CN107441637A - The intensity modulated radiation therapy Forecasting Methodology of 3-dimensional dose distribution and its application in the works - Google Patents
The intensity modulated radiation therapy Forecasting Methodology of 3-dimensional dose distribution and its application in the works Download PDFInfo
- Publication number
- CN107441637A CN107441637A CN201710851175.7A CN201710851175A CN107441637A CN 107441637 A CN107441637 A CN 107441637A CN 201710851175 A CN201710851175 A CN 201710851175A CN 107441637 A CN107441637 A CN 107441637A
- Authority
- CN
- China
- Prior art keywords
- dose
- patient
- voxel
- radiation therapy
- model
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
- A61N5/1031—Treatment planning systems using a specific method of dose optimization
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
- A61N5/1039—Treatment planning systems using functional images, e.g. PET or MRI
Abstract
The invention discloses a kind of intensity modulated radiation therapy Forecasting Methodology that 3-dimensional dose is distributed in the works, step are as follows:(1) collect effective intensity modulated radiation therapy planning data and form case database;(2) according to the resolution sizes of CT images, the target area (PTV) of patient, each organ that jeopardizes are divided into several small voxels;(3) anatomical features of each patient in database are extracted;(4) dose characteristics of each patient in database are extracted;(5) artificial neural network is built, the anatomical features and dose characteristics of patient is inputted, the mapping relations gone out by artificial neural network learning between anatomical features and dose characteristics, obtains the correlation model of the two;(6) it is distributed using the 3-dimensional dose of the new patient of correlation model prediction.The application of the above method is to use above-mentioned dosage distribution forecasting method, carries out patient and jeopardizes the dose prediction of organ, and realizes quality control.By the above-mentioned means, the present invention can realize the 3-dimensional dose forecast of distribution of intensity modulated radiation therapy plan, and it can be applied to Quality Control Links.
Description
Technical field
The present invention relates to medical radiotherapy technical field, in particular to intensity modulated radiation therapy in the works 3-dimensional dose distribution it is pre-
The concrete application of survey method and this method.
Background technology
Tumour radiotherapy using ray kill tumour cell, and be avoided as much as normal structure and jeopardize organ by
Irradiation, it is one of Main Means for treating malignant tumour.Realize beam energy high concentration in tumor region be improve radiotherapy matter
The key of amount.On radiotherapy technology, IMRT technology, that is, strong technology is adjusted, by the motion of multi-leaf optical grating and penetrated
The technology of beam intensity regulation etc. further increases the conformal degree of patient's body dosage distribution, is prostate, brain neck, encephalic etc.
Main flow therapeutic modality in the tumour of type.
Clinically, doctor's meeting reference radiotherapy planning clinical procedure, such as PTV coverage rate, the tolerance dose for jeopardizing organ,
To assess whether a plan can be used in patient.The specification sets different plan mesh for different types of tumour
Mark, these targets are all based on the data on patient census.Using target of the patient-specific data as plan is lacked, it is
Cause one of major reason that clinically radiotherapy planning quality good or not differs.In addition, the quality of plan further depends on physics
The experience of teacher and spent time in single plan and energy.Physics teacher rule of thumb judges radiotherapy planning system (TPS)
Whether the plan of generation also has improved space, if can not receive this plan, it is necessary to reset injectivity optimizing target, directly
To optimal radiotherapy planning is obtained, this is the process of a continuous trial and error.Corresponding to the correct precompensation parameter changes of physics Shi Ruoneng
Results change, obtain an optimal plan by more sure.But due to the limitation of experience and time, radiotherapy planning is reaching
After clinical procedure, physics Shi Buzai is further optimized, so that patient inadvertently receives the radiotherapy of suboptimum.From
Seen on clinical meaning, target area realizes that the maximum dose of surrounding tissue and organ is exempted on the premise of prescribed dose irradiation is met
It is the important channel for ensureing patient's therapeutic quality.
Strong dosage in the works is adjusted to be distributed in the parameter such as the prescribed dose that doctor provides and the optimization aim that physics teacher is set
Constraint under, it is highly conformable with target region shape.Therefore, exist between patient anatomy and dosage it is certain associate, can establish
The correlation model of the two with realize dosage distribution prediction.
2011, the A planning quality evaluation that zhu et al. is delivered on Med Phys publications
Tool for prostate adaptive IMRT based on machine learning, describe a kind of description dissection
The method of feature, the description describe to jeopardize the spatial relationship of organ (OAR) and target area (PTV) from distance and volume, but
This description method only considers influence of the two OAR and PTV spatial relationship to the OAR institutes acceptable dose, does not consider OAR completely
Between influence each other.In addition, the dose characteristics that this method is selected are the two-dimensional signals by extraction, it is impossible to fully reflection
Performance situation on the three dimensions of dosage distribution.
The content of the invention
It is an object of the invention to disclose a kind of 3-dimensional dose distribution forecasting method suitable for intensity modulated radiation therapy plan, with
Solves the problems such as anatomic information description is not comprehensive in the prior art.It is another object of the present invention to provide the Forecasting Methodology
Concrete application.
