CN117482415A - Intensity-modulated optimization method, system, equipment and medium based on dose correction - Google Patents
Intensity-modulated optimization method, system, equipment and medium based on dose correction Download PDFInfo
- Publication number
- CN117482415A CN117482415A CN202311707349.4A CN202311707349A CN117482415A CN 117482415 A CN117482415 A CN 117482415A CN 202311707349 A CN202311707349 A CN 202311707349A CN 117482415 A CN117482415 A CN 117482415A
- Authority
- CN
- China
- Prior art keywords
- dose
- optimization
- accurate
- calculating
- correction
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000012937 correction Methods 0.000 title claims abstract description 52
- 238000005070 sampling Methods 0.000 claims abstract description 49
- 238000004364 calculation method Methods 0.000 claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 230000003321 amplification Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 4
- 238000005728 strengthening Methods 0.000 claims 1
- 125000004122 cyclic group Chemical group 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000001959 radiotherapy Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
- A61N5/1031—Treatment planning systems using a specific method of dose optimization
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
- A61N5/1039—Treatment planning systems using functional images, e.g. PET or MRI
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/1048—Monitoring, verifying, controlling systems and methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
- A61N5/1031—Treatment planning systems using a specific method of dose optimization
- A61N2005/1034—Monte Carlo type methods; particle tracking
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Radiation-Therapy Devices (AREA)
Abstract
The invention relates to a dose correction-based intensity-modulated optimization method, a system, equipment and a medium, which comprise CT information, sketching information and planning information of an input user; obtaining an optimization result according to input optimization, calculating rough dosage of a sampling point, and finishing initial optimization; the accurate dose calculation method is called to calculate the accurate dose of the sampling point through the optimization result obtained by the first optimization; performing dose fitting on the accurate dose and the rough dose of the sampling points by a fitting method, calculating correction parameters, and correcting the dose of the sampling points; substituting the corrected sampling point dose into optimization to optimize a new optimization result and sampling point dose, and completing one-time cyclic optimization; calculating the accurate dose of the sampling point again, checking whether the error is smaller than a deviation threshold value, if so, ending the dose correction, ending the optimization and saving the plan; otherwise, continuing to correct the dosage by a fitting method. The invention can rapidly deliver accurate intensity-modulated planning.
Description
Technical Field
The invention relates to the technical field of dose calculation, in particular to a dose correction-based intensity-modulated optimization method, a system, equipment and a medium.
Background
In the radiotherapy industry, the calculation of the dose needs to be considered with both the calculation speed and the dose precision in the planning and optimizing process, and a coarser dose calculation method is generally adopted in the optimizing process; and after the optimization is finished, an accurate dose calculation method is adopted to ensure the accuracy. However, due to the two different dose calculation methods, the front and back doses deviate. Aiming at the problem, the technical proposal provided by the invention solves the problem that the calculation results of two dosage calculation algorithms are inconsistent.
Disclosure of Invention
The intensity-modulated optimizing method, the system and the storage medium based on the dose correction solve the problem that the calculation results of two dose calculation algorithms are inconsistent.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the intensity-modulated optimizing method based on the dose correction comprises the following steps,
s1, acquiring user input information;
s2, performing first optimization according to input information to obtain rough dose;
s3, calculating the accurate dose of the sampling point by calling an accurate dose calculation method for the first optimized result;
and S4, performing dose fitting on the accurate dose and the rough dose of the sampling points by a fitting method, calculating correction parameters, and correcting the dose.
Further, the dose correction method in step S4 is as follows:
s41, substituting the corrected dose into optimization to optimize new optimization results and dose, and completing one-time cycle optimization;
s42, calculating the accurate dose again by using an accurate dose calculation method, judging whether the error of the accurate dose is smaller than a deviation threshold value or not, if so, ending the dose correction, ending the optimization and saving the plan; otherwise, continuing to correct the dosage by a fitting method.
