CN112581475B - A method for predicting gamma pass rate for radiotherapy planning - Google Patents
A method for predicting gamma pass rate for radiotherapy planning Download PDFInfo
- Publication number
- CN112581475B CN112581475B CN202110212153.2A CN202110212153A CN112581475B CN 112581475 B CN112581475 B CN 112581475B CN 202110212153 A CN202110212153 A CN 202110212153A CN 112581475 B CN112581475 B CN 112581475B
- Authority
- CN
- China
- Prior art keywords
- mlc
- dimensional
- information
- value
- gamma
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001959 radiotherapy Methods 0.000 title claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000011176 pooling Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 12
- 238000000275 quality assurance Methods 0.000 abstract description 11
- 238000012795 verification Methods 0.000 abstract description 8
- 230000002159 abnormal effect Effects 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract 1
- 238000010801 machine learning Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 230000000052 comparative effect Effects 0.000 description 5
- 238000013136 deep learning model Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012733 comparative method Methods 0.000 description 1
- 238000002721 intensity-modulated radiation therapy Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/1048—Monitoring, verifying, controlling systems and methods
- A61N5/1071—Monitoring, verifying, controlling systems and methods for verifying the dose delivered by the treatment plan
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiation-Therapy Devices (AREA)
Abstract
The invention provides a method for predicting gamma passing rate of radiotherapy plan, which comprises the steps of extracting MLC aperture information and MU value information from VMAT plan and predicting gamma passing rate by artificial intelligence algorithm. The method has high accuracy of predicting the gamma passing rate, the average error reaches within 3 percent, and the workload of actual measurement of specific quality assurance of a patient by medical physicists can be greatly reduced. Meanwhile, the method can also identify the deviation of the actual measurement result caused by misoperation and abnormal accelerator state in the past measurement, provides a very valuable reference for the daily quality assurance work of medical physicists, and further optimizes the intensity-modulated verification process of hospitals.
Description
Technical Field
The invention belongs to the technical field of radiotherapy, and particularly relates to a method for predicting gamma passing rate of a radiotherapy plan.
Background
Volume rotational radiotherapy (VMAT) is an advanced radiation therapy technology. It allows the simultaneous adjustment of three parameters during the treatment: accelerator frame rotation speed, multi-leaf collimator (MLC) motion, and dose rate. In the uneven rotation process of the accelerator frame, the dosage rate is dynamically changed, and the MLC continuously moves. When planning volumetric rotational radiation therapy, specific quality assurance measurements are required for the patient. The purpose of the quality assurance measurement is to confirm the accuracy of the dose delivery. In order to assess the reliability of clinical delivery of radiation therapy and to ensure patient safety, patient-specific quality assurance is typically performed prior to radiotherapy planning of the clinical treatment.
In the field of radiotherapy, patient-specific quality assurance, as reported by TG-218, typically involves dose verification using gamma analysis methods before the patient's VMAT plan is delivered for clinical treatment. The gamma analysis method has the index of gamma passing rate, generally, the test of the gamma passing rate is the result obtained by simulating a patient by using a detector array, irradiating the detector by using a formulated radiotherapy plan, and evaluating the consistency of the measured dose distribution of the detector and the dose distribution and the consistency of the percentage of dose points calculated by a planning system, wherein the worst gamma passing rate is 0 percent, and the optimal gamma passing rate is 100 percent. This is done for each patient's radiotherapy plan, due to the need to actually simulate patient verification using the probe device, resulting in dose verification that is time consuming, laborious and sometimes erroneous in measurements. Therefore, the gamma passing rate is accurately predicted directly through the information of the radiotherapy plan, so that manpower and material resources are greatly saved, and the measurement error is favorably reduced.
Since 2016, there have been several studies in foreign countries on predicting the dose verification results of volume-rotating radiation therapy using machine learning. The existing technical scheme is mainly an intensity modulated radiation therapy automatic quality control method based on machine learning and adopting complexity indexes, and the basic idea is that a professional medical physicist selects the complexity indexes of a VMAT plan, the complexity indexes describe different aspects of the plan complexity, such as average dose rate, dose rate standard deviation, edge complexity indexes and the like, and the indexes are data in a numerical value form. Such differences in the index may result in differences in the calculated and measured dose, resulting in different gamma passage rates. The complexity index and the gamma passing rate have different degrees of correlation, the appropriate complexity index is selected as input data, a machine learning algorithm (such as a generalized linear model and a random forest model) is used for training, and the gamma passing rate is output.
