CN106777976A - Radiotherapy machine human tumour motion estimation prediction system and method based on particle filter - Google Patents
Radiotherapy machine human tumour motion estimation prediction system and method based on particle filter Download PDFInfo
- Publication number
- CN106777976A CN106777976A CN201611161947.6A CN201611161947A CN106777976A CN 106777976 A CN106777976 A CN 106777976A CN 201611161947 A CN201611161947 A CN 201611161947A CN 106777976 A CN106777976 A CN 106777976A
- Authority
- CN
- China
- Prior art keywords
- tumour
- particle filter
- particle
- motion estimation
- marker
- 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
Links
Classifications
-
- G06F19/3481—
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Radiation-Therapy Devices (AREA)
Abstract
The invention discloses a kind of radiotherapy machine human tumour motion estimation prediction system and method based on particle filter, methods described includes：S1, using breathing tracking cell and image positioning unit gathers the three-dimensional motion data of skin-marker and in-vivo tumour respectively；S2, according to three-dimensional motion data, the movement relation model set up between current time tumour and historical juncture tumour, and using the model as the state transition equation of particle filter, set up observational equation of the movement relation model in a period of time between skin-marker and in-vivo tumour as particle filter；S3, based on state transition equation and observational equation, the movement position of in-vivo tumour is estimated according to the exercise data of current time skin-marker using particle filter algorithm.The present invention can have stronger modeling ability with any type of state-space model for the nonlinear characteristic of variable parameter, and precision of prediction is higher.
Description
Technical field
The present invention relates to field of medical technology, more particularly to a kind of radiotherapy machine human tumour motion based on particle filter
Estimate forecasting system and method.
Background technology
The main method for the treatment of lung cancer is SRT at present, but the respiratory movement of human body has a strong impact on
The accuracy of radiotherapy.In order to reduce respirometric influence, most efficient method is respiratory movement real time technique for tracking, the technology
By the correlation model set up between in-vivo tumour and skin-marker, using prediction algorithm, the motion according to mark point is obtained
Following movable information of tumour, so that real-time adjustment beam, it is ensured that the geo-stationary of radioactive ray and tumour, is put with reaching tumour
The real-time tracking for the treatment of.
The time delay of three-dimensional radiotherapy system is to compensate for using prediction algorithm, look-ahead goes out tumour in future time instance
The position that will be reached.Some prediction algorithms of research include artificial neural network, Kalman filter, fuzzy control at present
Deng.But above-mentioned algorithm has the disadvantages that：
Artificial neural network learning efficiency is low, and convergence rate is slow, it is necessary to prolonged net training time, is not suitable for reality
When predict；
Kalman filter then requires that system is white Gaussian noise system, and be only applicable to linear system, and reality is exhaled
It is complicated non-linear process to inhale motion process, therefore Kalman filter is less suitable for use in the prediction of tumor motion；
Fuzzy control prediction effect is preferable, but this method adaptive ability is limited, and complexity is higher.
Particle filter solves the restriction that system must is fulfilled for Gaussian Profile, it is adaptable to any to use state-space model
The nonlinear system of expression, and have precision higher, the method is applied in radiotherapy machine people's real time technique for tracking, for carrying
The survival rate of patient high and the medical technology development tool of promotion China have very important significance.
Therefore, for above-mentioned technical problem, it is necessary to provide a kind of radiotherapy machine human tumour motion based on particle filter
Estimate forecasting system and method.
The content of the invention
In view of this, it is an object of the invention to provide a kind of radiotherapy machine human tumour estimation based on particle filter
Forecasting system and method, to solve the forecasting problem of the above-mentioned knub position in radiotherapy machine people precisely treatment.