Further, the step S4 adopts a segment fitting method, and the specific method is as follows:
s43, clustering the rough doses to divide the doses into [ d ] with different sizes j ，d j+1 ]J=0, …, m+1, where d 0 At minimum dose, d m+1 Maximum dose, the rest d j Is a clustering center;
for each dose interval [ d ] j ，d j+1 ]A fine and coarse dose mapping model is built, in the form,
y i ≈G(x i ，H，c，b)＝f(x i ) T Hf(x i )+c T f(x i )+b (1)
d j ≤x i ≤d j+1 ，j＝0，…，m (2)
wherein y is i For accurate dosage, x i For coarse dose H, c and b represent correction parameters, where H is the real symmetric matrix, c is the vector, b is the real number f (x i )＝[f 1 (x i )，…，f n (x i )]，x i0 D is a super parameter, and represents translation amount and amplification multiple respectively, and n represents a finite number;
s44, selecting a regression model with penalty terms to calculate correction parameters, wherein the correction parameters are represented by the following formula,
wherein x, y represent the vector composed of the coarse dose and the fine dose, α > =0 represents the penalty factor for controlling the model complexity, Ω represents the penalty term;
setting different alpha values, and calculating the above formula to obtain the optimal correction parameters H, c and b.
Further, in the step S1, the user input information includes CT information, sketching information, and planning information; and optimizing according to the input information to obtain an optimizing result, calculating the rough dosage of the point, and finishing the initial optimization.
On the other hand, the invention also discloses a dose correction-based intensity-modulated optimizing system which comprises the following units,
the user input module is used for inputting CT information, sketching information and planning information of a user;
the initial optimization module is used for obtaining an optimization result according to input optimization, calculating rough dosage of the sampling points and completing initial optimization;
the accurate dose calculation module is used for calculating the accurate dose of the sampling point by calling an accurate dose calculation method according to an optimization result obtained by first optimization;
the dose fitting module is used for performing dose fitting on the accurate dose and the rough dose of the sampling points through a fitting method, calculating correction parameters and correcting the doses of the sampling points;
the circulation optimization module is used for substituting the corrected sampling point dose into the optimization to optimize a new optimization result and the sampling point dose, so as to complete one-time circulation optimization;
the error judging module is used for calculating the accurate dose of the sampling point by recalling the accurate dose calculating method, checking whether the error is smaller than a deviation threshold value, if so, ending the dose correction, ending the optimization and saving the plan; otherwise, continuing to correct the dosage by a fitting method.
Further, the initial optimization module performs iterative optimization by adopting an optimization algorithm according to the input information of the user input module, calculates a plan result in the optimization, calculates rough dosage of the sampling points, judges that the optimization target is met, and ends the initial optimization.
Further, the dose fitting module adopts a piecewise fitting method, and the fitting steps are as follows:
clustering the rough doses of the sampling points to divide the doses into intervals [ d ] with different sizes j ,d j+1 ]J=0, …, m+1, where d 0 At minimum dose, d m+1 Maximum dose, the rest d j Is a clustering center;
for each ofDose interval [ d ] j ,d j+1 ]A sample point accurate dose and coarse dose mapping model is built, in the form,
y i ≈G(x i ，H，c，b)＝f(x i ) T Hf(x i )+c T f(x i )+b (1)
d j ≤x i ≤d j+1 ，j＝0，…，m (2)
wherein y is i For accurate dose of sampling point, x i For the coarse dose of the sampling points H, c and b represent correction parameters, where H is the real symmetric matrix, c is the vector, b is the real number f (x i )＝[f i (x i )，…，f n (x i )]，x i0 D is a super parameter, and represents translation amount and amplification multiple respectively, and n represents a finite number;
selecting regression model with punishment term to calculate correction parameters, and the formula is shown in the specification,
wherein x, y respectively represent vectors formed by coarse dose and accurate dose of sampling points, alpha > =0 represents penalty coefficients for controlling model complexity, and omega represents penalty items;
setting different alpha values, and calculating the above formula to obtain the optimal correction parameters H, c and b.
