CN109966662A - A kind of method and system for verifying radiotherapy dosage - Google Patents
A kind of method and system for verifying radiotherapy dosage Download PDFInfo
- Publication number
- CN109966662A CN109966662A CN201910360026.XA CN201910360026A CN109966662A CN 109966662 A CN109966662 A CN 109966662A CN 201910360026 A CN201910360026 A CN 201910360026A CN 109966662 A CN109966662 A CN 109966662A
- Authority
- CN
- China
- Prior art keywords
- trr
- image
- radiotherapy
- feature
- value
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/06—Radiation therapy using light
- A61N2005/0626—Monitoring, verifying, controlling systems and methods
- A61N2005/0627—Dose monitoring systems and methods
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)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The present invention relates to a kind of method and system for verifying radiotherapy dosage, method includes the following steps: S1, CT image before receiving radiotherapy, and target area is sketched out in CT image；S2 extracts multiple image group features of target area；S3 filters out the image group feature for having significant correlation with tumor regression ratio TRR from the multiple image group features extracted；S4, given dose value, and export to treated that CT image identifies by step S3 using preparatory trained radiation group model and obtain the tumor regression ratio TRR under the given dose value.The invention proposes a kind of new thinkings, obtain radiation group model based on machine learning method training, verify given variable using the TRR of radiation group model output, prediction result is not influenced by single dose, and verification result is more reliable.
Description
Technical field
The present invention relates to field of medical technology, in particular to a kind of method and system for verifying radiotherapy dosage.
Background technique
Radiotherapy dosimetry is adjusted according to individual biological effect dosage (Bd) at present, formula be Bd=E/ α=nd (1+d/ [α/
β])-loge2 (T-TK)/α Tp, wherein Bd, that is, BED is biological effective dose, and E is that total cell index kills, and α is that can not repair
Coefficient is killed again, i.e., index killing caused by every Gy irradiation, β is that can repair killing coefficient, i.e., index killing caused by every Gy irradiates
Square, n is fractionated irradiation number, and d is single fractionated dose, and T is total irradiation time, and Tk is cell when being proliferated beginning again
Between, Tp is the average time of cell quantity multiplication in Continuous irradiation.It can refer to " The linear quadratic formula
And progress in fractionated radiotherapy ", author: Fowler, J.F. " Br J Radiology "
1989；62:1261–1269.
In radiotherapy, in order to ensure a radiotherapy planning exactly impacts with patient, treatment plan system is used
The dosage distribution that system (Treatment Plan System, TPS) calculates must obtain the confirmation of experimental data.Tradition " L-
Q model " and its biological effect dosage (BED) model derived decline in the degree of fitting of high dose area, may over-evaluate tumour
Control and the reaction of normal tissue is underestimated.L-Q model only passes through isolated experiment fitting data, is detached from clinical practice, not
Reflect blood vessel and interstitial damage, and have ignored Radioresistance cell subsets to influence whole damage bring, is not suitable for single
Large Dose Irradiation equivalent biological dose assessment.Cellular damage mechanism shows linear-secondary relationship, and L-Q model is suitable for single
The equivalent biological dosage that dosage is no more than 15~20Gy situation is converted.
Summary of the invention
The object of the present invention is to provide a kind of method and system for verifying radiotherapy dosage, are not only a kind of new verifying
Method, but also dosage can be adjusted according to the TRR of output.
For this purpose, the embodiment of the invention provides a kind of methods for verifying radiotherapy dosage, comprising the following steps:
S1, the CT image before receiving radiotherapy, and target area is sketched out in CT image；
S2 extracts multiple image group features of target area；
S3, from the multiple image group features extracted, filtering out has significant correlation with tumor regression ratio TRR
Image group feature；
S4, given dose value, and using preparatory trained radiation group model to by step S3, treated that CT schemes
As being identified, output obtains the tumor regression ratio TRR under the given dose value.
As an implementation, described to filter out the image group that there is significant correlation with tumor regression ratio TRR
The step of feature, comprising:
Outlier in the multiple image group features extracted is rewritten as in multiple image group features except institute by S31
State the maximum value or minimum value other than outlier；
S32, will be by S31 treated all image group characteristic value progress Z-score normalizeds；
S33, according to Spearman's correlation coefficient, selects and swells to the data value after Z-score normalized
Tumor recession ratio has the feature of significant correlation.