However, the complexity index artificially designed by the physicist contains only limited information in the VMAT plan, which results in many pieces of information being missed, which have strong correlation with the results. All current methods do not reflect the complete dynamic process of VMAT in treatment. The index designed by people can only embody one piece of static and overall information, but cannot describe the dynamic process of the whole treatment, so that the prediction accuracy of the prediction methods is low, the average error is more than 5%, and the index is difficult to apply to the decision making in the clinical quality assurance.
Therefore, there is a need for a technique that can predict the gamma passage rate of VMAT plans more accurately, and effectively assist clinical decision making.
Disclosure of Invention
The invention aims to provide a gamma passing rate prediction technology based on a volume rotation radiotherapy plan file with high accuracy.
The invention provides a method for predicting gamma passing rate of radiotherapy plan, which comprises the following steps:
(1) extracting all control point information from a volume rotational radiotherapy (VMAT) plan, wherein the control point information comprises multi-leaf collimator (MLC) aperture information and accelerator jump number (MU) value information corresponding to each control point; the control points are time-sequenced;
(2) converting the MLC aperture information extracted in the step (1) into a two-dimensional MLC aperture image, and combining the two-dimensional MLC aperture image according to a control point time sequence to form a three-dimensional MLC aperture image;
(3) converting the three-dimensional MLC aperture image obtained in the step (2) into an MLC characteristic vector through a deep learning algorithm;
(4) converting the MU value information extracted in the step (1) into MU value vectors according to the time sequence of the control points;
(5) integrating the MLC characteristic vector obtained in the step (3) and the MU value vector obtained in the step (4), and outputting the predicted gamma passing rate through a neural network algorithm.
Further, the MLC aperture information in step (1) above includes MLC position information; the MU value information includes MU weights.
Further, the MLC position information is MLC leaves. And (4) sheet coordinate representation.
Further, the MU weights are expressed as a weight of the control point MU value to the planned total MU value.
Further, the deep learning algorithm in the step (3) is selected from at least one of a three-dimensional residual neural network (3D-ResNet), 3D resext, 3D squeezet, 3D MobileNet, 3D ShuffleNet, 3D mobilnetv 2, 3D shufflnetv 2 or other three-dimensional deep convolutional neural networks with time kernels, and is preferably a three-dimensional residual neural network (3D-ResNet).
Furthermore, the three-dimensional residual error neural network comprises a three-dimensional convolution layer, a pooling layer and a full-link layer.
Preferably, the convolution kernel size of the three-dimensional convolution layer is 3 × 3 × 3 with a step size of 1.
Further, the neural network algorithm in the step (5) is a fully connected neural network.
Experimental results show that the method has high accuracy in predicting the gamma passing rate, the average error is within 3%, and the workload of medical physicists for actually measuring the specific quality assurance of patients can be greatly reduced. Meanwhile, the method can also identify the deviation of the actual measurement result caused by misoperation and abnormal accelerator state in the past measurement, provides a very valuable reference for the daily quality assurance work of medical physicists, and further optimizes the intensity-modulated verification process of hospitals.
Obviously, many modifications, substitutions, and variations are possible in light of the above teachings of the invention, without departing from the basic technical spirit of the invention, as defined by the following claims.
The present invention will be described in further detail with reference to the following examples. This should not be understood as limiting the scope of the above-described subject matter of the present invention to the following examples. All the technologies realized based on the above contents of the present invention belong to the scope of the present invention.
Drawings
FIG. 1 is a technical route of a method for predicting gamma passage rate according to embodiment 1 of the present invention.
Detailed Description
All dose verification plans are calculated and derived by the Raystation planning System (Raystation Medical Laboratories AB, Stockholm, Sweden) and are produced by the Medical company Versa HD with an Agility multileaf collimatorTMThe and Elekta Synergy accelerator system (Elekta, Crawley, UK). Dose-validated gamma analyses were each measured with an ArcCHECK detector array with cavitypplug inserts and computationally analyzed by SNC pathway software (version 6.7). The study involves a deep learning model to train the GPU to NVIDIA Tesla P100.
