CN116688376A - Lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour - Google Patents
Lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour Download PDFInfo
- Publication number
- CN116688376A CN116688376A CN202310616501.1A CN202310616501A CN116688376A CN 116688376 A CN116688376 A CN 116688376A CN 202310616501 A CN202310616501 A CN 202310616501A CN 116688376 A CN116688376 A CN 116688376A
- Authority
- CN
- China
- Prior art keywords
- dose
- auxiliary
- lung cancer
- radiotherapy plan
- cancer radiotherapy
- 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
- 238000001959 radiotherapy Methods 0.000 title claims abstract description 85
- 206010058467 Lung neoplasm malignant Diseases 0.000 title claims abstract description 63
- 201000005202 lung cancer Diseases 0.000 title claims abstract description 63
- 208000020816 lung neoplasm Diseases 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000009826 distribution Methods 0.000 claims abstract description 76
- 238000005457 optimization Methods 0.000 claims abstract description 43
- 210000000920 organ at risk Anatomy 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 19
- 210000000056 organ Anatomy 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000004590 computer program Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 6
- 238000013461 design Methods 0.000 abstract description 13
- 230000009286 beneficial effect Effects 0.000 abstract description 6
- 210000004072 lung Anatomy 0.000 abstract description 5
- 230000006872 improvement Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000002721 intensity-modulated radiation therapy Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 208000035217 Ring chromosome 1 syndrome Diseases 0.000 description 2
- 208000032825 Ring chromosome 2 syndrome Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 101150007742 RING1 gene Proteins 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
- A61N5/1031—Treatment planning systems using a specific method of dose optimization
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
- A61N5/1039—Treatment planning systems using functional images, e.g. PET or MRI
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- 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
- A61N2005/1041—Treatment planning systems using a library of previously administered radiation treatment applied to other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides a lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour, which belong to the technical field of medical equipment and acquire lung cancer radiotherapy plan case data; processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target region and the organs at risk; generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization; obtaining a target region, a jeopardizing organ and a dose limit value of the auxiliary contour according to the auxiliary contour and the dose distribution; and (5) performing reverse optimization according to the auxiliary profile and the dose constraint limit value to generate the lung cancer radiotherapy plan. According to the invention, the minimum distance distribution from the patient voxels to the target region is incorporated into model training, so that the accuracy of dose prediction is improved; the auxiliary profile is generated by using the dose distribution, so that the optimization condition/target is more reasonable, and the design time is shortened; is beneficial to the protection of the lung of the organs at risk and the rapid improvement of the planning design level of the units with poor radiotherapy experience.
Description
Technical Field
The invention relates to the technical field of medical equipment, in particular to a lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour.
Background
Radiation therapy planning is a prerequisite for delivering radiation therapy, and current Intensity Modulated Radiation Therapy (IMRT) planning is based on complex inverse optimization algorithms. Auxiliary contours, optimization conditions/constraint targets and the like are manually formulated according to target region positions, prescription dose requirements and the like of a patient, a planning system generates a flux map according to the condition constraints through a complex optimization algorithm, and then the flux map is combined with the restriction constraints of an accelerator to generate field information (such as lead gate positions, multi-leaf collimator (MLC) shapes, MU of control points and the like) which can be actually executed.
Currently, radiation therapy planning systems also suffer from the following disadvantages: firstly, the IMRT plan design usually adopts a personal experience and trial-and-error mode, a plan designer needs to find a more satisfactory design scheme in tens or even tens of trial-and-error modes, the plan quality depends on the subjective experience of the plan designer and the time spent, and the complexity of a reverse optimization algorithm can lead to the problems of long optimization time, high hardware resource consumption and the like. Secondly, there is a considerable difference in the quality and planning time of the designed IMRT plans between different radiotherapy centers, even between different persons within the same radiotherapy center. How to improve the design efficiency and quality of radiotherapy plans is an urgent need for radiotherapy at present.