Further, the loop optimization module performs iterative optimization by adopting an optimization algorithm, calculates an optimization result, calculates a new sampling point dosage by utilizing the optimization result, brings the sampling point dosage into a formula (1) for correction, obtains the corrected sampling point dosage, judges whether the optimization target is met or the difference between two iterations is smaller than a threshold value, and ends the loop optimization, otherwise, re-optimizes the calculation optimization result until the condition is met and ends the loop optimization.
In yet another aspect, the invention also discloses a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method as described above.
In yet another aspect, the invention also discloses a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the method as above.
According to the technical scheme, in order to overcome the defects of the prior art, the invention aims to provide the intensity-modulated optimization method based on the dose correction, a regression model based on the dose mapping of segmented fitting is established, the rapid and accurate optimization of the intensity-modulated plan is realized, and the method has important practical value.
The invention provides a strength adjusting optimization method based on dose correction, which initially uses a piecewise fitting method to establish mapping between accurate doses of sampling points and rough doses of the sampling points and a circularly optimized strength adjusting optimization method. The method has the advantages that for piecewise fitting, firstly, the rough dose of the sampling points is divided into different categories through clustering, so that the aggregation and dispersion condition of the data per se can be explored, and further, different fitting functions can be used for fitting different categories. Next, the piecewise fitting method used in the present invention has a nonlinear portion (f (x) i ) T Hf(x i ) Power function and sigma function), also has a linear part (c T f(x i ) +b), so that complex situations can be fitted, penalty terms are provided, and the robustness of a fitting result can be ensured; for the intensity-modulated optimization method of the cyclic optimization, the method can ensure that the final optimized result converges, and the accuracy is higher than that of one-time optimization, so that the accuracy of the result is ensured. The dosage deviation in the whole space dosage calculation and optimization process caused by adopting two dosage calculation methods can be effectively reduced through segment fitting and cyclic optimization.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention;
fig. 2 is a system block diagram of an embodiment of the present invention.
FIG. 3 is a data scatter diagram of an embodiment of the present invention.
Fig. 4 is a dose fitting chart of an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention.
Example 1
As shown in fig. 1, the intensity-modulated optimization method based on dose correction in this embodiment includes the following steps:
s1, acquiring user input information;
s2, performing first optimization according to input information to obtain rough dose;
s3, calculating the accurate dose of the sampling point by calling an accurate dose calculation method for the first optimized result;
and S4, performing dose fitting on the accurate dose and the rough dose of the sampling points by a fitting method, calculating correction parameters, and correcting the dose.
The user input information comprises CT information, sketching information and planning information of a user;
and obtaining an optimization result (not limited to the field intensity) according to the input optimization, calculating the rough point dose, and completing the initial optimization.
The preferred method for dose correction in step S4 is as follows:
(1) Substituting the corrected dose into optimization to optimize new optimization results and dose, and completing one-time cyclic optimization;
(2) Calculating accurate dose again by using an accurate dose calculation method, judging whether the error of the accurate dose is smaller than a deviation threshold value or not, if so, ending dose correction, ending optimization and saving a plan; otherwise, continuing to correct the dosage by a fitting method.
The step S4 is preferably a segment fitting method, and the specific method is as follows:
s43, clustering the rough doses to divide the doses into [ d ] with different sizes j ,d j+1 ]J=0, …, m+1, where d 0 At minimum dose, d m+1 Maximum dose, the rest d j Is a clustering center;
for each dose interval [ d ] j ,d j+1 ]A fine and coarse dose mapping model is built, in the form,
y i ≈G(x i ，H，c，b)＝f(x i ) T Hf(x i )+c T f(x i )+b (1)
d j ≤x i ≤d j+1 ，j＝0，…，m (2)
wherein y is i For accurate dosage, x i For coarse dose H, c and b represent correction parameters, where H is the real symmetric matrix, c is the vector, b is the real number f (x i )＝[f 1 (x i )，…，f n (x i )]，x i0 D is a super parameter, and represents translation amount and amplification multiple respectively, and n represents a finite number;
s44, selecting a regression model with penalty terms to calculate correction parameters, wherein the correction parameters are represented by the following formula,
wherein x, y represent the vector composed of the coarse dose and the fine dose, α > =0 represents the penalty factor for controlling the model complexity, Ω represents the penalty term; setting different alpha values, calculating the above formula, y i Is the exact dose of the sampling point, equation (1) uses G-function to fit y i Equation (2) further shows f (x) in G i ) The function, G, is a function of the coarse dose of the sampling points, where H, c, b are unknowns representing the correction parameters, and equation (3) computes the optimal correction parameters H, c, b by minimizing a regression model with penalty terms.