To achieve these goals, technical scheme provided in an embodiment of the present invention is as follows：
A kind of radiotherapy machine human tumour motion estimation prediction system based on particle filter, the system includes：Breathing with
Track unit, image positioning unit, visual fusion unit and treatment plan unit, the breathing tracking cell are used to track patient's body
The exercise data of list notation point, the image positioning unit is used to track the exercise data of patient's in-vivo tumour, and the image melts
Closing unit is used to carry out the fusion based on particle filter to the exercise data collected and predicts the exercise data of tumour future time instance,
The treatment plan unit is used for real-time adjustment treatment beam and is accurately irradiated.
As a further improvement on the present invention, unit is also fixed and be automatically positioned to the system including sufferer and robot is thrown
Unit is penetrated, sufferer is fixed and is automatically positioned unit for immobilized patients and positioned, and robot projecting unit is controlled for control
Treat beam and reach target area.
As a further improvement on the present invention, the breathing tracking cell is infrared track unit, and it includes synchronous tracking
Video camera and it is fixed on some light emitting diodes of patient's belly.
As a further improvement on the present invention, the image positioning unit is X ray image positioning unit, and it includes X-ray
Penetrate source and non-crystalline silicon panadaptor.
As a further improvement on the present invention, the system also includes respiratory movement simulator, for simulating body in radiotherapy
Motion change relation between interior tumour and skin-marker.
The technical scheme that another embodiment of the present invention is provided is as follows：
A kind of radiotherapy machine human tumour motion estimation prediction method based on particle filter, methods described includes：
S1, using breathing tracking cell and image positioning unit gathers three maintenance and operations of skin-marker and in-vivo tumour respectively
Dynamic data；
S2, according to three-dimensional motion data, the movement relation model set up between current time tumour and historical juncture tumour,
And using the model as particle filter state transition equation, set up a period of time between skin-marker and in-vivo tumour
Movement relation model as particle filter observational equation；
S3, based on state transition equation and observational equation, using particle filter algorithm according to current time skin-marker
Exercise data estimate the movement position of in-vivo tumour.
As a further improvement on the present invention, the step S3 includes：
The movement position of tumour is estimated by particle filter, state transition equation is built by the Kinematic process of tumour
Vertical, observational equation is obtained by the movement relation being fitted between in-vivo tumour and skin-marker.
As a further improvement on the present invention, state transition equation is x in the step S2k=f (xk-1), observational equation
It is zk=h (xk), wherein, xkIt is the exercise data of k moment in-vivo tumours, zkIt is the motion number of the skin-marker that the k moment measures
According to.
As a further improvement on the present invention, the movement position for estimating tumour by particle filter in the step S3 has
Body is：
S31, one group of N number of random sample point is generated according to previous moment knub position data and its probability distribution is N number of grain
Son；
S32, will sampling particle substitute into state transition equation in obtain the estimate x of N number of tumour subsequent time positionk；
S33, the estimate of N number of knub position is substituted into the measurement estimate z that skin-marker is obtained in observational equationk,
The actual measured value z of mark point is obtained using radiotherapy machine people；
S34, according to zkThe weights different to particle imparting with z error degrees between the two, the small particle of error is assigned
Larger weights, the big particle of error assigns less weights, and carries out resampling to particle, by multiple resampling after,
The best estimate of knub position is obtained using the particle and its weight computing of final sampling；
S35, one group of random sample that the particle of final sampling is predicted as next round, repeat S32~S34, carry out down
One wheel particle filter.
As a further improvement on the present invention, in the step S31, the original state of N number of particle is in total state space
It is evenly distributed.
The beneficial effects of the invention are as follows：
The system of solving must is fulfilled for the restriction of Gaussian Profile, and particle filter utilizes particle set representations probability, Ke Yiyong
On any type of state-space model, there are stronger modeling ability, and prediction essence for the nonlinear characteristic of variable parameter
Degree is higher；
Using respiratory movement simulator synchronous breathing track algorithm is studied as experiment porch, it is to avoid human body is received for a long time
To the irradiation of X-ray, effectively comprehensive real-time imaging can be guided and synchronous breathing tracking technique in actual therapeutic, it is ensured that in disease
Stove obtains avoiding the tissue of surrounding normal to come to harm while maximum dose, reduces the incidence of complication.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments described in invention, for those of ordinary skill in the art, on the premise of not paying creative work,
Other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is that the module of the radiotherapy machine human tumour motion estimation prediction system based on particle filter in the present invention is illustrated
Figure；
Fig. 2 is that the flow of the radiotherapy machine human tumour motion estimation prediction method based on particle filter in the present invention is illustrated
Figure；
Fig. 3 a~3c is radiotherapy machine human tumour motion estimation prediction method and linear estimation methods based on particle filter
Experimental verification predicated error comparing result figure.
