CN107185117A - Towards the sigmatron zone routing optimization method of multiple tumor radiotherapy - Google Patents

Towards the sigmatron zone routing optimization method of multiple tumor radiotherapy Download PDF

Info

Publication number
CN107185117A
CN107185117A CN201710632208.9A CN201710632208A CN107185117A CN 107185117 A CN107185117 A CN 107185117A CN 201710632208 A CN201710632208 A CN 201710632208A CN 107185117 A CN107185117 A CN 107185117A
Authority
CN
China
Prior art keywords
actual
point
tumour
actual tumour
distance
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201710632208.9A
Other languages
Chinese (zh)
Other versions
CN107185117B (en
Inventor
赵烟桥
樊琪
史领
韩玉翠
吴海滨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Harbin University of Science and Technology
Original Assignee
Harbin University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Harbin University of Science and Technology filed Critical Harbin University of Science and Technology
Priority to CN201710632208.9A priority Critical patent/CN107185117B/en
Publication of CN107185117A publication Critical patent/CN107185117A/en
Application granted granted Critical
Publication of CN107185117B publication Critical patent/CN107185117B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61NELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N5/00Radiation therapy
    • A61N5/10X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
    • A61N5/103Treatment planning systems
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61NELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N5/00Radiation therapy
    • A61N5/10X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
    • A61N2005/1092Details

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 present invention belongs to Medical Devices and field of artificial intelligence towards the sigmatron zone routing optimization method of multiple tumor radiotherapy;Actual tumor region is degenerated to actual tumour point by this method first, it is determined that the coordinate of actual tumour point;Then the distance between actual tumour point of any two is calculated, distance matrix is set up;Reinitialize exploration parameter, calculates heuristic function initial value;Then optimal loop path is explored;Two maximum actual tumour points of distance in optimal loop path are eventually found, the line of described two actual tumour points is removed in optimal loop path, and remainder is final path;Actual tumor region is degenerated to a tumour point by the present invention, radiological scans problem is converted to and how to travel through all tumour points and shortest path problem, 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

