CN110084429A - Prediction technique, device, storage medium and the electronic equipment of sweep time - Google Patents
Prediction technique, device, storage medium and the electronic equipment of sweep time Download PDFInfo
- Publication number
- CN110084429A CN110084429A CN201910354981.2A CN201910354981A CN110084429A CN 110084429 A CN110084429 A CN 110084429A CN 201910354981 A CN201910354981 A CN 201910354981A CN 110084429 A CN110084429 A CN 110084429A
- Authority
- CN
- China
- Prior art keywords
- sweep time
- node
- subject
- pet
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Abstract
The application provides prediction technique, device, storage medium and the electronic equipment of a kind of sweep time, the sweep time of PET-CT inspection is carried out subject is rationally arranged, the prediction technique of the sweep time is used in PET-CT system, this method comprises: obtaining the personal information of subject and the check point of subject progress PET-CT inspection;Determine that the subject carries out the drug dose injected required for PET-CT is checked;The personal information, the check point and the drug dose are input to the sweep time model trained;It obtains and sweep time required for PET-CT is checked is carried out by the subject that the sweep time model prediction goes out.
Description
Technical field
This application involves the field of medical instrument technology, in particular to a kind of prediction technique of sweep time, device, storage are situated between
Matter and electronic equipment.
Background technique
With advances in technology and product is constantly brought forth new ideas, positron emission and X ray computer computed tomography (SPECT) system
(PET-CT system) by more and more extensive use, PET-CT system can play screening early period of tumour certain positive
Effect.
In current clinic PET-CT checking process, when for general tumour screening, generally require by operating doctor elder generation root
It carries out scanning bed required for PET-CT is checked according to empirically determined subject, then is scanned for each scanning bed, and
During the scanning process, General System can give each scanning Bed set up unified initial scan time, then by operation doctor according to
The information such as the check point of subject and the drug dose of injection by virtue of experience change the sweep time of each scanning bed, with
The scanning demand for subject is asked to scan optimum image within less sweep time.
However, above-mentioned clinic PET-CT checks the too many experience for relying on operation doctor, check point institute cannot be accurately determined
The sweep time needed, just will appear sweep time when sweep time is arranged is arranged unreasonable situation, so as to cause
Subject receives the overlong time of scanning or the problem that imaging effect is undesirable.
Summary of the invention
In view of this, the application provides prediction technique, device, storage medium and the electronic equipment of a kind of sweep time, use
The sweep time that subject carries out PET-CT inspection is rationally arranged.
In a first aspect, the embodiment of the present application provides the prediction technique of sweep time a kind of, the method is used for PET-CT
In system, which comprises
The personal information and the subject that obtain subject carry out the check point of PET-CT inspection;
Determine that the subject carries out the drug dose injected required for PET-CT is checked;
The personal information, the check point and the drug dose are input to the sweep time model trained;
It obtains and scanning required for PET-CT is checked is carried out by the subject that the sweep time model prediction goes out
Time.
The above method first obtains the personal information of subject, the check point of subject's progress PET-CT inspection, and determines
The subject carries out the drug dose injected required for PET-CT is checked, then by personal information, check point and drug dose
It is input to the sweep time model trained, PET-CT is carried out by the subject gone out to sweep time model prediction to obtain
Sweep time required for checking, when carrying out the scanning of PET-CT inspection according to the sweep time setting subject predicted later
Between, the sweep time being arranged in this way is more reasonable, meets the actual conditions of subject, so as to avoid subject from receiving scanning
Overlong time or the undesirable problem of imaging effect.
In a possible implementation, subject described in the sweep time model prediction is carried out needed for PET-CT inspection
The sweep time wanted, comprising:
Required for the sweep time model determines that the subject carries out PET-CT inspection according to the personal information
Each scanning bed;
The sweep time model predicts each according to the personal information, the check point and the drug dose
The scanning bed corresponding sweep time.
In a possible implementation, this method further include:
The subject that prediction is obtained carries out PET-CT and checks that required sweep time and the subject carry out
Association.
In a possible implementation, this method further include:
Obtain the personal information of different subjects, the check point for carrying out PET-CT inspection, the drug dose of injection and institute
The sweep time of setting;
Personal information based on each subject, the check point for carrying out PET-CT inspection, the drug dose of injection and set
Fixed sweep time establishes sample database;The list item of the sample database includes the identifier of check point;
According to the sample database, every decision tree of random forest is constructed, obtains the sweep time model.