Specific embodiment
In order that those skilled in the art more fully understand the technical scheme in the present invention, below in conjunction with of the invention real
The accompanying drawing in example is applied, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described implementation
Example is only a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, this area is common
The every other embodiment that technical staff is obtained under the premise of creative work is not made, should all belong to protection of the present invention
Scope.
Shown in ginseng Fig. 1, a kind of radiotherapy machine human tumour fortune based on particle filter is disclosed in an embodiment of the present invention
Dynamic to estimate forecasting system, the system includes breathing tracking cell 10, image positioning unit 20, visual fusion unit 30, treatment meter
Draw unit 40.Wherein, breathing tracking cell 10 is used to track the exercise data of patient body-surface mark point, and image positioning unit 20 is used
In the exercise data of tracking patient's in-vivo tumour, visual fusion unit 30 is used to that the exercise data collected to be carried out to be filtered based on particle
The fusion of ripple simultaneously predicts the exercise data of tumour future time instance, and treatment plan unit 40 is used for real-time adjustment treatment beam carries out essence
Really irradiation.
Further, unit is also fixed and be automatically positioned to the system in present embodiment including sufferer and robot projection is single
Unit, sufferer is fixed and is automatically positioned unit for immobilized patients and positioned, and robot projecting unit is used to control treatment to penetrate
Beam reaches target area.
Preferably, the breathing tracking cell 10 in present embodiment is infrared track unit, and it includes that synchronous tracking is imaged
Machine and it is fixed on some light emitting diodes of patient's belly.Synchronous tracking video camera and it is fixed on three of patient's belly luminous two
The external breathing tracing unit of pole pipe composition, for tracking skin-marker exercise data.
Preferably, the image positioning unit 20 in present embodiment is X ray image positioning unit, and it includes that X-ray penetrates source
And non-crystalline silicon panadaptor, the exercise data for tracking in-vivo tumour.
The correlation model set up between two groups of exercise datas, the position of tumour future time instance is predicted using particle filter algorithm
Put, visual fusion unit 30 and treatment plan unit 40 are accurately shone according to the number of tumors of prediction according to real-time adjustment treatment beam
Penetrate.
Specifically, in therapeutic process, patient is lain on radiotherapy machine people's parallel-connection structure operating table, same in breathing tracking cell
Step follows the trail of video camera is used to track the exercise data of skin-marker, and X-ray penetrates source and non-crystalline silicon panadaptor to be used to track body
The exercise data of interior tumour, by setting up the correlation model moved between mark point and tumour, is predicted using particle filter algorithm
The exercise data of tumour future time instance, treatment plan unit and visual fusion unit are adjusted according to the knub position prediction data for obtaining
Whole radiotherapy machine people drives linear accelerator to be moved to needs the position for the treatment of to be irradiated, so as to realize treatment beam to tumour
Real-time tracking and treatment.
Because Continuous irradiation is harmful, in order to avoid patient is irradiated by X-ray for a long time, so the body of collection
The exercise data of interior tumour is interruption, in order to obtain continuous respiratory movement data, in breathing tracking cell, can use breathing
Motion simulator replaces patient, for simulating the motion change relation in radiotherapy between in-vivo tumour and skin-marker, the mould
Intending device can not only reproduce real respiratory movement, and measuring continuous simulation in real time with NDI Polaris optical positioning systems exhales
Exercise data is inhaled, the validity of the data verification prediction algorithm of its offer can also be provided.Such as use Patent No.