As an implementation, the radiation group model is obtained by following steps training:
According to the CT image before radiotherapy and under various dose after radiotherapy, tumor regression ratio TRR, and root are calculated
It makes marks according to TRR to the CT image before radiotherapy；Wherein, ViIt is voxel i in target area
Volume, V1 is Gross Target Volume before radiotherapy, and V2 is Gross Target Volume after radiotherapy；
CT image before being directed to radiotherapy, according to abovementioned steps S2-S3, extracting has significant correlation with TRR
Image group feature；
Using packed algorithm, to by marking and extracting the CT image progress with the TRR feature with significant correlation
Study prediction, and prediction result is assessed, if the accuracy of prediction result is greater than given threshold and/or area under the curve
AUC is greater than the set value, then deconditioning, otherwise undated parameter, and is recycled and executed this step.
In the present embodiment, while providing a kind of system for verifying radiotherapy dosage, comprising:
Target delineations module for receiving the CT image before radiotherapy, and sketches out target area in CT image；
Characteristic extracting module, for extracting multiple image group features of target area；
Feature Selection module, for filtering out and tumor regression ratio TRR from the multiple image group features extracted
Image group feature with significant correlation；
TRR prediction module, is used for given dose value, and using preparatory trained radiation group model to filtering out and
There is TRR the CT image of the image group feature of significant correlation to be identified, output obtains the tumour under the given dose value
Recession ratio TRR.
On the other hand, invention also provides a kind of computer readable storage medium including computer-readable instruction,
The computer-readable instruction makes processor execute the operation in any embodiment the method for the present invention when executed.
On the other hand, invention also provides a kind of electronic equipment, the electronic equipment includes: memory, storage
Program instruction；Processor is connected with the memory, executes the program instruction in memory, realizes any implementation of the present invention
Step in mode the method.
Compared with prior art, the method for the present invention or system provide a kind of new thinking, are instructed based on machine learning method
Radiation group model is got, verifies given variable using the TRR of radiation group model output, prediction result is not by list
Secondary Dose Effect, and model is to reflect blood vessel and interstitial damage based on practical CT image training gained and Radioresistance is thin
Born of the same parents' subgroup influences whole damage bring, and verification result is more reliable.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the flow chart of the method for verifying radiotherapy dosage described in the present embodiment.
Fig. 2 is that the image group for having significant correlation with tumor regression ratio (TRR) is selected described in the present embodiment
The flow chart of feature.
Fig. 3 is the flow chart of training radiation group model described in the present embodiment.
Fig. 4 is the functional block diagram of the system of verifying radiotherapy dosage described in the present embodiment.
Fig. 5 is the functional block diagram of electronic equipment described in embodiment.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Referring to Fig. 1, present embodiments providing a kind of method for verifying radiotherapy dosage, comprising the following steps:
S1, CT (Computed Tomography, CT scan) figure before receiving the radiotherapy of input
Picture, and target area (Gross Tumor Volume) is sketched out in CT image.It can choose to use when drawing target outline and delineate manually.
S2 extracts the image group feature of target area.In the present embodiment, 57 shadows are automatically extracted out by LIFEx software
As group learns feature, comprising: single order feature, such as gray scale and shape；Textural characteristics, such as Grey-Level Zone Length
Matrix (gray level zone length matrix), Grey-Level Run Length Matrix (gray level running length square
Battle array), Neighborhood Grey-Level Different Matrix (field grey scale difference matrix), and Grey Level
Co-occurrence Matrix (gray level co-occurrence matrixes).57 image group features are not run business into particular one herein and are stated, in practical operation
It can be automatically extracted out using LIFEx software, also may refer to relevant technical literature, such as may refer to " LIFEx:
afreeware for radiomic feature calculation in multimodality imaging to
accelerate advances in the characterization of tumor heterogeneity《Cancer
Research ", 2018；78 (16): 4786-4789, C Nioche, F Orlhac, S Boughdad, S Reuz é, J Goya-
Outi,C Robert,C Pellot-Barakat,M Soussan,F Frouin,and I Buvat.In another example LIFEx-
Texture:M Soussan,F Orlhac,M Boubaya,L Zelek,M Ziol,V Eder,I Buvat；
Relationship between tumor heterogeneity measured on FDG-PET/CT and
pathological prognostic factors in invasive breast cancer.Plos One9:e94017,
2014。
S3 is selected to tumor regression ratio (TRR) from the 57 image group features extracted with significant related
The image group feature of property.