Example 1 prediction of Gamma passage Rate by the method of the invention
1. Creating and exporting, by a planning system, a volume rotational radiotherapy (VMAT) plan file;
2. completely inputting the plan file into a deep learning model, and predicting the gamma passing rate of the deep learning model by the following method:
(1) extracting all control point information from a volume rotational radiotherapy (VMAT) plan, wherein the control point information comprises multi-leaf collimator (MLC) aperture information and accelerator jump number (MU) value information corresponding to each control point; the control points are time-sequenced;
(2) converting the MLC aperture information extracted in the step (1) into a two-dimensional MLC aperture image, and combining the two-dimensional MLC aperture image according to a control point time sequence to form a three-dimensional MLC aperture image;
(3) converting the three-dimensional MLC aperture image obtained in the step (2) into MLC characteristic vectors sequentially through three-dimensional convolution (convolution kernel size is 3 multiplied by 3, step is 1), a three-dimensional pooling layer and a full connection layer;
(4) converting the MU value information extracted in the step (1) into MU value vectors according to the time sequence of the control points;
(5) integrating the MLC characteristic vector obtained in the step (3) and the MU value vector obtained in the step (4), and outputting the predicted gamma passing rate through a two-layer fully-connected neural network.
The specific flow is shown in figure 1.
Comparative example 1 prediction of Gamma passage Rate based on complexity index
(1) 54 required indexes which influence the VMAT dose delivery precision are calculated according to radiotherapy information and used for representing the modulation complexity of the VMAT plan, wherein the indexes comprise 54 indexes such as small aperture fraction, modulation coefficient and the like;
(2) and inputting the parameter indexes into a Poisson regression model with Lasso regularization. The machine learning model learns the mapping relation between 54 parameter indexes and the output gamma passing rate;
(3) the machine learning model outputs a predicted gamma pass rate.
The beneficial effects of the method of the invention are demonstrated by the following experimental examples.
Experimental example 1 evaluation of accuracy of predicting gamma passage rate by the method of the present invention
1. Experimental methods
(1) Accuracy evaluation of prediction gamma passing rate by using method of the invention
The experimental data are 719 cases in total, and are randomly divided into 551 training sets and 168 test sets, wherein the training sets are used for training the deep learning model, and the test sets are used for evaluating the experimental results in the embodiment 1.
(2) Comparative example 1 accuracy evaluation of prediction of gamma passage rate based on complexity index:
the experimental data are 303 in total, and are randomly divided into 255 training sets and 48 test sets, wherein the training sets are used for training the machine learning model of comparative example 1, and the test sets are used for evaluating the experimental result of comparative example 1.
The average absolute error of the two methods is regarded as the prediction error to be calculated respectively, and the formula is as follows:
where N denotes the number of test sets, piGamma pass rate, y, representing model predictioniRepresenting the measured gamma pass rate using the detector.
2. Results of the experiment
The accuracy results of the gamma passage rate predictions of the inventive and comparative methods are shown in table 1:
TABLE 1
| Example 1 | Comparative example 1 | |
| Prediction error | 2.38％ | About 5 percent |
The experimental result shows that the gamma passing rate of the VMAT plan predicted by the method has high accuracy, the average error is only 2.38%, and compared with the existing method that a professional medical physicist selects the complexity index of the VMAT plan as input data and trains the gamma passing rate prediction by using a machine learning algorithm (such as a generalized linear model and a random forest model), the method has lower prediction error.