A kind of respiratory movement simulator disclosed in ZL201420836958.X is used to simulate the respiratory movement of patient, the respiratory movement mould
Intend device to be made up of a Three Degree Of Freedom Linear slide platform, three stepper motors, a simulation tumour and two springs, be mainly used in mould
Motion change relation in plan radiotherapy between in-vivo tumour and skin-marker, the simulator can not only reproduce real human body
Respiratory movement can also utilize the validity of the data verification prediction algorithm of its offer.Wherein, analog mark point and simulation tumour
Exercise data can in real time be measured with NDI Polaris optical positioning systems.
At present research some prediction algorithms including artificial neural network, Kalman filter, fuzzy control etc., but this
A little algorithms have more or less weak point for complicated non-linear respiratory movement process.Particle filter solves system
It must is fulfilled for the restriction of Gaussian Profile, it is adaptable to any nonlinear system that can be expressed with state-space model, and has higher
Precision, it is adaptable to the prediction of respiratory movement knub position.
Shown in ginseng Fig. 2, a kind of radiotherapy machine human tumour based on particle filter is disclosed in another implementation method of the invention
Motion estimation prediction method, the method includes：
S1, using breathing tracking cell and image positioning unit gathers three maintenance and operations of skin-marker and in-vivo tumour respectively
Dynamic data；
S2, according to three-dimensional motion data, the movement relation model set up between current time tumour and historical juncture tumour,
And using the model as particle filter state transition equation, set up a period of time between skin-marker and in-vivo tumour
Movement relation model as particle filter observational equation；
S3, based on state transition equation and observational equation, using particle filter algorithm according to current time skin-marker
Exercise data estimate the movement position of in-vivo tumour.
Preferably, the movement position of tumour, state transfer are estimated in the step of present embodiment S3 by particle filter
Equation is set up by the Kinematic process of tumour, and observational equation is closed by the motion being fitted between in-vivo tumour and skin-marker
System obtains.
Specifically, state transition equation is x in step S2k=f (xk-1), observational equation is zk=h (xk), wherein, xkIt is k
The exercise data of moment in-vivo tumour, zkIt is the exercise data of the skin-marker that the k moment measures.
The movement position for estimating tumour by particle filter is specially：
S31, according to above two moment knub position data xk-1And xk-2And its probability distribution generates one group of random sample
Point is particle, it is assumed that have N number of particle, because original state is unknown, is considered as x0And x1The average mark in total state space
Cloth；
S32, the particle substitution state transition equation x by samplingk=f (xk-1) in obtain N number of tumour subsequent time position
Estimate xk；
S33, the estimate x N number of knub positionkSubstitute into observational equation zk=h (xk) in obtain the measurement of skin-marker
Estimate zk, the actual measured value z of mark point can be obtained using radiotherapy machine people system；
S34, according to zkThe weights different to particle imparting with z error degrees between the two, the small particle of error is assigned
Larger weights, the big particle of error assigns less weights, and carries out resampling to particle, by multiple resampling after,
The best estimate of knub position is obtained using the particle and its weight computing of final sampling；
S35, one group of random sample that the particle point of final sampling is predicted as next round, repeat S32~S34, carry out
Next round particle filter.
In order to verify the validity of the radiotherapy machine human tumour motion estimation prediction system and method based on particle filter,
Radiotherapy machine human tumour motion estimation prediction based on particle filter is entered with the experimental verification predicated error of linear estimation methods
Row contrast.2000 groups of real respiratory movement data are imported into respiratory movement simulator to be tested, the simulation for collecting is exhaled
Inhale exercise data to be applied in two kinds of prediction algorithms, the experimental result for obtaining is real on tri- directions of XYZ as shown in Fig. 3 a~3c
Checking predicated error result figure, is respectively adopted the linear estimation methods clinically applied and particle filter algorithm prediction tumour
Motion, is two kinds of differences of the respiratory cycle predicated error of prediction algorithm in figure, i.e. the error information of linear estimation methods subtracts grain
The result that the error information of sub- filtering algorithm is obtained, therefore data represent smaller based on particle filter algorithm error more than zero, if
Data are less than zero, illustrate that traditional linear estimation methods error is smaller.As can be seen that in whole respiratory movement from Fig. 3 a~3c
During, the large percentage shared by data more than zero, illustrate using particle filter predict tumor motion when precision of prediction compared with
It is high.