It is described according to the sample database in a possible implementation, every decision tree of random forest is constructed, is obtained
The sweep time model, comprising:
It is sampled based on the sample database, obtains different groups of training dataset;
For each group of training dataset, using this group of training dataset as the root node sample of decision tree, to the decision
Each node of tree carries out division processing, obtains a decision tree;
The sweep time model is formed by all decision trees, the sweep time of the sweep time model prediction is each
The mean value of the sweep time of the decision tree prediction.
In a possible implementation, the node to decision tree carries out division processing, comprising:
Calculate the loss function of present node;The loss function is the sweep time for reaching the training sample of present node
Function;
It takes so that the loss function obtains Split Attribute of the feature of minimum value as present node;
Present node is divided based on the Split Attribute.
In a possible implementation, the loss function is calculated by following formula:
Wherein,Indicate the average value of the sweep time of each training sample of j-th of node of arrival, SjIndicate j-th of section
The sample set of point, y indicate the sweep time of training sample x, and i indicates the child node of j-th of node,It indicates to reach j-th of section
The average value of the sweep time of each training sample of the child node i of point,Indicate the sample set of the child node i of j-th of node.
Second aspect, the embodiment of the present application also provides the prediction meanss of sweep time a kind of, including for executing first
The module of the prediction technique of sweep time in any possible implementation of aspect or first aspect.
The third aspect, the embodiment of the present application also provides a kind of storage mediums, are stored thereon with computer program, the journey
The prediction of the sweep time in any possible implementation of first aspect or first aspect is realized when sequence is executed by processor
The step of method.
Fourth aspect the embodiment of the present application also provides a kind of electronic equipment, including memory, processor and is stored in
On reservoir and the computer program that can run on a processor, the processor realizes first aspect or the when executing described program
The step of prediction technique of sweep time in any possible implementation of one side.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the prediction technique of sweep time provided by the embodiments of the present application;
Fig. 2 is the image schematic diagram of the scanning bed scanned in the embodiment of the present application;
Fig. 3 is a kind of structural schematic diagram of sweep time model in the embodiment of the present application;
Fig. 4 is the first structural schematic diagram of the prediction meanss of sweep time provided by the embodiments of the present application;
Fig. 5 is second of structural schematic diagram of the prediction meanss of sweep time provided by the embodiments of the present application;
Fig. 6 is the third structural schematic diagram of the prediction meanss of sweep time provided by the embodiments of the present application;
Fig. 7 is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
It is only to be not intended to be limiting the application merely for for the purpose of describing particular embodiments in term used in this application.
It is also intended in the application and the "an" of singular used in the attached claims, " described " and "the" including majority
Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps
It may be combined containing one or more associated any or all of project listed.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from
In the case where the application range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination ".
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description.
Referring to Fig. 1, the embodiment of the present application provides the prediction technique of sweep time a kind of, can be used for PET-CT system
In, this method may include steps of:
S101, the personal information for obtaining subject and the subject carry out the check point of PET-CT inspection;
Wherein, the personal information of subject may include: height, weight, gender, medical history position.Subject reserves
When registration, height, weight of the subject etc. can be obtained by intellectual measuring instrument.
S102, determine that the subject carries out the drug dose injected required for PET-CT is checked;
In some embodiments, it can determine that the subject carries out needed for PET-CT inspection based on the personal information of subject
The drug dose to be injected.
S103, personal information, check point and drug dose are input to the sweep time model trained;
When the subject progress PET-CT that S104, acquisition are gone out by sweep time model prediction checks required scanning
Between.
In a possible implementation, above-mentioned sweep time model prediction subject is carried out required for PET-CT inspection
Sweep time may include:
Sweep time model determines that the subject carries out required for PET-CT is checked respectively according to the personal information of subject
A scanning bed;
Sweep time model carries out the check point of PET-CT inspection according to the personal information of subject, the subject and is somebody's turn to do
The drug dose that subject inject required for PET-CT is checked predicts each scanning bed corresponding sweep time.
In a possible implementation, this method can also include:
The subject that prediction obtains is subjected to PET-CT and checks that required sweep time is associated with the subject.