Example 2
As shown in fig. 2, the intensity-modulated optimizing system for dose correction of this embodiment includes the following units:
the user input module is used for inputting CT information, sketching information and planning information of a user;
the initial optimization module is used for obtaining an optimization result (not limited to the field intensity) according to input optimization, calculating rough point dose and completing initial optimization;
the accurate dose calculation module is used for calling an accurate dose calculation method to calculate the accurate dose of the point through an optimization result (not limited to the field intensity) obtained by first optimization;
the dose fitting module is used for carrying out dose fitting on the accurate dose and the rough dose of the sampling points through a fitting method, calculating correction parameters and correcting the doses of the sampling points;
the circulation optimization module is used for substituting the corrected sampling point dose into the optimization to optimize a new optimization result (not limited to the field intensity) and the sampling point dose so as to finish one-time circulation optimization;
the error judging module is used for calculating the accurate dose of the sampling point by recalling the accurate dose calculation method based on the error judging module, checking whether the error is smaller than a deviation threshold value, if so, ending the dose correction, ending the optimization and saving the plan; otherwise, continuing to correct the dosage by a fitting method.
Wherein, initial optimization module includes: according to the input information of the user input module, iterative optimization is carried out by adopting an optimization algorithm, a planning result is obtained through calculation in the optimization, rough dosage of sampling points is obtained through calculation, the optimization target is judged to be met, and initial optimization is ended.
The dose fitting module employs a piecewise fitting method, as in example 1.
The cycle optimization module specifically comprises:
and (3) carrying out iterative optimization by adopting an optimization algorithm, calculating to obtain an optimization result, calculating a new sampling point dosage by utilizing the optimization result, carrying the sampling point dosage into a formula (1) for correction to obtain a corrected sampling point dosage, judging that the optimization target is met or the difference between two iterations is smaller than a threshold value, ending one-time loop optimization, otherwise, re-optimizing the calculation optimization result until the condition is met, and ending one-time loop optimization.
It should be explained that the invention provides a strength adjusting optimization method based on dose correction, initially uses a piecewise fitting method to establish the mapping between the accurate dose and the rough dose of the sampling points and a cyclic optimization strength adjusting optimization method, uses a piecewise fitting method to establish a mapping model of the accurate dose and the rough dose of the sampling points and a cyclic optimization strength adjusting optimization method, and can rapidly deliver an accurate strength adjusting plan.
As shown in fig. 3, the graph is a data scatter plot, with the horizontal axis being the coarse dose of sample points and the vertical axis being the precise dose of sample points. The rough dose of the sampling point and the accurate dose of the sampling point can be seen from the scatter diagram to show a positive correlation trend, a model of the dose fitting module is realized through a neural network, a loss function adopts a mean square error loss function, weight attenuation is used for representing a penalty term, a random gradient descent algorithm is used for training the model 1000 rounds, and after model training is completed, a fitting result is shown in fig. 4. From the fitting result, although the fitting function is a nonlinear function, a result close to linearity can be fitted, which shows that the algorithm has a relatively ideal fitting effect.
Both the rough dose and the accurate dose calculation methods in embodiments 1 and 2 can be implemented by the prior art, for example, the rough dose calculation method includes, but is not limited to, any one of a pencil beam dose calculation method, a spot-kernel dose calculation method, or other existing methods; the accurate dose calculation method includes, but is not limited to, any of a convolution stack dose calculation method, a discrete pilot dose calculation method, a Monte Carlo dose calculation method, or other existing methods.
In yet another aspect, the invention also discloses a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method as described above.