In inverse intensity-modulated plan optimization, a large number of auxiliary profiles are required for dose constraints to minimize the exposure dose to organs at risk outside the target volume. The clinically common auxiliary contours (e.g., ring, nt, fan, etc.) are all given by subjective experience of the planning designer, and are usually uniformly spread around the target area. When the lung cancer is planned, the dosage falls slowly in the front-back direction of the patient and falls quickly in the left-right direction of the patient due to the stronger dosage limit value to the lung region. The dose appears to drop significantly unevenly in all directions, which can result in too tight a regional dose limitation and too loose a regional dose limitation when using isotropic Ring, nt, fan as the dose limit, thereby affecting the optimization results. How to scientifically and reasonably make the auxiliary profile is an important factor affecting the design quality and efficiency of the radiotherapy plan.
Disclosure of Invention
The invention aims to provide a lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour, which are used for solving at least one technical problem in the background technology.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in one aspect, the invention provides a method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profile, comprising the following steps:
acquiring lung cancer radiotherapy planning case data;
processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target region and the organs at risk;
generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization;
obtaining a target region, a jeopardizing organ and a dose limit value of the auxiliary contour according to the auxiliary contour and the dose distribution;
and (5) performing reverse optimization according to the auxiliary profile and the dose constraint limit value to generate the lung cancer radiotherapy plan.
Optionally, the dose prediction model is trained by a training set, wherein the training set comprises a plurality of lung cancer radiotherapy plan cases, and the lung cancer radiotherapy plan cases at least comprise case CT images, dose distribution, target area and organ-at-risk outline, and minimum distance distribution from patient voxels to the target area; the model is trained based on the CT image, target and organ-at-risk contours, and the minimum distance distribution of patient voxels to the target as input data to the model, and the dose distribution as output from the model.
Optionally, the closest distance from the target at the ith point of the patient is defined as follows:
wherein D is i Representing the closest distance of the ith voxel to the target region target, (x) i 、y i 、z i ) Is the coordinates of the ith point, (x k 、y k 、z k ) Coordinates of a k point on the target area; when voxel i is located within the target region or outside the patient's body, D i Defined as 0.
Alternatively, training the dose prediction model uses a deep neural network framework including Vgg-Unet, res-Unet, trans-Unet, UNeXt.
Optionally, an anisotropic auxiliary profile is generated based on the model predicted dose according to the dose distribution characteristics of the lung cancer radiotherapy plan.
Optionally, the auxiliary profile varies around the target region with the predicted dose drop rate, and the width in each direction varies, being the area enclosed by the particular isodose line or patient profile.
Optionally, the dose constraint limit generation module generates dose constraint conditions of the auxiliary contour, the organs at risk and the target area according to the dose distribution, and introduces the dose constraint conditions into the planning system through an interface program for automatic optimization of radiotherapy planning.
In a second aspect, the present invention provides a lung cancer radiotherapy plan generation system based on dose prediction and auxiliary profile, comprising:
the acquisition module is used for acquiring lung cancer radiotherapy planning case data;
the prediction module is used for processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target area and the organs at risk;
a first determination module for generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization;
a second determining module for obtaining a dose limit for the target region, the organ at risk and the auxiliary profile from the auxiliary profile and the dose distribution;
and the reverse optimization module is used for carrying out reverse optimization according to the auxiliary profile and the dose constraint limit value to generate a lung cancer radiotherapy plan.
In a third aspect, the present invention provides a non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement a method of generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profiles as described above.
In a fourth aspect, the present invention provides a computer program product comprising a computer program for implementing a method of generating a lung cancer radiation therapy plan based on dose prediction and an auxiliary profile as described above, when run on one or more processors.
In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the instructions for implementing the lung cancer radiotherapy plan generation method based on dose prediction and auxiliary profile as described above.