In some embodiments, the incidence relation between sweep time and subject can also be added to sweep parameter pipe
Database is managed, so that the subsequent sweep parameter according in database determines the quantity of daily subject, the sequence of scanning, injection
The time etc. of medicament.When subject is scanned, the sweep time predicted can be set to subject and carry out PET-CT
The sweep time of inspection.
In some embodiments, the prediction technique of above-mentioned sweep time can also include the steps that training pattern, be situated between below
Continue the training process of sweep time model.
Step 1: it obtains the personal information of different subjects, carry out the medicament agent of the check point of PET-CT inspection, injection
Amount and set sweep time.
For example, the inspection that the personal information of different subjects can be obtained from a large amount of clinical datas, carry out PET-CT inspection
Look into position, the drug dose of injection and set sweep time, a large amount of clinical datas from different regions, Different hospital,
The sweep time that different operation doctor sets for the different check points of different subjects.
During clinical scanning, operation doctor can judge picture quality according to the real time imagery function in scanning process
Whether meet demands on examination, if satisfied, then operating the scanning that doctor stops Current Scan bed manually, carries out next scanning bed
The scanning of position, and the sweep time of Current Scan bed is recorded, if not satisfied, then continuing to scan until the scanning bed
Picture quality meets demands on examination, for example, being currently executing the scanning of scanning bed 3, operates doctor according to real time imagery
Image judges that picture quality meets demands on examination, just presses " next bed scanning " key, then executes sweeping for scanning bed 4
It retouches, and the sweep time of writing scan bed 3, as shown in Figure 2.
Step 2: personal information based on each subject, the check point for carrying out PET-CT inspection, injection drug dose
Sample database is established with set sweep time;The list item of the sample database includes the identifier of check point.
In some embodiments, the gender and physical feeling that subject can be identified using identifier, for example, using 0x1
The gender for indicating subject is male, indicates that the gender of subject is female with 0x2, indicates head with 0x1, indicates lung with 0x2, is used
0x3 indicates stomach, indicates liver with 0x4, indicates abdomen with 0x5, indicate thigh with 0x6, indicates shank with 0x7, indicated with 0x8
Foot indicates whole body with 0xff, indicates do not have medical history position with NA, by the personal information of subject, carries out PET-CT inspection
Check point, injection feature of the drug dose as the subject, the data of subject can be expressed as shown in formula (1)
Form.
Dij=(xi1,xi2,…,xin,yij) (1)
Wherein, DijIndicate that i-th of subject scans the data table items of j-th of check point, xinIndicate i-th of subject
N-th of feature, yijThe sweep time of i-th of subject, j-th of check point.
To the data got after above-mentioned processing, available sample database, as shown in following table one.
Table one
Step 3: according to sample database, every decision tree of random forest is constructed, sweep time model is obtained.
It is above-mentioned according to sample database in a possible implementation, every decision tree of random forest is constructed, is scanned
Time model may include:
It is sampled based on sample database, obtains different groups of training dataset;
For each group of training dataset, using this group of training dataset as the root node sample of decision tree, to the decision
Each node of tree carries out division processing, obtains a decision tree;
Sweep time model is formed by all decision trees, the sweep time of the sweep time model prediction is each decision tree
The mean value of the sweep time of prediction.
In some embodiments, sweep time model is composed of three classification regression trees (CART).
Such as: for the multidimensional input feature vector X of subject, it is scanned time model and obtains a corresponding scanning
Time Y can be indicated with estimated probability density function p (Y | X), as shown in figure 3, if sweep time model is by T (such as 3)
Classification regression tree (CART) is composed, when the sweep time of sweep time model prediction is the scanning of each decision tree prediction
Between mean value, can be calculated by following formula (2):
Wherein, V indicates that the multidimensional characteristic of input decision tree, y indicate sweep time for predicting by the decision tree, can be with
With estimated probability density function pt(y | V) it indicates.
In a possible implementation, division processing is carried out to the node of decision tree, may include:
Calculate the loss function of present node;The loss function is the sweep time for reaching the training sample of present node
Function;
It takes so that the loss function of present node obtains Split Attribute of the feature of minimum value as present node;
Present node is divided based on Split Attribute.