In conclusion, the invention provides a gamma passing rate prediction technology based on a volume rotation radiotherapy plan file, the accuracy of the gamma passing rate prediction is high, the average error reaches within 3 percent, and the workload of actual measurement of specific quality assurance of a patient by a medical physicist can be greatly reduced. Meanwhile, the method can also identify the deviation of the actual measurement result caused by misoperation and abnormal accelerator state in the past measurement, provides a very valuable reference for the daily quality assurance work of medical physicists, and further optimizes the intensity-modulated verification process of hospitals.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110212153.2A CN112581475B (en) | 2021-02-25 | 2021-02-25 | A method for predicting gamma pass rate for radiotherapy planning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110212153.2A CN112581475B (en) | 2021-02-25 | 2021-02-25 | A method for predicting gamma pass rate for radiotherapy planning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112581475A CN112581475A (en) | 2021-03-30 |
| CN112581475B true CN112581475B (en) | 2021-05-25 |
Family
ID=75114046
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110212153.2A Active CN112581475B (en) | 2021-02-25 | 2021-02-25 | A method for predicting gamma pass rate for radiotherapy planning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112581475B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113499091B (en) * | 2021-08-19 | 2023-08-15 | 四川大学华西医院 | Method and system for predicting tumor movement correlation and tumor internal mobility in body surface and body of patient |
| CN113517072B (en) * | 2021-09-13 | 2022-01-28 | 四川大学 | VMAT radiotherapy plan prediction device based on deep neural network |
| CN113516233B (en) * | 2021-09-13 | 2022-01-28 | 四川大学 | Neural network prediction device for VMAT radiotherapy plan |
| CN113827877B (en) * | 2021-09-15 | 2024-05-28 | 上海市胸科医院 | Method for realizing automatic dose verification based on accelerator log file |
| EP4516349A4 (en) * | 2022-05-31 | 2025-06-11 | Shanghai United Imaging Healthcare Co., Ltd. | QUALITY GUARANTEE PROCEDURES AND SYSTEM |
| CN117180638A (en) * | 2022-05-31 | 2023-12-08 | 上海联影医疗科技股份有限公司 | Quality assurance method and system |
| CN116525064B (en) * | 2023-07-03 | 2023-11-10 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Radiation therapy plan detection device, electronic equipment and computer readable storage medium |
| CN116839482B (en) * | 2023-08-23 | 2023-12-12 | 成都利尼科医学技术发展有限公司 | Mechanical isocenter measuring device and method for medical accelerator |
| CN117679671B (en) * | 2024-02-02 | 2024-05-14 | 四川大学华西医院 | A method and system for 4D dose reconstruction in radiotherapy |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107708808A (en) * | 2015-06-30 | 2018-02-16 | 医科达有限公司 | For the system and method that use quality index carries out target tracking during radiotherapy |
| CN110841205A (en) * | 2019-10-21 | 2020-02-28 | 温州医科大学附属第一医院 | Accurate dose verification method, device and equipment for tumor patient |
| CN110997063A (en) * | 2017-05-30 | 2020-04-10 | 反射医疗公司 | Method for real-time image-guided radiation therapy |
| CN111246915A (en) * | 2017-10-26 | 2020-06-05 | 瓦里安医疗系统国际股份公司 | Method and apparatus for using a multi-layer multi-leaf collimation system |
| CN111408072A (en) * | 2015-04-02 | 2020-07-14 | 瓦里安医疗系统国际股份公司 | Portal dosimetry system, device and method |
| CN111494813A (en) * | 2020-04-21 | 2020-08-07 | 上海联影医疗科技有限公司 | Modeling method, verification method, device, equipment 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 |
| CN111589000A (en) * | 2020-05-27 | 2020-08-28 | 浙江省肿瘤医院 | A verification method of medical linear accelerator parameters |
| CN112035778A (en) * | 2020-09-01 | 2020-12-04 | 苏州雷泰医疗科技有限公司 | Multi-leaf grating side-penetrating penumbra calculation method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150272497A1 (en) * | 2014-03-25 | 2015-10-01 | Mobius Medical Systems, Lp | Methods, systems, and computer readable media for verifying the accuracy of medical treatment in accordance with a treatment plan |
| CN104117151B (en) * | 2014-08-12 | 2017-01-25 | 章桦 | Optimization method of online self-adaption radiotherapy plan |
-
2021
- 2021-02-25 CN CN202110212153.2A patent/CN112581475B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111408072A (en) * | 2015-04-02 | 2020-07-14 | 瓦里安医疗系统国际股份公司 | Portal dosimetry system, device and method |
| CN107708808A (en) * | 2015-06-30 | 2018-02-16 | 医科达有限公司 | For the system and method that use quality index carries out target tracking during radiotherapy |
