CN116052840B - Dose distribution data processing device based on radiotherapy, electronic equipment and storage medium - Google Patents
Dose distribution data processing device based on radiotherapy, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116052840B CN116052840B CN202310338802.2A CN202310338802A CN116052840B CN 116052840 B CN116052840 B CN 116052840B CN 202310338802 A CN202310338802 A CN 202310338802A CN 116052840 B CN116052840 B CN 116052840B
- Authority
- CN
- China
- Prior art keywords
- data
- dose distribution
- model
- distribution data
- target
- 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
Images
Classifications
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Radiology & Medical Imaging (AREA)
- Surgery (AREA)
- Urology & Nephrology (AREA)
- Radiation-Therapy Devices (AREA)
Abstract
The application discloses a dose distribution data processing device based on radiotherapy, electronic equipment and a storage medium. Wherein the device includes: the acquisition module is used for acquiring a target image and first dose distribution data corresponding to a target object; the data processing module is used for processing the first dose distribution data and the target image through the target model to obtain target dose distribution data, wherein the similarity of the target dose distribution data and the second dose distribution data is larger than that of the first dose distribution data and the second dose distribution data, and the second dose distribution data is used for representing dose distribution information corresponding to a target object calculated by using a simulation algorithm. The method and the device solve the technical problems that in the prior art, when a radiotherapy plan is optimized, precision and speed cannot be considered when intermediate dose distribution data with high similarity of dose distribution data in the final radiotherapy plan are generated, and the resulting radiotherapy plan is low in optimization efficiency.
Description
Technical Field
The present application relates to the field of medical science and technology, and in particular, to a radiotherapy-based dose distribution data processing device, an electronic device, and a storage medium.
Background
Tumor therapy is an important part of current clinical medicine, among which radiation therapy technology, chemotherapy technology, and surgical therapy technology are called as three-major tumor therapy means. Currently, before radiation treatment is performed on a patient, in order to improve the treatment effect of radiation treatment, a radiation treatment plan needs to be formulated according to the specific situation of each patient, and factors such as the size, shape, position, surrounding organ distribution and the like of a tumor are considered.
In addition, when a proper radiation treatment plan is formulated for a patient, a radiation therapy physical operator needs to repeatedly perform dose adjustment and simulation in a radiation treatment planning system to realize optimization of the radiation treatment plan, and this process can also be defined as a process of intermediate dose correction, and as the radiation therapy physical operator optimizes the radiation treatment plan continuously, the resulting intermediate dose is also closer to the dose in the final radiation treatment plan.
However, there are significant drawbacks to the current optimization of radiation treatment plans, for example, if the intermediate dose is calculated in a simulation using the Monte Carlo dose algorithm during the optimization of radiation treatment plans, the simulation effect is close to the true level, but the single calculation time is long; if a dose calculation method with a higher speed but lower accuracy is selected in the optimization process of the radiation treatment plan, for example, a pencil beam algorithm, an anisotropic analysis algorithm, a cone beam convolution algorithm and other algorithms are used for analog calculation of the intermediate dose, although the determination speed of the intermediate dose can be improved, due to the poor accuracy of such algorithms, a problem that a proper modification direction cannot be determined may occur when the radiation treatment plan is optimized based on the dose calculation result later, and thus the optimization time of the overall plan may also be increased.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The application provides a dose distribution data processing device, electronic equipment and storage medium based on radiotherapy to solve at least prior art when optimizing the radiotherapy plan, can't compromise precision and speed when generating the intermediate dose distribution data that dose distribution data similarity is high with final radiotherapy plan, the radiotherapy plan that leads to optimizes the technical problem that inefficiency.
According to an aspect of the present application, there is provided a radiotherapy-based dose distribution data processing apparatus comprising: the acquisition module is used for acquiring a target image corresponding to a target object and first dose distribution data, wherein the target image at least comprises a CT image corresponding to the target object, a contour sketch image of a target radiotherapy target area of the target object and a contour sketch image corresponding to a target organs at risk of the target object, and the first dose distribution data is used for representing dose distribution information to be evaluated corresponding to the target object; the data processing module is used for processing the first dose distribution data and the target image through the target model to obtain target dose distribution data, wherein the similarity of the target dose distribution data and the second dose distribution data is larger than that of the first dose distribution data and the second dose distribution data, and the second dose distribution data is used for representing dose distribution information corresponding to a target object calculated by using a simulation algorithm.
Further, the data processing module includes: the first data conversion unit is used for converting the first dose distribution data into first data through a first model branch in the target model, wherein the robustness corresponding to the multi-granularity information in the first data is higher than that in the first dose distribution data; the second data conversion unit is used for converting the first dose distribution data into second data through a second model branch in the target model, wherein the accuracy corresponding to the profile information in the second data is greater than that in the first dose distribution data; the data processing unit is used for processing the first data, the second data and the target image through a third model branch in the target model to obtain target dose distribution data.