To reach above-mentioned purpose, the present invention is realized using following technical proposals:3-dimensional dose is distributed intensity modulated radiation therapy in the works
Forecasting Methodology, by predict the dosage of each voxel realize 3-dimensional dose be distributed prediction, comprise the following steps:
(1) collect effective intensity modulated radiation therapy planning data and form case database;
(2) according to the resolution sizes of CT images, the target area (PTV) of patient, each organ that jeopardizes are divided into several
Small voxel;
(3) anatomical features of each patient in database are extracted, including PTV volumes, small voxel are to PTV borders most narrow spacing
From, small voxel to each minimum range for jeopardizing organ boundaries;
(4) dose characteristics of each patient in database are extracted;
(5) artificial neural network is built, the anatomical features and dose characteristics of patient are inputted, by artificial neural network learning
The mapping relations gone out between anatomical features and dose characteristics, obtain the correlation model of the two;
(6) it is distributed using the 3-dimensional dose of the new patient of correlation model prediction.
As a preferred embodiment, in the step (3), small voxel to PTV and each minimum range for jeopardizing organ boundaries are all
To PTV or jeopardize the minimum ranges of organ boundaries for small voxel on three dimensions.
As a preferred embodiment, in the step (3) and (4), the anatomical features and dose characteristics of patient are in input nerve net
Before network, be first normalized, by each characteristic value in anatomical features and dose characteristics value distinguish Linear Mapping to [-
1,1] in the range of.
As a preferred embodiment, in the step (5), the foundation of correlation model is realized by MATLAB softwares, is specifically included
Following steps:
(5.1) artificial neural network tool box is called in MATLAB;
(5.2) neutral net is built using MATLAB artificial neural networks tool box, the network settings are three layers of nerve net
Network;Input neuronal quantity is determined by anatomical features quantity;Output neuron quantity is 1;Hidden layer neuron quantity determines
The specific quantity of hidden layer neuron is determined in the range of 3 to twice of input neuronal quantity, then by model checking;
Training function selects Regularization algorithms;Excitation function selects tanh S type functions;
(5.3) anatomical features extracted and dose characteristics are inputted into network, trains the correlation model of the two.
As a preferred embodiment, in the step (5.2), determine that hidden layer neuron is specific amount of by model checking
Concretely comprise the following steps:
(5.2.1) establishes the different neutral net of hidden layer neuron quantity, net according to hidden layer neuron quantitative range
Network quantity is determined by neuronal quantity scope;
Existing case is divided into training group and test group by (5.2.2) according to the ratio of 70% and 30%;
(5.2.3) sequentially inputs the anatomical features of each patient and dose characteristics in training group in single Neural,
A model is trained, in this way, going out the model of respective numbers using all neural metwork trainings;
(5.2.4) sequentially inputs the anatomical features of each patient in test group in single model, obtains each patient and exists
Predicted dose characteristic value in single model, so calculate predicted dose characteristic value of each patient in each model;
(5.2.5) calculates average forecasting error D of the single model in all test group casesmn, specific formula is:
Wherein | | it is the operation that takes absolute value, DclinIt is the actual dose of voxel, DpredIt is predicted dose, n is single patient
Number of voxel, m are the quantity of test group patient;
(5.2.6) contrasts the average forecasting error D of each modelmn, the minimum model of average forecasting error is selected, its is corresponding
Hidden layer neuron quantity be selected quantity.
As a preferred embodiment, in the step (5.3), the training of correlation model comprises the following steps:
(5.3.1) filters out the clinical program of same type tumour in case database, extracts the patient's solution each planned
Cut open feature and dose characteristics;
(5.3.2) inputs the small voxel from different interest regions in the artificial neural network set respectively, instruction
Get the first correlation model of each area-of-interest (ROI);
(5.3.3) assesses each first fit solution of the correlation model in single plan successively, filters out first at this
The drill program for being preferably intended to be the ROI refined models is fitted on correlation model, wherein the plan filtered out accounts for general plan
The 70% of quantity;
(5.3.4) is by the plan chosen in each ROI training the refined model of the ROI.
As a preferred embodiment, assessment models method of fit solution in each plan is in the step (5.3.3), it is first
The mean absolute error of each case is first calculated, specific formula is:
Wherein | | it is the operation that takes absolute value, DclinIt is the actual dose value of single voxel, DpredIt is the prediction agent of single voxel
Value, n are the number of voxel of single patient;Illustrate that the fitting effect of the case is better if mean absolute error is smaller, conversely,
Then fitting effect is poorer.
As a preferred embodiment, the specific of the 3-dimensional dose distribution of the new patient of correlation model prediction is used in the step (6)
Step is:
A the anatomical features of new patient) are extracted;
B) input in correlation model and calculate corresponding dose characteristics value;
C after) the dose characteristics value arrangement of each voxel is integrated according to position of the voxel in CT images, new patient is obtained
Prediction 3-dimensional dose distribution.
The application of a kind of intensity modulated radiation therapy 3-dimensional dose forecast of distribution in the works, using above-mentioned a kind of intensity modulated radiation therapy in the works three
Dosage distribution forecasting method is tieed up, carries out intensity modulated radiation therapy plan quality control.