As can be seen from the above technical solutions, compared with prior art, the present invention has the advantages that：
The system of solving must is fulfilled for the restriction of Gaussian Profile, and particle filter utilizes particle set representations probability, Ke Yiyong
On any type of state-space model, there are stronger modeling ability, and prediction essence for the nonlinear characteristic of variable parameter
Degree is higher；
Using respiratory movement simulator synchronous breathing track algorithm is studied as experiment porch, it is to avoid human body is received for a long time
To the irradiation of X-ray, effectively comprehensive real-time imaging can be guided and synchronous breathing tracking technique in actual therapeutic, it is ensured that in disease
Stove obtains avoiding the tissue of surrounding normal to come to harm while maximum dose, reduces the incidence of complication.
Present invention can apply in the treatment of lung tumors, this is for improving the survival rate of patient and promoting China's medical treatment
The development tool of technology has very important significance.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be in other specific forms realized.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires to be limited rather than described above, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as the claim involved by limitation.
Moreover, it will be appreciated that although the present specification is described in terms of embodiments, not each implementation method is only wrapped
Containing an independent technical scheme, this narrating mode of specification is only that for clarity, those skilled in the art should
Specification an as entirety, the technical scheme in each embodiment can also be formed into those skilled in the art through appropriately combined
May be appreciated other embodiment.
Claims (10)
1. a kind of radiotherapy machine human tumour motion estimation prediction system based on particle filter, it is characterised in that the system bag
Include：Breathing tracking cell, image positioning unit, visual fusion unit and treatment plan unit, the breathing tracking cell are used for
The exercise data of patient body-surface mark point is tracked, the image positioning unit is used to track the exercise data of patient's in-vivo tumour,
The visual fusion unit is used to carry out the exercise data collected the fusion based on particle filter and predict tumour future time instance
Exercise data, the treatment plan unit be used for real-time adjustment treatment beam accurately irradiated.
2. the radiotherapy machine human tumour motion estimation prediction system based on particle filter according to claim 1, its feature
It is that unit and robot projecting unit are also fixed and be automatically positioned to the system including sufferer, sufferer is fixed and is automatically positioned
Unit is used for immobilized patients and is positioned, and robot projecting unit is used to control treatment beam to reach target area.
3. the radiotherapy machine human tumour motion estimation prediction system based on particle filter according to claim 1, its feature
It is that the breathing tracking cell is infrared track unit, if it includes synchronous tracking video camera and is fixed on patient's belly
Dry light emitting diode.
4. the radiotherapy machine human tumour motion estimation prediction system based on particle filter according to claim 1, its feature
It is that the image positioning unit is X ray image positioning unit, and it includes that X-ray penetrates source and non-crystalline silicon panadaptor.
5. the radiotherapy machine human tumour motion estimation prediction system based on particle filter according to claim 1, its feature
It is that the system also includes respiratory movement simulator, for simulating the fortune in radiotherapy between in-vivo tumour and skin-marker
Dynamic variation relation.
6. a kind of radiotherapy machine human tumour motion estimation prediction method based on particle filter, it is characterised in that methods described bag
Include：
S1, using breathing tracking cell and image positioning unit gathers the three-dimensional motion number of skin-marker and in-vivo tumour respectively
According to；
S2, according to three-dimensional motion data, the movement relation model set up between current time tumour and historical juncture tumour, and will
The model sets up the motion between skin-marker and in-vivo tumour in a period of time as the state transition equation of particle filter
Relational model as particle filter observational equation；
S3, based on state transition equation and observational equation, using particle filter algorithm according to the fortune of current time skin-marker
Dynamic data estimation goes out the movement position of in-vivo tumour.