Further, the radiotherapy-based dose distribution data processing apparatus further includes: the first acquisition module is used for acquiring intermediate dose distribution data corresponding to the historical cases, wherein the intermediate dose distribution data is used for representing dose distribution information to be optimized corresponding to the historical cases; the third data generation module is used for carrying out interpolation complement processing on the intermediate dose distribution data to obtain third data, wherein the interpolation complement processing is used for carrying out data filling on the intermediate dose distribution data so as to improve the continuity of the data in the intermediate dose distribution data; and the model generating module is used for generating a target model according to the third data.
Further, the model generating module includes: the fourth data generation unit is used for carrying out isodose line regional processing on the third data to obtain fourth data, wherein the isodose line regional processing is used for improving the robustness corresponding to the multi-granularity information in the data; the fifth data generation unit is used for carrying out dose change gradient processing on the third data to obtain fifth data, wherein the dose change gradient processing is used for improving the accuracy corresponding to the profile information in the data; and the model generating unit is used for generating a target model according to the fourth data and the fifth data.
Further, the model generation unit includes: the first model branch generation subunit is used for training according to the fourth data and first historical data corresponding to the historical cases to obtain a first model branch in the target model, wherein the first historical data is a training label used for training the first model branch; the second model branch generation subunit is used for training to obtain a second model branch in the target model according to fifth data and second historical data corresponding to the historical cases, wherein the second historical data is a training label used for training the second model branch; and the model generation subunit is used for generating a target model according to the first model branch and the second model branch.
Further, the radiotherapy-based dose distribution data processing apparatus further includes: the second acquisition module is used for acquiring a historical image corresponding to the historical case and third dose distribution data, wherein the historical image at least comprises a CT image corresponding to the historical case, a contour sketch image of a radiotherapy target zone of the historical case and a contour sketch image corresponding to a organs at risk of the historical case, and the third dose distribution data is used for representing dose distribution information in an actual radiotherapy plan corresponding to the historical case; the first historical data generation module is used for carrying out isodose line regional treatment on the third dose distribution data to obtain first historical data; and the second historical data generation module is used for carrying out dose change gradient processing on the third dose distribution data to obtain second historical data.
Further, the first model branch generating subunit includes: the first neural network branch processing submodule is used for carrying out iterative optimization processing on the first neural network branch according to the fourth data until the first neural network branch subjected to the iterative optimization processing can adjust the fourth data into sixth data, and determining the first neural network branch at the current moment as a first model branch, wherein the similarity between the sixth data and the first historical data is greater than or equal to the preset similarity; and/or, a second model branch generation subunit comprising: the second neural network branch processing submodule is used for carrying out iterative optimization processing on the second neural network branch according to the fifth data until the second neural network branch subjected to the iterative optimization processing can adjust the fifth data into seventh data, and determining the second neural network branch at the current moment as a second model branch, wherein the similarity of the seventh data and the second historical data is greater than or equal to the preset similarity.
Further, the model generation subunit includes: a third model branch generation sub-module for generating a third model branch in the target model according to the historical image, the sixth data, the seventh data and the third data; the model generation sub-module is used for generating a target model according to the first model branch, the second model branch and the third model branch.
Further, the third model leg generation submodule includes: the third neural network branch processing submodule is used for carrying out iterative optimization processing on the third neural network branch according to the historical image, the sixth data, the seventh data and the third data until the third neural network branch subjected to the iterative optimization processing can output eighth data, and determining that the third neural network branch at the current moment is a third model branch, wherein the similarity of the eighth data and the third dose distribution data is greater than or equal to the preset similarity, and the third dose distribution data is used for representing dose distribution information in an actual radiotherapy plan corresponding to a historical case.
According to another aspect of the present application, there is also provided a computer readable storage medium having a computer program stored therein, wherein the computer program is controlled to control the radiotherapy-based dose distribution data processing apparatus described above by a device in which the computer readable storage medium is located when the computer program is run.
According to another aspect of the present application there is also provided an electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to control the radiotherapy-based dose distribution data processing apparatus described above.
As can be seen from the foregoing, the target model obtained by training processes the first dose distribution data and the target image input to the target model to obtain the target dose distribution data, where the first dose distribution data is the dose distribution information to be evaluated in the process of optimizing the radiotherapy plan, and the target dose distribution data is the intermediate dose distribution data obtained in the process of optimizing the radiotherapy plan, and since the time spent for realizing dose distribution reconstruction in use of the deep learning model is very short, and the accuracy of the obtained intermediate dose distribution data is higher than that of the intermediate dose distribution data calculated by the low-accuracy algorithms such as the pencil beam algorithm, the anisotropic analysis algorithm, the cone beam convolution algorithm, and the like, the technical scheme of the present application overcomes the technical defect that the radiotherapy plan optimization efficiency is low due to the fact that the accuracy and the speed cannot be considered when the intermediate dose distribution data with high similarity between the dose distribution data in the generated and the final radiotherapy plan is optimized in the prior art.
