CN107441635B - It is a kind of for reducing the multiple tumor radioactive ray method for optimizing route for the treatment of time - Google Patents
It is a kind of for reducing the multiple tumor radioactive ray method for optimizing route for the treatment of time Download PDFInfo
- Publication number
- CN107441635B CN107441635B CN201710630403.8A CN201710630403A CN107441635B CN 107441635 B CN107441635 B CN 107441635B CN 201710630403 A CN201710630403 A CN 201710630403A CN 107441635 B CN107441635 B CN 107441635B
- Authority
- CN
- China
- Prior art keywords
- practical
- tumour
- point
- distance
- matrix
- 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.)
- Expired - Fee Related
Links
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
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
A kind of multiple tumor radioactive ray method for optimizing route for reducing treatment time of the present invention belongs to Medical Devices and field of artificial intelligence；Practical tumor region is degenerated to practical tumour point first by this method, determines the coordinate of practical tumour point；Then the distance between practical tumour point of any two is calculated, distance matrix is established；It reinitializes and explores parameter, calculate heuristic function initial value；Then optimal loop path is explored；Distance in optimal loop path maximum two practical tumour points are eventually found, the line of described two practical tumour points is removed in optimal loop path, and remainder is final path；Practical tumor region is degenerated to a tumour point by the present invention, radiological scans problem is converted to and how to traverse the most short problem of all tumour points and path, and propose a kind of method for optimizing route, substantially reduce treatment time, mitigate Case treatment pain, positive facilitation will be played to development of the artificial intelligence in Medical Devices.
Description
Technical field
A kind of multiple tumor radioactive ray method for optimizing route for reducing treatment time of the present invention belongs to Medical Devices
And field of artificial intelligence.
Background technique
Tumour radiotherapy is a kind of local therapeutic approaches using radiation cure tumour.Radioactive ray include that radioactivity is same
Position element generate α, β, gamma-rays and all kinds of roentgenotherapia machines or accelerator generate X-ray, electric wire, proton beam and other
Particle beams etc..According to statistics, about 70% cancer patient needs to use radiotherapy during treating cancer, and there are about 40%
Cancer can be eradicated with radiotherapy.Effect and status of the radiotherapy in oncotherapy become increasingly conspicuous, it has also become treatment is pernicious swollen
One of main means of tumor.
Malignant tumour can shift, i.e., the cancer cell in primary malignant neoplasm passes through around blood vessel, lymphatic vessel and tumour
Tissue, with the operation of blood, lymph and body fluid, to the tissue and organ metastasis of other distant sites, and " taking root ",
" germination " forms the malignant tumour with primary tumor same property type, since these malignant tumours show as sending out in many places
It is raw, therefore referred to as multiple tumor.
For the radiation cure of multiple tumor, the mode of early stage is that multiple tumor is regarded as to multiple independent swollen
Tumor carries out radiation cure just for one of tumour every time, and this mode, which needs repeatedly to treat, could complete a course for the treatment of,
Treatment time is long, and treatment cost is high.
The problem that for the above method, but the multiple tumor for a kind of similar printer printing document occur is put
Ray scanning method regards multiple tumor as the big tumour for only needing local treatment in this approach, wherein needs
Region to be treated is practical tumor region, is practical non-tumor region, radiation generator without region to be treated
The inswept big tumour in a manner of printing of inkjet printer document projects radioactive ray in practical tumor region, in practical non-tumour
Region does not project radioactive ray.Although this mode technology is relative complex, seance can complete a course for the treatment of, significantly
Treatment time is shortened, treatment cost is reduced, it has also become the main method of multiple tumor radiation cure at this stage.
In the above-mentioned methods, since radiation generator also wants the non-tumor region of inswept reality, and practical non-tumor area
The area in domain is often far longer than practical tumor region, and therefore, a large amount for the treatment of times have been wasted in practical non-tumor region scanning
In the process, if it is possible to which the sweep time for reducing this partial region rapidly moves to another reality from a practical tumor region
Border tumor region can substantially reduce treatment time, mitigate Case treatment pain, however, having found relevant side not yet
Method occurs.
Summary of the invention
In view of the above-mentioned problems, the multiple tumor radioactive ray path that the invention discloses a kind of for reducing treatment time is excellent
Change method, this method are developed from the multiple tumor radiological scans method of similar printer printing document, utilize reality
Non- tumor region is often much larger than the characteristics of practical tumor region, and practical tumor region is degenerated to a tumour point, will be radiated
Line scanning problem is converted to how to traverse the most short problem of all tumour points and path, and proposes a kind of method for optimizing route, this
Kind method is conducive to substantially reduce treatment time, mitigates Case treatment pain, by the development to artificial intelligence in Medical Devices
Play positive facilitation.