Specifically, referring to Fig. 2, selection has the image group feature of significant correlation with tumor regression ratio (TRR)
Process the following steps are included:
S31 scales outlier, that is, the outlier in 57 characteristic values is changed in 57 characteristic values except outlier
Maximum value or minimum value in addition, to eliminate influence of the extremum to feature.Outlier (outlier), also referred to as outlier, refer to
There are one or several numerical value compared with other numerical value in data, differs greatly.As an example, it can generally will deviate from
Numerical value of the probability less than or equal to 1/ (2n) of observation average value is defined as outlier, and wherein n is the number of case load.Certainly,
It is customized to can according to need progress.For example, having 1,2,10 in a group data, then it is considered as outlier for 10, which is revised as 1
Or 2.
S32, Z-score normalized.That is, converting new data by following formula for actual data value indicates: Z
=(x- μ)/σ, wherein x is a certain specific features value, and μ is characterized the average of value, and σ is standard deviation.
For example, to an ordered series of numbers: 2,5,8,13,18, after Z-score normalized are as follows: -1.12859, -
.65834 ,-.18810,0.59564,1.37938.
S33 selects the spy for having significant correlation with tumor regression ratio (TRR) according to Spearman's correlation coefficient
Each characteristic value and tumor regression ratio (TRR) are carried out correlation detection, are less than with significance by sign, two-tailed test
The image group feature of setting value (such as 0.05) is judged as the feature for having significant correlation with TRR.According to Spearman correlation
Property is detected as existing mature technology, therefore does not run business into particular one and state to specific detection process herein.
The feature finally elected has 5, is respectively as follows: HISTO_Skewness, deflection histogram；HISTO_Energy,
Energy histogram；SHAPE_Volume, (volume)；GLRLM_LRE(The grey-level run length matrix-
Long Run Emphasis) gray scale run-length matrix-length operating point；GLZLM_SZE, gray scale head of district matrix _ short area emphasis.
S4, using preparatory trained radiation group model, to process step S3, treated that CT image identifies, and
Given dose value, output obtain tumor regression ratio (TRR) under the dose value, given agent can be verified according to the TRR of output
Whether magnitude is reasonable.
Radiation group model described herein makes it have and works as in advance by the practical CT image under study various dose
The function of corresponding TRR can be exported when inputting the dosage of setting, and dosage can be adjusted according to the TRR of output with this, led to
BED can be adjusted by crossing adjustment dosage, and then export corresponding TRR, and then can determine that gross tumor volume is complete according to output TRR
Dosage needed for subsiding.
In the present embodiment, the radiation group model is by the following method obtained by training:
It step 1, (is same before and after radiotherapy according to the CT image before radiotherapy and under various dose after radiotherapy
The CT image of one patient), tumor regression ratio TRR is calculated, and mark to the CT image before radiotherapy according to following Table2
Note, i.e., the CT image tagged for being 1,0.6-1 to the TRR CT image tagged for being 0-0.6 are 2.The calculation of tumor regression ratio TRR
Are as follows: V=∑iVi,Wherein, ViIt is the volume of voxel i in target area, V1 is Gross Target Volume before radiotherapy, and V2 is to put
Gross Target Volume after treatment.
Step 2, the CT image before being directed to radiotherapy extracts and has with TRR according to the method for abovementioned steps S2-S3
There are 5 image group features of significant correlation.It, will be biological in order to be comparable the radiological dose between case when training
Effect dose (Bd) is used as a non-visual group of feature introduced feature collection.Feature set is described as shown in Table 3.
Without point of sequence between above-mentioned steps 1 and step 2.
Step 3, using packed algorithm, to by marking and extracting the CT figure with the TRR feature with significant correlation
As carrying out study prediction, so that radiation group model is corresponding TRR under the exportable dosage after given dose.Packed algorithm
Advantage be, accuracy rate be apparently higher than combination in any single classifier, for biggish noise performance be unlikely to very poor, and
And there is robustness, it is not easy to overfitting, so using packed algorithm in the present embodiment.
Specifically, referring to Fig. 3, being primarily based on learning data set D generates several training sets D1~Dk, then with corresponding
Classifier M1~Mk of number, is trained prediction to each training set respectively, then again inputs new test data set
Different classifiers obtains K different prediction results, is finally made with the prediction result of quantity at most (i.e. the minority is subordinate to the majority)
For the result finally exported.Such as 55 are obtained the result is that Isosorbide-5-Nitrae 4 the result is that 0, then determines final result with 99 kinds of classification methods
It is 1.Therefore, K is preferably odd number.