The invention has the beneficial effects that: the minimum distance distribution from the patient voxels to the target region is brought into model training, so that the accuracy of dose prediction is improved; the auxiliary profile is generated by using the dose distribution, so that the optimization condition/target is more reasonable, and the planning and design time is greatly shortened; in normal tissue protection, the automatic planning method is beneficial to the protection of the lung of the organs at risk; the automatic completion of the design of the lung cancer radiotherapy plan is beneficial to the rapid improvement of the plan design level of the units with insufficient radiotherapy experience.
The advantages of additional aspects of the invention will be set forth in part in the description which follows, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a structural flow chart of an automatic lung cancer planning method based on dose prediction and auxiliary contour generation according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of generating an auxiliary profile based on a predicted dose according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements throughout or elements having like or similar functionality. The embodiments described below by way of the drawings are exemplary only and should not be construed as limiting the invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, and/or groups thereof.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
In order that the invention may be readily understood, a further description of the invention will be rendered by reference to specific embodiments that are illustrated in the appended drawings and are not to be construed as limiting embodiments of the invention.
It will be appreciated by those skilled in the art that the drawings are merely schematic representations of examples and that the elements of the drawings are not necessarily required to practice the invention.
Example 1
In this embodiment 1, there is provided a lung cancer radiotherapy plan generation system based on dose prediction and auxiliary profile, including: the acquisition module is used for acquiring lung cancer radiotherapy planning case data; the prediction module is used for processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target area and the organs at risk; a first determination module for generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization; a second determining module for obtaining a dose limit for the target region, the organ at risk and the auxiliary profile from the auxiliary profile and the dose distribution; and the reverse optimization module is used for carrying out reverse optimization according to the auxiliary profile and the dose constraint limit value to generate a lung cancer radiotherapy plan.
In this embodiment 1, a method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profile is implemented by using the system described above, including: an acquisition module is used for acquiring lung cancer radiotherapy planning case data; using a model training module to perform model training by using lung cancer radiotherapy plan case data to obtain a radiotherapy dosage prediction model; using a prediction module, and processing radiotherapy plan case data by using a trained dose prediction model to obtain a dose distribution result of a target region and a jeopardizing organ; generating, using a first determination module, an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization; obtaining dose limits for the target region, the organ at risk and the auxiliary profile from the auxiliary profile and the dose distribution using a second determination module; and (3) performing reverse optimization by using a reverse optimization module according to the auxiliary profile and the dose constraint limit value to generate a lung cancer radiotherapy plan.
The dose prediction model is trained by a training set, the training set comprises a plurality of lung cancer radiotherapy plan cases, and the lung cancer radiotherapy plan cases at least comprise case CT images, dose distribution, target areas, organs at risk outlines and minimum distance distribution from patient voxels to the target areas; the model is trained based on the CT image, target and organ-at-risk contours, and the minimum distance distribution of patient voxels to the target as input data to the model, and the dose distribution as output from the model.
The closest distance from the patient's ith point to the target area is defined as follows:
wherein D is i Representing the closest distance of the ith voxel to the target region target, (x) i 、y i 、z i ) Is the coordinates of the ith point, (x k 、y k 、z k ) Coordinates of a k point on the target area; when voxel i is located within the target region or outside the patient's body, D i Defined as 0.
The dose prediction model is trained using a deep neural network framework including Vgg-Unet, res-Unet, trans-Unet, UNeXt.
And generating an anisotropic auxiliary profile based on the model predicted dose according to the dose distribution characteristics of the lung cancer radiotherapy plan. The auxiliary contour is different along with the difference of the speed of the predicted dose falling around the target area, and the width of each direction is different and is defined by a specific isodose line or the contour of a patient. The generation dose constraint limit module generates an auxiliary contour, a jeopardizing organ and a target area dose constraint condition according to the dose distribution, and introduces the auxiliary contour, the jeopardizing organ and the target area dose constraint condition into a planning system through an interface program for automatic optimization of radiotherapy planning.