Towards the sigmatron zone routing optimization method of multiple tumor radiotherapy
Technical field
The present invention towards multiple tumor radiotherapy sigmatron zone routing optimization method belong to Medical Devices and Field of artificial intelligence.
Background technology
Tumour radiotherapy is a kind of local therapeutic approaches using radiation cure tumour.It is same that radioactive ray include radioactivity Position element produce α, β, gamma-rays and all kinds of roentgenotherapia machines or accelerator produce 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, there are about 40% Cancer can be effected a radical cure 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 knurl.
Malignant tumour can be shifted, i.e., the cancer cell in primary malignant neoplasm by blood vessel, lymphatic vessel and tumour around 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, because 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 to regard multiple tumor as multiple independent to swell Knurl, carries out radiation cure just for one of tumour every time, and this mode needs repeatedly treatment to complete a course for the treatment of, Treatment time is long, and treatment cost is high.
The problem that for the above method, occur in that a kind of multiple tumor of similar printer printed document is put again Ray scanning method, in this approach, regarding multiple tumor as one only needs the huge tumour of local treatment, and this is huge swollen Region shared by knurl is referred to as the big region of tumour, it is necessary to which the region for the treatment of is actual tumor region in the big region of tumour, without The region to be treated is actual non-tumor region, radiation generator inswept tumour in the way of printing of inkjet printer document Big region, radioactive ray are projected in actual tumor region, and radioactive ray are not projected in actual non-tumor region.Although this mode technology It is relative complex, but seance can just complete a course for the treatment of, substantially reduce treatment time, reduce treatment cost, Main method as multiple tumor radiation cure at this stage.
In the above-mentioned methods, because radiation generator also wants the non-tumor region of inswept reality, and actual non-tumor area The area in domain is often far longer than actual tumor region, therefore, and a large amount for the treatment of times have been wasted in actual non-tumor region scanning During, if it is possible to the sweep time of this subregion is reduced, another reality is rapidly moved to from an actual tumor region Border tumor region, can substantially reduce treatment time, mitigate Case treatment pain, however, not finding the side of correlation also Method occurs.
The content of the invention
In view of the above-mentioned problems, the invention discloses a kind of sigmatron region road towards multiple tumor radiotherapy Footpath optimization method, this method is developed from the multiple tumor radiological scans method of similar printer printed document, is utilized The characteristics of actual non-tumor region is often much larger than actual tumor region, a tumour point is degenerated to by actual tumor region, will How radiological scans problem travels through all tumour points and shortest path problem if being converted to, and propose a kind of path optimization side Method, this method is conducive to substantially reducing treatment time, mitigates Case treatment pain, by artificial intelligence in Medical Devices Positive facilitation is played in development.
The object of the present invention is achieved like this:
Towards the sigmatron zone routing optimization method of multiple tumor radiotherapy, comprise the following steps:
Step a, actual tumor region is degenerated to actual tumour point, it is determined that the coordinate of actual tumour point;
Specially:
Actual tumour point coordinates is filled up in actual tumour dot matrix, every a line of the actual tumour dot matrix is represented One actual tumour point coordinates, the first row of actual tumour dot matrix represents actual tumour point abscissa, actual tumour dot matrix Secondary series represent actual tumour point ordinate;
The distance between step b, calculating actual tumour point of any two, set up distance matrix;
Specially:
Build a ranks number with actual tumour count identical square matrix, the square matrix the i-th row jth row Represent the distance of i-th of actual j-th of actual tumour point of tumour point distance;
Parameter is explored in step c, initialization, calculates heuristic function initial value;
Specially:
Initialization explores dimension, heuristic factor, retention factors, knowledge matrix, exploration initial value and explores final value;
Heuristic function is the inverse of distance matrix;
Step d, exploration optimal loop path;
Specially:
Since being explored initial value, it is iterated to final value is explored, in iterative process each time, multiple dimension joint explorations Optimal path, comprises the following steps:
Step d1, under each dimension, using any one actual tumour point as explore starting point, and initialization path record Table;
Step d2, each dimension of supplement exploration path;
Specially:
Step d21, differentiation have accessed actual tumour point;
Step d22, differentiation actual tumour point to be visited;
Exploration probability between step d23, calculating actual tumour point to be visited;Specially:
Wherein, PijRepresent that actual tumour o'clock has been detected from i-th under the exploration current dimension of probability does not detect reality to j-th The probability of tumour point, τijFor the i-th row jth column element in knowledge matrix, represent to have detected reality from i-th under the current dimension of guide Tumour o'clock is to the degree for not detecting actual tumour point for j-th;ηijIt is actual with i-th of actual tumour point and j-th for heuristic function The distance between tumour point is inversely proportional;β represents heuristic factor;
Step d24, using wheel disc bet method determine the next actual tumour point to be explored;
Step d3, the distance for calculating exploration path under each dimension;
Step d4, the most short exploration distance of calculating;
Step d5, fresh information matrix;Specially:
Above formula is the τ on the right of assignment statement, equationijThe i-th row jth column element in knowledge matrix is represented under current exploration value, The τ on the equation left sideijThe i-th row jth column element in knowledge matrix is represented under next exploration value, ρ represents retention factors;
Wherein, LengthDimensionRepresent under current dimension, detected total distance of actual tumour point;
