CN114344737A - Tumor radiotherapy control system and storage medium - Google Patents
Tumor radiotherapy control system and storage medium Download PDFInfo
- Publication number
- CN114344737A CN114344737A CN202210019456.7A CN202210019456A CN114344737A CN 114344737 A CN114344737 A CN 114344737A CN 202210019456 A CN202210019456 A CN 202210019456A CN 114344737 A CN114344737 A CN 114344737A
- Authority
- CN
- China
- Prior art keywords
- target area
- tumor
- dose
- risk
- organs
- 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.)
- Pending
Links
- 206010028980 Neoplasm Diseases 0.000 title claims abstract description 219
- 238000001959 radiotherapy Methods 0.000 title claims abstract description 70
- 210000000920 organ at risk Anatomy 0.000 claims abstract description 112
- 238000012545 processing Methods 0.000 claims abstract description 53
- 210000000056 organ Anatomy 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000003384 imaging method Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 2
- 230000002829 reductive effect Effects 0.000 abstract description 4
- 230000005855 radiation Effects 0.000 description 8
- 210000001519 tissue Anatomy 0.000 description 8
- 238000013461 design Methods 0.000 description 7
- 238000009826 distribution Methods 0.000 description 7
- 201000011510 cancer Diseases 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 3
- 206010067484 Adverse reaction Diseases 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 2
- 230000006838 adverse reaction Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 231100000419 toxicity Toxicity 0.000 description 2
- 230000001988 toxicity Effects 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 208000004232 Enteritis Diseases 0.000 description 1
- 201000008808 Fibrosarcoma Diseases 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 1
- 206010060862 Prostate cancer Diseases 0.000 description 1
- 208000000236 Prostatic Neoplasms Diseases 0.000 description 1
- 206010037765 Radiation pneumonitis Diseases 0.000 description 1
- 210000003815 abdominal wall Anatomy 0.000 description 1
- 238000002679 ablation Methods 0.000 description 1
- 208000009956 adenocarcinoma Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002512 chemotherapy Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000002721 intensity-modulated radiation therapy Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 201000005202 lung cancer Diseases 0.000 description 1
- 208000020816 lung neoplasm Diseases 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 208000006178 malignant mesothelioma Diseases 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000000693 radiobiological effect Effects 0.000 description 1
- 230000003439 radiotherapeutic effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007086 side reaction Methods 0.000 description 1
- 206010041823 squamous cell carcinoma Diseases 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 210000001541 thymus gland Anatomy 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 206010044412 transitional cell carcinoma Diseases 0.000 description 1
- 208000026517 ureter neoplasm Diseases 0.000 description 1
- 201000011476 ureteral benign neoplasm Diseases 0.000 description 1
Images
Landscapes
- Radiation-Therapy Devices (AREA)
Abstract
The invention discloses a tumor radiotherapy control system and a storage medium, wherein the system comprises: the dose prediction module is used for inputting the image of the patient and the structure set containing the pushed target area, the tumor target area and the region of the endangered organ in the image into the dose prediction model so as to carry out prediction processing on the dose indexes borne by the tumor and the endangered organ by utilizing the dose prediction model; the judging module is used for judging whether the predicted dose indexes borne by the tumor and the organs at risk meet the plan requirements or not; and the optimization and adjustment module is used for automatically adjusting the pushed target area within the range of the tumor target area when the planning requirement is not met, and after the adjusted pushed target area is obtained by the optimization and adjustment module, the prediction processing and the judgment processing are repeated until the predicted dose indexes of the tumor and the organs at risk meet the planning requirement, so that the time of a planning process is shortened, the consistency of the planning quality is improved, and the planning cost is reduced.
Description
Technical Field
The invention relates to the field of medical instruments, in particular to a tumor radiotherapy control system and a storage medium.
Background
The tumor burden refers to the number of cancer cells, the size of tumor and the total number of cancer lesions in human body, generally, the tumor burden of cancer patients is large, the cancer patients have close relationship with surrounding normal tissues, the internal blood supply is insufficient, and the effects of surgery, chemotherapy and conventional segmentation radiotherapy (short for radiotherapy) are unsatisfactory. Radiation oncologists have been working to develop new tumor radiotherapy protocols to address this problem for the last several decades.
In tumor radiotherapy, the Biologically Effective Dose (BED) refers to the total Dose required for a given regimen to produce the same cell kill at infinitely low Dose rates or at infinitely small doses; physical dose refers to the radiation dose absorbed by the human body; the tumor target area refers to a ray irradiation area formed after a certain distance is expanded outside a tumor area visible for an image and is used for radiotherapy plan design; the tumor extrapolated target area (abbreviated as extrapolated target area, GTVb) refers to an area in the tumor target area where the radiation dose is increased; tissue or Organ At Risk (OAR) refers to human tissue or Organ that needs protection during radiation therapy.
According to the radiobiological theory, the higher the BED of the tumor region, the higher the local control rate, and the better the tumor radiotherapy effect. Stereotactic Ablation Radiotherapy (SABR) is a novel Radiotherapy method that can accurately deliver high-dose radiation to a tumor target region, and the BED of the tumor region is obviously improved. However, due to dose limitations of adjacent tissues and organs, SABR is generally considered to be applicable only to small tumors. The reason is that as the tumor volume increases, the tumor is often closely related to surrounding normal tissues, the toxic reaction of the SABR to the whole tumor is large, and the risk of radiation side reactions such as radiation pneumonitis and radiation enteritis of patients is greatly increased.
In order to solve the problems of the SABR, Partial SABR (P-SABR) appears, and the P-SABR can improve the BED of the tumor to the maximum extent on the premise of not increasing the OAR receiving quantity, thereby achieving the purpose of improving the local control rate of the tumor with equal toxicity (namely under the condition that the radiotherapy side effects of patients are the same). Specifically, P-SABR is a modified treatment scheme combining Conventional Fractionated Radiation Therapy (CFRT) with SABR, and the embodiment scheme is as follows: the first program applies SABR to deliver maximum local thrust in the tumor, i.e. to deliver higher dose to one or more regions within the tumor region than to the surrounding regions, as shown in fig. 1a, where the larger closed region is the whole tumor region and one of the smaller closed regions is the designated region, i.e. the thrust target region; the second pass uses CFRT to complement the prescribed dose for the full tumor area, as shown in fig. 1b, where the larger enclosed area is the full tumor area. In clinic, P-SABR has been applied to cancers of various pathological types such as squamous carcinoma, adenocarcinoma, fibrosarcoma, transitional cell carcinoma, malignant mesothelioma, and the like. When used for treating tumors of multiple parts of the whole body, such as ureteral tumors, lung cancer, thymus gland cancer, abdominal wall tumor, prostatic cancer and the like, the traditional Chinese medicine composition has obvious curative effect, obviously improves local control rate and has low incidence rate of adverse reaction.