| CN110997063A (en) * | 2017-05-30 | 2020-04-10 | 反射医疗公司 | Method for real-time image-guided radiation therapy |
| CN111246915A (en) * | 2017-10-26 | 2020-06-05 | 瓦里安医疗系统国际股份公司 | Method and apparatus for using a multi-layer multi-leaf collimation system |
| CN110841205A (en) * | 2019-10-21 | 2020-02-28 | 温州医科大学附属第一医院 | Accurate dose verification method, device and equipment for tumor patient |
| CN111494813A (en) * | 2020-04-21 | 2020-08-07 | 上海联影医疗科技有限公司 | Modeling method, verification method, device, equipment 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 |
| CN111589000A (en) * | 2020-05-27 | 2020-08-28 | 浙江省肿瘤医院 | A verification method of medical linear accelerator parameters |
| CN112035778A (en) * | 2020-09-01 | 2020-12-04 | 苏州雷泰医疗科技有限公司 | Multi-leaf grating side-penetrating penumbra calculation method and device |
Non-Patent Citations (4)
| Title |
|---|
| Automatic VMAT Planning via MLC Dynamic Sequence Prediction (AVP-DSP): A Novel Deep-Learning Method for Real-Time Prostate Treatment Planning;Y. Ni等;《Oral Scientific Sessions》;20201101;第108卷(第35期);S93-S94 * |
| Description and evaluation of a new volumetric-modulated arc therapy plan complexity metric;Guangjun Li等;《Medical Dosimetry》;20210119;1-7 * |
| Prediction of VMAT delivery accuracy with textural features calculated from fluence maps;Jong Min Park等;《Radiation Oncology》;20191223;1-14 * |
| 基于机器学习构建宫颈癌VMAT计划剂量预测模型及其自动计划的研究;吴先想;《中国优秀硕士学位论文全文数据库医药卫生科技辑》;20190915(第09期);E060-212 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112581475A (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112581475B (en) | A method for predicting gamma pass rate for radiotherapy planning | |
| CN110841205B (en) | A precise dose verification device for tumor patients | |
| CN104338240B (en) | Automatic optimization device for on-line self-adaption radiotherapy plan | |
| US10449388B2 (en) | Systems and methods for specifying treatment criteria and treatment parameters for patient specific radiation therapy planning | |
| US8976929B2 (en) | Automatic generation of patient-specific radiation therapy planning parameters | |
| AU2020274863B2 (en) | Dose guided real-time adaptive radiotherapy | |
| CN111540437B (en) | Dose verification method and system based on artificial intelligence | |
| CN109859817A (en) | Dosimetric assessment methods and assessment systems for organs at risk in esophageal radiation therapy planning | |
| US20200360728A1 (en) | Machine learning based dose guided real-time adaptive radiotherapy | |
| CN112635024A (en) | Automatic planning and designing system for radiotherapy and construction method thereof | |
| Zhu et al. | Patient‐specific quality assurance prediction models based on machine learning for novel dual‐layered MLC linac | |
| CN117219292A (en) | Automatic dose verification and evaluation method and device for tumor patient before accurate radiotherapy | |
| Lizar et al. | Patient-specific IMRT QA verification using machine learning and gamma radiomics | |
| Lambri et al. | Multicentric evaluation of a machine learning model to streamline the radiotherapy patient specific quality assurance process | |
| Tozuka et al. | Improvement of deep learning prediction model in patient‐specific QA for VMAT with MLC leaf position map and patient's dose distribution | |
| Ni et al. | Fast VMAT planning for prostate radiotherapy: dosimetric validation of a deep learning-based initial segment generation method | |
| Newpower et al. | Spot delivery error predictions for intensity modulated proton therapy using robustness analysis with machine learning | |
| CN113516233A (en) | A neural network prediction method for VMAT radiotherapy planning | |
| Zhong et al. | Generation of a novel phase‐space‐based cylindrical dose kernel for IMRT optimization | |
| Shen et al. | A quantitative quality control method of big data in cancer patients using artificial neural network | |
| Andersson | Monte Carlo and machine learning approach to in-vivo transmission dosimetry for dynamic radiation treatments | |
| CN119008032B (en) | Radiotherapy monitoring management system and method based on cloud computing | |
| Strauss et al. | Automated dose verification in specialized radiotherapy (ADViSR): a tool for Monte Carlo based dose verification | |
| DeJesus et al. | Machine and Deep Learning for Patient-Specific Quality Assurance in Intensity Modulated Radiotherapy Using Log Files: Current Techniques and Emerging Directions | |
| CN119517301A (en) | A method for rapidly predicting BNCT treatment plans using convolutional neural networks |
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 |