In some embodiments, loss function is calculated by following formula (3):
Wherein,Indicate the average value of the sweep time of each training sample of j-th of node of arrival, SjIndicate j-th of section
The sample set of point, y indicate the sweep time of training sample x, and i indicates the child node of j-th of node,It indicates to reach j-th of section
The average value of the sweep time of each training sample of the child node i of point,Indicate the sample set of the child node i of j-th of node.
Based on the same inventive concept, referring to fig. 4, the embodiment of the present application also provides the prediction meanss of sweep time a kind of,
The device includes: data obtaining module 11, drug dose determining module 12 and prediction module 13.
Data obtaining module 11, personal information and subject for obtaining subject carry out the inspection portion of PET-CT inspection
Position;
Drug dose determining module 12, for determining that subject carries out the drug dose injected required for PET-CT is checked;
Prediction module 13, for personal information, check point and drug dose to be input to the sweep time mould trained
Type;It obtains and sweep time required for PET-CT is checked is carried out by the subject that sweep time model prediction goes out.
In a possible implementation, prediction module 13 specifically can be used for:
Required for determining that the subject carries out PET-CT inspection according to the personal information of subject by sweep time model
Each scanning bed;
Each scanning is predicted according to the personal information of subject, check point and drug dose by sweep time model
Bed corresponding sweep time.
In a possible implementation, referring to Fig. 5, above-mentioned apparatus can also include:
Management module 14, for will predict to obtain, subject carry out sweep time required for PET-CT is checked with should
Subject is associated.
In a possible implementation, referring to Fig. 6, above-mentioned apparatus be can further include:
Training data obtains module 15, for obtaining the personal information of different subjects from a large amount of clinical datas, carrying out
The drug dose of check point, injection that PET-CT is checked and set sweep time;
Sample database establishes module 16, for based on each subject personal information, carry out PET-CT inspection check point,
The drug dose of injection and set sweep time establish sample database;The list item of the sample database includes the mark of check point
Symbol;
Model training module 17, for constructing every decision tree of random forest, obtaining sweep time mould according to sample database
Type.
In a possible implementation, model training module 17 specifically can be used for:
It is sampled based on sample database, obtains different groups of training dataset;
For each group of training dataset, using this group of training dataset as the root node sample of decision tree, to the decision
Each node of tree carries out division processing, obtains a decision tree;
Sweep time model is formed by all decision trees, the sweep time of the sweep time model prediction is each decision tree
The mean value of the sweep time of prediction.
In a possible implementation, model training module carries out division processing to the node of decision tree, may include:
Calculate the loss function of present node;The loss function is the sweep time for reaching the training sample of present node
Function;
It takes so that the loss function obtains Split Attribute of the feature of minimum value as present node;
Present node is divided based on Split Attribute.
In some embodiments, loss function is calculated by above formula (3).
The function of each unit and the realization process of effect are specifically detailed in the above method and correspond to step in above-mentioned apparatus
Realization process, details are not described herein.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
The purpose for needing to select some or all of the modules therein to realize application scheme.Those of ordinary skill in the art are not paying
Out in the case where creative work, it can understand and implement.
Based on the same inventive concept, the embodiment of the present application also provides a kind of storage mediums, are stored thereon with computer journey
Sequence realizes the step of the prediction technique of the sweep time in above-mentioned any possible implementation when described program is executed by processor
Suddenly.
Optionally, which is specifically as follows memory.
Based on the same inventive concept, referring to Fig. 7, the embodiment of the present application also provides a kind of electronic equipment, including memory
71 (such as nonvolatile memories), processor 72 and it is stored in the computer that can be run on memory 71 and on processor 72
Program, processor 72 realize the prediction technique of the sweep time in above-mentioned any possible implementation when executing described program
Step.The electronic equipment can be for example PC, in PET-CT system.
As shown in fig. 7, the electronic equipment generally can also include: memory 73, network interface 74 and internal bus 75.
Other than these components, it can also include other hardware, this is repeated no more.
It should be pointed out that the prediction meanss of above-mentioned sweep time can be anticipated by software realization as a logic
Device in justice is the computer program that will be stored in nonvolatile memory by the processor 72 of the electronic equipment where it
Instruction reads what operation in memory 73 was formed.