However, in practical applications, the P-SABR plan includes iterative steps based on dose (including physical dose and/or bio-effective dose) determination, and the work flow is quite complex, as shown in fig. 2, and mainly includes: patient positioning CT and other image data import and registration, GTVb and other structure delineation, plan design, dose calculation, plan evaluation, GTVb adjustment based on the evaluation results, and plan output. In the P-SABR program, the range of GTvb is crucial to improve the BED of a tumor region, and clinical application mainly depends on the empirical evaluation of tumors, especially macro-block tumors and adjacent OARs by senior radiotherapists and then manual delineation. Then, the radiotherapy doctor needs to deliver the structure set containing GTvb and other organs to the radiotherapy physicist for calculation to obtain the dose indexes of tumor and OAR. The clinician evaluates, modifies (e.g., enlarges or reduces) the range of GTVb based on the dose indices of tumor and OAR until the dose indices of tumor and OAR meet the clinical requirement, i.e., the dose index of tumor reaches the prescribed dose and the dose index of OAR is below the clinical dose index limit. This procedure is often repeated several times or even ten times, taking 8-20 working days, in order to maximize the in-tumor BED without increasing the radiotherapeutic toxicity of normal tissues.
It is clear that the P-SABR planning procedure suffers from the following problems:
1. the extrapolated target area range cannot be quantified.
In practice, the target area is manually delineated by the clinician according to experience. The target area is sketched out too much, which can cause the dosage of surrounding normal organs to increase and generate adverse reactions caused by radiotherapy; too small delineation, insignificant increase in BED in the tumor area, and poor local control of the tumor. In clinic, iterative calculation and modification of the target range are often needed to find the limit range of the target to be increased.
2. The quality is not consistent.
The planning stage involves subjective judgment of a large number of physicists and manual operation of clinicians, so that the planning quality is poor and the diversity is large, and the popularization and the use of the P-SABR are not easy.
3. The planning cost is high.
The mapping of the target area and the adjustment of the range require doctors and physicists to spend a lot of time, and the balance between the improvement of the BED and the protection of normal organs is constant. Meanwhile, the high-intensity and high-requirement planning and design work can cause the clinical workers to have reactions such as fatigue and anxiety in the actual work, and influence the clinical radiotherapy process. Namely, the time cost and the economic cost are high.
Disclosure of Invention
Embodiments of the present invention provide a tumor radiotherapy control system and a storage medium to solve the above problems.
An embodiment of the present invention provides a tumor radiotherapy control system, which includes: the dose prediction module is used for inputting the image of the patient and the structure set containing the pushed target area, the tumor target area and the region of the endangered organ in the image into the dose prediction model so as to carry out prediction processing on the dose indexes borne by the tumor and the endangered organ by utilizing the dose prediction model; the judging module is used for judging whether the predicted dose indexes borne by the tumor and the organs at risk meet the plan requirements or not; the optimization and adjustment module is used for automatically adjusting the pushed target area within the range of the tumor target area to obtain an adjusted pushed target area when the predicted dose indexes of the tumor and the organs at risk do not meet the plan requirement; after the optimized adjustment module obtains the adjusted pushed target area, the prediction processing of the dose prediction module and the judgment processing of the judgment module are repeated until the dose indexes of the tumor and the organs at risk predicted by the dose prediction module meet the plan requirement.
Preferably, the dose prediction module is further configured to train the dose prediction model by using historical data to obtain a trained dose prediction model, so as to perform prediction processing by using the trained dose prediction model; wherein the historical data comprises: the method comprises the steps of imaging images of historical patients, structural sets containing a thrust target area, a tumor target area and a region where an organ at risk is located in the imaging images, and dose indexes of tumors and organs at risk meeting planning requirements.
Preferably, the pushed target area during the first prediction processing is the tumor target area, and the optimization adjustment module is specifically configured to divide the pushed target area by taking a geometric center of the pushed target area as a centroid and taking a first preset angle as an interval, so as to obtain a plurality of first division lines; taking a position point where each first dividing line is intersected with the edge of the pushed target area as a starting point, and moving the first dividing line where the starting point is located to the centroid by a first preset distance to obtain a new position point; and determining the closed area obtained after the adjacent new position points are connected pairwise as the adjusted estimated target area so as to repeat the prediction processing of the dose prediction module and the judgment processing of the judgment module until the dose indexes of the tumor and the organs at risk predicted by the dose prediction module meet the plan requirement, and determining the corresponding estimated target area as the estimated target area for the radiotherapy of the patient.
Preferably, the optimization adjustment module is specifically configured to, when the pushed target area is within the range of the tumor target area and dose indexes of the tumor and the organs at risk predicted based on the pushed target area meet plan requirements, divide the pushed target area by taking a geometric center of the pushed target area as a centroid and a second preset angle as an interval to obtain a plurality of second dividing lines; taking a position point where each second dividing line intersects with the edge of the pushed target area as a starting point, and moving the edge of the tumor target area by a second preset distance along the second dividing line where the starting point is located to obtain a new position point; and determining the closed area obtained after the adjacent new position points are connected pairwise as the adjusted estimated target area so as to repeat the prediction processing of the dose prediction module and the judgment processing of the judgment module until the judgment module determines that the dose indexes of the tumor and the organs at risk predicted by the dose prediction module do not meet the plan requirements, and determining the estimated target area which can meet the plan requirements before adjustment as the estimated target area for the radiotherapy of the patient.
Preferably, the system further comprises: the transmission module is used for transmitting a structure set containing corresponding pushed target areas, tumor target areas and regions where the organs at risk are located in the image images to a radiotherapy planning system when the dose indexes borne by the tumors and the organs at risk meet the planning requirements; or when the dose indexes of the tumor and the organs at risk predicted based on the pre-adjustment estimated target area do not meet the plan requirements and the adjusted estimated target area is not completely within the range of the tumor target area, transmitting a structural set containing the pre-adjustment estimated target area, the tumor target area and the region of the organs at risk in the image to a radiotherapy planning system.
Preferably, the volume of the tumor is greater than or equal to 5 cubic centimeters.
An embodiment of the present invention provides a storage medium, where a program is stored on the storage medium, and when the program is executed by a processor, the program implements the following steps: inputting an image of a patient and a structure set containing a thrust target area, a tumor target area and a region where an organ at risk is located in the image into a dose prediction model so as to perform prediction processing on dose indexes borne by the tumor and the organ at risk by using the dose prediction model; judging whether the predicted dose indexes of the tumor and the organs at risk meet the planning requirements or not; and when the predicted dose indexes of the tumor and the organs at risk do not meet the planning requirement, automatically adjusting the pushed target area within the range of the tumor target area to obtain an adjusted pushed target area, and repeating the prediction treatment and the judgment treatment after obtaining the adjusted pushed target area until the predicted dose indexes of the tumor and the organs at risk meet the planning requirement.
Preferably, the extrapolated target area at the time of the first prediction treatment is the tumor target area, and the program stored on the storage medium, when executed by the processor, specifically implements the steps of: dividing the pushed target area by taking the geometric center of the pushed target area as a centroid and taking a first preset angle as an interval to obtain a plurality of first dividing lines; taking a position point where each first dividing line is intersected with the edge of the pushed target area as a starting point, and moving the first dividing line where the starting point is located to the centroid by a first preset distance to obtain a new position point; determining a closed area obtained after the adjacent new position points are connected pairwise as an adjusted estimated target area; and repeating the prediction processing and the judgment processing until the predicted dose indexes of the tumor and the organs at risk meet the plan requirement, and determining the corresponding target volume of the estimated volume as the target volume of the estimated volume for the radiotherapy of the patient.
