second sample as output, training a second sub-neural network initial network model, and obtaining a second sub-neural network.
Based on the plurality of second sample radiation count data obtained in the step S401 and the uniformity data of the scanned image corresponding to each second sample radiation count data, the computer device takes each second sample radiation count data as input, takes the uniformity data of the scanned image corresponding to each second sample radiation count data as output, trains a second sub-neural network initial network model to obtain a second sub-neural network, the trained second sub-neural network functions to predict the uniformity data of the scanned image according to the radiation count data of the PET system, and can determine the relationship between the hardware state of the PET system and the uniformity of the scanned image according to the uniformity data of the scanned image.
In the hardware state analysis method provided by this embodiment, the computer device trains the second sub-neural network according to the uniformity data of the scanned image corresponding to the plurality of second sample radiation count data and the plurality of second sample radiation count data, so that the second sub-neural network has a function of predicting the uniformity data of the scanned image, and the function of comprehensively analyzing the hardware state of the scanning device is greatly ensured.
The following describes the acquisition process of the radiation count data and the acquisition environment in the embodiments of the present application with specific embodiments, and optionally, the first radiation count data and the second radiation count data each include single event data on a PET system rod source and coincidence event data on a barrel source; the single event data comprises intensity distribution information and energy distribution information; the coincidence event data includes intensity distribution information and time-of-flight distribution information. Optionally, the rod source is centered in the field of view of the PET system when acquiring single event data for the rod source. Optionally, when acquiring coincidence event data of the barrel source, the barrel source is located in the center of the visual field of the axis of the PET system; the axis of the PET system is superposed with the axis of the rod source.
Wherein the computer device in acquiring the first radiation count data, the second radiation count data, and the first sample radiation count data and the second sample radiation count data in the above embodiments, the environment may illustratively include a bar source and a bucket source, wherein the bar source and the homologous top view may be as shown in fig. 7, the rings of the bar source and the bucket source may be concentric, each of which may be 30cm in length, the inner diameter of the bar source may be 0.5cm, the diameter of the bucket source may be 20cm, the bar source being in communication. Based on the environment, when computer equipment acquires data, firstly injecting incident drugs (such as 1 mciFDG) into a rod source and uniformly shaking the rod source, wherein the rod source can be divided into two beds for subsequent radiation counting data acquisition, the axis of the rod source is superposed with the axis of a system (PET system), the rod source is axially parallel to the PET system, then the rod source is moved to the center of the visual field of the PET system to acquire single-event data, and intensity distribution information and energy distribution information are separated from the single-event data; the computer equipment moves a barrel source to the center of the axis visual field of the PET system for collection, collects coincidence event data sent by the barrel source, and analyzes flight time distribution information from the coincidence events, wherein the flight time distribution information can be obtained through the symmetry of tof sonograms on a sinogram, and lor coincidence event data passing through a rod source with block as a unit has symmetry on the flight time distribution information; and simultaneously carrying out image reconstruction on the data to obtain uniformity data of the image. The neural network model in the embodiment can also be applied to daily state monitoring and evaluation of CT, MR and other imaging systems. Of course, the diameter and the three-dimensional size of the rod source used above may be changed within a certain range, and this embodiment is not particularly limited thereto. The method for establishing the relationship between the radiation count data and the image uniformity may also be used for establishing the relationship between other images such as CRC, which is not limited in this embodiment, and may be changed according to actual situations.
It should be understood that although the various steps in the flow charts of fig. 2-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-6 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 8, there is provided a hardware state analyzing apparatus including: a first data acquisition module 10, a second data acquisition module 11, and an analytical data prediction module 12, wherein,
the first data acquisition module 10 is used for acquiring first radiation count data of the PET system in an initial state;
the second data acquisition module 11 is configured to acquire second radiation count data after the PET system operates for a preset time;
the analysis data prediction module 12 is configured to input the first radiation count data and the second radiation count data into a preset neural network to obtain hardware state analysis data of the PET system; the hardware state analysis data of the PET system is used to predict radiation count data after a preset operating time, radiation count data of an initial state, and uniformity data of a scanned image.
The implementation principle and technical effect of the hardware state analysis device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, the neural network includes a first sub neural network and a second sub neural network, and as shown in fig. 9, there is provided a hardware state analysis apparatus, where the analysis data prediction module 12 includes: a first analytical data determination unit 121, a second analytical data determination unit 122 and a third analytical data determination unit 123, wherein,
the first analysis data determining unit 121 is configured to input the first radiation count data to the first sub-neural network, so as to obtain radiation count data after a preset working time corresponding to the first radiation count data;
the second analysis data determining unit 122 is configured to input the second radiation count data to the first sub-neural network, so as to obtain standard radiation count data corresponding to the second radiation count data;
the third analysis data determining unit 123 is configured to input the second radiation count data to the second sub-neural network, so as to obtain uniformity data of the scanned image corresponding to the second radiation count data.