Therefore, the technical scheme of the application achieves the aim of considering precision and speed when calculating the intermediate dose distribution data, so that the problem that the precision and speed cannot be considered when the intermediate dose distribution data with high similarity between the dose distribution data in the final radiotherapy plan is generated when the radiotherapy plan is optimized in the prior art, the efficiency of optimizing the radiotherapy plan is low, and the technical effect of shortening the overall optimization time of the radiotherapy plan is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a schematic view of a radiotherapy-based dose distribution data processing apparatus according to an embodiment of the present application;
FIG. 2 is an alternative target dose distribution data generation flow chart according to an embodiment of the present application;
FIG. 3 is a flowchart of an alternative training process for a target model according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, related information (including, but not limited to, user equipment information, user personal information, and electronic medical record information of a user) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.
The present application is further illustrated below in conjunction with various embodiments.
Example 1
According to an embodiment of the present application, there is provided a dose distribution data processing device based on radiotherapy. Wherein, fig. 1 is a schematic diagram of a radiotherapy-based dose distribution data processing apparatus according to an embodiment of the present application, and as shown in fig. 1, the radiotherapy-based dose distribution data processing apparatus includes the following modules:
the acquiring module 101 is configured to acquire a target image corresponding to a target object and first dose distribution data, where the target image at least includes a CT image corresponding to the target object, a contour sketch image of a target radiotherapy target area of the target object, and a contour sketch image corresponding to a target organs at risk of the target object, and the first dose distribution data is used to characterize dose distribution information to be evaluated corresponding to the target object.
It should be noted that the target object is a patient to be treated with radiation. The first dose distribution data is sparse intermediate dose distribution data used in optimizing the radiotherapy plan of the target object, and it should be noted that the sparse intermediate dose distribution data may be represented in an image form such as a two-dimensional array or a three-dimensional array, and therefore, the first dose distribution data may also be referred to as a sparse intermediate dose distribution map. In addition, the first dose distribution data is not dose distribution data actually applied to the radiation treatment of the target object, but is only reference dose distribution data selected for planning the radiation treatment of the target object.
In addition, the radiotherapy-based dose distribution data processing apparatus further includes a data processing module 102 configured to process the first dose distribution data and the target image through the target model to obtain target dose distribution data, where a similarity between the target dose distribution data and the second dose distribution data is greater than a similarity between the first dose distribution data and the second dose distribution data, and the second dose distribution data is used to characterize dose distribution information corresponding to the target object calculated using the simulation algorithm.
Optionally, the target model is a deep learning neural network model which is trained in advance, and the target dose distribution data can be understood as intermediate dose distribution data in the process of optimizing the radiotherapy plan of the target object, which is the same as the first dose distribution data, and the target dose distribution data can also be represented by a two-dimensional array or a three-dimensional array and other image forms, so that the target dose distribution data can also be called a corrected dose distribution map.
It should be noted that the target dose distribution data is dose distribution data obtained by correcting the first dose distribution data by using the target model, and therefore, compared with the first dose distribution data, the target dose distribution data is closer to the second dose distribution data, i.e., the similarity between the target dose distribution data and the second dose distribution data is greater than the similarity between the first dose distribution data and the second dose distribution data. The second dose distribution data is used for representing dose distribution information corresponding to the target object calculated by using model algorithms such as a Monte Carlo dose algorithm. In the field of radiotherapy, the monte carlo dose algorithm is called an algorithm used by a gold standard, the accuracy of dose distribution data obtained by simulation calculation by using the algorithm is high and is close to a real level, but the monte carlo dose algorithm also has a disadvantage that single calculation time is long, and although a lot of acceleration methods at present use a GPU to calculate the monte carlo dose algorithm, because the GPU acceleration is limited by parallel programming and hardware level, a method capable of well considering calculation accuracy and calculation time is not available at present under the condition of the same hardware level.
However, if a dose calculation method with a relatively high speed but reduced accuracy is selected in the optimization process of the radiation treatment plan, such as a pencil beam algorithm, an anisotropic analysis algorithm, a cone beam convolution algorithm, etc., it is possible that a proper modification direction cannot be determined when the radiation treatment plan is subsequently optimized for the dose result adjustment, thereby increasing the overall plan optimization time.
In order to solve the problems, the target model obtained through training processes the first dose distribution data and the target image input into the target model to obtain target dose distribution data, and because the time spent for realizing dose distribution reconstruction in use of the deep learning model is very short, compared with a Monte Carlo dose algorithm, the intermediate dose distribution data can be obtained faster, and the accuracy of the obtained intermediate dose distribution data is higher than that of the intermediate dose distribution data calculated by a pencil beam algorithm, an anisotropic analysis algorithm, a cone beam convolution algorithm and other low-accuracy algorithms, the technical scheme of the application solves the problems that in the conventional radiation treatment plan optimization, the accuracy and the speed cannot be considered when the conventional intermediate dose correction method generates and finally executes the intermediate dose with high dose similarity in the radiation treatment plan, so that the radiation treatment plan optimization efficiency is low.
In addition, in the practical application process of the technical scheme of the application, the second dose distribution data is not required to be calculated truly by using the Monte Carlo dose algorithm, and only the target dose distribution data is required to be output through the target model. The second dose distribution data is presented in order to more clearly illustrate, on the one hand, that the adjustment process of the intermediate dose distribution data is such that the resulting intermediate dose distribution data is gradually closer to the second dose distribution data, and, on the other hand, that the difference between the target dose distribution data and the first dose distribution data, i.e. the target dose distribution data is closer to the second dose distribution data than the first dose distribution data, is described more clearly.