Theme described in this specification and the embodiment of feature operation can be realized in the following: Fundamental Digital Circuit,
Computer software or firmware, the computer including structure disclosed in this specification and its structural equivalents of tangible embodiment are hard
The combination of part or one or more of which.The embodiment of theme described in this specification can be implemented as one or
Multiple computer programs, i.e. coding are executed by data processing equipment on tangible non-transitory program carrier or are controlled at data
Manage one or more modules in the computer program instructions of the operation of device.Alternatively, or in addition, program instruction can be with
It is coded on manually generated transmitting signal, such as electricity, light or electromagnetic signal that machine generates, the signal are generated will believe
Breath encodes and is transferred to suitable receiver apparatus to be executed by data processing equipment.Computer storage medium can be machine can
Read storage equipment, machine readable storage substrate, random or serial access memory equipment or one or more of which group
It closes.
Processing described in this specification and logic flow can by execute one of one or more computer programs or
Multiple programmable calculators execute, to execute corresponding function by the way that output is operated and generated according to input data.Institute
It states processing and logic flow can also be by dedicated logic circuit-such as FPGA (field programmable gate array) or ASIC (dedicated collection
At circuit) Lai Zhihang, and device also can be implemented as dedicated logic circuit.
The computer for being suitable for carrying out computer program includes, for example, general and/or special microprocessor or it is any its
The central processing unit of his type.In general, central processing unit will refer to from read-only memory and/or random access memory reception
Order and data.The basic module of computer includes central processing unit for being practiced or carried out instruction and for storing instruction
With one or more memory devices of data.In general, computer will also be including one or more great Rong for storing data
Amount storage equipment, such as disk, magneto-optic disk or CD etc. or computer will be coupled operationally with this mass-memory unit
To receive from it data or have both at the same time to its transmission data or two kinds of situations.However, computer is not required to have in this way
Equipment.In addition, computer can be embedded in another equipment, such as mobile phone, personal digital assistant (PDA), mobile sound
Frequency or video player, game console, global positioning system (GPS) receiver or such as universal serial bus (USB) flash memory
The portable memory apparatus of driver, names just a few.
It is suitable for storing computer program instructions and the computer-readable medium of data including the non-volatile of form of ownership
Memory, medium and memory devices, for example including semiconductor memory devices (such as EPROM, EEPROM and flash memory device),
Disk (such as internal hard drive or removable disk), magneto-optic disk and CD ROM and DVD-ROM disk.Processor and memory can be by special
It is supplemented or is incorporated in dedicated logic circuit with logic circuit.
Although this specification includes many specific implementation details, these are not necessarily to be construed as the model for limiting any invention
It encloses or range claimed, and is primarily used for describing the feature of the specific embodiment of specific invention.In this specification
Certain features described in multiple embodiments can also be combined implementation in a single embodiment.On the other hand, individually implementing
Various features described in example can also be performed separately in various embodiments or be implemented with any suitable sub-portfolio.This
Outside, although feature can work in certain combinations as described above and even initially so be claimed, institute is come from
One or more features in claimed combination can be removed from the combination in some cases, and claimed
Combination can be directed toward the modification of sub-portfolio or sub-portfolio.
Similarly, although depicting operation in the accompanying drawings with particular order, this is understood not to require these behaviour
Make the particular order shown in execute or sequentially carry out or require the operation of all illustrations to be performed, to realize desired knot
Fruit.In some cases, multitask and parallel processing may be advantageous.In addition, the various system modules in above-described embodiment
Separation with component is understood not to be required to such separation in all embodiments, and it is to be understood that described
Program assembly and system can be usually integrated in together in single software product, or be packaged into multiple software product.
The specific embodiment of theme has been described as a result,.Other embodiments are within the scope of the appended claims.?
In some cases, the movement recorded in claims can be executed in different order and still realize desired result.This
Outside, the processing described in attached drawing and it is nonessential shown in particular order or sequential order, to realize desired result.In certain realities
In existing, multitask and parallel processing be may be advantageous.
The foregoing is merely the preferred embodiments of the application, not to limit the application, all essences in the application
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the application protection.
Claims (16)
1. a kind of prediction technique of sweep time, which is characterized in that the method is used in PET-CT system, the method packet
It includes:
The personal information and the subject that obtain subject carry out the check point of PET-CT inspection;
Determine that the subject carries out the drug dose injected required for PET-CT is checked;
The personal information, the check point and the drug dose are input to the sweep time model trained;
It obtains and sweep time required for PET-CT is checked is carried out by the subject that the sweep time model prediction goes out.