The implementation principle and technical effect of the hardware state analysis device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, as shown in fig. 10, there is provided a hardware state analyzing apparatus, further comprising: a first training data acquisition module 13 and a first network training module 14, wherein,
the first training data acquisition module 13 is configured to acquire a plurality of first sample radiation count data of the PET system in an initial state and a plurality of second sample radiation count data after a preset working duration;
and the first network training module 14 is configured to train a first sub-neural network initial network model to obtain a first neural network by taking the first sample radiation count data as input and the second sample radiation count data as output, and taking the second sample radiation count data as input and the first sample radiation count data as output.
The implementation principle and technical effect of the hardware state analysis device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, as shown in fig. 11, there is provided a hardware status analysis apparatus, further comprising: a second training data acquisition module 15 and a second network training module 16, wherein,
the second training data acquisition module 15 is configured to acquire a plurality of second sample radiation count data of the PET system after a preset working duration and uniformity data of a scanned image corresponding to each second sample radiation count data;
and the second network training module 16 is configured to train a second sub-neural network initial network model to obtain a second sub-neural network by taking the radiation count data of each second sample as input and taking the uniformity data of the scanned image corresponding to the radiation count data of each second sample as output.
The implementation principle and technical effect of the hardware state analysis device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, as shown in fig. 12, there is provided a hardware status analysis apparatus, and the second training data obtaining module 15 includes: a training data acquisition unit 151 and a data reconstruction unit 152, wherein,
a training data obtaining unit 151, configured to obtain bucket source data corresponding to each second sample radiation count data;
and a data reconstruction unit 152, configured to perform image reconstruction on the bucket source data to obtain uniformity data of the scanned image.
The implementation principle and technical effect of the hardware state analysis device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, the first and second radiation count data each comprise single event data on a PET system rod source and coincidence event data on a barrel source; the single event data comprises intensity distribution information and energy distribution information; the coincidence event data includes time-of-flight distribution information. In one embodiment, the rod source is centered in the field of view of the PET system when acquiring single event data for the rod source. In one embodiment, the coincidence event data of the bucket source is collected, the bucket source is positioned in the center of the visual field of the axis of the PET system; the axis of the PET system is superposed with the axis of the rod source.
The implementation principle and technical effect of the hardware state analysis device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
For specific limitations of the hardware state analysis device, reference may be made to the above limitations of the hardware state analysis method, which is not described herein again. The modules in the hardware state analysis device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, the internal structure of which may be partially shown above in fig. 1. The computer device comprises a processor, a memory, a network interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a hardware state analysis method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 1 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring first radiation counting data of a PET system in an initial state;
acquiring second radiation counting data of the PET system after working for a preset time;
inputting the first radiation counting data and the second radiation counting data into a preset neural network to obtain hardware state analysis data of the PET system; and the hardware state analysis data of the PET system is used for predicting radiation count data after preset working time, radiation count data in an initial state and uniformity data of a scanned image.
The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring first radiation counting data of a PET system in an initial state;
acquiring second radiation counting data of the PET system after working for a preset time;
inputting the first radiation counting data and the second radiation counting data into a preset neural network to obtain hardware state analysis data of the PET system; and the hardware state analysis data of the PET system is used for predicting radiation count data after preset working time, radiation count data in an initial state and uniformity data of a scanned image.
The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for analyzing hardware status, the method comprising:
acquiring first radiation count data of a positron emission computed tomography (PET) system in an initial state;
acquiring second radiation counting data after the PET system works for a preset time;
inputting the first radiation counting data and the second radiation counting data into a preset neural network to obtain hardware state analysis data of the PET system; and the hardware state analysis data of the PET system is used for predicting radiation counting data after preset working time, radiation counting data in an initial state and uniformity data of a scanned image.
2. The method of claim 1, wherein the neural network comprises a first sub-neural network and a second sub-neural network;
inputting the first radiation count data and the second radiation count data into a preset neural network to obtain hardware state analysis data of the PET system, including:
inputting the first radiation counting data into the first sub-neural network to obtain radiation counting data after a preset working time corresponding to the first radiation counting data;
inputting the second radiation counting data into the first sub-neural network to obtain standard radiation counting data corresponding to the second radiation counting data;
and inputting the second radiation counting data into the second sub-neural network to obtain uniformity data of the scanning image corresponding to the second radiation counting data.
3. The method of claim 2, further comprising:
acquiring a plurality of first sample radiation count data and a plurality of second sample radiation count data after working for a preset time length of the PET system in an initial state;
and training a first sub-neural network initial network model by taking the first sample radiation count data as input and the second sample radiation count data as output, taking the second sample radiation count data as input and the first sample radiation count data as output, and obtaining the first sub-neural network.