In an alternative embodiment, the data processing module in the radiotherapy-based dose distribution data processing apparatus further comprises: a first data conversion unit, a second data conversion unit and a data processing unit.
Specifically, the first data conversion unit is configured to convert the first dose distribution data into first data through a first model branch in the target model, where robustness corresponding to multi-granularity information in the first data is higher than robustness corresponding to multi-granularity information in the first dose distribution data.
And the second data conversion unit is used for converting the first dose distribution data into second data through a second model branch in the target model, wherein the accuracy corresponding to the profile information in the second data is greater than that in the first dose distribution data.
The data processing unit is used for processing the first data, the second data and the target image through a third model branch in the target model to obtain target dose distribution data.
Optionally, fig. 2 shows an optional target dose distribution data generation flowchart according to an embodiment of the present application, where the generation of the target dose distribution data may be divided into at least two processes, the first process being a preprocessing process and the second process being a model processing process.
Specifically, as shown in fig. 2, in the preprocessing process, the radiotherapy-based dose distribution data processing apparatus first performs interpolation and complementation processing on the sparse intermediate dose distribution map (corresponding to the first dose distribution data) to obtain a target dense intermediate dose distribution map corresponding to the target object. It should be noted that the interpolation process is applicable to the case where the dose distribution map is discontinuous due to sparse sampling, and by numerically filling the discontinuous sparse intermediate dose distribution map with the interpolation process, a continuous dose map (i.e., a target dense intermediate dose distribution map) close to the actual effect can be generated.
In an alternative embodiment, if the data continuity of the first dose distribution data is high, which itself may be regarded as a dense intermediate dose distribution map, no interpolation may be performed.
Optionally, as shown in fig. 2, after the sparse intermediate dose distribution map is converted into the target dense intermediate dose distribution map, the dose distribution data processing device based on radiotherapy performs isodose line regionalization on the target dense intermediate dose distribution map, and assuming that the target dense intermediate dose distribution map after the isodose line regionalization is an initial isodose line region map, the dose distribution data processing device based on radiotherapy inputs the initial isodose line region map into a dose reconstruction model B (corresponding to a first model branch in the target model), where the dose reconstruction model B is used to enhance robustness of multi-granularity information in the initial isodose line region map, and the dose reconstruction model B outputs the target isodose line region map (corresponding to the first data).
In addition, as shown in fig. 2, the radiotherapy-based dose distribution data processing apparatus further performs dose variation gradient processing on the target dense intermediate dose distribution map, and assuming that the target dense intermediate dose distribution map after the dose variation gradient processing is an initial dose variation gradient map, the radiotherapy-based dose distribution data processing apparatus inputs the initial dose variation gradient map into a dose reconstruction model C (corresponding to a second model branch in the target model), where the dose reconstruction model C is used to enhance the accuracy of contour information in the initial dose variation gradient map, and the dose reconstruction model C outputs the target dose variation gradient map (corresponding to the second data).
Furthermore, as shown in fig. 2, after the target dose change gradient map and the target isodose region map are obtained, the radiotherapy-based dose distribution data processing apparatus inputs all of the target dose change gradient map, the target isodose region map, and the target image into the dose reconstruction model a (corresponding to the third model branch in the target model), and then the dose reconstruction model a outputs the corrected dose distribution map (corresponding to the target dose distribution data).
In an alternative embodiment, equation (1) is an isodose line localized loss function Liso with which the first model leg can be trained.
Wherein, in the formula (1),
，/>
。
additionally, in an alternative embodiment, equation (2) is a dose gradient loss function Lgra with which the second model leg may be trained.
Wherein in the formula (1) and the formula (2), W is width (one of two-dimensional image size parameters); h is height (one of two-dimensional image size parameters);
and +.>
Representing the average division of the dose into several intervals, representing the upper and lower limits of a certain interval corresponding to the dose value, e.g.>
For dose after reconstitution->
The interval in which the Chinese herb is located is similarly- >
For the dose as tag (label)>
In the interval where m and n may be the same or different, preferably, m and n are the same value in the present application. S () characterizes the graded dose (realized based on sobel operator).
In addition, it should be noted that for complex cancer species such as nasopharyngeal carcinoma, a larger number of radiation fields are used in preparing a radiotherapy plan in order to ensure protection of peripheral organs, and clinical dose distribution is complex. In this case, the use of only bilinear differences in the preprocessing to achieve dose distribution completion based on the linear relationship between similar pixels necessarily results in a significant loss of information in the input provided by the model. The method and the device can provide additional priori knowledge close to actual conditions by training the additional isodose line regional and gradient reconstruction model, and effectively improve the accuracy of the reconstruction model in the main task.