Example 2
The invention provides an automatic planning method based on dose prediction and auxiliary contour generation, which is based on deep learning prediction dose distribution, automatically generates constraint conditions of auxiliary contour and dose limit required by optimization according to the dose distribution, and realizes automatic and efficient planning design by using a radiation treatment planning system and a script program thereof. The automatic lung cancer planning method based on dose prediction and auxiliary contour generation comprises a data set establishment module, a deep neural network dose prediction module, an anisotropic auxiliary contour generation module and a dose constraint limit generation module; the data set module is used for establishing a lung cancer radiotherapy plan case data set, and the case data set is high-quality reverse intensity modulated radiotherapy plan data approved to be implemented clinically, and comprises CT images, outline structures of a target area and a jeopardizing organ, minimum distance distribution from the target area and dose distribution; the deep neural network dose prediction module uses a deep neural network framework comprising Vgg-Unet, res-Unet, trans-Unet and uneXt; the anisotropic auxiliary contour generation module is used for generating an anisotropic auxiliary contour based on the dose predicted by the model according to the dose distribution characteristic of the lung cancer radiotherapy plan.
An anisotropic auxiliary profile is generated, including the area surrounded by the auxiliary profile around the target region, the width of each direction being different, and the area being defined by a specific isodose line or patient profile, depending on the predicted dose drop rate. The generation dose constraint limit module generates an auxiliary contour, a jeopardizing organ and a target area dose constraint condition according to the dose distribution, and introduces the auxiliary contour, the jeopardizing organ and the target area dose constraint condition into a planning system through an interface program for automatic optimization of radiotherapy planning.
Specific:
and establishing a case data set, wherein the case data set is intensity modulated radiation therapy planning data, and the intensity modulated radiation therapy planning data at least comprises a case CT image, a dose distribution, a target area, a jeopardized organ outline and a minimum distance distribution from a patient voxel to the target area.
The closest distance from the patient's ith point to the target area is defined as follows:
wherein D is i Representing the closest distance of the ith voxel to the target region target, (x) i 、y i 、z i ) Is the coordinates of the ith point, (x k 、y k 、z k ) Is the coordinates of the k point on the target. When voxel i is located within the target region or outside the patient's body, D i Defined as 0.
And performing deep learning training on CT images, target areas, and endangered organ outlines in the data set, minimum distance distribution information from voxels to the target areas and dose distribution, and constructing a three-dimensional dose prediction model.
The case data is input into a trained deep learning based predictive model, and a predicted dose of the target region and the organ at risk has been obtained.
The auxiliary profile generation is to generate an anisotropic auxiliary profile based on the predicted dose distribution in combination with dose constraints required for inverse optimization. When the auxiliary contour is generated, the generated auxiliary contour Ring1 is a region of interest surrounded by a 95% prescription dose line and a 90% prescription dose line. When the auxiliary contour is generated, the generated auxiliary contour Ring2 is a region of interest surrounded by a 90% prescription dose line and an 85% prescription dose line.
When the auxiliary contour is generated, the generated auxiliary contour Nt is a region of interest surrounded by a 70% prescription dose line and a body surface contour. When the auxiliary contour is generated, the generated auxiliary contour Fan is a region of interest surrounded by a 50% prescription dose line and a body surface contour.
The dose limiting conditions of the auxiliary profile, the organs at risk and the target area are calculated by a program algorithm based on the dose distribution. And converting the dose limiting conditions into the optimizing conditions of the system through a script program of the planning system, and completing the subsequent optimization.
In summary, the automatic planning method based on dose prediction and auxiliary contour generation according to the embodiment brings the minimum distance distribution from the patient voxel to the target area into model training, thereby improving the accuracy of dose prediction; the auxiliary profile is generated by using the dose distribution, so that the optimization condition/target is more reasonable, and the planning and design time is greatly shortened; in normal tissue protection, the automatic planning method is beneficial to the protection of the lung of the organs at risk; the automatic completion of the design of the lung cancer radiotherapy plan is beneficial to the rapid improvement of the plan design level of the units with insufficient radiotherapy experience.