Step e, two actual tumour points for finding distance maximum in optimal loop path, optimal loop path is removed described The line of two actual tumour points, remainder is final path.
The above-mentioned sigmatron zone routing optimization method towards multiple tumor radiotherapy is used to treat multiple swollen Knurl.
The above-mentioned sigmatron zone routing optimization method towards multiple tumor radiotherapy is in radiotherapy equipment Application.
Beneficial effect:
Firstth, the present invention is developed from the multiple tumor radiological scans method of similar printer printed document, profit The characteristics of being often much larger than actual tumor region with actual non-tumor region, a tumour point is degenerated to by actual tumor region, Radiological scans problem is converted to and how to travel through all tumour points and shortest path problem, and proposes a kind of path optimization side Method, this method is prevented effectively from a large amount for the treatment of times and has been wasted in actual non-tumor region scanning process, is conducive to dropping significantly Low treatment time, mitigate Case treatment pain, positive facilitation will be played to development of the artificial intelligence in Medical Devices.
Secondth, in method for optimizing route of the present invention, it is proposed that a kind of alternative manner, by explore dimension, heuristic factor, Mutual computing between retention factors, knowledge matrix, realizes the exploration to beeline.
3rd, in the methods of the invention, by quoting wheel disc bet method, the change for exploring path is realized, spy is prevented effectively from Rope path focuses on local optimum.
Brief description of the drawings
Fig. 1 is sigmatron zone routing optimization method flow chart of the present invention towards multiple tumor radiotherapy.
Fig. 2 is the operation result of the program of emulation experiment.
Fig. 3 is the Matlab software interface sectional drawings of emulation experiment.
Embodiment
The specific embodiment of the invention is described in further detail below in conjunction with the accompanying drawings.
Embodiment one
The following is the present invention towards the sigmatron zone routing optimization method of multiple tumor radiotherapy embodiment party Formula.
The sigmatron zone routing optimization method towards multiple tumor radiotherapy of present embodiment, flow chart As shown in figure 1, this method comprises the following steps:
Step a, actual tumor region is degenerated to actual tumour point, it is determined that the coordinate of actual tumour point;
Specially:
Actual tumour point coordinates is filled up in actual tumour dot matrix, every a line of the actual tumour dot matrix is represented One actual tumour point coordinates, the first row of actual tumour dot matrix represents actual tumour point abscissa, actual tumour dot matrix Secondary series represent actual tumour point ordinate;
The distance between step b, calculating actual tumour point of any two, set up distance matrix;
Specially:
Build a ranks number with actual tumour count identical square matrix, the square matrix the i-th row jth row Represent the distance of i-th of actual j-th of actual tumour point of tumour point distance;
Parameter is explored in step c, initialization, calculates heuristic function initial value;
Specially:
Initialization explores dimension, heuristic factor, retention factors, knowledge matrix, exploration initial value and explores final value;
Heuristic function is the inverse of distance matrix;
Step d, exploration optimal loop path;
Specially:
Since being explored initial value, it is iterated to final value is explored, in iterative process each time, multiple dimension joint explorations Optimal path, comprises the following steps:
Step d1, under each dimension, using any one actual tumour point as explore starting point, and initialization path record Table;
Step d2, each dimension of supplement exploration path;
Specially:
Step d21, differentiation have accessed actual tumour point;
Step d22, differentiation actual tumour point to be visited;
Exploration probability between step d23, calculating actual tumour point to be visited;Specially:
Wherein, PijRepresent that actual tumour o'clock has been detected from i-th under the exploration current dimension of probability does not detect reality to j-th The probability of tumour point, τijFor the i-th row jth column element in knowledge matrix, represent to have detected reality from i-th under the current dimension of guide Tumour o'clock is to the degree for not detecting actual tumour point for j-th;ηijIt is actual with i-th of actual tumour point and j-th for heuristic function The distance between tumour point is inversely proportional;β represents heuristic factor;
Step d24, using wheel disc bet method determine the next actual tumour point to be explored;
Step d3, the distance for calculating exploration path under each dimension;
Step d4, the most short exploration distance of calculating;
Step d5, fresh information matrix;Specially:
Above formula is the τ on the right of assignment statement, equationijThe i-th row jth column element in knowledge matrix is represented under current exploration value, The τ on the equation left sideijThe i-th row jth column element in knowledge matrix is represented under next exploration value, ρ represents retention factors;
Wherein, LengthDimensionRepresent under current dimension, detected total distance of actual tumour point;
Step e, two actual tumour points for finding distance maximum in optimal loop path, optimal loop path is removed described The line of two actual tumour points, remainder is final path.
Below with Matlab to the present invention towards multiple tumor radiotherapy sigmatron zone routing optimization method Emulated, simulated program is as follows:
The operation result of the program of emulation experiment is as shown in Fig. 2 figure it is seen that beeline is 2487.9366 Unit.
The Matlab software interfaces sectional drawing of emulation experiment as shown in figure 3, from figure 3, it can be seen that most short path 6,9,1, 8th, 2,10,5,7,4,3, software used time 1.248304s.
Embodiment two
Application the following is the present invention towards the sigmatron zone routing optimization method of multiple tumor radiotherapy is real Apply example.
The sigmatron zone routing optimization method towards multiple tumor radiotherapy in present embodiment, for tool Method described in body embodiment one, methods described is used to treat multiple tumor.
Embodiment three
Application the following is the present invention towards the sigmatron zone routing optimization method of multiple tumor radiotherapy is real Apply example.
The sigmatron zone routing optimization method towards multiple tumor radiotherapy in present embodiment, for tool Method described in body embodiment one, methods described is applied to radiotherapy equipment.