In other words, the first model branch and the second model branch in the application can be regarded as auxiliary branches of the third model branch, and the first model branch and the second model branch are obtained through training in advance, so that more accurate auxiliary information can be provided for the input of the third model branch to compensate for the problem that the original sparse intermediate dose graph serving as the input is inaccurate. It can be understood that: the third model branch needs to be input and output, and under the condition that the original input data is inaccurate, the output result obtained when the new input data is replaced after the training of the third model branch is finished is still not necessarily accurate. In order to solve this problem, before the training of the third model branch is completed, training of two additional model branches (i.e., the first model branch and the second model branch) is completed, and since the two model branches have been trained and the outputs of the two model branches have been calibrated to some extent, it is clear that the accuracy of the input data of the third model branch can be improved when the two more accurate outputs are input as auxiliary information into the third model branch, and thus the accuracy of the output result of the third model branch is improved.
The training process of the target model in the present application is described below.
In an alternative embodiment, the radiotherapy-based dose distribution data processing apparatus further comprises: the system comprises a first acquisition module, a third data generation module and a model generation module.
Specifically, the first acquisition module is configured to acquire intermediate dose distribution data corresponding to a historical case, where the intermediate dose distribution data is used to characterize dose distribution information to be optimized corresponding to the historical case.
And the third data generation module is used for carrying out interpolation complement processing on the intermediate dose distribution data to obtain third data, wherein the interpolation complement processing is used for carrying out data filling on the intermediate dose distribution data so as to improve the continuity of the data in the intermediate dose distribution data.
And the model generating module is used for generating a target model according to the third data.
In the present application, the model is trained according to the dose distribution information used by the history case in the actual treatment process, so that the accuracy of the prediction of the target model can be ensured.
Alternatively, FIG. 3 shows a flowchart of an alternative training process for a target model according to an embodiment of the present application. As shown in fig. 3, first, the first acquisition module acquires intermediate dose distribution data corresponding to the historical case, where the intermediate dose distribution data corresponding to the historical case is also a sparse intermediate dose map. Then, the third data generating module performs interpolation complement processing on the intermediate dose distribution data so as to obtain a dense intermediate dose map with better data continuity, namely third data. Finally, a model generating module in the radiotherapy-based dose distribution data processing device trains and generates a target model according to the third data.
In an alternative embodiment, the model generation module includes: a fourth data generating unit, a fifth data generating unit and a model generating unit.
Specifically, the fourth data generating unit is configured to perform isodose line regionalization processing on the third data to obtain fourth data, where the isodose line regionalization processing is used to improve robustness corresponding to multi-granularity information in the data.
And a fifth data generation unit, configured to perform dose change gradient processing on the third data to obtain fifth data, where the dose change gradient processing is used to improve accuracy corresponding to the profile information in the data.
And the model generating unit is used for generating a target model according to the fourth data and the fifth data.
Optionally, as shown in fig. 3, after the third data is generated, the fourth data generating unit in the model generating module performs isodose line regionalization on the third data to obtain fourth data. In addition, the fifth data generating unit in the model generating module also performs dose change gradient processing on the third data to obtain fifth data. It should be noted that the generation process of the fourth data and the generation process of the fifth data may be performed synchronously or asynchronously.
Finally, a model generating unit in the model generating module trains and generates a target model according to the fourth data and the fifth data.
In an alternative embodiment, the model generating unit further comprises: the model generation system comprises a first model branch generation subunit, a second model branch generation subunit and a model generation subunit.
Specifically, the first model branch generation subunit is configured to train to obtain a first model branch in the target model according to the fourth data and first historical data corresponding to the historical case, where the first historical data is a training label used when training the first model branch.
The second model branch generation subunit is used for training to obtain a second model branch in the target model according to the fifth data and second historical data corresponding to the historical cases, wherein the second historical data is a training label used for training the second model branch.
And the model generation subunit is used for generating a target model according to the first model branch and the second model branch.
Alternatively, the dose reconstruction model B in fig. 3 is the first model branch described above, and the dose reconstruction model C in fig. 3 is the second model branch described above.
In an alternative embodiment, the first historical data is used as training labels when training the first model leg and the second historical data is used as training labels when training the second model leg. Therefore, the radiotherapy-based dose distribution data processing device needs to acquire the first historical data and the second historical data in advance, and the two historical data acquisition processes are as follows:
The radiotherapy-based dose distribution data processing apparatus further comprises: the second acquisition module is used for acquiring a historical image corresponding to the historical case and third dose distribution data, wherein the historical image at least comprises a CT image corresponding to the historical case, a contour sketch image of a radiotherapy target zone of the historical case and a contour sketch image corresponding to a organs at risk of the historical case, and the third dose distribution data is used for representing dose distribution information in an actual radiotherapy plan corresponding to the historical case.
The radiotherapy-based dose distribution data processing apparatus further comprises: the first historical data generation module is used for carrying out isodose line regional treatment on the third dose distribution data to obtain first historical data;
the radiotherapy-based dose distribution data processing apparatus further comprises: and the second historical data generation module is used for carrying out dose change gradient processing on the third dose distribution data to obtain second historical data.
It should be noted that the third dose distribution data is dose distribution information in the actual radiotherapy plan corresponding to the historical case. For example, assuming that the history case is the history patient 1, if the dose distribution data in the radiotherapy plan used by the history patient 1 during the actual treatment is the dose distribution data 1-1, the dose distribution data 1-1 is the third dose distribution data corresponding to the history patient 1. It is easy to understand that training the model using dose distribution data actually applied by the historic patient can ensure that the predicted outcome of the trained model approaches the real outcome to the greatest extent.