In yet another aspect, the invention also discloses a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the method as above.
In yet another embodiment provided herein, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the dose-modifying based intensity-modulated optimization methods of the above embodiments.
It may be understood that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and explanation, examples and beneficial effects of the related content may refer to corresponding parts in the above method.
The embodiment of the application also provides an electronic device, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus,
a memory for storing a computer program;
and the processor is used for realizing the intensity-modulated optimization method based on the dose correction when executing the program stored in the memory.
The communication bus mentioned by the above electronic device may be a peripheral component interconnect standard (english: peripheral Component Interconnect, abbreviated: PCI) bus or an extended industry standard architecture (english: extended Industry Standard Architecture, abbreviated: EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, abbreviated as RAM) or nonvolatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; it may also be a digital signal processor (English: digital Signal Processing; DSP; for short), an application specific integrated circuit (English: application Specific Integrated Circuit; ASIC; for short), a Field programmable gate array (English: field-Programmable Gate Array; FPGA; for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A strengthening optimization method based on dose correction is characterized by comprising the following steps,
s1, acquiring user input information;
s2, performing first optimization according to input information to obtain rough dose;
s3, calculating the accurate dose of the sampling point by calling an accurate dose calculation method for the first optimized result;
and S4, performing dose fitting on the accurate dose and the rough dose of the sampling points by a fitting method, calculating correction parameters, and correcting the dose.
2. The dose-based intensity-modulated optimization method of claim 1, wherein said dose-modifying method of step S4 is as follows:
s41, substituting the corrected dose into optimization to optimize new optimization results and dose, and completing one-time cycle optimization;
s42, calculating the accurate dose again by using an accurate dose calculation method, judging whether the error of the accurate dose is smaller than a deviation threshold value or not, if so, ending the dose correction, ending the optimization and saving the plan; otherwise, continuing to correct the dosage by a fitting method.
3. The intensity-modulated optimizing method based on dose correction according to claim 1, wherein the step S4 adopts a piecewise fitting method, and the specific method is as follows:
s43, clustering the rough doses to divide the doses into [ d ] with different sizes j ，d j+1 ]J=0, …, m+1, where d 0 At minimum dose, d m+1 Maximum dose, the rest d j Is a clustering center;
for each dose interval [ d ] j ，d j+1 ]A fine and coarse dose mapping model is built, in the form,
y i ≈G(x i ，H，c，b)＝f(x i ) T Hf(x i )+c T f(x i )+b (1)
wherein y is i For accurate dosage, x i For coarse dose H, c and b represent correction parameters, where H is the real symmetric matrix, c is the vector, b is the real number f (x i )＝[f l (x i )，…，f n (x i )]，x i0 D is a super parameter, and represents translation amount and amplification multiple respectively, and n represents a finite number;
s44, selecting a regression model with penalty terms to calculate correction parameters, wherein the correction parameters are represented by the following formula,
wherein x, y represent the vector composed of the coarse dose and the fine dose, α > =0 represents the penalty factor for controlling the model complexity, Ω represents the penalty term;
setting different alpha values, and calculating the above formula to obtain the optimal correction parameters H, c and b.
4. The dose-correction-based intensity-modulated optimization method of claim 1, wherein in said step S1, the user input information includes CT information, delineation information, and planning information; and optimizing according to the input information to obtain an optimizing result, calculating the rough dosage of the point, and finishing the initial optimization.
5. A dose-modifying intensity-modulated optimization system, characterized by: comprising the following units of the device,
the user input module is used for inputting user information required by optimization;
the initial optimization module is used for obtaining an optimization result according to input optimization, calculating rough dosage of the sampling points and completing initial optimization;
the accurate dose calculation module is used for calculating the accurate dose of the sampling point by calling an accurate dose calculation method according to an optimization result obtained by first optimization;
and the dose fitting module is used for performing dose fitting on the accurate dose and the rough dose of the sampling points through a fitting method, calculating correction parameters and correcting the dose.