The object of the present invention is achieved like this:
Sigmatron zone routing optimization method towards multiple tumor radiotherapy, comprising the following steps:
Step a, practical tumor region is degenerated to practical tumour point, determines the coordinate of practical tumour point；
Specifically:
Practical tumour point coordinate is filled up in practical tumour dot matrix, every a line of the practical tumour dot matrix indicates
The first row of one practical tumour point coordinate, practical tumour dot matrix indicates practical tumour point abscissa, practical tumour dot matrix
Secondary series indicate practical tumour point ordinate；
Step b, the distance between practical tumour point of any two is calculated, distance matrix is established；
Specifically:
Construct a ranks number identical square matrix with practical tumour points, the i-th row jth column of the square matrix
Indicate the distance of i-th of practical j-th of distance of tumour point practical tumour point；
Step c, parameter is explored in initialization, calculates heuristic function initial value；
Specifically:
Initialization explores dimension, heuristic factor, retention factors, knowledge matrix, explores initial value and explore final value；
Heuristic function is the inverse of distance matrix；
Step d, optimal loop path is explored；
Specifically:
Since exploring initial value, it is iterated to final value is explored, in iterative process each time, multiple dimension joint explorations
Optimal path, comprising the following steps:
Step d1, under each dimension, using any one practical tumour point as exploration starting point, and initialization path is recorded
Table；
Step d2, the exploration path of each dimension is supplemented；
Specifically:
Step d21, it distinguishes and has accessed practical tumour point；
Step d22, practical tumour point to be visited is distinguished；
Step d23, the exploration probability between practical tumour point to be visited is calculated；Specifically: under current dimension, for not visiting
The practical tumour point of rope, first calculating Aij=τij·[ηij]β, wherein τijFor the i-th row jth column element, η in knowledge matrixijFor
Heuristic function, the distance between i-th of practical tumour point and j-th of practical tumour point are inversely proportional, and β indicates heuristic factor；So
B=∑ A is calculated afterwardsij；0 square matrix P is finally constructed, and according to Pij=AijThe algorithm of/B gives matrix P assignment；
Step d24, the next practical tumour point to be explored using wheel disc bet method determination；
Step d3, the distance that path is explored under each dimension is calculated；
Step d4, most short exploration distance is calculated；
Step d5, information matrix is updated；Specifically:
Above formula is assignment statement, the τ on the right of equationijIndicate under current exploration value the i-th row jth column element in knowledge matrix,
The τ on the equation left sideijIndicate that the i-th row jth column element, ρ indicate retention factors in knowledge matrix under next exploration value；
Step e, distance in optimal loop path maximum two practical tumour points are found, optimal loop path is removed described
The line of two practical tumour points, remainder are final path.
The above-mentioned sigmatron zone routing optimization method towards multiple tumor radiotherapy is multiple swollen for treating
Tumor.
The above-mentioned sigmatron zone routing optimization method towards multiple tumor radiotherapy is in radiotherapy equipment
Application.
The utility model has the advantages that
The first, the present invention is developed from the multiple tumor radiological scans method of similar printer printing document, benefit
The characteristics of being often much larger than practical tumor region with practical non-tumor region, is degenerated to a tumour point for practical tumor region,
Radiological scans problem is converted to and how to traverse the most short problem of all tumour points and path, and proposes a kind of path optimization side
Method, this method effectively avoid a large amount for the treatment of times from being wasted in practical non-tumor region scanning process, are conducive to drop significantly
Low treatment time mitigates Case treatment pain, will play positive facilitation to development of the artificial intelligence in Medical Devices.
The second, in method for optimizing route of the present invention, propose a kind of alternative manner, by explore dimension, heuristic factor,
Mutual operation between retention factors, knowledge matrix, realizes the exploration to the shortest distance.
Third, in the methods of the invention realizes the change for exploring path, effectively avoids visiting by quoting wheel disc bet method
Rope path focuses on local optimum.