In a trained example, learning data set is that the CT image of 34 patients with lung cancer (all passes through step 1 and step 2
Processing), Clinical symptoms is as shown in Table 1.If TRRv is prediction label, it is divided into two grades, as shown in Table 2.
Table1.
Table2.
| TRR | (-∞,0.6) | [0.6,1) |
| TRRv | 1 | 2 |
Table 3.
Step 4, the output result of step 3 is assessed, if accuracy is greater than given threshold and/or area under the curve
AUC is greater than the threshold value of setting, then deconditioning, otherwise return step 3, and updates model parameter, and circulation executes step 3-4.
Prediction model uses the packed algorithm in integrated study, 10 times of cross validations.The algorithm shows fabulous effect,
Accuracy 97.1%, area under the curve (AUC) are 0.99.
Based on inventive concept same as mentioned above, a kind of verifying radiotherapy dosage is provided in the present embodiment simultaneously
System.As shown in figure 4, the system of the verifying radiotherapy dosage includes:
Target delineations module for receiving the CT image before radiotherapy, and sketches out target area in CT image；
Characteristic extracting module, for extracting multiple image group features of target area；
Feature Selection module, for filtering out and tumor regression ratio TRR from the multiple image group features extracted
Image group feature with significant correlation；
TRR prediction module, is used for given dose value, and using preparatory trained radiation group model to filtering out and
There is TRR the CT image of the image group feature of significant correlation to be identified, output obtains the tumour under the given dose value
Recession ratio TRR.
Wherein, Feature Selection module includes:
Data zooming submodule, for being rewritten as multiple shadows for the outlier in the multiple image group features extracted
As group learns the maximum value or minimum value in feature in addition to the outlier；
Submodule is normalized, all image group characteristic values for exporting data zooming submodule carry out Z-
Score normalized；
Correlation detection submodule, for the data value to normalization submodule output, according to Spearman's correlation coefficient,
Select the feature that there is significant correlation with tumor regression ratio.
Wherein, radiation group model is obtained by following steps training:
According to the CT image before radiotherapy and under various dose after radiotherapy, tumor regression ratio TRR, and root are calculated
It makes marks according to TRR to the CT image before radiotherapy；V=∑iVi,Wherein, ViIt is voxel i in target area
Volume, V1 are Gross Target Volumes before radiotherapy, and V2 is Gross Target Volume after radiotherapy；
CT image before being directed to radiotherapy extracts the image group feature for having significant correlation with TRR；
Using packed algorithm, to by marking and extracting the CT image progress with the TRR feature with significant correlation
Study prediction, and prediction result is assessed, if the accuracy of prediction result is greater than given threshold and/or area under the curve
AUC is greater than the set value, then deconditioning, otherwise undated parameter, and is recycled and executed this step.
As shown in figure 5, the present embodiment provides a kind of electronic equipment simultaneously, which may include 51 He of processor
Memory 52, wherein memory 52 is coupled to processor 51.It is worth noting that, the figure is exemplary, it can also be used
The structure is supplemented or substituted to the structure of his type, realizes that data are extracted, chart is redrawn, communicates or other function.
As shown in figure 5, the electronic equipment can also include: input unit 53, display unit 54 and power supply 55.It is worth noting
, which is also not necessary to include all components shown in Fig. 5.In addition, electronic equipment can also include
The component being not shown in Fig. 5 can refer to the prior art.
Processor 51 is sometimes referred to as controller or operational controls, may include microprocessor or other processor devices and/
Or logic device, the processor 51 receive the operation of all parts of input and controlling electronic devices.
Wherein, memory 52 for example can be buffer, flash memory, hard disk driver, removable medium, volatile memory, it is non-easily
The property lost one of memory or other appropriate devices or a variety of, can store configuration information, the processor 51 of above-mentioned processor 51
The instruction of execution, record the information such as list data.Processor 51 can execute the program of the storage of memory 52, to realize information
Storage or processing etc..It in one embodiment, further include buffer storage in memory 52, i.e. buffer, with the intermediate letter of storage
Breath.
Input unit 53 is for example for before providing radiotherapy to processor 51 or postradiation CT image or given agent
Magnitude.The TRR or the various intermediate result figures in treatment process that display unit 54 is used to show output, the display unit example
It can be such as LCD display, but the present invention is not limited thereto.Power supply 55 is used to provide electric power for electronic equipment.
The embodiment of the present invention also provides a kind of computer-readable instruction, wherein when executing described instruction in the electronic device
When, described program makes electronic equipment execute the operating procedure that the method for the present invention is included.