Preferably, the program stored on the storage medium, when executed by the processor, embodies the steps of: when the pushed target area is within the range of the tumor target area and the dose indexes of the tumor and the organs at risk predicted based on the pushed target area meet the plan requirements, dividing the pushed target area by taking the geometric center of the pushed target area as a centroid and a second preset angle as an interval to obtain a plurality of second dividing lines; taking a position point where each second dividing line intersects with the edge of the pushed target area as a starting point, and moving the edge of the tumor target area by a second preset distance along the second dividing line where the starting point is located to obtain a new position point; determining a closed area obtained after the adjacent new position points are connected pairwise as an adjusted estimated target area; and repeating the prediction processing and the judgment processing until the predicted dose indexes of the tumor and the organs at risk do not meet the plan requirement, and determining the adjusted estimated target area which can meet the plan requirement as the estimated target area for the radiotherapy of the patient.
Preferably, the program stored on the storage medium, when executed by the processor, further implements the steps of: when the dose indexes borne by the tumor and the organs at risk meet the planning requirements, transmitting a structure set containing corresponding pushed target areas, tumor target areas and the regions of the organs at risk in the image images to a radiotherapy planning system; or when the dose indexes of the tumor and the organs at risk predicted based on the pre-adjustment estimated target area do not meet the plan requirements and the adjusted estimated target area is not completely within the range of the tumor target area, transmitting a structural set containing the pre-adjustment estimated target area, the tumor target area and the region of the organs at risk in the image to a radiotherapy planning system.
According to the tumor radiotherapy control system and the storage medium provided by the embodiment of the invention, the dose indexes borne by the tumor and the organs at risk are predicted by using the dose prediction model, the pushed target area is automatically adjusted when the predicted dose indexes borne by the tumor and the organs at risk do not meet the planning requirement, and the pushed target area with proper size and position can be quickly and accurately and automatically determined through continuous prediction, judgment and automatic adjustment processes, so that the dose indexes borne by the tumor and the organs at risk meet the planning requirement, the time of a planning process is shortened, the consistency of the planning quality is improved, and the planning cost is reduced.
Drawings
FIG. 1a is a diagram of a practical case applying the SABR plan;
FIG. 1b is a diagram of a practical case in which the CFRT plan is applied;
FIG. 2 is a flow chart of clinical P-SABR planning;
FIG. 3 is a block diagram of a schematic structure of a tumor radiotherapy control system provided by an embodiment of the present invention;
FIG. 4 is a flow chart of dose prediction provided by an embodiment of the present invention;
FIG. 5 is a flow chart of optimization tuning provided by an embodiment of the present invention;
FIG. 6 is a graph illustrating a moving pattern of coordinate points of the inferred target area according to an embodiment of the present invention;
FIG. 7 is a flow chart of tumor radiation therapy control provided by an embodiment of the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the following description, suffixes such as "module", "part", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no peculiar meaning in itself. Thus, "module", "component" or "unit" may be used mixedly.
Example one
Fig. 3 is a schematic block diagram of a tumor radiotherapy control system according to an embodiment of the present invention, and the system includes a dose prediction module, a determination module, and an optimization adjustment module, as shown in fig. 3.
One, the dose prediction module
The dose prediction module is used for inputting the image of the patient and the structure set containing the thrust target area, the tumor target area and the region of the endangered organ in the image into the dose prediction model so as to carry out prediction processing on the dose indexes of the tumor and the endangered organ by utilizing the dose prediction model.
In addition, the dose prediction module is further configured to train the dose prediction model by using historical data to obtain a trained dose prediction model, so as to perform prediction processing by using the trained dose prediction model; wherein the historical data comprises: the method comprises the steps of imaging images of historical patients, structural sets containing a thrust target area, a tumor target area and a region where an organ at risk is located in the imaging images, and dose indexes of tumors and organs at risk meeting planning requirements.
The dose prediction model may employ a deep learning model such as a convolutional neural network, a cyclic neural network, a long-short term memory network, a U-Net, and the like.
Wherein, the image includes but is not limited to CT image, nuclear magnetic resonance image.
Wherein the structural set containing the thrust target area, the tumor target area and the region where the organ at risk is located in the image is obtained after the thrust target area, the tumor target area and the region where the organ at risk is located are delineated in the image. The image can be sketched in a manual sketching mode, an automatic sketching mode or a manual and automatic combined sketching mode if necessary.
II, the judging module
And the judging module is used for judging whether the predicted dose indexes of the tumor and the organs at risk meet the plan requirements or not. Specifically, the determination module determines whether the predicted dose index experienced by the tumor reaches the prescribed dose and whether the predicted dose index experienced by the organ at risk is below a clinical dose limit.
Thirdly, the optimization adjustment module
And the optimization and adjustment module is used for automatically adjusting the pushed target area within the range of the tumor target area to obtain the adjusted pushed target area when the predicted dosage indexes of the tumor and the organs at risk do not meet the plan requirements. After the optimized adjustment module obtains the adjusted pushed target area each time, the prediction processing of the dose prediction module and the judgment processing of the judgment module are repeated until the dose indexes of the tumor and the organs at risk predicted by the dose prediction module meet the plan requirement.
In a first embodiment, the target volume to be pushed for the first prediction processing is the target volume to be tumor, and the optimization and adjustment module finds a suitable target volume to be pushed by continuously reducing the range of the target volume to be pushed, specifically, the optimization and adjustment module divides the target volume to be pushed by taking the geometric center of the target volume to be pushed as the centroid and taking a first preset angle as an interval, so as to obtain a plurality of first division lines; taking a position point where each first dividing line is intersected with the edge of the pushed target area as a starting point, and moving the first dividing line where the starting point is located to the centroid by a first preset distance to obtain a new position point; and determining the closed area obtained after the adjacent new position points are connected pairwise as the adjusted estimated target area so as to repeat the prediction processing of the dose prediction module and the judgment processing of the judgment module until the dose indexes of the tumor and the organs at risk predicted by the dose prediction module meet the plan requirement, and determining the corresponding estimated target area as the estimated target area for the radiotherapy of the patient.
Wherein the first preset angle may be any angle between 0 and 10 degrees, for example, 5 degrees. The first preset angle may be the same each time the pushing target area is adjusted, for example, the first preset angle is 5 degrees, but the positions of the first dividing lines of any two adjustments are random. Of course, the first preset angle may be different, for example, the first preset angle may be 5 degrees in the first adjustment, and the first preset angle may be 4 degrees in the second adjustment. The embodiment of the present invention is not limited thereto.
Wherein the first predetermined distance may be any distance between 0-10mm, for example 5 mm. When the thrust target area is adjusted each time, the first preset distance may be the same, for example, the first preset distance is 5mm, and the first preset distance may also be different, for example, the first preset distance may be 5mm during the first adjustment, and the first preset distance may be 4mm during the second adjustment. The embodiment of the present invention is not limited thereto.