4th, the patent of invention " high energy X towards multiple tumor radiotherapy that the present invention applies on the same day with this seminar
Field of radiation method for optimizing route " it compares, due to by under current dimension, having detected reality in the step of updating information matrix
The total distance of border tumour point replaces with 1；Patent of invention " a kind of radiotherapy for multiple tumor applied on the same day with this seminar
Equipment high-energy light beam guiding method for optimizing route " it compares, since in the step of updating information matrix, by under current dimension, i-th is
The practical tumour o'clock of detection does not detect the distance between practical tumour point to j-th and replaces with 1, therefore saves the calculating of total distance
The calling process of distance between process and two practical tumour points, so that the algorithm used time is also less.
Detailed description of the invention
Fig. 1 is that the present invention is a kind of for reducing the multiple tumor radioactive ray method for optimizing route flow chart for the treatment of time.
Fig. 2 is the operation result of the program of emulation experiment.
Fig. 3 is the Matlab software interface screenshot of emulation experiment.
Specific embodiment
The specific embodiment of the invention is described in further detail with reference to the accompanying drawing.
Specific embodiment one
It is that the present invention is a kind of for reducing the implementation of the multiple tumor radioactive ray method for optimizing route for the treatment of time below
Mode.
Present embodiment it is a kind of for reducing the multiple tumor radioactive ray method for optimizing route for the treatment of time, flow chart
As shown in Figure 1, method includes the following steps:
Step a, practical tumor region is degenerated to practical tumour point, determines the coordinate of practical tumour point；
Specifically:
Practical tumour point coordinate is filled up in practical tumour dot matrix, every a line of the practical tumour dot matrix indicates
The first row of one practical tumour point coordinate, practical tumour dot matrix indicates practical tumour point abscissa, practical tumour dot matrix
Secondary series indicate practical tumour point ordinate；
Step b, the distance between practical tumour point of any two is calculated, distance matrix is established；
Specifically:
Construct a ranks number identical square matrix with practical tumour points, the i-th row jth column of the square matrix
Indicate the distance of i-th of practical j-th of distance of tumour point practical tumour point；
Step c, parameter is explored in initialization, calculates heuristic function initial value；
Specifically:
Initialization explores dimension, heuristic factor, retention factors, knowledge matrix, explores initial value and explore final value；
Heuristic function is the inverse of distance matrix；
Step d, optimal loop path is explored；
Specifically:
Since exploring initial value, it is iterated to final value is explored, in iterative process each time, multiple dimension joint explorations
Optimal path, comprising the following steps:
Step d1, under each dimension, using any one practical tumour point as exploration starting point, and initialization path is recorded
Table；
Step d2, the exploration path of each dimension is supplemented；
Specifically:
Step d21, it distinguishes and has accessed practical tumour point；
Step d22, practical tumour point to be visited is distinguished；
Step d23, the exploration probability between practical tumour point to be visited is calculated；Specifically: under current dimension, for not visiting
The practical tumour point of rope, first calculating Aij=τij·[ηij]β, wherein τijFor the i-th row jth column element, η in knowledge matrixijFor
Heuristic function, the distance between i-th of practical tumour point and j-th of practical tumour point are inversely proportional, and β indicates heuristic factor；So
B=∑ A is calculated afterwardsij；0 square matrix P is finally constructed, and according to Pij=AijThe algorithm of/B gives matrix P assignment；
Step d24, the next practical tumour point to be explored using wheel disc bet method determination；
Step d3, the distance that path is explored under each dimension is calculated；
Step d4, most short exploration distance is calculated；
Step d5, information matrix is updated；Specifically:
Above formula is assignment statement, the τ on the right of equationijIndicate under current exploration value the i-th row jth column element in knowledge matrix,
The τ on the equation left sideijIndicate that the i-th row jth column element, ρ indicate retention factors in knowledge matrix under next exploration value；
Step e, distance in optimal loop path maximum two practical tumour points are found, optimal loop path is removed described
The line of two practical tumour points, remainder are final path.
It is a kind of for reducing the multiple tumor radioactive ray path optimization side for the treatment of time to the present invention with Matlab below
Method is emulated, and simulated program is as follows:
clear all
close all
clc
tic
%% step a, practical tumor region is degenerated to practical tumour point, determines the coordinate of practical tumour point；
Tumorregion=[656 706；36 32；849 277；934 46；679 97；758 823；743 95；392
317；655 950；171 34]；
The distance between %% step b, calculating practical tumour point of any two, establish distance matrix；
Parameter is explored in %% step c, initialization, calculates heuristic function；
%% step d, optimal loop path is explored；
%% step e, distance in optimal loop path maximum two practical tumour points are found, optimal loop path is removed
The line of described two practical tumour points, remainder is final path；
The operation result of the program of emulation experiment is as shown in Fig. 2, figure it is seen that the shortest distance is 2432.6172
Unit.