7. the radiotherapy machine human tumour motion estimation prediction method based on particle filter according to claim 6, its feature
It is that the step S3 includes：
The movement position of tumour is estimated by particle filter, state transition equation is set up by the Kinematic process of tumour, seen
Movement relation of the equation by being fitted between in-vivo tumour and skin-marker is surveyed to obtain.
8. the radiotherapy machine human tumour motion estimation prediction method based on particle filter according to claim 7, its feature
It is that state transition equation is x in the step S2k=f (xk-1), observational equation is zk=h (xk), wherein, xkIt is k moment bodies
The exercise data of interior tumour, zkIt is the exercise data of the skin-marker that the k moment measures.
9. the radiotherapy machine human tumour motion estimation prediction method based on particle filter according to claim 8, its feature
It is that the movement position for estimating tumour by particle filter in the step S3 is specially：
S31, one group of N number of random sample point is generated according to previous moment knub position data and its probability distribution is N number of particle；
S32, will sampling particle substitute into state transition equation in obtain the estimate x of N number of tumour subsequent time positionk；
S33, the estimate of N number of knub position is substituted into the measurement estimate z that skin-marker is obtained in observational equationk, using putting
Treat the actual measured value z that robot obtains mark point；
S34, according to zkThe weights different to particle imparting with z error degrees between the two, the small particle of error assigns larger
Weights, the big particle of error assigns less weights, and carries out resampling to particle, by multiple resampling after, using most
The particle and its weight computing of sampling obtain the best estimate of knub position eventually；
S35, one group of random sample that the particle of final sampling is predicted as next round, repeat S32~S34, carry out next round
Particle filter.
10. the radiotherapy machine human tumour motion estimation prediction method based on particle filter according to claim 9, its feature
It is that in the step S31, the original state of N number of particle is evenly distributed in total state space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611161947.6A CN106777976B (en) | 2016-12-15 | 2016-12-15 | Radiotherapy robot tumor motion estimation prediction system and method based on particle filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611161947.6A CN106777976B (en) | 2016-12-15 | 2016-12-15 | Radiotherapy robot tumor motion estimation prediction system and method based on particle filtering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106777976A true CN106777976A (en) | 2017-05-31 |
| CN106777976B CN106777976B (en) | 2021-06-11 |
Family
ID=58891494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611161947.6A Active CN106777976B (en) | 2016-12-15 | 2016-12-15 | Radiotherapy robot tumor motion estimation prediction system and method based on particle filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106777976B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110176306A (en) * | 2019-05-17 | 2019-08-27 | 上海交通大学 | A kind of soft tissue drift target spot automatic positioning method based on the polynary LSTM network of dynamic |
| CN110678224A (en) * | 2017-06-19 | 2020-01-10 | 深圳市奥沃医学新技术发展有限公司 | Method and device for tracking and irradiating target spot by using radiotherapy equipment and radiotherapy equipment |
| CN113499091A (en) * | 2021-08-19 | 2021-10-15 | 四川大学华西医院 | Method and system for predicting motion correlation and intra-tumor mobility of tumors on body surface and in body of patient |
| CN114177545A (en) * | 2022-01-17 | 2022-03-15 | 中国科学院合肥物质科学研究院 | Non-contact respiratory rhythm monitoring device and method used in radiotherapy |