In addition, in practical applications, in order to ensure the robustness of the target model, a plurality of the number of historical cases is required, and a plurality of corresponding third dose distribution data is also required.
Further, based on the third dose distribution data, the dose distribution data processing device based on radiotherapy performs isodose line regionalization processing on the third dose distribution data through the first historical data generating module to obtain first historical data. Meanwhile, the dose distribution data processing device based on radiotherapy carries out dose change gradient processing on the third dose distribution data through the second historical data generating module to obtain second historical data.
Since the third dose distribution data, the first history data, and the second history data may all be represented in the form of images such as a two-dimensional array or a three-dimensional array, the third dose distribution data may be represented by a GT-dose map, the first history data may be represented by a GT-isodose line region map, and the second history data may be represented by a GT-dose change gradient map.
In an alternative embodiment, as shown in fig. 3, the first model leg generation subunit includes: the first neural network branch processing submodule is used for carrying out iterative optimization processing on the first neural network branch according to the fourth data until the first neural network branch subjected to the iterative optimization processing can adjust the fourth data into sixth data, and determining the first neural network branch at the current moment as a first model branch (namely a dose reconstruction model B in fig. 3), wherein the similarity between the sixth data and the first historical data is greater than or equal to a preset similarity; and/or, a second model branch generation subunit comprising: the second neural network branch processing sub-module is configured to perform iterative optimization processing on the second neural network branch according to the fifth data until the second neural network branch after the iterative optimization processing can adjust the fifth data to seventh data, and determine that the second neural network branch at the current moment is a second model branch (i.e. a dose reconstruction model C in fig. 3), where a similarity between the seventh data and the second historical data is greater than or equal to a preset similarity.
Optionally, after the fourth data is obtained, the dose distribution data processing device based on radiotherapy inputs the fourth data into the first neural network branch, then the first neural network branch adjusts the fourth data to obtain an adjusted fourth data, the dose distribution data processing device based on radiotherapy compares the adjusted fourth data with the first historical data, and if the similarity between the adjusted fourth data and the first historical data is greater than or equal to a preset similarity, the dose distribution data processing device based on radiotherapy determines that the adjusted fourth data is sixth data, and the current first neural network branch is the first model branch. However, if the similarity between the adjusted fourth data and the first historical data is smaller than the preset similarity, the dose distribution data processing device based on radiotherapy performs optimization adjustment on the first neural network branch, adjusts the fourth data again through the optimized and adjusted first neural network branch, if the similarity between the adjusted fourth data and the first historical data is larger than or equal to the preset similarity, the dose distribution data processing device based on radiotherapy determines that the optimized and adjusted first neural network branch is the first model branch, and if the similarity between the adjusted fourth data and the first historical data is still smaller than the preset similarity, the first neural network branch is continuously adjusted until the first neural network branch after iterative optimization processing can adjust the fourth data into sixth data, and the first model branch is obtained.
Similarly, after the fifth data is obtained, the dose distribution data processing device based on radiotherapy inputs the fifth data into the second neural network branch, then the second neural network branch adjusts the fifth data to obtain adjusted fifth data, the dose distribution data processing device based on radiotherapy compares the adjusted fifth data with the second historical data, if the similarity between the adjusted fifth data and the second historical data is greater than or equal to a preset similarity, the dose distribution data processing device based on radiotherapy determines that the adjusted fifth data is seventh data, and the current second neural network branch is the second model branch. However, if the similarity between the adjusted fifth data and the second historical data is smaller than the preset similarity, the dose distribution data processing device based on radiotherapy performs optimization adjustment on the second neural network branch, and adjusts the fifth data again through the optimized and adjusted second neural network branch, if the similarity between the adjusted fifth data and the second historical data is larger than or equal to the preset similarity, the dose distribution data processing device based on radiotherapy determines that the optimized and adjusted second neural network branch is the second model branch, and if the similarity between the adjusted fifth data and the second historical data is still smaller than the preset similarity, the second neural network branch is continuously adjusted until the second neural network branch after iterative optimization processing can adjust the fifth data into seventh data, so as to obtain the second model branch.
In an alternative embodiment, the model generation subunit further comprises: the third model branch generation sub-module and the model generation sub-module. The third model branch generation submodule is used for generating a third model branch in the target model according to the historical image, the sixth data, the seventh data and the third data; the model generation sub-module is used for generating a target model according to the first model branch, the second model branch and the third model branch.
Optionally, the third model leg generation submodule includes: the third neural network branch processing submodule is used for carrying out iterative optimization processing on the third neural network branch according to the historical image, the sixth data, the seventh data and the third data until the third neural network branch subjected to the iterative optimization processing can output eighth data, and determining that the third neural network branch at the current moment is a third model branch, wherein the similarity of the eighth data and the third dose distribution data is greater than or equal to the preset similarity, and the third dose distribution data is used for representing dose distribution information in an actual radiotherapy plan corresponding to a historical case.