2. the method according to claim 1, wherein subject described in the sweep time model prediction carries out
Sweep time required for PET-CT is checked, comprising:
The sweep time model determines each required for subject's progress PET-CT is checked according to the personal information
Scan bed;
Described in the sweep time model predicts each according to the personal information, the check point and the drug dose
Scan bed corresponding sweep time.
3. method according to claim 1 or 2, which is characterized in that this method further include:
The subject that prediction obtains is subjected to PET-CT and checks that required sweep time is associated with the subject.
4. the method according to claim 1, wherein this method further include:
It obtains the personal information of different subjects, carry out the check point of PET-CT inspection, the drug dose of injection and set
Sweep time;
Personal information based on each subject, the check point for carrying out PET-CT inspection, the drug dose of injection and set
Sweep time establishes sample database;The list item of the sample database includes the identifier of check point;
According to the sample database, every decision tree of random forest is constructed, obtains the sweep time model.
5. according to the method described in claim 4, constructing the every of random forest it is characterized in that, described according to the sample database
Decision tree, obtains the sweep time model, comprising:
It is sampled based on the sample database, obtains different groups of training dataset;
For each group of training dataset, using this group of training dataset as the root node sample of decision tree, to the decision tree
Each node carries out division processing, obtains a decision tree;
The sweep time model is formed by all decision trees, the sweep time of the sweep time model prediction is each described
The mean value of the sweep time of decision tree prediction.
6. according to the method described in claim 5, it is characterized in that, the node to decision tree carries out division processing, comprising:
Calculate the loss function of present node;The loss function is the letter for reaching the sweep time of training sample of present node
Number;
It takes so that the loss function obtains Split Attribute of the feature of minimum value as present node;
Present node is divided based on the Split Attribute.
7. according to the method described in claim 6, it is characterized in that, the loss function is calculated by following formula:
Wherein,Indicate the average value of the sweep time of each training sample of j-th of node of arrival, SjIndicate j-th of node
Sample set, y indicate the sweep time of training sample x, and i indicates the child node of j-th of node,It indicates to reach j-th of node
The average value of the sweep time of each training sample of child node i,Indicate the sample set of the child node i of j-th of node.
8. a kind of prediction meanss of sweep time, which is characterized in that described device includes:
Data obtaining module, personal information and the subject for obtaining subject carry out the inspection portion of PET-CT inspection
Position;
Drug dose determining module, for determining that the subject carries out the drug dose injected required for PET-CT is checked;
Prediction module, for the personal information, the check point and the drug dose to be input to the scanning trained
Time model;It obtains and scanning required for PET-CT is checked is carried out by the subject that the sweep time model prediction goes out
Time.
9. device according to claim 8, which is characterized in that the prediction module is specifically used for:
Required for determining that the subject carries out PET-CT inspection according to the personal information by the sweep time model
Each scanning bed;
Each is predicted according to the personal information, the check point and the drug dose by the sweep time model
The scanning bed corresponding sweep time.
10. device according to claim 8 or claim 9, which is characterized in that described device further include:
Management module, the subject for that will predict to obtain carry out sweep time required for PET-CT is checked and it is described by
Inspection person is associated.
11. device according to claim 10, which is characterized in that described device further comprises:
Training data obtains module, for obtaining personal information, the check point for carrying out PET-CT inspection, note of different subjects
The drug dose penetrated and set sweep time;
Sample database establishes module, for based on each subject personal information, carry out PET-CT inspection check point, injection
Drug dose and set sweep time establish sample database;The list item of the sample database includes the identifier of check point;
Model training module, for constructing every decision tree of random forest, obtaining the sweep time according to the sample database
Model.
12. device according to claim 11, which is characterized in that the model training module is specifically used for:
It is sampled based on the sample database, obtains different groups of training dataset;
For each group of training dataset, using this group of training dataset as the root node sample of decision tree, to the decision tree
Each node carries out division processing, obtains a decision tree;
The sweep time model is formed by all decision trees, the sweep time of the sweep time model prediction is each described
The mean value of the sweep time of decision tree prediction.