Claims (3)

1. towards the sigmatron zone routing optimization method of multiple tumor radiotherapy, it is characterised in that including following step Suddenly:
Step a, actual tumor region is degenerated to actual tumour point, it is determined that the coordinate of actual tumour point;
Specially:
Actual tumour point coordinates is filled up in actual tumour dot matrix, every a line of the actual tumour dot matrix represents one Actual tumour point coordinates, the first row of actual tumour dot matrix represents actual tumour point abscissa, the of actual tumour dot matrix Two row represent actual tumour point ordinate;
The distance between step b, calculating actual tumour point of any two, set up distance matrix;
Specially:
Build a ranks number with actual tumour count identical square matrix, the square matrix the i-th row jth row represent The distance of i-th of actual j-th of actual tumour point of tumour point distance;
Parameter is explored in step c, initialization, calculates heuristic function initial value;
Specially:
Initialization explores dimension, heuristic factor, retention factors, knowledge matrix, exploration initial value and explores final value;
Heuristic function is the inverse of distance matrix;
Step d, exploration optimal loop path;
Specially:
Since being explored initial value, it is iterated to final value is explored, in iterative process each time, multiple dimension joint explorations are optimal Path, comprises the following steps:
Step d1, under each dimension, using any one actual tumour point as exploring starting point, and initialization path record sheet;
Step d2, each dimension of supplement exploration path;
Specially:
Step d21, differentiation have accessed actual tumour point;
Step d22, differentiation actual tumour point to be visited;
Exploration probability between step d23, calculating actual tumour point to be visited;Specially:
Wherein, PijRepresent that actual tumour o'clock has been detected from i-th under the exploration current dimension of probability does not detect actual tumour to j-th The probability of point, τijFor the i-th row jth column element in knowledge matrix, represent to have detected actual tumour from i-th under the current dimension of guide O'clock to the degree for not detecting actual tumour point for j-th;ηijFor heuristic function, with i-th of actual tumour point and j-th of actual tumour The distance between point is inversely proportional;β represents heuristic factor;
Step d24, using wheel disc bet method determine the next actual tumour point to be explored;
Step d3, the distance for calculating exploration path under each dimension;
Step d4, the most short exploration distance of calculating;
Step d5, fresh information matrix;Specially:
Above formula is the τ on the right of assignment statement, equationijRepresent under current exploration value the i-th row jth column element, equation in knowledge matrix The τ on the left sideijThe i-th row jth column element in knowledge matrix is represented under next exploration value, ρ represents retention factors;
Wherein, LengthDimensionRepresent under current dimension, detected total distance of actual tumour point;
Step e, two actual tumour points for finding distance maximum in optimal loop path, optimal loop path removes described two The line of actual tumour point, remainder is final path.
2. the sigmatron zone routing optimization method described in claim 1 towards multiple tumor radiotherapy is used to treat Multiple tumor.
3. the sigmatron zone routing optimization method described in claim 1 and 2 towards multiple tumor radiotherapy is in radiation Application in therapeutic equipment.
CN201710632208.9A 2017-07-28 2017-07-28 Sigmatron zone routing optimization method towards multiple tumor radiotherapy Expired - Fee Related CN107185117B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710632208.9A CN107185117B (en) 2017-07-28 2017-07-28 Sigmatron zone routing optimization method towards multiple tumor radiotherapy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710632208.9A CN107185117B (en) 2017-07-28 2017-07-28 Sigmatron zone routing optimization method towards multiple tumor radiotherapy

Publications (2)

Publication Number Publication Date
CN107185117A true CN107185117A (en) 2017-09-22
CN107185117B CN107185117B (en) 2019-05-28