As a preferred embodiment, comprise the following steps:
(A) for the new patient beyond training case, after radiotherapy system (TPS) generates the plan of the patient, extraction
Its anatomical features and dose characteristics, its dose characteristics value are the actual dose of current planning;
(B) area-of-interest is selected successively, and the anatomical features of the region voxel are inputted into the corresponding correlation model in the region
In, calculate the predicted dose characteristic value in the region;
(C) using dose value as abscissa, percent by volume is ordinate, is drawn respectively according to actual dose and predicted dose
The actual dose volume histogram (DVH) and predicted dose volume histogram of all area-of-interests of new patient;
(D) each ROI DVH is contrasted, if prediction DVH curves on some or multiple ROI be present is less than actual DVH curves,
Then the current planning of the undertaker patient is prompted improved space to be present.
The operation principle of this Forecasting Methodology is, from the point of view of the generation process planned by force is adjusted, the distribution of its dosage and patient anatomical
Certain association between information be present, correlation model among these can be calculated by the method for machine learning, thus, new to suffer from
The dosage distribution of person can predict from anatomic information.
The present invention compared with prior art, has advantages below and beneficial effect:
(1) anatomical features of patient can comprehensively be described from volume information, spatial information etc..
(2) the dosage distribution of three-dimensional is predicted, so that more dosage informations are presented.
(3) method of machine learning has been borrowed.
Brief description of the drawings
Fig. 1 is intensity modulated radiation therapy 3-dimensional dose distribution forecasting method flow chart in the works.
Fig. 2 is distance-dose relationship figure of bladder voxel, and the wherein distance is minimum range of the voxel to PTV borders.
Fig. 3 is distance-dose relationship figure of bladder voxel, and the wherein distance is minimum range of the voxel to rectum border.
Fig. 4 is distance-dose relationship figure of bladder voxel, wherein the distance be voxel to fl boundary in front most narrow spacing
From.
Fig. 5 is distance-dose relationship figure of bladder voxel, and wherein the distance is most narrow spacing of the voxel to right femoral head border
From.
Fig. 6 is distance-dose relationship figure of bladder voxel, and wherein the distance is most narrow spacing of the voxel to bulb urethrae border
From.
Fig. 7 is the structure chart of neutral net.
Fig. 8 is the setting interface of neutral net.
Fig. 9 is actual DVH and prediction DVH comparison diagram in embodiment 2.
Embodiment
The method of the present invention is described in further detail with reference to embodiment, but the applicable tumor type of the present invention
This is not limited to, without departing from the idea case in the present invention described above, according to ordinary skill knowledge and customary means,
Various replacements and change are made, all should be included within the scope of the invention.
Embodiment 1:
The present embodiment carries out dose prediction to the bladder of patients with prostate cancer, have chosen the VMAT of 14 patients with prostate cancer
It is designed for the training of model.
First, the voxel by the anatomical structure dispersion composition resolution of patient for 2.3438 × 2.3438 × 3mm sizes.
Then, the anatomical features and dose characteristics of patient's bladder are extracted using MATLAB, wherein anatomical features include PTV's
Volume, the minimum range of bladder voxel to PTV borders, the minimum range of bladder voxel to rectum border, bladder voxel to left stock
Minimum range, the minimum range of bladder voxel to right femoral head border on bone border, and bladder voxel is to bulb urethrae border
Minimum range, the quantity of model, which is equal to, on single patient jeopardizes organ number and adds PTV quantity, as jeopardizes organ number and adds
1.Relation between the visible each features of Fig. 2 to Fig. 6 and dosage, in addition, dose characteristics are the agent that bladder voxel receives
Value, after this, respectively to each anatomical features value and the linear normalization of dose characteristics value to [- 1,1] in the range of.
Finally, establish artificial neural network using MATLAB artificial neural networks tool box, and train anatomical features and
The correlation model of dose characteristics, detailed process are as follows:
" nntool " order is inputted in MATLAB command windows, the setting interface of artificial neural network can be ejected, at this
In embodiment, three-layer neural network is set;It is 6 to input neuronal quantity;Output neuron quantity is 1;Train function choosing
Use Regularization algorithms;Excitation function selects tanh S type functions, and iterations is 500 times;Hidden layer neuron number
The scope of amount elects 3 to twice of input neuronal quantity, i.e. [3,12] as, then establishes 10 neutral nets, its hidden layer
Number is respectively 3 to 12, and 14 cases are randomly divided into training group and test group afterwards, there is 10 cases and 4 cases respectively, will
Training group sequentially inputs 10 networks, trains 10 models, test group finally is sequentially input into model, calculated according to formula 1
Go out average forecasting error D of each model in all training casesmn, specific formula is:
Wherein | | it is the operation that takes absolute value, DclinIt is the actual dose of voxel, DpredIt is predicted dose, n is single patient
Number of voxel, m are the quantity of test group patient.