13. device according to claim 12, which is characterized in that the model training module carries out the node of decision tree
Division processing, comprising:
Calculate the loss function of present node;The loss function is the letter for reaching the sweep time of training sample of present node
Number;
It takes so that the loss function obtains Split Attribute of the feature of minimum value as present node;
Present node is divided based on the Split Attribute.
14. device according to claim 13, which is characterized in that the loss function is calculated by following formula:
Wherein,Indicate the average value of the sweep time of each training sample of j-th of node of arrival, SjIndicate j-th of node
Sample set, y indicate the sweep time of training sample x, and i indicates the child node of j-th of node,It indicates to reach j-th of node
The average value of the sweep time of each training sample of child node i,Indicate the sample set of the child node i of j-th of node.
15. a kind of storage medium, is stored thereon with computer program, which is characterized in that real when described program is executed by processor
The step of any one of existing claim 1-7 the method.
16. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes the step of any one of claim 1-7 the method when executing described program
Suddenly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910354981.2A CN110084429A (en) | 2019-04-29 | 2019-04-29 | Prediction technique, device, storage medium and the electronic equipment of sweep time |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910354981.2A CN110084429A (en) | 2019-04-29 | 2019-04-29 | Prediction technique, device, storage medium and the electronic equipment of sweep time |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110084429A true CN110084429A (en) | 2019-08-02 |
Family
ID=67417597
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910354981.2A Pending CN110084429A (en) | 2019-04-29 | 2019-04-29 | Prediction technique, device, storage medium and the electronic equipment of sweep time |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110084429A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111161857A (en) * | 2019-12-26 | 2020-05-15 | 东软医疗系统股份有限公司 | Method, device and management system for determining inspection sequence |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101084839A (en) * | 2006-01-09 | 2007-12-12 | 西门子公司 | Control method as well as an imaging appliance |
CN103800027A (en) * | 2012-11-14 | 2014-05-21 | 上海联影医疗科技有限公司 | Positron emission computed tomography scanning method and system |
CN105193442A (en) * | 2015-09-17 | 2015-12-30 | 沈阳东软医疗系统有限公司 | Method and device for determining PET (Positron Emission Tomography) scanning time |
US20170007148A1 (en) * | 2015-07-07 | 2017-01-12 | Tesla Health, Inc | Fast scaning based on magnetic resonance history |
CN107423551A (en) * | 2016-05-24 | 2017-12-01 | 西门子医疗有限公司 | For performing the imaging method of medical inspection |
CN107870810A (en) * | 2017-10-31 | 2018-04-03 | 广东欧珀移动通信有限公司 | Using method for cleaning, device, storage medium and electronic equipment |
JP2018139901A (en) * | 2017-02-28 | 2018-09-13 | 国立大学法人信州大学 | Contrast ct scanner apparatus, operation method of contrast ct scanner apparatus and method for acquiring contrast ct scan image |
CN108962381A (en) * | 2017-05-19 | 2018-12-07 | 西门子保健有限责任公司 | The method based on study of personalized evaluation, long-term forecast and management for atherosclerosis |
CN109009193A (en) * | 2018-07-13 | 2018-12-18 | 沈阳东软医疗系统有限公司 | Dose modulation, device and helical CT device |
CN109350100A (en) * | 2018-09-27 | 2019-02-19 | 上海联影医疗科技有限公司 | Medical imaging procedure, medical imaging devices and computer readable storage medium |
-
2019
- 2019-04-29 CN CN201910354981.2A patent/CN110084429A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101084839A (en) * | 2006-01-09 | 2007-12-12 | 西门子公司 | Control method as well as an imaging appliance |
CN103800027A (en) * | 2012-11-14 | 2014-05-21 | 上海联影医疗科技有限公司 | Positron emission computed tomography scanning method and system |
US20170007148A1 (en) * | 2015-07-07 | 2017-01-12 | Tesla Health, Inc | Fast scaning based on magnetic resonance history |
CN105193442A (en) * | 2015-09-17 | 2015-12-30 | 沈阳东软医疗系统有限公司 | Method and device for determining PET (Positron Emission Tomography) scanning time |