The embodiment of the present invention also provides a kind of storage medium for being stored with computer-readable instruction, wherein the computer can
Reading instruction makes electronic equipment execute the operating procedure that the method for the present invention is included.
It should be understood that in various embodiments of the present invention, magnitude of the sequence numbers of the above procedures are not meant to execute suitable
Sequence it is successive, the execution of each process sequence should be determined by its function and internal logic, the implementation without coping with the embodiment of the present invention
Process constitutes any restriction.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is
The specific work process of system, device and unit, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.In addition, shown or beg for
Opinion mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING of device or unit
Or communication connection, it is also possible to electricity, mechanical or other form connections.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention
Portion or part steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.
Claims (8)
1. a kind of method for verifying radiotherapy dosage, which comprises the following steps:
S1, the CT image before receiving radiotherapy, and target area is sketched out in CT image；
S2 extracts multiple image group features of target area；
S3 filters out the shadow for having significant correlation with tumor regression ratio TRR from the multiple image group features extracted
As group learns feature；
S4, given dose value, and using preparatory trained radiation group model to process step S3 treated CT image into
Row identification, output obtain the tumor regression ratio TRR under the given dose value.
2. the method according to claim 1, wherein described filter out has significantly with tumor regression ratio TRR
The step of image group feature of correlation, comprising:
S31, by the outlier in the multiple image group features extracted, be rewritten as in multiple image group features except it is described from
Maximum value or minimum value other than group's value；
S32, will be by step S31 treated all image group characteristic value progress Z-score normalizeds；
S33 is selected and is disappeared with tumour according to Spearman's correlation coefficient to the data value after Z-score normalized
Move back the feature that ratio has significant correlation.
3. the method according to claim 1, wherein the radiation group model is trained by following steps
It arrives:
According to the CT image before radiotherapy and under various dose after radiotherapy, tumor regression ratio TRR is calculated, and according to
TRR makes marks to the CT image before radiotherapy；Wherein, ViIt is voxel i in target area
Volume, V1 are Gross Target Volumes before radiotherapy, and V2 is Gross Target Volume after radiotherapy；
CT image before being directed to radiotherapy extracts the shadow for having significant correlation with TRR according to abovementioned steps S2-S3
As group learns feature；
Using packed algorithm, the CT image by marking and extracting the feature with TRR with significant correlation is learnt
Prediction, and prediction result is assessed, if the accuracy of prediction result is greater than given threshold and/or area under the curve AUC is big
In setting value, then deconditioning, otherwise undated parameter, and recycle and execute this step.
4. a kind of system for verifying radiotherapy dosage characterized by comprising
Target delineations module for receiving the CT image before radiotherapy, and sketches out target area in CT image；
Characteristic extracting module, for extracting multiple image group features of target area；
Feature Selection module, for from the multiple image group features extracted, filtering out to have with tumor regression ratio TRR
The image group feature of significant correlation；
TRR prediction module, is used for given dose value, and using preparatory trained radiation group model to filtering out and TRR tool
There is the CT image of the image group feature of significant correlation to be identified, output obtains the tumor regression ratio under the given dose value
Example TRR.
5. system according to claim 4, which is characterized in that the Feature Selection module includes:
Data zooming submodule, for being rewritten as multiple image groups for the outlier in the multiple image group features extracted
Learn the maximum value or minimum value in feature in addition to the outlier；
Submodule is normalized, all image group characteristic values for exporting data zooming submodule carry out Z-score and return
One change processing；
Correlation detection submodule, for the data value to normalization submodule output, according to Spearman's correlation coefficient, selection
There is with tumor regression ratio the feature of significant correlation out.
6. system according to claim 4, which is characterized in that the radiation group model is trained by following steps
It arrives:
According to the CT image before radiotherapy and under various dose after radiotherapy, tumor regression ratio TRR is calculated, and according to
TRR makes marks to the CT image before radiotherapy；Wherein, ViIt is voxel i in target area
Volume, V1 are Gross Target Volumes before radiotherapy, and V2 is Gross Target Volume after radiotherapy；
CT image before being directed to radiotherapy extracts the image group feature for having significant correlation with TRR；
Using packed algorithm, the CT image by marking and extracting the feature with TRR with significant correlation is learnt
Prediction, and prediction result is assessed, if the accuracy of prediction result is greater than given threshold and/or area under the curve AUC is big
In setting value, then deconditioning, otherwise undated parameter, and recycle and execute this step.