The Matlab software interface screenshot of emulation experiment as shown in figure 3, from figure 3, it can be seen that shortest path 5,7,4,
3,6,9,1,8,10,2, software used time 0.882737s.
Patent of invention " the sigmatron region road towards multiple tumor radiotherapy applied on the same day with this seminar
Diameter optimization method " it compares, the obtained shortest distance shortens to 2432.6172 units from 2487.9366 units, that is, explores
The shortest distance arrived is shorter, and the used time shortens to 0.882737s from 1.248304s, and the used time is also less.
Patent of invention " a kind of radiotherapy apparatus high-energy light beam guiding path for multiple tumor applied on the same day with this seminar
Optimization method " it compares, the obtained shortest distance is all 2432.6172 units, that is, the shortest distance explored is equally short, is used
When from 0.892959s shorten to 0.882737s, the used time is also less.
Specific embodiment two
It is that the present invention is a kind of for reducing the application of the multiple tumor radioactive ray method for optimizing route for the treatment of time below
Embodiment.
One of present embodiment is used to reduce the multiple tumor radioactive ray method for optimizing route for the treatment of time, for tool
Method described in body embodiment one, the method is for treating multiple tumor.
Specific embodiment three
It is that the present invention is a kind of for reducing the application of the multiple tumor radioactive ray method for optimizing route for the treatment of time below
Embodiment.
One of present embodiment is used to reduce the multiple tumor radioactive ray method for optimizing route for the treatment of time, for tool
Method described in body embodiment one, the method are applied to radiotherapy equipment.
Claims (1)
1. the sigmatron zone routing optimization method towards multiple tumor radiotherapy, which is characterized in that including following step
It is rapid:
Step a, practical tumor region is degenerated to practical tumour point, determines the coordinate of practical tumour point；
Specifically:
Practical tumour point coordinate is filled up in practical tumour dot matrix, every a line of the practical tumour dot matrix indicates one
Practical tumour point coordinate, the first row of practical tumour dot matrix indicate practical tumour point abscissa, the of practical tumour dot matrix
Two column indicate practical tumour point ordinate；
Step b, the distance between practical tumour point of any two is calculated, distance matrix is established；
Specifically:
A ranks the number identical square matrix with practical tumour points, the i-th row jth of the square matrix is constructed to arrange and indicate
The distance of i-th of practical j-th of distance of tumour point practical tumour point；
Step c, parameter is explored in initialization, calculates heuristic function initial value；
Specifically:
Initialization explores dimension, heuristic factor, retention factors, knowledge matrix, explores initial value and explore final value；
Heuristic function is the inverse of distance matrix；
Step d, optimal loop path is explored；
Specifically:
Since exploring initial value, it is iterated to final value is explored, in iterative process each time, multiple dimension joint explorations are best
Path, comprising the following steps:
Step d1, under each dimension, using any one practical tumour point as exploration starting point, and initialization path record sheet；
Step d2, the exploration path of each dimension is supplemented；
Specifically:
Step d21, it distinguishes and has accessed practical tumour point；
Step d22, practical tumour point to be visited is distinguished；
Step d23, the exploration probability between practical tumour point to be visited is calculated；Specifically: under current dimension, for what is do not explored
Practical tumour point, first calculating Aij=τij·[ηij]β, wherein τijFor the i-th row jth column element, η in knowledge matrixijTo inspire
Function, the distance between i-th of practical tumour point and j-th of practical tumour point are inversely proportional, and β indicates heuristic factor；Then it counts
Calculate B=∑ Aij；0 square matrix P is finally constructed, and according to Pij=AijThe algorithm of/B gives matrix P assignment；
Step d24, the next practical tumour point to be explored using wheel disc bet method determination；
Step d3, the distance that path is explored under each dimension is calculated；
Step d4, most short exploration distance is calculated；
Step d5, information matrix is updated；Specifically:
Above formula is assignment statement, the τ on the right of equationijIndicate under current exploration value the i-th row jth column element, equation in knowledge matrix
The τ on the left sideijIndicate that the i-th row jth column element, ρ indicate retention factors in knowledge matrix under next exploration value；
Step e, distance in optimal loop path maximum two practical tumour points are found, the distance is removed in optimal loop path