6. The dose-correction-based intensity-modulated optimizing system of claim 5, further comprising a loop optimizing module and an error judging module;
the circulation optimization module is used for substituting the corrected dose into the optimization to optimize a new optimization result and dose, so as to complete one-time circulation optimization;
the error judging module is used for calculating the accurate dose by recalling the accurate dose calculating method, checking whether the error is smaller than a deviation threshold value, if so, finishing dose correction, finishing optimization and saving a plan; otherwise, continuing to correct the dosage by a fitting method.
7. A dose-modifying intensity-modulated optimizing system as defined in claim 5, wherein: the loop optimization module comprises the steps of carrying out iterative optimization by adopting an optimization algorithm, calculating to obtain an optimization result, calculating a new dosage by utilizing the optimization result, carrying the dosage into a formula (1) for correction to obtain a corrected dosage, judging that the optimization target is met or the difference between two iterations is smaller than a threshold value, ending the loop optimization once, otherwise, re-optimizing the calculation optimization result until the condition is met, ending the loop optimization once.
8. A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method of any one of claims 1 to 4.
9. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311707349.4A CN117482415A (en) | 2023-12-12 | 2023-12-12 | Intensity-modulated optimization method, system, equipment and medium based on dose correction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311707349.4A CN117482415A (en) | 2023-12-12 | 2023-12-12 | Intensity-modulated optimization method, system, equipment and medium based on dose correction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117482415A true CN117482415A (en) | 2024-02-02 |
Family
ID=89683048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311707349.4A Pending CN117482415A (en) | 2023-12-12 | 2023-12-12 | Intensity-modulated optimization method, system, equipment and medium based on dose correction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117482415A (en) |
-
2023
- 2023-12-12 CN CN202311707349.4A patent/CN117482415A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113051777B (en) | Method for correcting data by using vector fitting | |
| CN111695624B (en) | Updating method, device, equipment and storage medium of data enhancement strategy | |
| CN112597610B (en) | Optimization method, device and equipment for lightweight design of mechanical arm structure | |
| US20240046086A1 (en) | Quantization method and quantization apparatus for weight of neural network, and storage medium | |
| CN112987724B (en) | Path optimization method, path optimization device, robot and storage medium | |
| CN110555231A (en) | Dynamic simulation model correction method | |
| CN112233200A (en) | Dose determination method and device | |
| CN112133440A (en) | Dose calculation system, dose quality assurance system and storage medium | |
| TW202244758A (en) | Fingerprint recognition method, fingerprint module, and electronic device | |
| WO2020082595A1 (en) | Image classification method, terminal device and non-volatile computer readable storage medium | |
| CN117115551A (en) | Image detection model training method and device, electronic equipment and storage medium | |
| CN117482415A (en) | Intensity-modulated optimization method, system, equipment and medium based on dose correction | |
| CN116089844B (en) | non-Gaussian feature verification method for pose data of unmanned aerial vehicle | |
| CN110060314B (en) | CT iterative reconstruction acceleration method and system based on artificial intelligence | |
| CN110852451B (en) | Recursive kernel self-adaptive filtering method based on kernel function | |
| JP2023536792A (en) | Multi-exponential error extrapolation | |
| CN111368792A (en) | Characteristic point mark injection molding type training method and device, electronic equipment and storage medium | |
| CN110572875A (en) | Wireless positioning method based on improved machine learning algorithm | |
| CN113640115A (en) | Optimization method and system suitable for solving inverse problem of quasi-isentropic compression experiment data | |
| CN111382757A (en) | Method for dynamically adjusting training samples in deep learning classification algorithm and terminal equipment | |
| CN115405402B (en) | Determination method and device of carbon loading model, electronic equipment and storage medium | |
| CN117579988B (en) | Anchor point-free positioning method and anchor point-free positioning system based on filtering under condition of high-capacity channel feature library | |
| Saatci et al. | Posterior Cramer–Rao lower bounds for dual Kalman estimation | |
| CN110648021B (en) | Two-stage power load prediction result coordination method, device and equipment | |
| CN117475968A (en) | Gamma voltage setting method and device 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 |