7. a kind of computer readable storage medium including computer-readable instruction, which is characterized in that the computer-readable finger
Enable the operation for requiring processor perform claim in any the method for 1-3.
8. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
Memory stores program instruction；
Processor is connected with the memory, executes the program instruction in memory, realizes that claim 1-3 is any described
Step in method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910360026.XA CN109966662B (en) | 2019-04-30 | 2019-04-30 | System for verifying radiation therapy dosage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910360026.XA CN109966662B (en) | 2019-04-30 | 2019-04-30 | System for verifying radiation therapy dosage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109966662A true CN109966662A (en) | 2019-07-05 |
| CN109966662B CN109966662B (en) | 2020-11-24 |
Family
ID=67087298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910360026.XA Active CN109966662B (en) | 2019-04-30 | 2019-04-30 | System for verifying radiation therapy dosage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109966662B (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110338906A (en) * | 2019-07-10 | 2019-10-18 | 清华大学深圳研究生院 | Smart therapeutics system and method for building up for photo-crosslinking operation |
| CN110705626A (en) * | 2019-09-26 | 2020-01-17 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111388879A (en) * | 2020-03-19 | 2020-07-10 | 上海联影医疗科技有限公司 | Radiation dose determination system, radiation dose determination device and storage medium |
| CN111540437A (en) * | 2020-04-23 | 2020-08-14 | 北京大学第三医院（北京大学第三临床医学院） | Dose verification method and system based on artificial intelligence |
| 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 |
| US11090508B2 (en) | 2019-03-08 | 2021-08-17 | Varian Medical Systems Particle Therapy Gmbh & Co. Kg | System and method for biological treatment planning and decision support |
| US11103727B2 (en) | 2019-03-08 | 2021-08-31 | Varian Medical Systems International Ag | Model based PBS optimization for flash therapy treatment planning and oncology information system |
| US11116995B2 (en) | 2019-03-06 | 2021-09-14 | Varian Medical Systems, Inc. | Radiation treatment planning based on dose rate |
| US11291859B2 (en) | 2019-10-03 | 2022-04-05 | Varian Medical Systems, Inc. | Radiation treatment planning for delivering high dose rates to spots in a target |
| US11348755B2 (en) | 2018-07-25 | 2022-05-31 | Varian Medical Systems, Inc. | Radiation anode target systems and methods |
| US11478664B2 (en) | 2017-07-21 | 2022-10-25 | Varian Medical Systems, Inc. | Particle beam gun control systems and methods |
| US11529532B2 (en) | 2016-04-01 | 2022-12-20 | Varian Medical Systems, Inc. | Radiation therapy systems and methods |
| US11534625B2 (en) | 2019-03-06 | 2022-12-27 | Varian Medical Systems, Inc. | Radiation treatment based on dose rate |
| US11541252B2 (en) | 2020-06-23 | 2023-01-03 | Varian Medical Systems, Inc. | Defining dose rate for pencil beam scanning |
| US11554271B2 (en) | 2019-06-10 | 2023-01-17 | Varian Medical Systems, Inc | Flash therapy treatment planning and oncology information system having dose rate prescription and dose rate mapping |
| US11590364B2 (en) | 2017-07-21 | 2023-02-28 | Varian Medical Systems International Ag | Material inserts for radiation therapy |
| US11673003B2 (en) | 2017-07-21 | 2023-06-13 | Varian Medical Systems, Inc. | Dose aspects of radiation therapy planning and treatment |
| US11712579B2 (en) | 2017-07-21 | 2023-08-01 | Varian Medical Systems, Inc. | Range compensators for radiation therapy |
| US11766574B2 (en) | 2017-07-21 | 2023-09-26 | Varian Medical Systems, Inc. | Geometric aspects of radiation therapy planning and treatment |
| US11857805B2 (en) | 2017-11-16 | 2024-01-02 | Varian Medical Systems, Inc. | Increased beam output and dynamic field shaping for radiotherapy system |
| US11865361B2 (en) | 2020-04-03 | 2024-01-09 | Varian Medical Systems, Inc. | System and method for scanning pattern optimization for flash therapy treatment planning |
| US11957934B2 (en) | 2020-07-01 | 2024-04-16 | Siemens Healthineers International Ag | Methods and systems using modeling of crystalline materials for spot placement for radiation therapy |
| US11986677B2 (en) | 2017-07-21 | 2024-05-21 | Siemens Healthineers International Ag | Triggered treatment systems and methods |