As shown in fig. 3, the dose reconstruction model a in fig. 3 is the third model branch described above. When the third model branch is generated, the third neural network branch processing submodule inputs the historical image, the sixth data, the seventh data and the third data into the third neural network branch, detects whether the data output by the third neural network branch is eighth data with the similarity greater than or equal to the preset similarity with the third dose distribution data, and determines that the third neural network branch at the moment is the third model branch if the third neural network branch does not output the eighth data, and performs optimization adjustment on the third neural network branch if the third neural network branch outputs the eighth data.
It should be noted that the preset similarity can be set in a user-defined manner according to actual situations, which is not limited in the present application.
In an alternative embodiment, the radiotherapy-based dose distribution data processing apparatus further comprises: the device comprises a first computing module, a second computing module and a fourth determining module.
Specifically, a first calculation module is configured to calculate an average absolute error between the first dose distribution data and the second dose distribution data, so as to obtain a first numerical value; the second calculation module is used for calculating the average absolute error between the target dose distribution data and the second dose distribution data to obtain a second numerical value; and the fourth determining module is used for determining the accuracy of the target model according to the second numerical value and the first numerical value.
Optionally, the fourth determining module includes: the calculating unit is used for calculating the ratio of the second value to the first value; and the determining unit is used for determining the accuracy of the target model according to the ratio, wherein the accuracy of the target model and the ratio are in a negative correlation relationship.
Optionally, in order to evaluate the performance of the target model, the average absolute error (Mean Absolute Error) is calculated by using the target dose distribution data generated by the target model and the first dose distribution data as the initial input and the second dose distribution data as the correction target, and it is assumed that the ratio of the average absolute errors obtained by the previous and subsequent calculation is X, and the smaller X is the better the correction performance of the target model.
In an alternative embodiment, when generating the target dose distribution data corresponding to the target object, the radiotherapy-based dose distribution data processing device in the application needs to perform interpolation complement processing on the first dose distribution data in the preprocessing process, and perform normalization processing on the first dose distribution data and the target image, so that potential problems possibly caused by magnitude differences in the data are eliminated.
In addition, in the present application, the target model is actually a multi-task learning model, and in the target model, two branches of an isodose line region map reconstruction branch (i.e., a first model branch) and a dose change gradient map reconstruction branch (i.e., a second model branch) are added in addition to a third model branch which is a target dose reconstruction route. Wherein, three model branches are all realized by super-resolution networks.
Finally, the radiotherapy-based dose distribution data processing apparatus further comprises two modules: the normalization compensation module and the output processing module. The normalization compensation module is mainly used for restoring the normalization proportion compensation difference stored in the preprocessing process, namely, the normalization compensation module is used for carrying out normalization compensation on target dose data output by the target model. The output processing module has different effects at different stages. In the training stage, the output processing module calculates the mean square error according to the model output result and the true value of the training label, and updates the overall model weight; in the using stage, the output processing module calculates and stores the difference value according to the model output result and the corresponding point of the initial dose map as the correction factor of the subsequent optimization.
From the foregoing, it can be seen that the technical solutions of the present application at least provide the following technical effects.
1) And realizing accurate adaptation on the input of the deep learning model aiming at the actual use scene. Specifically, the deep learning model can effectively improve the fitting degree of cases by training and utilizing the data similarity relation, and has higher adaptability, namely the deep learning model can realize effective dose distribution effect reconstruction after reasonable training. Especially has more obvious optimizing effect on the same cancer cases treated by the same physicist in the same hospital. In addition, the isodose line region diagram can better provide the influence on the dose distribution caused by factors such as the field in actual implementation; the dose change gradient map can provide dose distribution change information more accurately, and the suitability of the deep learning model to a scene can be effectively improved after the dose change gradient map is combined with intermediate dose distribution data, CT images, contour sketching images of a radiotherapy target area and contour sketching images corresponding to organs at risk and then input.
2) The actual use speed is high and the precision is high. Specifically, compared with the problem that the speed and the precision cannot be achieved by using a dose algorithm based on simulated particle motion in a traditional plan optimization system, the deep learning model can be effectively used as a substitute or complement tool, a more accurate dose distribution result can be stably provided in each optimization process than the dose distribution obtained by using a simulation algorithm, and meanwhile, the time spent for realizing the complete reconstruction of the dose distribution in the use of the deep learning model is very short.
3) The small amount of adjustment can be used as a module in different plan optimization systems (including automatic plan optimization systems). Specifically, the core part of the deep learning model can be used as an insert after a small amount of adjustment, and is suitable for radiation treatment plan optimization systems of different types and service conditions. The method has the characteristics of high precision and high speed, and has great contribution to the situation that the real dose simulation needs to be repeatedly used for a plurality of times, such as manual adjustment or automatic plan optimization system.
The present application also provides an electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to control the radiotherapy-based dose distribution data processing apparatus described above.
The application also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and the equipment where the computer readable storage medium is located is controlled to control the radiotherapy-based dose distribution data processing device when the computer program runs.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of units may be a logic function division, and there may be another division manner in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution, in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.