Generally, the smaller the first preset angle is, the smaller the first preset distance is, the more optimal the found pushed amount target area is, and specific numerical values of the first preset angle and the first preset distance may be set according to circumstances in specific implementation.
In addition, all the first dividing lines may be located in the same plane, for example, the horizontal plane is divided by a first preset angle, and all the obtained first dividing lines are located in the horizontal plane. The first dividing line may also be located in the three-dimensional space, for example, starting with the centroid, and dividing the three-dimensional space at intervals of a first preset angle.
In a second embodiment, the pushed target area during the first prediction processing is within the range of the tumor target area, and the optimization and adjustment module divides the pushed target area by taking the geometric center of the pushed target area as the centroid and a second preset angle as an interval when the pushed target area is within the range of the tumor target area and the dose indexes of the tumor and the organs at risk predicted based on the pushed target area meet the plan requirements, so as to obtain a plurality of second dividing lines; taking a position point where each second dividing line intersects with the edge of the pushed target area as a starting point, and moving the edge of the tumor target area by a second preset distance along the second dividing line where the starting point is located to obtain a new position point; and determining the closed area obtained after the adjacent new position points are connected pairwise as the adjusted estimated target area so as to repeat the prediction processing of the dose prediction module and the judgment processing of the judgment module until the judgment module determines that the dose indexes of the tumor and the organs at risk predicted by the dose prediction module do not meet the plan requirements, and determining the estimated target area which can meet the plan requirements before adjustment as the estimated target area for the radiotherapy of the patient.
Wherein the second preset angle may be any angle between 0 and 10 degrees, for example, 5 degrees. The second predetermined angle may be the same each time the thrust target area is adjusted, for example, the second predetermined angle is 5 degrees, but the positions of the first dividing lines adjusted at any two times are random. Of course, the second preset angle may be different, for example, the second preset angle may be 5 degrees in the first adjustment, and the second preset angle may be 4 degrees in the second adjustment. The embodiment of the present invention is not limited thereto.
Wherein the second predetermined distance may be any distance between 0-10mm, for example 5 mm. When the pushing target area is adjusted each time, the second preset distance may be the same, for example, the second preset distance is 5mm, the second preset distance may also be different, for example, the second preset distance may be 5mm during the first adjustment, and the second preset distance may be 4mm during the second adjustment. The embodiment of the present invention is not limited thereto.
Generally, the smaller the second preset angle is, the smaller the second preset distance is, the more optimal the found pushed amount target area is, and specific values of the second preset angle and the second preset distance may be set according to circumstances in specific implementation.
In addition, all the second dividing lines may be located in the same plane, for example, the horizontal plane is divided by a second preset angle, and all the second dividing lines are located in the horizontal plane. The second division line may also be located in the three-dimensional space, for example, starting with the centroid, and dividing the three-dimensional space at intervals of a second preset angle.
In a third embodiment, the two aforementioned embodiments may be combined, specifically, the first embodiment is performed, for example, by taking a tumor target area as a target volume, continuously reducing the range of the target volume based on a first preset angle and a first preset distance until the dose prediction module meets the planning requirement according to the dose indexes of the tumor and the organs at risk predicted by the reduced target volume, and recording the target volume used in the current prediction, which is denoted as the first target volume for convenience of description. Then, the method is performed according to the second embodiment, for example, based on a second preset angle and a second preset distance, the range is continuously expanded on the basis of the first pushed target area until the dose prediction module predicts that the dose index of the tumor and the organ at risk according to the expanded pushed target area does not meet the plan requirement, at this time, the pushed target area used in the current prediction is not appropriate, and the pushed target area used in the previous prediction should be adopted.
The first preset angle is greater than the second preset angle, and the first preset distance is greater than the second preset distance.
The system further comprises a transmitting module (not shown in the figure) for communicating with the radiotherapy planning system, and in particular for transmitting a structural set containing corresponding thrust target, tumor target and the region of the organ at risk in the image to the radiotherapy planning system when the dose index of the tumor and the organ at risk meets the planning requirement; or when the dose indexes of the tumor and the organs at risk predicted based on the pre-adjustment estimated target area do not meet the plan requirements and the adjusted estimated target area is not completely within the range of the tumor target area, transmitting a structural set containing the pre-adjustment estimated target area, the tumor target area and the region of the organs at risk in the image to a radiotherapy planning system.
The system provided by the embodiment of the invention carries out prediction processing and judgment processing based on the new structure set of the updated estimation target area, can quickly find out the position of the appropriate estimation target area, is suitable for tumors with all volumes, and is particularly suitable for tumors with the volume of more than or equal to 5 cubic centimeters.
The tumor radiotherapy control system provided by the embodiment of the invention carries out prediction processing on the dose indexes borne by the tumor and the organs at risk by using the dose prediction model, automatically adjusts the pushed target area when the predicted dose indexes borne by the tumor and the organs at risk do not meet the planning requirement, and can quickly, accurately and automatically determine the pushed target area with proper size and position by continuously carrying out the processes of prediction, judgment and automatic adjustment, so that the dose indexes borne by the tumor and the organs at risk meet the planning requirement, the time of the planning process is shortened, the consistency of the planning quality is improved, and the planning cost is reduced.
Example 2
In order to overcome the defects that the target area range cannot be quantized, the quality is not uniform and the time is consumed in the design of a P-SABR plan, the embodiment of the invention applies deep learning to the design of a clinical radiotherapy plan and assists the design of a target area by means of artificial intelligence. In the designed P-SABR plan, the delineation range of a P-SABR estimated target area and dose data established by the target area and the set dose are stored, the target area and the dose are deeply learned in the conventional P-SABR plan to obtain a dose prediction model for predicting the radiotherapy dose, and then the optimal target area range meeting the dose limit is searched by means of strong calculation and self-learning capacity of a computer, so that the aim of automatically generating the optimized target area is fulfilled, the equivalent biological dose of the tumor is greatly increased, the risk of normal organ tissues around the tumor is not increased, and a solution is provided for clinically and safely and efficiently formulating the radiotherapy plan. In addition, the limitation of equipment and experience among hospitals and doctors is solved, and the possibility is provided for further popularization of the radiotherapy method.
The present invention will be described in detail below with reference to fig. 4 to 6.
Fig. 4 is a flowchart of dose prediction provided by the embodiment of the present invention, as shown in fig. 4, specifically as follows:
step S401: patient image images and dose limit requirements are entered.
The user inputs patient image data including, but not limited to, CT images, magnetic resonance images. The dose limits for the irradiated region and the organs at risk are manually defined in conjunction with patient clinical data and treatment guidelines.
Step S402: the initial thrust target area, the tumor target area and the organs at risk of the patient are manually drawn and/or automatically drawn based on the image.
The automatic sketching method comprises the following steps: automatically segmenting and delineating a planned tumor target area and a endangered organ based on machine learning to generate an initial estimate target area in a planned tumor target area range;
the manual sketching method comprises the following steps: based on the image and the experience of the radiotherapy doctor, an initial thrust target area (a higher irradiation dose is given to a specified area in the tumor area than to the surrounding area), a planned tumor target area (a tumor target area for short, which is an area for radiotherapy planning formed after a solid tumor visible to the image is expanded to a certain extent) and a structure of a compromised organ are manually delineated.