| US12023519B2 (en) | 2022-02-25 | 2024-07-02 | Siemens Healthineers International Ag | Radiation treatment planning for delivering high dose rates to spots in a target |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105854191A (en) * | 2016-04-26 | 2016-08-17 | 中国科学院合肥物质科学研究院 | System and method for three-dimensional dose verification in radiosurgery |
| US20180272152A1 (en) * | 2017-03-22 | 2018-09-27 | Varian Medical Systems International Ag. | Systems and methods for dose calculation in generating radiation treatment plans |
| 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 |
| CN109147952A (en) * | 2018-09-19 | 2019-01-04 | 泰山医学院 | A kind of Radiotherapy dosimetry verification method, processor and system |
-
2019
- 2019-04-30 CN CN201910360026.XA patent/CN109966662B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105854191A (en) * | 2016-04-26 | 2016-08-17 | 中国科学院合肥物质科学研究院 | System and method for three-dimensional dose verification in radiosurgery |
| US20180272152A1 (en) * | 2017-03-22 | 2018-09-27 | Varian Medical Systems International Ag. | Systems and methods for dose calculation in generating radiation treatment plans |
| 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 |
| CN109147952A (en) * | 2018-09-19 | 2019-01-04 | 泰山医学院 | A kind of Radiotherapy dosimetry verification method, processor and system |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11529532B2 (en) | 2016-04-01 | 2022-12-20 | Varian Medical Systems, Inc. | Radiation therapy systems and methods |
| US11712579B2 (en) | 2017-07-21 | 2023-08-01 | Varian Medical Systems, Inc. | Range compensators for radiation therapy |
| US11986677B2 (en) | 2017-07-21 | 2024-05-21 | Siemens Healthineers International Ag | Triggered treatment systems and methods |
| US11766574B2 (en) | 2017-07-21 | 2023-09-26 | Varian Medical Systems, Inc. | Geometric aspects of radiation therapy planning and treatment |
| US11673003B2 (en) | 2017-07-21 | 2023-06-13 | Varian Medical Systems, Inc. | Dose aspects of radiation therapy planning and treatment |
| US11590364B2 (en) | 2017-07-21 | 2023-02-28 | Varian Medical Systems International Ag | Material inserts for radiation therapy |
| US11478664B2 (en) | 2017-07-21 | 2022-10-25 | Varian Medical Systems, Inc. | Particle beam gun control systems and methods |
| US11857805B2 (en) | 2017-11-16 | 2024-01-02 | Varian Medical Systems, Inc. | Increased beam output and dynamic field shaping for radiotherapy system |
| US11348755B2 (en) | 2018-07-25 | 2022-05-31 | Varian Medical Systems, Inc. | Radiation anode target systems and methods |
| US11854761B2 (en) | 2018-07-25 | 2023-12-26 | Varian Medical Systems, Inc. | Radiation anode target systems and methods |
| US11116995B2 (en) | 2019-03-06 | 2021-09-14 | Varian Medical Systems, Inc. | Radiation treatment planning based on dose rate |
| US11534625B2 (en) | 2019-03-06 | 2022-12-27 | Varian Medical Systems, Inc. | Radiation treatment based on dose rate |
| US11090508B2 (en) | 2019-03-08 | 2021-08-17 | Varian Medical Systems Particle Therapy Gmbh & Co. Kg | System and method for biological treatment planning and decision support |
| US11103727B2 (en) | 2019-03-08 | 2021-08-31 | Varian Medical Systems International Ag | Model based PBS optimization for flash therapy treatment planning and oncology information system |
| US11554271B2 (en) | 2019-06-10 | 2023-01-17 | Varian Medical Systems, Inc | Flash therapy treatment planning and oncology information system having dose rate prescription and dose rate mapping |
| US11865364B2 (en) | 2019-06-10 | 2024-01-09 | Varian Medical Systems, Inc. | Flash therapy treatment planning and oncology information system having dose rate prescription and dose rate mapping |
| CN110338906A (en) * | 2019-07-10 | 2019-10-18 | 清华大学深圳研究生院 | Smart therapeutics system and method for building up for photo-crosslinking operation |
| JP2022530413A (en) * | 2019-09-26 | 2022-06-29 | ベイジン・センスタイム・テクノロジー・デベロップメント・カンパニー・リミテッド | Image processing methods and equipment, electronic devices, storage media and computer programs |
| CN110705626A (en) * | 2019-09-26 | 2020-01-17 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| WO2021057174A1 (en) * | 2019-09-26 | 2021-04-01 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, electronic device, storage medium, and computer program |