The minimum model of error is selected, using the hidden layer neuron quantity of this network as the setting of model backward, at this
In embodiment, the quantity of hidden layer neuron is arranged to 4;Remaining parameter is acquiescence.Network structure is as shown in fig. 7, network
Set as shown in Figure 8.
The anatomical features of 14 patients and dose characteristics are input to the network set, training obtains first model, is
Fit solution of the model in each case is obtained, the anatomical features of 14 cases are sequentially input in model again, is exported
Dose characteristics value under each case prediction;The mean absolute error of single case is calculated further according to formula 2:
Wherein | | it is the operation that takes absolute value, DclinIt is the actual dose value of single voxel, DpredIt is the prediction agent of single voxel
Value, n are the number of voxel of single patient;Illustrate that the fitting effect of the case is better if mean absolute error is smaller, conversely,
Then fitting effect is poorer.
According to the mean absolute error of each case, training of 10 less cases of error as refined model is filtered out
Case, as a result as shown in table 1:
The first model training case the result table of table 1
Trained to obtain refined model with garbled case, and calculate the mean absolute error of each training case, by
This assesses the precision of refined model, as a result as shown in table 2:
The refined model of table 2 trains case the result table
Embodiment 2:
The present embodiment by the intensity modulated radiation therapy described in above-described embodiment in the works 3-dimensional dose distribution Forecasting Methodology based on,
The concrete application method of the Forecasting Methodology is provided, is concretely comprised the following steps:
In units of bladder voxel, 6 anatomical features of new patient's bladder voxel are extracted, including PTV volume, voxel arrive
The minimum range on PTV borders, the minimum range of voxel to rectum border, voxel to the fl minimum range on boundary, voxel in front
To the minimum range on right femoral head border, and voxel is to the minimum range on bulb urethrae border;
In the correlation model that anatomical features input is trained, the prediction bladder dose characteristics value of new patient is obtained;
(C) using dose value as abscissa, percent by volume is ordinate, is drawn respectively according to actual dose and predicted dose
The actual dose volume histogram (DVH) and predicted dose volume histogram of new patient's bladder, are shown in Fig. 9;
(D) actual bladder DVH curves and prediction bladder DVH curves are contrasted, if prediction bladder DVH curves are less than actual DVH
Curve, then it is assumed that current planning has improved space, and such as the patient 3 in Fig. 9, whole piece prediction DVH curves are significantly less than real
Border DVH curves, can prompt undertaker's current planning still can further optimize.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that:Not
A variety of change, modification, replacement and modification can be carried out to these embodiments by departing under the principle and objective of the present invention, of the invention
Scope claim and its equivalent unlimited.
Claims (10)
1. a kind of intensity modulated radiation therapy Forecasting Methodology that 3-dimensional dose is distributed in the works, is realized by predicting the dosage of each voxel
The prediction of 3-dimensional dose distribution, it is characterised in that comprise the following steps:
(1) collect effective intensity modulated radiation therapy planning data and form case database;
(2) according to the resolution sizes of CT images, the target area (PTV) of patient, each organ that jeopardizes are divided into several corpusculums
Element;
(3) anatomical features of each patient in database are extracted, including PTV volumes, small voxel are to PTV borders minimum range, small
Voxel is to each minimum range for jeopardizing organ boundaries;
(4) dose characteristics of each patient in database are extracted;
(5) artificial neural network is built, inputs the anatomical features and dose characteristics of patient, goes out solution by artificial neural network learning
The mapping relations between feature and dose characteristics are cutd open, obtain the correlation model of the two;
(6) it is distributed using the 3-dimensional dose of the new patient of correlation model prediction.
A kind of 2. intensity modulated radiation therapy according to claim 1 Forecasting Methodology that 3-dimensional dose is distributed in the works, it is characterised in that
In the step (3), small voxel to PTV and it is each jeopardize organ boundaries minimum range be all on three dimensions small voxel arrive
PTV or the minimum range for jeopardizing organ boundaries.
A kind of 3. intensity modulated radiation therapy according to claim 1 Forecasting Methodology that 3-dimensional dose is distributed in the works, it is characterised in that
In the step (3) and (4), place is first normalized before neutral net is inputted in the anatomical features and dose characteristics of patient
Reason, each characteristic value in anatomical features and dose characteristics value are distinguished into Linear Mapping in the range of [- 1,1].
A kind of 4. intensity modulated radiation therapy according to claim 1 Forecasting Methodology that 3-dimensional dose is distributed in the works, it is characterised in that
In the step (5), the foundation of correlation model is realized by MATLAB softwares, specifically includes following steps:
(5.1) artificial neural network tool box is called in MATLAB;
(5.2) neutral net is built using MATLAB artificial neural networks tool box, the network settings are three-layer neural network;It is defeated
Enter neuronal quantity to be determined by anatomical features quantity;Output neuron quantity is 1;Hidden layer neuron quantity is determined at 3
The specific quantity of hidden layer neuron is determined in the range of twice of input neuronal quantity, then by model checking;Training
Function selects Regularization algorithms;Excitation function selects tanh S type functions;
(5.3) anatomical features extracted and dose characteristics are inputted into network, trains the correlation model of the two.