| CN114927215A (en) * | 2022-04-27 | 2022-08-19 | 苏州大学 | Method and system for directly predicting tumor respiratory movement based on body surface point cloud data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020065580A1 (en) * | 2000-09-11 | 2002-05-30 | Iraj Derakhshan | Method and system for determining native neurological dominant hemisphere functionality and use of such information for therapeutics and for control of prostheses and robotics |
| US20030125891A1 (en) * | 2001-12-31 | 2003-07-03 | Dempster Philip T. | Calibration methods and apparatus for plethysmographic measurement chambers |
| US20050265589A1 (en) * | 2000-12-20 | 2005-12-01 | Raghu Raghavan | Method for dynamic characterization of density fields in a compound structure |
| CN101794357A (en) * | 2010-03-30 | 2010-08-04 | 江苏瑞尔医疗科技有限公司 | Fuzzy prediction method and predictor for position signal of respiration synchronous tracking system |
| CN103229178A (en) * | 2010-10-29 | 2013-07-31 | 艾可瑞公司 | Method and apparatus for treating a target's partial motion range |
| CN103294931A (en) * | 2013-06-28 | 2013-09-11 | 上海交通大学 | System state estimation method based on improved nonlinear robust filtering algorithm |
| CN203694431U (en) * | 2014-01-10 | 2014-07-09 | 郑晓天 | Radiotherapy apparatus for real-time tracking of digital image target |
| CN105930640A (en) * | 2016-04-11 | 2016-09-07 | 南京工业大学 | Fractional order Kalman filtering method for processing Levy noise |
-
2016
- 2016-12-15 CN CN201611161947.6A patent/CN106777976B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020065580A1 (en) * | 2000-09-11 | 2002-05-30 | Iraj Derakhshan | Method and system for determining native neurological dominant hemisphere functionality and use of such information for therapeutics and for control of prostheses and robotics |
| US20050265589A1 (en) * | 2000-12-20 | 2005-12-01 | Raghu Raghavan | Method for dynamic characterization of density fields in a compound structure |
| US20030125891A1 (en) * | 2001-12-31 | 2003-07-03 | Dempster Philip T. | Calibration methods and apparatus for plethysmographic measurement chambers |
| CN101794357A (en) * | 2010-03-30 | 2010-08-04 | 江苏瑞尔医疗科技有限公司 | Fuzzy prediction method and predictor for position signal of respiration synchronous tracking system |
| CN103229178A (en) * | 2010-10-29 | 2013-07-31 | 艾可瑞公司 | Method and apparatus for treating a target's partial motion range |
| CN103294931A (en) * | 2013-06-28 | 2013-09-11 | 上海交通大学 | System state estimation method based on improved nonlinear robust filtering algorithm |
| CN203694431U (en) * | 2014-01-10 | 2014-07-09 | 郑晓天 | Radiotherapy apparatus for real-time tracking of digital image target |
| CN105930640A (en) * | 2016-04-11 | 2016-09-07 | 南京工业大学 | Fractional order Kalman filtering method for processing Levy noise |
Non-Patent Citations (3)
| Title |
|---|
| BLOTT MARGARET 等: ""The ultrasonographic assessment of the fetal thorax and fetal breathing movements in the prediction of pulmonary hypoplasia"", 《ELSEVIER》 * |
| MENG DOU 等: ""UT transform based tumor respiratory motion estimation and prediction for radiosurgery robot"", 《ROBOTICS AND BIOMIMETICS (ROBIO)》 * |
| 田珍 等: "" 放疗过程中呼吸引起的肿瘤运动补偿问题的研究进展"", 《华中科技大学学报(自然科学版)》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110678224A (en) * | 2017-06-19 | 2020-01-10 | 深圳市奥沃医学新技术发展有限公司 | Method and device for tracking and irradiating target spot by using radiotherapy equipment and radiotherapy equipment |
| US11241589B2 (en) | 2017-06-19 | 2022-02-08 | Our New Medical Technologies | Target tracking and irradiation method and device using radiotherapy apparatus and radiotherapy apparatus |
| CN110678224B (en) * | 2017-06-19 | 2022-05-13 | 深圳市奥沃医学新技术发展有限公司 | Device for tracking and irradiating target spot by using radiotherapy equipment and radiotherapy equipment |
| CN110176306A (en) * | 2019-05-17 | 2019-08-27 | 上海交通大学 | A kind of soft tissue drift target spot automatic positioning method based on the polynary LSTM network of dynamic |