CN107423551A (en) * | 2016-05-24 | 2017-12-01 | 西门子医疗有限公司 | For performing the imaging method of medical inspection |
JP2018139901A (en) * | 2017-02-28 | 2018-09-13 | 国立大学法人信州大学 | Contrast ct scanner apparatus, operation method of contrast ct scanner apparatus and method for acquiring contrast ct scan image |
CN108962381A (en) * | 2017-05-19 | 2018-12-07 | 西门子保健有限责任公司 | The method based on study of personalized evaluation, long-term forecast and management for atherosclerosis |
CN107870810A (en) * | 2017-10-31 | 2018-04-03 | 广东欧珀移动通信有限公司 | Using method for cleaning, device, storage medium and electronic equipment |
CN109009193A (en) * | 2018-07-13 | 2018-12-18 | 沈阳东软医疗系统有限公司 | Dose modulation, device and helical CT device |
CN109350100A (en) * | 2018-09-27 | 2019-02-19 | 上海联影医疗科技有限公司 | Medical imaging procedure, medical imaging devices and computer readable storage medium |
Non-Patent Citations (5)
Title |
---|
李祥霞等: "基于放射影像组学和随机森林算法的肺结节良恶性分类", 《华南理工大学学报(自然科学版)》 * |
秦英等: "基于PET-CT的Tomita评分在脊柱转移瘤患者生存周期预测中的应用", 《分子影像学杂志》 * |
蒋雪晴: "基于随机森林和BSS特征的PET-CT肺肿瘤分割", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
赵予涵等: "某公立医院CT检查量的时间趋势分析及预测研究", 《论著》 * |
鲁宗豪: "基于机器学习方法的脑胶质瘤影像分级研究", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111161857A (en) * | 2019-12-26 | 2020-05-15 | 东软医疗系统股份有限公司 | Method, device and management system for determining inspection sequence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102629376B (en) | Image registration | |
US20210012486A1 (en) | Image synthesis with generative adversarial network | |
Menze et al. | The multimodal brain tumor image segmentation benchmark (BRATS) | |
CN205665697U (en) | Medical science video identification diagnostic system based on cell neural network or convolution neural network | |
BR112020022270A2 (en) | systems and methods for unifying statistical models for different data modalities | |
CN110047056A (en) | With the cross-domain image analysis and synthesis of depth image to image network and confrontation network | |
CN107209945A (en) | Use the system and method for the conversion for medical imaging of machine learning | |
EP3338636B1 (en) | An apparatus and associated method for imaging | |
US20040027359A1 (en) | System and method for generating movie loop display from medical image data | |
CN112435341B (en) | Training method and device for three-dimensional reconstruction network, and three-dimensional reconstruction method and device | |
Chen et al. | Adaptive hierarchical dual consistency for semi-supervised left atrium segmentation on cross-domain data | |
CN110211165A (en) | A kind of image multi-mode registration method based on the study of asynchronous deeply | |
CN106062782A (en) | Unsupervised training for an atlas-based registration | |
Kesner et al. | Medical imaging data in the digital innovation age | |
Ankenbrand et al. | Deep learning‐based cardiac cine segmentation: Transfer learning application to 7T ultrahigh‐field MRI | |
CN115601352A (en) | Medical image segmentation method based on multi-mode self-supervision | |
CN107833229A (en) | Information processing method, apparatus and system | |
CN110084429A (en) | Prediction technique, device, storage medium and the electronic equipment of sweep time | |
CN109147927B (en) | Man-machine interaction method, device, equipment and medium | |
CN117034142B (en) | Unbalanced medical data missing value filling method and system | |
CN108765410A (en) | Medical image processing method and device and terminal | |
US20230126877A1 (en) | Synthetic data generation and annotation for tumor diagnostics and treatment | |
CN109102845B (en) | Medical document auditing method, device, computer equipment and storage medium | |
CN115861175A (en) | Medical image quality monitoring method and device, electronic equipment and storage medium | |
CN113901764A (en) | Content typesetting method and device, electronic 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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230425 Address after: Room 308, No. 177-2 Chuangxin Road, Hunnan District, Shenyang City, Liaoning Province, 110167 Applicant after: Shenyang Zhihe Medical Technology Co.,Ltd. Address before: 110167 No. 177-1 Innovation Road, Hunnan District, Shenyang City, Liaoning Province Applicant before: Shenyang Neusoft Medical Systems Co.,Ltd. |
|
TA01 | Transfer of patent application right |