4. The method of claim 2, further comprising:
acquiring a plurality of second sample radiation counting data of the PET system after working for a preset time length and uniformity data of a scanned image corresponding to each second sample radiation counting data;
and taking the radiation count data of each second sample as input, taking the uniformity data of the scanned image corresponding to the radiation count data of each second sample as output, and training a second sub-neural network initial network model to obtain the second sub-neural network.
5. The method of claim 4, wherein said acquiring uniformity data for a scan image for each of said second sample radiation count data comprises:
acquiring barrel source data corresponding to the second sample radiation count data;
and carrying out image reconstruction on the bucket source data to obtain uniformity data of the scanned image.
6. The method of claims 1-5, wherein the first and second radiation count data each comprise single event data on the PET system rod source and coincidence event data on a barrel source; the single event data comprises intensity distribution information and energy distribution information; the coincidence event data includes intensity distribution information and time-of-flight distribution information.
7. The method of claim 6, wherein the rod source is centered in a field of view of the PET system when acquiring single event data for the rod source.
8. The method of claim 6, wherein the coincidence event data for the barrel source is acquired with the barrel source centered in the field of view of the axis of the PET system; and the axis of the PET system is superposed with the axis of the rod source.
9. A hardware state analysis apparatus, comprising:
the first data acquisition module is used for acquiring first radiation count data of the Positron Emission Tomography (PET) system in an initial state;
the second data acquisition module is used for acquiring second radiation counting data after the PET system works for a preset time;
the analysis data prediction module is used for inputting the first radiation count data and the second radiation count data into a preset neural network to obtain hardware state analysis data of the PET system; and the hardware state analysis data of the PET system is used for predicting radiation counting data after preset working time, radiation counting data in an initial state and uniformity data of a scanned image.
10. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 8 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 CN110037718A (en) | 2019-07-23 |
| CN110037718B true 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) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8299440B2 (en) * | 2007-12-20 | 2012-10-30 | Koninklijke Philips Electronics N.V. | Radiation detector for counting or integrating signals |
| CN107976706B (en) * | 2016-10-25 | 2019-10-29 | 上海东软医疗科技有限公司 | A kind of counting loss bearing calibration of PET system and device |
| CN109308728B (en) * | 2018-10-25 | 2023-01-03 | 上海联影医疗科技股份有限公司 | Positron emission computed tomography image processing method and device |
| CN109523584B (en) * | 2018-10-26 | 2021-04-20 | 上海联影医疗科技股份有限公司 | Image processing method and device, multi-modality imaging system, storage medium and equipment |
-
2019
- 2019-04-24 CN CN201910333538.7A patent/CN110037718B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110037718A (en) | 2019-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Memarzadeh et al. | Value of information in sequential decision making: Component inspection, permanent monitoring and system-level scheduling | |
| CN109965897B (en) | PET scanner correction method, PET scanner correction device, computer equipment and readable storage medium | |
| US20180144244A1 (en) | Distributed clinical workflow training of deep learning neural networks | |
| CN111078910A (en) | Medical image storage method, device, system, equipment and storage medium | |
| CN110584698A (en) | Detector quality control validation method, detector quality control validation device, computer equipment and storage medium | |
| CN109567852B (en) | Method for determining scanning range, method, device and equipment for acquiring medical image | |
| US20150051921A1 (en) | Superimposed verified photo with order or request | |
| CN110025329B (en) | Coincidence counting chord graph generation method and device, computer equipment and storage medium | |
| CN103365950A (en) | Method for loading medical image data and device for performing the method | |
| Doyle et al. | Multivariate decoding of brain images using ordinal regression | |
| CN108898238A (en) | Medical equipment failure forecasting system and correlation technique, device and equipment | |
| CN111588399B (en) | Method, device and computer device for monitoring medical imaging device state | |
| CN110866909A (en) | Training method of image generation network, image prediction method and computer equipment | |
| CN110037718B (en) | Hardware state analysis method and device, computer equipment and storage medium | |
| CN110327065B (en) | Single-event counting rate correction method and device, computer equipment and storage medium | |
| CN110687585B (en) | Method, device, computer equipment and storage medium for obtaining crystal efficiency | |
| CN111027469B (en) | Human body part recognition method, computer device, and readable storage medium | |
| CN108873047B (en) | Method, system, computer device and storage medium for detecting activity of radioactive source | |
| CN111128345A (en) | Medical image acquisition method, medical scanning device and computer storage medium | |
| DE10230878B4 (en) | Method and computer system for automatically processing studies of imaging examination systems | |
| CN111210414A (en) | Medical image analysis method, computer device and readable storage medium | |
| CN112006713B (en) | Dynamic reconstruction, scan object positioning, count rate display method and PET scanning device | |
| CN111728633A (en) | PET system cross coincidence data processing method and device and computer equipment | |
| CN108703769B (en) | Method, device and system for correcting TOF data and computer-readable storage medium | |
| CN109480886B (en) | Bone injury detection method and device, computer equipment and 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 |