A kind of 5. intensity modulated radiation therapy according to claim 4 Forecasting Methodology that 3-dimensional dose is distributed in the works, it is characterised in that
In the step (5.2), concretely comprised the following steps by model checking to determine that hidden layer neuron is specific amount of:
(5.2.1) establishes the different neutral net of hidden layer neuron quantity, network number according to hidden layer neuron quantitative range
Amount is determined by neuronal quantity scope;
Existing case is divided into training group and test group by (5.2.2) according to the ratio of 70% and 30%;
(5.2.3) sequentially inputs the anatomical features of each patient and dose characteristics in training group in single Neural, training
Go out a model, in this way, going out the model of respective numbers using all neural metwork trainings;
(5.2.4) sequentially inputs the anatomical features of each patient in test group in single model, obtains each patient single
Predicted dose characteristic value in model, so calculate predicted dose characteristic value of each patient in each model;
(5.2.5) calculates average forecasting error D of the single model in all test group casesmn, specific formula is:
Wherein | | it is the operation that takes absolute value, DclinIt is the actual dose of voxel, DpredIt is the predicted dose of voxel, n is single patient
Number of voxel, m is the quantity of test group patient;
(5.2.6) contrasts the average forecasting error D of each modelmn, the minimum model of average forecasting error is selected, it is corresponding hidden
It is selected quantity to hide layer neuronal quantity.
A kind of 6. intensity modulated radiation therapy according to claim 4 Forecasting Methodology that 3-dimensional dose is distributed in the works, it is characterised in that
In the step (5.3), the training of correlation model comprises the following steps:
(5.3.1) filters out the clinical program of same type tumour in case database, and it is special to extract the patient anatomical each planned
Seek peace dose characteristics;
(5.3.2) inputs the small voxel from different interest regions in the artificial neural network set respectively, trains
To the first correlation model of each area-of-interest (ROI);
(5.3.3) assesses each first fit solution of the correlation model in single plan successively, filters out in the first secondary association
The drill program for being preferably intended to be the ROI refined models is fitted on model, wherein the plan filtered out accounts for general plan quantity
70%;
(5.3.4) is by the plan chosen in each ROI training the refined model of the ROI.
7. a kind of intensity modulated radiation therapy according to claim 6 in the works 3-dimensional dose distribution Forecasting Methodology characterized in that,
Assessment models method of fit solution in each plan is to calculate being averaged for each case first in the step (5.3.3)
Absolute error, specific formula are:
Wherein | | it is the operation that takes absolute value, DclinIt is the actual dose value of single voxel, DpredIt is the predicted dose of single voxel
Value, n is the number of voxel of single patient;Illustrate that the fitting effect of the case is better if mean absolute error is smaller, conversely, then
Fitting effect is poorer.
A kind of 8. intensity modulated radiation therapy according to claim 1 Forecasting Methodology that 3-dimensional dose is distributed in the works, it is characterised in that
Concretely comprised the following steps in the step (6) using what the 3-dimensional dose of the new patient of correlation model prediction was distributed:
A the anatomical features of new patient) are extracted;
B) input in correlation model and calculate corresponding dose characteristics value;
C after) the dose characteristics value arrangement of each voxel is integrated according to position of the voxel in CT images, the pre- of new patient is obtained
Survey 3-dimensional dose distribution.
A kind of 9. application of intensity modulated radiation therapy 3-dimensional dose forecast of distribution in the works, it is characterised in that using the claims it
A kind of intensity modulated radiation therapy described in one 3-dimensional dose distribution forecasting method in the works, carries out intensity modulated radiation therapy plan quality control.