Step S403: data related to the past P-SABR plan, including image and structure set data and dose data, are acquired to construct a dose prediction model (i.e., a physical dose or biological dose model) based on deep learning.
Step S404: the patient data set (i.e., the image and structure set data) is imported into a Dose prediction model, which automatically predicts Dose distributions (i.e., physical Dose or biological Dose distributions) and Dose Volume Histograms (DVH) for tumors and organs-at-risk.
The dose prediction module imports a historical P-SABR plan comprising data such as images, a structure set (containing files of target areas and regions where organs at risk are located in the images), plans and the like, trains a deep learning model such as a convolutional neural network, a cyclic neural network, a long-short term memory network, a U-Net and the like by using the historical P-SABR plan to learn and establish a correlation between the anatomical positions and the dose (physical dose or biological dose) between the target areas and the organs at risk, and predicts dose indexes of tumors and the organs at risk by using the obtained trained deep learning model as a dose prediction model, specifically, organ dose indexes (namely, volume percentages of different doses on the target areas or OARs), global dose distribution (namely, dose values corresponding to different spatial positions on the images) and the like, DVH plots (i.e., a display plot of the percentage of different doses on the target or OAR).
For a newly entered patient data set, the dose prediction module automatically extracts and organizes the data for dose prediction (i.e., physical dose or biological dose prediction) to obtain the organ dose index, global dose distribution, and DVH map for that patient.
Fig. 5 is a flowchart of optimization adjustment provided in the embodiment of the present invention, as shown in fig. 5, specifically as follows:
step S501: and acquiring the target volume of the pushed amount, the target volume of the tumor and the surrounding organ structures of the tumor.
If the first dose prediction is for the patient, the initial bolus target may be a tumor target.
Step S502: the dose prediction module inputs the image of the patient and the structure set containing the pushed target area, the tumor target area and the surrounding organ structure in the region of the image into the dose prediction model so as to carry out prediction processing on the dose indexes borne by the tumor and the organs at risk by utilizing the dose prediction model.
Step S503: based on the dose limit in step S401 and the prediction result obtained in step S502, it is determined whether the dose index of the organ at risk exceeds the dose limit, if yes, step S504-step S508 are executed, the target volume of the tumor is adjusted by reverse optimization, otherwise, step S509 is executed.
Based on the prediction result of step S502, target dose and organ-at-risk dose limit evaluation is automatically performed on the P-SABR plan, and if in the prediction result, there is an organ-at-risk dose indicator exceeding the dose limit in the aforementioned step S401, e.g., one or more or all organ-at-risk dose indicators are greater than the dose limit, the plan dataset is passed to the optimization adjustment module, otherwise step S509 is performed.
Step S504: the optimization and adjustment module carries out three-dimensional reconstruction on the tissue structure on the image, the geometric center of the initial thrust target area is used as a centroid or a circle center, the horizontal plane is divided in a clockwise 360-degree rotation mode, the interval is n degrees, and n is a natural number which can be evenly divided by 360 degrees.
Step S505: using the center of mass as a starting point, and pushing along each dividing lineThe target area is reversely projected, and the intersection point of the target area and the boundary of the estimated target area is recorded as miWherein i is 1, 2, …, (360 °/n °).
Step S506: calculate each intersection miLinear distance from centroid lmiTaking the distance change interval as kmm, wherein k can be any value within 0-10 mm; m is to beiMoving at equal intervals along the dividing line to obtain ui。
Step S507: judgment uiIf it is in the planned tumor target area, then set u is establishediThe target volume of the estimated volume is updated, and the image and the updated structure set are transmitted to the dose prediction module, so as to execute the dose prediction step of step S503, and to circularly perform the dose prediction and target volume update, otherwise, to execute step S509.
In this embodiment, when calculating the range of the estimated tumor target area, the optimization module defaults to perform the dose evaluation of the organs at risk by using the original tumor target area as the estimated area, if yes, directly performs step S509, and if not, adjusts the range of the estimated target area. For example, as shown in fig. 6, the connecting lines are uniformly arranged at 360-degree clockwise intervals and 5-degree angular intervals around the geometric center 0 of the conventional thrust target region during adjustment. The connecting lines are rays with the geometric center of the target region as an end point. When a connecting line intersects with the boundary of the existing target area, the intersection point is set as miI is 1, 2, …, 72. Then the intersection point miMoving the connecting line to the geometric center 0 by 5mm in the direction of the connecting line, and setting the point at which the connecting line is moved as uiAt this time uiThe distance from the geometric center 0 is denoted as lui. Then l is put inmiAnd miIs set to luiAnd uiAnd based on the above, updating the range of the estimated target area. The structure set of the updated estimated target region is introduced into the dose prediction model to perform dose prediction, that is, step S503 is executed, and if the prediction result does not meet the dose limit value input in step S401, step S504-step S508 are repeatedly executed, otherwise step S509 is executed.
Step S509: and automatically generating an executable radiotherapy plan based on the updated extrapolated target area data, transmitting a structure set file containing the final extrapolated target area back to a radiotherapy planning system during specific implementation, and calculating and generating the executable radiotherapy plan by the radiotherapy planning system. The radiation therapy planning system then outputs a radiation therapy plan and associated reports, including an intensity modulated radiation therapy plan (determining the dose distribution map of the radiation field by inverse design), a stereotactic (using both coplanar and non-coplanar radiation fields) radiation therapy plan.
In actual operation, firstly, image data in a patient Dicom format is imported into the system, the number of times and total dose of irradiation are input, and a generation mode of a radiotherapy target area and a corresponding critical organ is selected. Secondly, the dose and volume requirements to be met by the organs at risk are manually input, the required dose distribution, the dose definition (i.e. the biological dose or the physical dose) in the DVH map are selected, if the physical dose is selected, the physical dose unit required to be displayed is selected, and if the biological dose is selected, the biological model parameter values corresponding to different organs at risk are input. Then, the system determines the maximum range of the estimated target area according to the input parameters, namely the critical organ dose and volume limit value, the image data, the total irradiation dose and the like, completes the generation and writing of the corresponding structure and outputs the structure as a structure set file. And the system outputs a DVH (digital video graphics) graph corresponding to the structure set data, and shows the predicted global dose distribution graph.
EXAMPLE III
Embodiments of the present invention provide a storage medium storing one or more programs for tumor radiation therapy control, the one or more programs being executable by one or more processors to perform the following specific steps as shown in fig. 7:
step S701: and inputting the image of the patient and the structure set containing the thrust target area, the tumor target area and the region of the endangered organ in the image into a dose prediction model so as to carry out prediction processing on the dose indexes borne by the tumor and the endangered organ by utilizing the dose prediction model.
Wherein, the image includes but is not limited to CT image, nuclear magnetic resonance image.
Wherein the structural set containing the thrust target area, the tumor target area and the region where the organ at risk is located in the image is obtained after the thrust target area, the tumor target area and the region where the organ at risk is located are delineated in the image. The image can be sketched in a manual sketching mode, an automatic sketching mode or a manual and automatic combined sketching mode if necessary.