Example 3
As shown in fig. 1, in embodiment 3, a flowchart of an automatic lung cancer planning method based on dose prediction and auxiliary contour generation is provided, which includes functional modules of data set establishment, model training, auxiliary contour generation, and dose constraint limit generation.
The established data set is intensity modulated radiotherapy plan data of a lung cancer patient, CT images, outline structures (including target areas and organs at risk) and dose distribution are extracted from a radiotherapy plan, the CT images, the outline structures and the dose distribution are converted into a three-dimensional matrix form, coordinate alignment is carried out on the three-dimensional matrix form, and the three-dimensional matrix form is stored in a file in a specified format (such as ". H5", ". Npz") for model training.
Wherein, the CT image is obtained by analog positioning CT scanning; the outline structure can be obtained by manually sketching on a CT image of a doctor, or can be obtained by automatically sketching by automatic sketching software, and in the embodiment, the outline structure of a target area and a jeopardy organ is obtained by manually sketching by the doctor; the dose distribution is the dose information calculated by the planning system; to increase the accuracy of model predictions, a minimum distance distribution is introduced as input data for model training.
Wherein, the nearest distance from the ith point to the target area is defined as follows:
wherein D is i Representing the closest distance of the ith voxel to the target region, (x) i 、y i 、z i ) Is the coordinates of the ith point, (x k 、y k 、z k ) Is the coordinates of the k point on the target. When voxel i is located within the target region or outside the patient's body, D i Defined as 0.
The model is trained to establish a deep learning network for dose prediction, the model network is of a 3D network structure, the model can select networks such as Vgg-Unet, res-Unet, trans-Unet, uneXt and the like, and the embodiment selects Vgg-Unet. The CT image, contour structure, minimum distance distribution are used as input data of the model, and the dose distribution is used as output data of the model. The dataset is divided into two parts, a training set and a validation set. The training set is used for training and optimizing the structural parameters of the deep neural network, and the verification set is used for evaluating the prediction effect of the model and preventing the model from being excessively fitted.
The deep neural network dose prediction module extracts abstract features from input data through a plurality of hidden layers, and the output layer predicts according to the extracted features. A neural network consists of neurons and connections between neurons. The neural network is divided into an input layer, a hidden layer, and an output layer. The "depth" of the deep neural network is reflected in more hidden layers, more flexible and complex connections, and a more powerful nonlinear representation than the shallow neural network, which can extract more essential features from the input image, thereby achieving more accurate predictions.
The generation of the auxiliary profile is an anisotropic auxiliary profile required to obtain a dose distribution from a predictive model and to obtain a reverse optimization from the dose distribution, as shown in fig. 2.
When the lung cancer is planned, the dosage is dropped at different speeds in the front-back direction and the left-right direction of the patient due to the stronger dosage limit value to the lung region. In this case, the dose limit using the auxiliary profile such as isotropy Ring, nt, fan may result in deterioration of the quality of the plan. The auxiliary profile of anisotropy generated based on the dose distribution in this embodiment is as follows:
ring1, the region of interest enclosed by the 95% and 90% prescription dose lines;
ring2, the region of interest enclosed by the 90% and 85% prescription dose lines;
nt, the region of interest enclosed by the 70% prescribed dose line and body surface contour.
The generated dose constraint limit is a dose constraint condition for calculating an auxiliary contour, a jeopardizing organ and a target area according to a dose distribution through a program algorithm. And converting the dose limiting conditions into the optimizing conditions of the system through a script program of the planning system, and completing the subsequent optimization.
Example 4
Embodiment 4 provides a non-transitory computer-readable storage medium for storing computer instructions which, when executed by a processor, implement a method of generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profiles as described above, the method comprising:
acquiring lung cancer radiotherapy planning case data;
processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target region and the organs at risk;
generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization;
obtaining a target region, a jeopardizing organ and a dose limit value of the auxiliary contour according to the auxiliary contour and the dose distribution;
and (5) performing reverse optimization according to the auxiliary profile and the dose constraint limit value to generate the lung cancer radiotherapy plan.