10. application according to claim 9, it is characterised in that comprise the following steps:
(A) for the new patient beyond training case, after radiotherapy system (TPS) generates the plan of the patient, its solution is extracted
Feature and dose characteristics are cutd open, its dose characteristics value is the actual dose of current planning;
(B) area-of-interest is selected successively, the anatomical features of the region voxel are inputted in the corresponding correlation model in the region, is counted
Calculate the predicted dose characteristic value in the region;
(C) using dose value as abscissa, percent by volume is ordinate, and new trouble is drawn respectively according to actual dose and predicted dose
The actual dose volume histogram (DVH) and predicted dose volume histogram of all area-of-interests of person;
(D) each ROI DVH is contrasted, if prediction DVH curves on some or multiple ROI be present is less than actual DVH curves, is carried
Show that the current planning of the undertaker patient has improved space.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710760552 | 2017-08-30 | ||
CN2017107605526 | 2017-08-30 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107441637A true CN107441637A (en) | 2017-12-08 |
CN107441637B CN107441637B (en) | 2019-06-07 |
Family
ID=60497219
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710851175.7A Active CN107441637B (en) | 2017-08-30 | 2017-09-20 | Intensity modulated radiation therapy 3-dimensional dose is distributed in the works prediction technique and its application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107441637B (en) |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108364678A (en) * | 2018-02-10 | 2018-08-03 | 福建省肿瘤医院(福建省肿瘤研究所、福建省癌症防治中心) | A kind of nasopharyngeal carcinoma radiotherapy plan the Automation Design method based on machine learning |
CN108648811A (en) * | 2018-05-11 | 2018-10-12 | 南方医科大学 | A kind of automatic radiotherapy planning quality evaluating method based on the prediction of indication item |
CN108717866A (en) * | 2018-04-03 | 2018-10-30 | 陈辛元 | A kind of method, apparatus, equipment and the storage medium of the distribution of prediction radiotherapy planning dosage |
CN108899093A (en) * | 2018-05-11 | 2018-11-27 | 南方医科大学 | Intensity modulated radiation therapy intended dose indication item prediction technique based on intelligence learning |
CN109166613A (en) * | 2018-08-20 | 2019-01-08 | 北京东方瑞云科技有限公司 | Radiotherapy treatment planning assessment system and method based on machine learning |
CN109754860A (en) * | 2018-12-21 | 2019-05-14 | 苏州雷泰医疗科技有限公司 | A method of the automatic Prediction plan complexity based on DVH prediction model |
CN109979564A (en) * | 2017-12-28 | 2019-07-05 | 北京连心医疗科技有限公司 | A kind of intelligence radiotherapy planning method, equipment and storage medium |
CN110085298A (en) * | 2019-04-26 | 2019-08-02 | 南方医科大学 | Intensity modulated radiation therapy plan 3-dimensional dose distribution forecasting method based on depth e-learning |
CN110124214A (en) * | 2019-05-24 | 2019-08-16 | 南方医科大学 | Intensity modulated radiation therapy plan optimization method and application based on predicted dose distribution guidance |
CN110141801A (en) * | 2019-05-17 | 2019-08-20 | 天津大学 | Towards close-range particle Inner irradiation operation smart dosage planing method |
CN110197709A (en) * | 2019-05-29 | 2019-09-03 | 广州瑞多思医疗科技有限公司 | A kind of 3-dimensional dose prediction technique based on deep learning Yu priori plan |
CN110327554A (en) * | 2019-07-08 | 2019-10-15 | 南方医科大学 | Intensity modulated radiation therapy plan optimization method and application based on predicted dose distribution guidance |
CN110354406A (en) * | 2019-07-30 | 2019-10-22 | 安徽大学 | A kind of the 3-dimensional dose prediction technique and system of radiotherapy |
CN110433405A (en) * | 2019-07-09 | 2019-11-12 | 苏州雷泰智能科技有限公司 | A kind of TPS optimization method and device of predicted dose guidance |
CN110464353A (en) * | 2019-08-21 | 2019-11-19 | 南方医科大学 | A kind of pseudo- CT synthetic method and application based on depth convolutional neural networks |
CN111035860A (en) * | 2018-10-11 | 2020-04-21 | 海创时代(深圳)医疗科技有限公司 | Automatic optimization method and device for planning system |
WO2020199836A1 (en) * | 2019-04-01 | 2020-10-08 | 安徽大学 | Method and system for dosimetry evaluation on organs at risk in esophageal radiotherapy plan |
CN111951245A (en) * | 2020-08-11 | 2020-11-17 | 北京易康医疗科技有限公司 | Method for determining radiotherapy dosage according to characteristic parameters of tumor molecular image |
CN112041026A (en) * | 2018-04-30 | 2020-12-04 | 医科达有限公司 | Radiation therapy treatment plan modeling using generative countermeasure networks |
CN113101548A (en) * | 2021-04-20 | 2021-07-13 | 黄晓延 | Photon intensity modulated radiotherapy control method for reducing skin dose |
CN114007538A (en) * | 2019-06-27 | 2022-02-01 | 康坦手术股份有限公司 | Deep learning-based method for planning tissue ablation |
CN115300811A (en) * | 2022-08-08 | 2022-11-08 | 中山大学肿瘤防治中心(中山大学附属肿瘤医院、中山大学肿瘤研究所) | Dose distribution determination method and device based on machine learning |