Step S702: and judging whether the predicted dose indexes of the tumor and the organs at risk meet the requirements of the plan.
Specifically, it is determined whether the predicted dose index to the tumor has reached the prescribed dose and the predicted dose index to the organ at risk is below the clinical dose limit.
Step S703: and when the predicted dose indexes of the tumor and the organs at risk do not meet the plan requirement, automatically adjusting the target volume of the pushed amount within the range of the target volume of the tumor to obtain the adjusted target volume of the pushed amount.
Step S704: after the adjusted estimated target area is obtained, the prediction processing and the judgment processing are repeated until the predicted dose indexes of the tumor and the organs at risk meet the plan requirement.
In the first embodiment, the target volume of the estimated volume in the first prediction processing is the target volume of the tumor, and the steps S703 and S704 implemented when the program stored in the storage medium is executed by the processor may specifically be: dividing the pushed target area by taking the geometric center of the pushed target area as a centroid and taking a first preset angle as an interval to obtain a plurality of first dividing lines; taking a position point where each first dividing line is intersected with the edge of the pushed target area as a starting point, and moving the first dividing line where the starting point is located to the centroid by a first preset distance to obtain a new position point; determining a closed area obtained after the adjacent new position points are connected pairwise as an adjusted estimated target area; and repeating the prediction processing and the judgment processing until the predicted dose indexes of the tumor and the organs at risk meet the plan requirement, and determining the corresponding target volume of the estimated volume as the target volume of the estimated volume for the radiotherapy of the patient.
Wherein the first preset angle may be any angle between 0 and 10 degrees, for example, 5 degrees. The first preset angle may be the same each time the pushing target area is adjusted, for example, the first preset angle is 5 degrees, but the positions of the first dividing lines of any two adjustments are random. Of course, the first preset angle may be different, for example, the first preset angle may be 5 degrees in the first adjustment, and the first preset angle may be 4 degrees in the second adjustment. The embodiment of the present invention is not limited thereto.
Wherein the first predetermined distance may be any distance between 0-10mm, for example 5 mm. When the thrust target area is adjusted each time, the first preset distance may be the same, for example, the first preset distance is 5mm, and the first preset distance may also be different, for example, the first preset distance may be 5mm during the first adjustment, and the first preset distance may be 4mm during the second adjustment. The embodiment of the present invention is not limited thereto.
Generally, the smaller the first preset angle is, the smaller the first preset distance is, the more optimal the found pushed amount target area is, and specific numerical values of the first preset angle and the first preset distance may be set according to circumstances in specific implementation.
In addition, all the first dividing lines may be located in the same plane, for example, the horizontal plane is divided by a first preset angle, and all the obtained first dividing lines are located in the horizontal plane. The first dividing line may also be located in the three-dimensional space, for example, starting with the centroid, and dividing the three-dimensional space at intervals of a first preset angle.
In the second embodiment, the target volume of the estimated volume in the first prediction processing is within the target volume of the tumor, and the steps S703 and S704 implemented when the program stored in the storage medium is executed by the processor may specifically be: when the pushed target area is within the range of the tumor target area and the dose indexes of the tumor and the organs at risk predicted based on the pushed target area meet the plan requirements, dividing the pushed target area by taking the geometric center of the pushed target area as a centroid and a second preset angle as an interval to obtain a plurality of second dividing lines; taking a position point where each second dividing line intersects with the edge of the pushed target area as a starting point, and moving the edge of the tumor target area by a second preset distance along the second dividing line where the starting point is located to obtain a new position point; determining a closed area obtained after the adjacent new position points are connected pairwise as an adjusted estimated target area; and repeating the prediction processing and the judgment processing until the predicted dose indexes of the tumor and the organs at risk do not meet the plan requirement, and determining the adjusted estimated target area which can meet the plan requirement as the estimated target area for the radiotherapy of the patient.
Wherein the second preset angle may be any angle between 0 and 10 degrees, for example, 5 degrees. The second predetermined angle may be the same each time the thrust target area is adjusted, for example, the second predetermined angle is 5 degrees, but the positions of the first dividing lines adjusted at any two times are random. Of course, the second preset angle may be different, for example, the second preset angle may be 5 degrees in the first adjustment, and the second preset angle may be 4 degrees in the second adjustment. The embodiment of the present invention is not limited thereto.
Wherein the second predetermined distance may be any distance between 0-10mm, for example 5 mm. When the pushing target area is adjusted each time, the second preset distance may be the same, for example, the second preset distance is 5mm, the second preset distance may also be different, for example, the second preset distance may be 5mm during the first adjustment, and the second preset distance may be 4mm during the second adjustment. The embodiment of the present invention is not limited thereto.
Generally, the smaller the second preset angle is, the smaller the second preset distance is, the more optimal the found pushed amount target area is, and specific values of the second preset angle and the second preset distance may be set according to circumstances in specific implementation.
In addition, all the second dividing lines may be located in the same plane, for example, the horizontal plane is divided by a second preset angle, and all the second dividing lines are located in the horizontal plane. The second division line may also be located in the three-dimensional space, for example, starting with the centroid, and dividing the three-dimensional space at intervals of a second preset angle.
In the third embodiment, the two foregoing embodiments may be combined, and specifically, the steps S703 and S704 implemented when the program stored in the storage medium is executed by the processor may specifically be: first, according to the first embodiment, for example, a tumor target area is used as a target area, the range of the target area is continuously narrowed based on a first preset angle and a first preset distance until the dose indexes of the tumor and the organs at risk predicted by the narrowed target area meet the plan requirements, and the target area used in the prediction is recorded, and for convenience of description, the target area is recorded as the first target area. Then, the method is performed according to the second embodiment, for example, based on the second preset angle and the second preset distance, the range is continuously expanded on the basis of the first estimation target area until the dose indexes of the tumor and the organs at risk predicted according to the expanded estimation target area do not meet the plan requirements, at this time, the estimation target area used in the current prediction is not appropriate, and the estimation target area used in the previous prediction should be adopted.
The first preset angle is greater than the second preset angle, and the first preset distance is greater than the second preset distance.
Further, the program stored on the storage medium, when executed by the processor, may further implement the steps of: and training the dose prediction model by using historical data to obtain a trained dose prediction model, and performing prediction processing by using the trained dose prediction model. Wherein the historical data comprises: the method comprises the steps of imaging images of historical patients, structural sets containing a thrust target area, a tumor target area and a region where an organ at risk is located in the imaging images, and dose indexes of tumors and organs at risk meeting planning requirements. The dose prediction model may employ a deep learning model such as a convolutional neural network, a cyclic neural network, a long-short term memory network, a U-Net, and the like.
Further, the program stored on the storage medium, when executed by the processor, further implements the steps of: when the dose indexes borne by the tumor and the organs at risk meet the planning requirements, transmitting a structure set containing corresponding pushed target areas, tumor target areas and the regions of the organs at risk in the image images to a radiotherapy planning system; or when the dose indexes of the tumor and the organs at risk predicted based on the pre-adjustment estimated target area do not meet the plan requirements and the adjusted estimated target area is not completely within the range of the tumor target area, transmitting a structural set containing the pre-adjustment estimated target area, the tumor target area and the region of the organs at risk in the image to a radiotherapy planning system.