Family

ID=59884998

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710632208.9A Expired - Fee Related CN107185117B (en) 2017-07-28 2017-07-28 Sigmatron zone routing optimization method towards multiple tumor radiotherapy

Country Status (1)

Country Link
CN (1) CN107185117B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102752721A (en) * 2012-06-28 2012-10-24 上海交通大学 Route recovery method suitable for interference environment of wireless sensor network
CN102743821A (en) * 2011-04-18 2012-10-24 株式会社日立制作所 Treatment planning apparatus and particle therapy apparatus
CN104284696A (en) * 2012-05-14 2015-01-14 三菱电机株式会社 Particle beam scanning irradiation system
CN105654202A (en) * 2015-12-30 2016-06-08 中国科学院合肥物质科学研究院 Method for optimizing proton radiotherapy path in active scanning manner by considering scanning speed change
US20170036037A1 (en) * 2014-04-30 2017-02-09 Stc.Unm Optimization methods for radiation therapy planning

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102743821A (en) * 2011-04-18 2012-10-24 株式会社日立制作所 Treatment planning apparatus and particle therapy apparatus
CN104284696A (en) * 2012-05-14 2015-01-14 三菱电机株式会社 Particle beam scanning irradiation system
CN102752721A (en) * 2012-06-28 2012-10-24 上海交通大学 Route recovery method suitable for interference environment of wireless sensor network
US20170036037A1 (en) * 2014-04-30 2017-02-09 Stc.Unm Optimization methods for radiation therapy planning
CN105654202A (en) * 2015-12-30 2016-06-08 中国科学院合肥物质科学研究院 Method for optimizing proton radiotherapy path in active scanning manner by considering scanning speed change

Also Published As

Publication number Publication date
CN107185117B (en) 2019-05-28

Similar Documents

Publication Publication Date Title
EP3741431B1 (en) Determining a radiation treatment plan for delivering radiation to a patient using an external-beam radiation treatment system
US9245336B2 (en) Contour guided deformable image registration
US20060259282A1 (en) Deterministic computation of radiation transport for radiotherapy dose calculations and scatter correction for image reconstruction
US20080091388A1 (en) Method for calculation radiation doses from acquired image data
WO2005057463A1 (en) Method and system for optimizing dose delivery of radiation
Cao et al. Incorporating deliverable monitor unit constraints into spot intensity optimization in intensity-modulated proton therapy treatment planning
US11541252B2 (en) Defining dose rate for pencil beam scanning
Liu et al. A deep learning model to predict dose–volume histograms of organs at risk in radiotherapy treatment plans
US9486644B2 (en) Method and system for dose determination of radiation therapy
Liu et al. Dose prediction using a three-dimensional convolutional neural network for nasopharyngeal carcinoma with tomotherapy
CN106621071B (en) Treatment planning system based on cloud computing and using method thereof
CN111494815B (en) Three-dimensional dose calculation method, device and medium based on mixed variable-scale model
Matsuura et al. Predictive gamma passing rate of 3D detector array-based volumetric modulated arc therapy quality assurance for prostate cancer via deep learning
CN107185117A (en) Towards the sigmatron zone routing optimization method of multiple tumor radiotherapy
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
CN107281657B (en) A kind of radiotherapy apparatus high-energy light beam guiding method for optimizing route for multiple tumor
CN107441635B (en) It is a kind of for reducing the multiple tumor radioactive ray method for optimizing route for the treatment of time
Lin et al. Measurement‐based Monte Carlo dose calculation system for IMRT pretreatment and on‐line transit dose verifications
CN116440426A (en) Space division radiotherapy target area arrangement method and system
CN114298177A (en) Expansion enhancement method and system suitable for deep learning training data and readable storage medium
Qi et al. Region-specific three-dimensional dose distribution prediction: a feasibility study on prostate VMAT cases
Zhong et al. Generation of a novel phase‐space‐based cylindrical dose kernel for IMRT optimization
Alhazmi et al. ESP: euclidean spheres packing implementation for volume data using slicer3D
Liu et al. Variation method for inverse treatment planning

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

Granted publication date: 20190528

Termination date: 20210728

CF01 Termination of patent right due to non-payment of annual fee