WO2024002793A1 (en) * | 2022-06-29 | 2024-01-04 | Siemens Healthineers International Ag | Detecting anomalous dose volume histogram information |
US11896847B2 (en) | 2020-02-07 | 2024-02-13 | Elekta, Inc. | Adversarial prediction of radiotherapy treatment plans |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101247852A (en) * | 2005-07-25 | 2008-08-20 | 卡尔·奥托 | Methods and apparatus for the planning and delivery of radiation treatments |
CN103038669A (en) * | 2010-06-22 | 2013-04-10 | 卡尔·奥托 | System and method for estimating and manipulating estimated radiation dose |
CN104117151A (en) * | 2014-08-12 | 2014-10-29 | 章桦 | Optimization method of online self-adaption radiotherapy plan |
CN104645500A (en) * | 2015-02-12 | 2015-05-27 | 上海联影医疗科技有限公司 | Method and system for optimizing intensity modulated radiation therapy |
-
2017
- 2017-09-20 CN CN201710851175.7A patent/CN107441637B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101247852A (en) * | 2005-07-25 | 2008-08-20 | 卡尔·奥托 | Methods and apparatus for the planning and delivery of radiation treatments |
CN103038669A (en) * | 2010-06-22 | 2013-04-10 | 卡尔·奥托 | System and method for estimating and manipulating estimated radiation dose |
CN104117151A (en) * | 2014-08-12 | 2014-10-29 | 章桦 | Optimization method of online self-adaption radiotherapy plan |
CN104645500A (en) * | 2015-02-12 | 2015-05-27 | 上海联影医疗科技有限公司 | Method and system for optimizing intensity modulated radiation therapy |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109979564A (en) * | 2017-12-28 | 2019-07-05 | 北京连心医疗科技有限公司 | A kind of intelligence radiotherapy planning method, equipment and storage medium |
CN108364678B (en) * | 2018-02-10 | 2022-02-01 | 福建省肿瘤医院(福建省肿瘤研究所、福建省癌症防治中心) | Nasopharyngeal carcinoma radiotherapy plan automatic design method based on machine learning |
CN108364678A (en) * | 2018-02-10 | 2018-08-03 | 福建省肿瘤医院(福建省肿瘤研究所、福建省癌症防治中心) | A kind of nasopharyngeal carcinoma radiotherapy plan the Automation Design method based on machine learning |
CN108717866A (en) * | 2018-04-03 | 2018-10-30 | 陈辛元 | A kind of method, apparatus, equipment and the storage medium of the distribution of prediction radiotherapy planning dosage |
CN108717866B (en) * | 2018-04-03 | 2022-10-11 | 中国医学科学院肿瘤医院 | Method, device, equipment and storage medium for predicting radiotherapy plan dose distribution |
CN112041026B (en) * | 2018-04-30 | 2023-02-28 | 医科达有限公司 | Method and system for generating a radiation therapy dose distribution |
US11557390B2 (en) | 2018-04-30 | 2023-01-17 | Elekta, Inc. | Radiotherapy treatment plan modeling using generative adversarial networks |
CN112041026A (en) * | 2018-04-30 | 2020-12-04 | 医科达有限公司 | Radiation therapy treatment plan modeling using generative countermeasure networks |
CN108648811A (en) * | 2018-05-11 | 2018-10-12 | 南方医科大学 | A kind of automatic radiotherapy planning quality evaluating method based on the prediction of indication item |
CN108899093A (en) * | 2018-05-11 | 2018-11-27 | 南方医科大学 | Intensity modulated radiation therapy intended dose indication item prediction technique based on intelligence learning |
CN109166613A (en) * | 2018-08-20 | 2019-01-08 | 北京东方瑞云科技有限公司 | Radiotherapy treatment planning assessment system and method based on machine learning |
CN111035860A (en) * | 2018-10-11 | 2020-04-21 | 海创时代(深圳)医疗科技有限公司 | Automatic optimization method and device for planning system |
CN109754860B (en) * | 2018-12-21 | 2020-11-10 | 苏州雷泰医疗科技有限公司 | Method for automatically predicting planning difficulty level based on DVH prediction model |
CN109754860A (en) * | 2018-12-21 | 2019-05-14 | 苏州雷泰医疗科技有限公司 | A method of the automatic Prediction plan complexity based on DVH prediction model |
WO2020199836A1 (en) * | 2019-04-01 | 2020-10-08 | 安徽大学 | Method and system for dosimetry evaluation on organs at risk in esophageal radiotherapy plan |
US11515025B2 (en) | 2019-04-01 | 2022-11-29 | The Affiliated Hospital Of Qingdao University | Dosimetry assessment method and system for organ at risk in esophageal radiotherapy plan |
CN110085298B (en) * | 2019-04-26 | 2022-02-01 | 南方医科大学 | Intensity modulated radiotherapy plan three-dimensional dose distribution prediction method based on deep network learning |
CN110085298A (en) * | 2019-04-26 | 2019-08-02 | 南方医科大学 | Intensity modulated radiation therapy plan 3-dimensional dose distribution forecasting method based on depth e-learning |
CN110141801B (en) * | 2019-05-17 | 2021-04-27 | 天津大学 | Intelligent dose planning method for close-range intra-particle radiotherapy operation |
CN110141801A (en) * | 2019-05-17 | 2019-08-20 | 天津大学 | Towards close-range particle Inner irradiation operation smart dosage planing method |
CN110124214A (en) * | 2019-05-24 | 2019-08-16 | 南方医科大学 | Intensity modulated radiation therapy plan optimization method and application based on predicted dose distribution guidance |
CN110124214B (en) * | 2019-05-24 | 2020-09-04 | 南方医科大学 | Predictive dose distribution guided intensity modulated radiotherapy plan optimization systems, media and devices |
CN110197709A (en) * | 2019-05-29 | 2019-09-03 | 广州瑞多思医疗科技有限公司 | A kind of 3-dimensional dose prediction technique based on deep learning Yu priori plan |