Including, but not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer.
The invention can achieve the following technical effects:
1. assists a radiotherapy doctor and a physicist to determine the range of the target volume of the thrust, solves the problem that the manual delineation (estimating the drop distance of the dose by experience) has the limitation that the target volume of the tumor thrust cannot be maximized, is suitable for tumors with various volumes, and particularly can remarkably improve the volume to be more than 5cm3The tumor radiotherapy dosage can further improve the tumor control rate, benefit the survival of patients, save the medical cost and have obvious social benefit.
2. The quality consistency of the P-SABR plan can be improved. The advantages in the aspects of data volume and technology are utilized, the blank in the field of delineation of the complex target area of the tumor at present is filled, the intellectualization of clinical work is further promoted, and the popularization of the impulse radiotherapy is promoted.
3. The time of the P-SABR planning flow can be obviously shortened.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and are not to be construed as limiting the scope of the invention. Any modifications, equivalents and improvements which may occur to those skilled in the art without departing from the scope and spirit of the present invention are intended to be within the scope of the claims.
Claims (10)
1. A tumor radiotherapy control system, the system comprising:
the dose prediction module is used for inputting the image of the patient and the structure set containing the pushed target area, the tumor target area and the region of the endangered organ in the image into the dose prediction model so as to carry out prediction processing on the dose indexes borne by the tumor and the endangered organ by utilizing the dose prediction model;
the judging module is used for judging whether the predicted dose indexes borne by the tumor and the organs at risk meet the plan requirements or not;
the optimization and adjustment module is used for automatically adjusting the pushed target area within the range of the tumor target area to obtain an adjusted pushed target area when the predicted dose indexes of the tumor and the organs at risk do not meet the plan requirement;
after the optimized adjustment module obtains the adjusted pushed target area, the prediction processing of the dose prediction module and the judgment processing of the judgment module are repeated until the dose indexes of the tumor and the organs at risk predicted by the dose prediction module meet the plan requirement.
2. The system of claim 1, wherein the dose prediction module is further configured to train the dose prediction model using historical data to obtain a trained dose prediction model, and to perform the prediction process using the trained dose prediction model; wherein the historical data comprises: the method comprises the steps of imaging images of historical patients, structural sets containing a thrust target area, a tumor target area and a region where an organ at risk is located in the imaging images, and dose indexes of tumors and organs at risk meeting planning requirements.
3. The system according to claim 1, wherein the extrapolated target area at the first prediction treatment is the tumor target area, and the optimization and adjustment module is specifically configured to divide the extrapolated target area by taking a geometric center of the extrapolated target area as a centroid and a first preset angle as an interval, so as to obtain a plurality of first division lines; taking a position point where each first dividing line is intersected with the edge of the pushed target area as a starting point, and moving the first dividing line where the starting point is located to the centroid by a first preset distance to obtain a new position point; and determining the closed area obtained after the adjacent new position points are connected pairwise as the adjusted estimated target area so as to repeat the prediction processing of the dose prediction module and the judgment processing of the judgment module until the dose indexes of the tumor and the organs at risk predicted by the dose prediction module meet the plan requirement, and determining the corresponding estimated target area as the estimated target area for the radiotherapy of the patient.
4. The system according to claim 1, wherein the optimization and adjustment module is specifically configured to, when the inferred volume target area is within the range of the tumor target area and the dose indexes of the tumor and the organs at risk predicted based on the inferred volume target area meet the plan requirement, divide the inferred volume target area by taking a geometric center of the inferred volume target area as a centroid and a second preset angle as an interval to obtain a plurality of second dividing lines; taking a position point where each second dividing line intersects with the edge of the pushed target area as a starting point, and moving the edge of the tumor target area by a second preset distance along the second dividing line where the starting point is located to obtain a new position point; and determining the closed area obtained after the adjacent new position points are connected pairwise as the adjusted estimated target area so as to repeat the prediction processing of the dose prediction module and the judgment processing of the judgment module until the judgment module determines that the dose indexes of the tumor and the organs at risk predicted by the dose prediction module do not meet the plan requirements, and determining the estimated target area which can meet the plan requirements before adjustment as the estimated target area for the radiotherapy of the patient.
5. The system of any one of claims 1-4, further comprising:
the transmission module is used for transmitting a structure set containing corresponding pushed target areas, tumor target areas and regions where the organs at risk are located in the image images to a radiotherapy planning system when the dose indexes borne by the tumors and the organs at risk meet the planning requirements; or when the dose indexes of the tumor and the organs at risk predicted based on the pre-adjustment estimated target area do not meet the plan requirements and the adjusted estimated target area is not completely within the range of the tumor target area, transmitting a structural set containing the pre-adjustment estimated target area, the tumor target area and the region of the organs at risk in the image to a radiotherapy planning system.
6. The system of claim 1, wherein the tumor has a volume greater than or equal to 5 cubic centimeters.
7. A storage medium having stored thereon a program which, when executed by a processor, performs the steps of:
inputting an image of a patient and a structure set containing a thrust target area, a tumor target area and a region where an organ at risk is located in the image into a dose prediction model so as to perform prediction processing on dose indexes borne by the tumor and the organ at risk by using the dose prediction model;
judging whether the predicted dose indexes of the tumor and the organs at risk meet the planning requirements or not;
and when the predicted dose indexes of the tumor and the organs at risk do not meet the planning requirement, automatically adjusting the pushed target area within the range of the tumor target area to obtain an adjusted pushed target area, and repeating the prediction treatment and the judgment treatment after obtaining the adjusted pushed target area until the predicted dose indexes of the tumor and the organs at risk meet the planning requirement.
8. The storage medium of claim 7, wherein the extrapolated target volume at the time of the first prediction process is the tumor target volume, and wherein the program stored on the storage medium, when executed by the processor, implements the steps of:
dividing the pushed target area by taking the geometric center of the pushed target area as a centroid and taking a first preset angle as an interval to obtain a plurality of first dividing lines;
taking a position point where each first dividing line is intersected with the edge of the pushed target area as a starting point, and moving the first dividing line where the starting point is located to the centroid by a first preset distance to obtain a new position point;
determining a closed area obtained after the adjacent new position points are connected pairwise as an adjusted estimated target area;
and repeating the prediction processing and the judgment processing until the predicted dose indexes of the tumor and the organs at risk meet the plan requirement, and determining the corresponding target volume of the estimated volume as the target volume of the estimated volume for the radiotherapy of the patient.
9. The storage medium of claim 7, wherein the program stored on the storage medium when executed by the processor performs the steps of:
when the pushed target area is within the range of the tumor target area and the dose indexes of the tumor and the organs at risk predicted based on the pushed target area meet the plan requirements, dividing the pushed target area by taking the geometric center of the pushed target area as a centroid and a second preset angle as an interval to obtain a plurality of second dividing lines;
taking a position point where each second dividing line intersects with the edge of the pushed target area as a starting point, and moving the edge of the tumor target area by a second preset distance along the second dividing line where the starting point is located to obtain a new position point;
determining a closed area obtained after the adjacent new position points are connected pairwise as an adjusted estimated target area;
and repeating the prediction processing and the judgment processing until the predicted dose indexes of the tumor and the organs at risk do not meet the plan requirement, and determining the adjusted estimated target area which can meet the plan requirement as the estimated target area for the radiotherapy of the patient.