The line of maximum two practical tumour points, remainder is final path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710630403.8A CN107441635B (en) | 2017-07-28 | 2017-07-28 | It is a kind of for reducing the multiple tumor radioactive ray method for optimizing route for the treatment of time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710630403.8A CN107441635B (en) | 2017-07-28 | 2017-07-28 | It is a kind of for reducing the multiple tumor radioactive ray method for optimizing route for the treatment of time |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107441635A CN107441635A (en) | 2017-12-08 |
| CN107441635B true CN107441635B (en) | 2019-06-25 |
Family
ID=60489447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710630403.8A Expired - Fee Related CN107441635B (en) | 2017-07-28 | 2017-07-28 | It is a kind of for reducing the multiple tumor radioactive ray method for optimizing route for the treatment of time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107441635B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1567191A (en) * | 2003-06-17 | 2005-01-19 | 中国科学院等离子体物理研究所 | Path optimization technology of traversing cell sensitive spots for microbeam device |
| CN101422640B (en) * | 2008-11-25 | 2011-10-19 | 中国科学院等离子体物理研究所 | Multiple-objective optimization method and system capable of optimizing radiotherapy beam intensity distribution |
| US8492735B2 (en) * | 2010-05-27 | 2013-07-23 | Mitsubishi Electric Research Laboratories, Inc. | Method for optimization radiotherapy particle beams |
| DE102011056339B3 (en) * | 2011-12-13 | 2013-06-06 | Gsi Helmholtzzentrum Für Schwerionenforschung Gmbh | Creation of an irradiation plan with moving target volume without motion compensation |
| JP5791793B2 (en) * | 2012-05-14 | 2015-10-07 | 三菱電機株式会社 | Particle beam scanning irradiation system |
-
2017
- 2017-07-28 CN CN201710630403.8A patent/CN107441635B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN107441635A (en) | 2017-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20080091388A1 (en) | Method for calculation radiation doses from acquired image data | |
| Xing et al. | A feasibility study on deep learning‐based radiotherapy dose calculation | |
| US20060259282A1 (en) | Deterministic computation of radiation transport for radiotherapy dose calculations and scatter correction for image reconstruction | |
| Cao et al. | Incorporating deliverable monitor unit constraints into spot intensity optimization in intensity-modulated proton therapy treatment planning | |
| Fiege et al. | PARETO: A novel evolutionary optimization approach to multiobjective IMRT planning | |
| Cao et al. | Proton energy optimization and reduction for intensity-modulated proton therapy | |
| US11541252B2 (en) | Defining dose rate for pencil beam scanning | |
| Ojala et al. | Quantification of dose differences between two versions of Acuros XB algorithm compared to Monte Carlo simulations—the effect on clinical patient treatment planning | |
| Ma et al. | A feasibility study on deep learning‐based individualized 3D dose distribution prediction | |
| CN105561485A (en) | Radiotherapy treatment planning optimization method and device | |
| Wang et al. | An integrated solution of deep reinforcement learning for automatic IMRT treatment planning in non-small-cell lung cancer | |
| CN106621071B (en) | Treatment planning system based on cloud computing and using method thereof | |
| Bhagroo et al. | Secondary monitor unit calculations for VMAT using parallelized Monte Carlo simulations | |
| CN107441635B (en) | It is a kind of for reducing the multiple tumor radioactive ray method for optimizing route for the treatment of time | |
| CN111494815B (en) | Three-dimensional dose calculation method, device and medium based on mixed variable-scale model | |
| Zhang et al. | A two-stage sequential linear programming approach to IMRT dose optimization | |
| CN107185117B (en) | Sigmatron zone routing optimization method towards multiple tumor radiotherapy | |
| Matsuura et al. | Predictive gamma passing rate of 3D detector array-based volumetric modulated arc therapy quality assurance for prostate cancer via deep learning | |
| Carlsson et al. | Iterative regularization in intensity‐modulated radiation therapy optimization | |
| Takada et al. | Development of Monte Carlo based real-time treatment planning system with fast calculation algorithm for boron neutron capture therapy | |
| CN103268400A (en) | Method for deriving and reestablishing dosage-volume histograms from Pinnacle radiotherapy plan system | |
| Bogner et al. | Application of an inverse kernel concept to Monte Carlo based IMRT | |
| Gifford et al. | Comparison of a 3D multi‐group particle transport code with Monte Carlo for intercavitary brachytherapy of the cervix uteri | |
| CN114298177A (en) | Expansion enhancement method and system suitable for deep learning training data and readable storage medium | |
| Bedford | Inverse planning of lung radiotherapy with photon and proton beams using a discrete ordinates Boltzmann solver |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190625 Termination date: 20210728 |