CN110197709B (en) * | 2019-05-29 | 2023-06-20 | 广州瑞多思医疗科技有限公司 | Three-dimensional dose prediction method based on deep learning and priori planning |
CN114007538A (en) * | 2019-06-27 | 2022-02-01 | 康坦手术股份有限公司 | Deep learning-based method for planning tissue ablation |
CN110327554A (en) * | 2019-07-08 | 2019-10-15 | 南方医科大学 | Intensity modulated radiation therapy plan optimization method and application based on predicted dose distribution guidance |
CN110433405A (en) * | 2019-07-09 | 2019-11-12 | 苏州雷泰智能科技有限公司 | A kind of TPS optimization method and device of predicted dose guidance |
CN110354406A (en) * | 2019-07-30 | 2019-10-22 | 安徽大学 | A kind of the 3-dimensional dose prediction technique and system of radiotherapy |
CN110464353A (en) * | 2019-08-21 | 2019-11-19 | 南方医科大学 | A kind of pseudo- CT synthetic method and application based on depth convolutional neural networks |
US11896847B2 (en) | 2020-02-07 | 2024-02-13 | Elekta, Inc. | Adversarial prediction of radiotherapy treatment plans |
CN111951245A (en) * | 2020-08-11 | 2020-11-17 | 北京易康医疗科技有限公司 | Method for determining radiotherapy dosage according to characteristic parameters of tumor molecular image |
CN111951245B (en) * | 2020-08-11 | 2021-04-06 | 山东省肿瘤防治研究院(山东省肿瘤医院) | Method for determining radiation therapy dosage according to characteristic parameters of tumor molecular image |
CN113101548B (en) * | 2021-04-20 | 2023-04-28 | 中山大学肿瘤防治中心 | Photon intensity modulated radiotherapy control method for reducing skin dose |
CN113101548A (en) * | 2021-04-20 | 2021-07-13 | 黄晓延 | Photon intensity modulated radiotherapy control method for reducing skin dose |
WO2024002793A1 (en) * | 2022-06-29 | 2024-01-04 | Siemens Healthineers International Ag | Detecting anomalous dose volume histogram information |
CN115300811A (en) * | 2022-08-08 | 2022-11-08 | 中山大学肿瘤防治中心(中山大学附属肿瘤医院、中山大学肿瘤研究所) | Dose distribution determination method and device based on machine learning |
CN115300811B (en) * | 2022-08-08 | 2024-01-05 | 中山大学肿瘤防治中心(中山大学附属肿瘤医院、中山大学肿瘤研究所) | Dose distribution determining method and device based on machine learning |
Also Published As
Publication number | Publication date |
---|---|
CN107441637B (en) | 2019-06-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107441637B (en) | Intensity modulated radiation therapy 3-dimensional dose is distributed in the works prediction technique and its application | |
US10328282B2 (en) | System and method for novel chance-constrained optimization in intensity-modulated proton therapy planning to account for range and patient setup uncertainties | |
US10265543B2 (en) | Beam segment-level dose computation and temporal motion tracking for adaptive treatment planning | |
US9744379B2 (en) | Studying dosimetric impact of motion to generate adaptive patient-specific margins in EBRT planning | |
WO2022142770A1 (en) | Automatic radiation treatment planning system and method, and computer program product | |
US20210093893A1 (en) | Dose-distribution estimation in proton therapy | |
JP2007514499A (en) | System and method for global optimization of treatment plans for external beam irradiation therapy | |
US10076673B2 (en) | Interactive dose gradient based optimization technique to control IMRT delivery complexity | |
CN113557057A (en) | Graphical display of dose rate information for radiation treatment planning | |
US20210393982A1 (en) | Correlation of dose and dose rate information to volume for radiation treatment planning | |
CN107223066A (en) | A kind of method of localized heat/cold spot in the IMRT planning reduced based on DMPO | |
CN110327554A (en) | Intensity modulated radiation therapy plan optimization method and application based on predicted dose distribution guidance | |
Biston et al. | Time of PTV is ending, robust optimization comes next | |
EP4168113A1 (en) | Correlation of dose and dose rate information to volume for radiation treatment planning | |
US11724126B2 (en) | Methods and systems for quality-aware continuous learning for radiotherapy treatment planning | |
Leal et al. | MLC leaf width impact on the clinical dose distribution: a Monte Carlo approach | |
CN113178242B (en) | Automatic plan optimization system based on coupled generation countermeasure network | |
Yan et al. | Evaluation of an artificial intelligence guided inverse planning system: clinical case study | |
Robinson et al. | Can the use of knowledge-based planning systems improve stereotactic radiotherapy planning? A systematic review | |
LU500593B1 (en) | Automatic direct aperture optimization method and system | |
Suvira | Dosimetric differences between scheduled and adapted plans generated from ethos adaptive radiotherapy for patients with prostate cancer | |
Christiansen | A framework for the robust delivery of respiratory motion adaptive arc radiotherapy | |
Sprouts | Advancing the Radiation Oncology Clinic with Motion Management and Automatic Treatment Planning | |
Xu | Image Guided Adaptive Therapy Strategies for Robustly Optimized Intensity Modulated Proton Therapy | |
Ahmed et al. | Intensity-modulated radiotherapy (IMRT) for carcinoma of the maxillary sinus: A comparison of IMRT planning systems |
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 |