Example 5
This embodiment 5 provides a computer program product comprising a computer program for implementing a method of generating a lung cancer radiation therapy plan based on dose prediction and an auxiliary profile as described above, when run on one or more processors, the method comprising:
acquiring lung cancer radiotherapy planning case data;
processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target region and the organs at risk;
generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization;
obtaining a target region, a jeopardizing organ and a dose limit value of the auxiliary contour according to the auxiliary contour and the dose distribution;
and (5) performing reverse optimization according to the auxiliary profile and the dose constraint limit value to generate the lung cancer radiotherapy plan.
Example 6
Embodiment 6 provides an electronic device including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and wherein the computer program is stored in the memory, said processor executing the computer program stored in said memory when the electronic device is running, to cause the electronic device to execute instructions implementing a method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profiles as described above, the method comprising:
acquiring lung cancer radiotherapy planning case data;
processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target region and the organs at risk;
generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization;
obtaining a target region, a jeopardizing organ and a dose limit value of the auxiliary contour according to the auxiliary contour and the dose distribution;
and (5) performing reverse optimization according to the auxiliary profile and the dose constraint limit value to generate the lung cancer radiotherapy plan.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it should be understood that various changes and modifications could be made by one skilled in the art without the need for inventive faculty, which would fall within the scope of the invention.
Claims (10)
1. The lung cancer radiotherapy plan generation method based on dose prediction and auxiliary contour is characterized by comprising the following steps of:
acquiring lung cancer radiotherapy planning case data;
processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target region and the organs at risk;
generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization;
obtaining a target region, a jeopardizing organ and a dose limit value of the auxiliary contour according to the auxiliary contour and the dose distribution;
and (5) performing reverse optimization according to the auxiliary profile and the dose constraint limit value to generate the lung cancer radiotherapy plan.
2. The method of claim 1, wherein the dose prediction model is trained by a training set comprising a plurality of lung cancer radiotherapy plan cases including at least case CT images, dose distribution, target and organ-at-risk contours, minimum distance distribution of patient voxels to target; the model is trained based on the CT image, target and organ-at-risk contours, and the minimum distance distribution of patient voxels to the target as input data to the model, and the dose distribution as output from the model.
3. The method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary contour according to claim 2, wherein the closest distance from the ith point of the patient to the target region is defined as follows:
D i ＝Min((x i -x k ) 2 +(y i -y k ) 2 +(z i -z k ) 2 )
wherein D is i Representing the closest distance of the ith voxel to the target region target, (x) i 、y i 、z i ) Is the coordinates of the ith point, (x k 、y k 、z k ) Coordinates of a k point on the target area; when voxel i is located within the target region or outside the patient's body, D i Defined as 0.
4. The method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary contour according to claim 2, wherein training the dose prediction model uses a deep neural network framework including Vgg-uiet, res-uiet, trans-uiet, UNeXt.
5. The method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profile according to claim 2, wherein the anisotropic auxiliary profile is generated based on the model predicted dose according to the dose distribution characteristics of the lung cancer radiotherapy plan.
6. The method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profiles according to claim 5, wherein the auxiliary profiles are different around the target region along with the difference of the falling speed of the predicted dose, and the widths of the auxiliary profiles in all directions are different, and are the areas surrounded by specific isodose lines or patient profiles.
7. The method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profiles according to claim 6, wherein the generation of the dose constraint limit module is to generate the auxiliary profiles, the dose constraint conditions of the organs at risk and the target region according to the dose distribution, and introduce the dose constraint conditions into the planning system through an interface program for automatic optimization of the radiotherapy plan.