10. The storage medium according to any one of claims 7-9, wherein the program stored on the storage medium, when executed by the processor, further performs the steps of:
when the dose indexes borne by the tumor and the organs at risk meet the planning requirements, transmitting a structure set containing corresponding pushed target areas, tumor target areas and the regions of the organs at risk in the image images to a radiotherapy planning system;
or when the dose indexes of the tumor and the organs at risk predicted based on the pre-adjustment estimated target area do not meet the plan requirements and the adjusted estimated target area is not completely within the range of the tumor target area, transmitting a structural set containing the pre-adjustment estimated target area, the tumor target area and the region of the organs at risk in the image to a radiotherapy planning system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210019456.7A CN114344737A (en) | 2022-01-07 | 2022-01-07 | Tumor radiotherapy control system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210019456.7A CN114344737A (en) | 2022-01-07 | 2022-01-07 | Tumor radiotherapy control system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114344737A true CN114344737A (en) | 2022-04-15 |
Family
ID=81107762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210019456.7A Pending CN114344737A (en) | 2022-01-07 | 2022-01-07 | Tumor radiotherapy control system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114344737A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024097A (en) * | 2010-12-29 | 2011-04-20 | 深圳市海博科技有限公司 | Target spot layout optimization method in treatment plan and treatment plan system |
| CN102043909A (en) * | 2010-12-29 | 2011-05-04 | 深圳市海博科技有限公司 | Target spot arrangement optimizing method for use in treatment planning and treatment planning system |
| CN103247046A (en) * | 2013-04-19 | 2013-08-14 | 深圳先进技术研究院 | Automatic target volume sketching method and device in radiotherapy treatment planning |
| CN107545137A (en) * | 2017-08-16 | 2018-01-05 | 强深智能医疗科技（昆山）有限公司 | Tumour radiotherapy plan intelligent optimization method |
| CN110290832A (en) * | 2017-01-30 | 2019-09-27 | 皇家飞利浦有限公司 | Assessment to realizability of the therapeutic purpose in radiotherapy |
| CN110475588A (en) * | 2017-04-05 | 2019-11-19 | 光线搜索实验室公司 | System and method for automatic radiotherapeutic treatment plan |
| CN112546463A (en) * | 2021-02-25 | 2021-03-26 | 四川大学 | Radiotherapy dose automatic prediction method based on deep neural network |
| CN113674834A (en) * | 2021-08-16 | 2021-11-19 | 于金明 | Radiotherapy target region establishing and correcting method based on dose distribution preview system |
-
2022
- 2022-01-07 CN CN202210019456.7A patent/CN114344737A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024097A (en) * | 2010-12-29 | 2011-04-20 | 深圳市海博科技有限公司 | Target spot layout optimization method in treatment plan and treatment plan system |
| CN102043909A (en) * | 2010-12-29 | 2011-05-04 | 深圳市海博科技有限公司 | Target spot arrangement optimizing method for use in treatment planning and treatment planning system |
| CN103247046A (en) * | 2013-04-19 | 2013-08-14 | 深圳先进技术研究院 | Automatic target volume sketching method and device in radiotherapy treatment planning |
| CN110290832A (en) * | 2017-01-30 | 2019-09-27 | 皇家飞利浦有限公司 | Assessment to realizability of the therapeutic purpose in radiotherapy |
| CN110475588A (en) * | 2017-04-05 | 2019-11-19 | 光线搜索实验室公司 | System and method for automatic radiotherapeutic treatment plan |
| CN107545137A (en) * | 2017-08-16 | 2018-01-05 | 强深智能医疗科技（昆山）有限公司 | Tumour radiotherapy plan intelligent optimization method |
| CN112546463A (en) * | 2021-02-25 | 2021-03-26 | 四川大学 | Radiotherapy dose automatic prediction method based on deep neural network |
| CN113674834A (en) * | 2021-08-16 | 2021-11-19 | 于金明 | Radiotherapy target region establishing and correcting method based on dose distribution preview system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10987522B2 (en) | Three dimensional localization and tracking for adaptive radiation therapy | |
| US10152790B2 (en) | Three dimensional localization of a moving target for adaptive radiation therapy | |
| Harkenrider et al. | Image-based brachytherapy for the treatment of cervical cancer | |
| CN107072624B (en) | System and method for automated treatment planning | |
| Pötter et al. | Present status and future of high-precision image guided adaptive brachytherapy for cervix carcinoma | |
| JP2009545394A (en) | Biologically guided adaptive treatment planning | |
| US11786204B2 (en) | Automatically-registered patient fixation device images | |
| US11478660B2 (en) | Automatically-planned radiation-based treatment | |
| Yoshida et al. | Preliminary results of MRI-assisted high-dose-rate interstitial brachytherapy for uterine cervical cancer | |
| CN113181563B (en) | Method, system and medium for planning radiotherapy dose in particle implantation tumor | |
| CN115666717A (en) | Method and apparatus for deriving and using virtual volume structures to predict potential collisions in delivering therapeutic radiation | |
| Kawamura et al. | Revolutionizing radiation therapy: the role of AI in clinical practice | |
| CN113941100A (en) | Method and apparatus for generating deliverable radiotherapy plan according to three-dimensional spatial dose distribution | |
| CN114344737A (en) | Tumor radiotherapy control system and storage medium | |
| Levitt et al. | Evolution of computerized radiotherapy in radiation oncology: potential problems and solutions | |
| Tran | Dose tracking assessment for image-guided radiotherapy of cervical cancer treatment using a hybrid deformable image registration (DIR) method | |
| Lee et al. | BIOLOGICAL PLANNING OPTIMIZATION FOR HIGH‐DOSE‐RATE BRACHYTHERAPY AND ITS APPLICATION TO CERVICAL CANCER TREATMENT | |
| Lan et al. | An improved convex programming model for the inverse problem in intensity-modulated radiation therapy | |
| Udeji | Improving Realtime 3-D Tracking of High Dose Rate Radiation Source Using a Flat Panel Detector | |
| Nomden et al. | SP-0421: Brachytherapy pelvic and MRI-Linac combination | |
| Thongphiew | ON-LINE RE-OPTIMIZATION OF PROSTATE IMRT PLAN FOR ADAPTIVE RADIATION THERAPY–A FEASIBILITY STUDY AND IMPLEMENTATION | |
| Brahme | Radiation therapy | |
| Yu | Improving Cervical Cancer Nodal Boost Radiation Therapy by Quantifying Uncertainties and Exploring Advanced Radiation Therapy Modalities | |
| Mathayomchan | Multiobjective Approach to Morphological Based Radiation Treatment Planning | |
| Shojaei | Dosimetric and Radiobiological Plan Evaluation Parameters for |
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 |