| CN113499091A (en) * | 2021-08-19 | 2021-10-15 | 四川大学华西医院 | Method and system for predicting motion correlation and intra-tumor mobility of tumors on body surface and in body of patient |
| CN113499091B (en) * | 2021-08-19 | 2023-08-15 | 四川大学华西医院 | Method and system for predicting tumor movement correlation and tumor internal mobility in body surface and body of patient |
| CN114177545A (en) * | 2022-01-17 | 2022-03-15 | 中国科学院合肥物质科学研究院 | Non-contact respiratory rhythm monitoring device and method used in radiotherapy |
| CN114177545B (en) * | 2022-01-17 | 2023-11-07 | 中国科学院合肥物质科学研究院 | Contactless respiratory rhythm monitoring device and method for radiotherapy |
| CN114927215A (en) * | 2022-04-27 | 2022-08-19 | 苏州大学 | Method and system for directly predicting tumor respiratory movement based on body surface point cloud data |
| CN114927215B (en) * | 2022-04-27 | 2023-08-25 | 苏州大学 | Method and system for directly predicting tumor respiratory motion based on body surface point cloud data |
| WO2023206850A1 (en) * | 2022-04-27 | 2023-11-02 | 苏州大学 | Method and system for directly predicting respiratory movement of tumor on basis of body surface point cloud data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106777976B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106777976A (en) | Radiotherapy machine human tumour motion estimation prediction system and method based on particle filter | |
| Wang et al. | A feasibility of respiration prediction based on deep Bi-LSTM for real-time tumor tracking | |
| CN107441637B (en) | Intensity modulated radiation therapy 3-dimensional dose is distributed in the works prediction technique and its application | |
| CN105031833B (en) | The dosage verifying system of radiotherapy unit | |
| Sheng | Artificial intelligence in radiotherapy: a technological review | |
| CN106563210B (en) | Tumor respiratory motion estimation and prediction method of radiotherapy robot based on UT (user-implemented) transformation | |
| CN104274914A (en) | Breath guide device and method for ion beam respiratory-gated treatment | |
| CN103027702B (en) | Time-resolved tomosynthesis imaging | |
| CN110378881A (en) | A kind of tumor-localizing system based on deep learning | |
| CN104888356B (en) | Image-guided and breath Motion Estimation system | |
| CN107980008A (en) | Medical Image Processing equipment, treatment system and Medical Image Processing program | |
| Park et al. | Quasi‐breath‐hold technique using personalized audio‐visual biofeedback for respiratory motion management in radiotherapy | |
| Mukumoto et al. | Positional accuracy of novel x‐ray‐image‐based dynamic tumor‐tracking irradiation using a gimbaled MV x‐ray head of a Vero4DRT (MHI‐TM2000) | |
| CN110097580A (en) | A kind of ultrasound image marker motion tracking method | |
| Fan et al. | Verification of the machine delivery parameters of a treatment plan via deep learning | |
| CN109276820A (en) | A kind of real-time dynamic compensating system of radiotherapy respiratory movement and method | |
| CN109741830A (en) | The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement | |
| Guidi et al. | Real-time lung tumour motion modeling for adaptive radiation therapy using lego mindstorms | |
| CN215961606U (en) | System for maintaining regular respiration of tumor radiotherapy patient | |
| Teo et al. | Evaluating tracking and prediction of tumor motion in a motion-compensating system for adaptive radiotherapy | |
| Lee | Respiration Gating Using Near-Infrared Thermal Imaging | |
| Sano et al. | Optimal threshold of a control parameter for tomotherapy respiratory tracking: A phantom study | |
| Yu et al. | A 3D-printed phantom for stereotactic body radiation therapy simulation | |
| Cui | Dosiomics and Radiomics Guided Precision Neoadjuvant Chemoradiotherapy for Esophageal Squamous Cell Carcinoma Patients | |
| Cao | Using Varian TrueBeam Developer Mode and Varian TrueBeam Couch (6-DOF) to Simulate 4D Respiratory Motion and to Counteract the Phantom Motion in Real Time |
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 |