| US11986672B2 (en) | 2019-10-03 | 2024-05-21 | Siemens Healthineers International Ag | Radiation treatment planning for delivering high dose rates to spots in a target |
| US11291859B2 (en) | 2019-10-03 | 2022-04-05 | Varian Medical Systems, Inc. | Radiation treatment planning for delivering high dose rates to spots in a target |
| CN111388879A (en) * | 2020-03-19 | 2020-07-10 | 上海联影医疗科技有限公司 | Radiation dose determination system, radiation dose determination device and storage medium |
| CN111388879B (en) * | 2020-03-19 | 2022-06-14 | 上海联影医疗科技股份有限公司 | Radiation dose determination system, radiation dose determination device and storage medium |
| US11865361B2 (en) | 2020-04-03 | 2024-01-09 | Varian Medical Systems, Inc. | System and method for scanning pattern optimization for flash therapy treatment planning |
| CN111540437A (en) * | 2020-04-23 | 2020-08-14 | 北京大学第三医院（北京大学第三临床医学院） | Dose verification method and system based on artificial intelligence |
| US11541252B2 (en) | 2020-06-23 | 2023-01-03 | Varian Medical Systems, Inc. | Defining dose rate for pencil beam scanning |
| US11957934B2 (en) | 2020-07-01 | 2024-04-16 | Siemens Healthineers International Ag | Methods and systems using modeling of crystalline materials for spot placement for radiation therapy |
| 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 |
| US12023519B2 (en) | 2022-02-25 | 2024-07-02 | Siemens Healthineers International Ag | Radiation treatment planning for delivering high dose rates to spots in a target |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109966662B (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109966662A (en) | A kind of method and system for verifying radiotherapy dosage | |
| US11386557B2 (en) | Systems and methods for segmentation of intra-patient medical images | |
| US11869202B2 (en) | Method and system for processing multi-modality image | |
| Men et al. | More accurate and efficient segmentation of organs‐at‐risk in radiotherapy with convolutional neural networks cascades | |
| Peng et al. | A method of rapid quantification of patient‐specific organ doses for CT using deep‐learning‐based multi‐organ segmentation and GPU‐accelerated Monte Carlo dose computing | |
| Gao et al. | Prostate segmentation by sparse representation based classification | |
| EP3195257B1 (en) | Systems and methods for segmenting medical images based on anatomical landmark-based features | |
| Pillai et al. | Using artificial intelligence to improve the quality and safety of radiation therapy | |
| EP3268931B1 (en) | Method and apparatus for assessing image registration | |
| WO2017066247A1 (en) | Pseudo-ct generation from mr data using a feature regression model | |
| EP3362146A1 (en) | Pseudo-ct generation from mr data using tissue parameter estimation | |
| CN106846317A (en) | A kind of feature based extracts the method for retrieving medicine image with Similarity matching | |
| CN110604550A (en) | Prediction method of normal tissue organ complications after tumor radiotherapy | |
| Ebert et al. | Spatial descriptions of radiotherapy dose: normal tissue complication models and statistical associations | |
| Abdollahi et al. | Radiomics-guided radiation therapy: opportunities and challenges | |
| CN103518194A (en) | Knowledge-based automatic image segmentation | |
| Bibault et al. | Artificial intelligence in oncology | |
| Adrien‐Maxence et al. | Comparison of error rates between four pretrained DenseNet convolutional neural network models and 13 board‐certified veterinary radiologists when evaluating 15 labels of canine thoracic radiographs | |
| Krawczyk et al. | Segmentation of bone structures with the use of deep learning techniques | |
| Sobecki et al. | MRI imaging texture features in prostate lesions classification | |
| Zhao et al. | [Retracted] Application of Artificial Intelligence in Radiotherapy of Nasopharyngeal Carcinoma with Magnetic Resonance Imaging | |
| Ni et al. | Fast VMAT planning for prostate radiotherapy: dosimetric validation of a deep learning-based initial segment generation method | |
| Vazquez et al. | A deep learning-based approach for statistical robustness evaluation in proton therapy treatment planning: a feasibility study | |
| Bi et al. | Automated thresholded region classification using a robust feature selection method for PET-CT | |
| Ip et al. | Current landscape and potential future applications of artificial intelligence in medical physics and radiotherapy |
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 |