8. A lung cancer radiotherapy plan generation system based on dose prediction and auxiliary profiles, comprising:
the acquisition module is used for acquiring lung cancer radiotherapy planning case data;
the prediction module is used for processing the radiotherapy plan case data by using the trained dose prediction model to obtain a dose distribution result of the target area and the organs at risk;
a first determination module for generating an anisotropic auxiliary profile from the predicted dose distribution in combination with dose constraints required for inverse optimization;
a second determining module for obtaining a dose limit for the target region, the organ at risk and the auxiliary profile from the auxiliary profile and the dose distribution;
and the reverse optimization module is used for carrying out reverse optimization according to the auxiliary profile and the dose constraint limit value to generate a lung cancer radiotherapy plan.
9. A non-transitory computer readable storage medium storing computer instructions which, when executed by a processor, implement the dose prediction and auxiliary profile based lung cancer radiotherapy plan generation method of any one of claims 1-7.
10. An electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and wherein the computer program is stored in the memory, which processor, when the electronic device is running, executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the method for generating a lung cancer radiotherapy plan based on dose prediction and auxiliary profiles according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310616501.1A CN116688376A (en) | 2023-05-29 | 2023-05-29 | Lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310616501.1A CN116688376A (en) | 2023-05-29 | 2023-05-29 | Lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116688376A true CN116688376A (en) | 2023-09-05 |
Family
ID=87835036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310616501.1A Pending CN116688376A (en) | 2023-05-29 | 2023-05-29 | Lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116688376A (en) |
-
2023
- 2023-05-29 CN CN202310616501.1A patent/CN116688376A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11386557B2 (en) | Systems and methods for segmentation of intra-patient medical images | |
| CN110197709B (en) | Three-dimensional dose prediction method based on deep learning and priori planning | |
| CN108717866B (en) | Method, device, equipment and storage medium for predicting radiotherapy plan dose distribution | |
| CN106920234B (en) | Combined automatic radiotherapy planning method | |
| CN106029170B (en) | The establishment of increment treatment plan | |
| CN104117151A (en) | Optimization method of online self-adaption radiotherapy plan | |
| CN110415785A (en) | The method and system of artificial intelligence guidance radiotherapy planning | |
| CN112546463B (en) | Radiotherapy dose automatic prediction method based on deep neural network | |
| CN103566489A (en) | Treatment planning system | |
| CN106682409B (en) | Sampling method, radiotherapy plan optimization method and dose calculation method | |
| CN110124214A (en) | Intensity modulated radiation therapy plan optimization method and application based on predicted dose distribution guidance | |
| CN104815392B (en) | A kind of interactive radiotherapy treatment planning system optimization system | |
| JP2016520385A (en) | Interactive dose gradient based optimization method to control IMRT delivery complexity | |
| CN104636618B (en) | Radiotherapy planning system | |
| CN102722641B (en) | Method for quickly obtaining dose distribution in concave tumor target region | |
| CN107349531A (en) | A kind of radiotherapy apparatus, storage medium, Ziye shape generation method and device | |
| CN110706779B (en) | Automatic generation method of accurate target function of radiotherapy plan | |
| CN116688376A (en) | Lung cancer radiotherapy plan generation method and system based on dose prediction and auxiliary contour | |
| CN116785601A (en) | Method and system for robust radiotherapy treatment planning with dose mapping uncertainty | |
| CN105477789A (en) | Dynamic intensity-modulated radiotherapy method based on quadratic programming model suppressing total beam-out time | |
| CN113178242B (en) | Automatic plan optimization system based on coupled generation countermeasure network | |
| CN112635023B (en) | Method for generating dose prediction model of nasopharyngeal carcinoma, dose prediction method and device | |
| Liu et al. | A fast online replanning algorithm based on intensity field projection for adaptive radiotherapy | |
| Chandran et al. | MemU-Net: A new volumetric dose prediction model using deep learning techniques in radiation treatment planning | |
| CN117456315B (en) | Training method and device for dose prediction model and computer readable storage medium |
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 |