Claims (10)
1. A radiation therapy-based dose distribution data processing apparatus, comprising:
the acquisition module is used for acquiring a target image corresponding to a target object and first dose distribution data, wherein the target image at least comprises a CT image corresponding to the target object, a contour sketch image of a target radiotherapy target area of the target object and a contour sketch image corresponding to a target organs at risk of the target object, and the first dose distribution data is used for representing dose distribution information to be evaluated corresponding to the target object;
the data processing module is used for processing the first dose distribution data and the target image through a target model to obtain target dose distribution data, wherein the similarity of the target dose distribution data and second dose distribution data is larger than that of the first dose distribution data and the second dose distribution data, the second dose distribution data is used for representing dose distribution information corresponding to a target object calculated by using a simulation algorithm, and the target model is a deep learning neural network model which is trained in advance;
The data processing module comprises: the first data conversion unit is used for converting the first dose distribution data into first data through a first model branch in the target model, wherein the robustness corresponding to the multi-granularity information in the first data is higher than that in the first dose distribution data;
a second data conversion unit, configured to convert the first dose distribution data into second data through a second model branch in the target model, where accuracy corresponding to profile information in the second data is greater than accuracy corresponding to profile information in the first dose distribution data;
and the data processing unit is used for processing the first data, the second data and the target image through a third model branch in the target model to obtain the target dose distribution data.
2. The radiation therapy-based dose distribution data processing apparatus of claim 1, wherein the radiation therapy-based dose distribution data processing apparatus further comprises:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring intermediate dose distribution data corresponding to a historical case, and the intermediate dose distribution data is used for representing dose distribution information to be optimized corresponding to the historical case;
The third data generation module is used for carrying out interpolation complement processing on the intermediate dose distribution data to obtain third data, wherein the interpolation complement processing is used for carrying out data filling on the intermediate dose distribution data;
and the model generation module is used for generating the target model according to the third data.
3. Radiotherapy-based dose distribution data processing apparatus according to claim 2, characterized in that the model generation module comprises:
a fourth data generating unit, configured to perform isodose line regional processing on the third data to obtain fourth data;
a fifth data generating unit, configured to perform dose variation gradient processing on the third data to obtain fifth data;
and the model generating unit is used for generating the target model according to the fourth data and the fifth data.
4. A radiotherapy-based dose distribution data processing apparatus according to claim 3, in which the model generation unit comprises:
a first model branch generating subunit, configured to train to obtain a first model branch in the target model according to the fourth data and first historical data corresponding to the historical case, where the first historical data is a training label used when training the first model branch;
A second model branch generating subunit, configured to train to obtain a second model branch in the target model according to the fifth data and second historical data corresponding to the historical case, where the second historical data is a training label used when training the second model branch;
and the model generation subunit is used for generating the target model according to the first model branch and the second model branch.
5. The radiation therapy-based dose distribution data processing apparatus of claim 4, wherein the radiation therapy-based dose distribution data processing apparatus further comprises:
the second acquisition module is used for acquiring a historical image corresponding to the historical case and third dose distribution data, wherein the historical image at least comprises a CT image corresponding to the historical case, a contour sketch image of a radiotherapy target zone of the historical case and a contour sketch image corresponding to a jeopardy organ of the historical case, and the third dose distribution data is used for representing dose distribution information in an actual radiotherapy plan corresponding to the historical case;
the first historical data generation module is used for carrying out isodose line regionalization on the third dose distribution data to obtain the first historical data;
And the second historical data generation module is used for carrying out the dose change gradient processing on the third dose distribution data to obtain the second historical data.
6. The radiation therapy-based dose distribution data processing apparatus of claim 5, wherein,
a first model branch generation subunit comprising:
the first neural network branch processing submodule is used for carrying out iterative optimization processing on the first neural network branch according to the fourth data until the first neural network branch subjected to the iterative optimization processing can adjust the fourth data into sixth data, and determining the first neural network branch at the current moment as the first model branch, wherein the similarity between the sixth data and the first historical data is greater than or equal to a preset similarity;
and/or, a second model branch generation subunit comprising:
and the second neural network branch processing submodule is used for carrying out iterative optimization processing on the second neural network branch according to the fifth data until the second neural network branch subjected to the iterative optimization processing can adjust the fifth data into seventh data, and determining the second neural network branch at the current moment as the second model branch, wherein the similarity of the seventh data and the second historical data is greater than or equal to the preset similarity.
7. Radiotherapy-based dose distribution data processing apparatus according to claim 6, characterized in that the model generation subunit comprises:
a third model branch generation sub-module for generating a third model branch in the target model according to the historical image, the sixth data, the seventh data, and the third data;
and the model generation sub-module is used for generating the target model according to the first model branch, the second model branch and the third model branch.
8. The radiotherapy-based dose distribution data processing apparatus of claim 7, wherein the third model leg generation submodule comprises:
and the third neural network branch processing submodule is used for carrying out iterative optimization processing on the third neural network branch according to the historical image, the sixth data, the seventh data and the third data until the third neural network branch subjected to the iterative optimization processing can output eighth data, and determining the third neural network branch at the current moment as the third model branch, wherein the similarity of the eighth data and the third dose distribution data is greater than or equal to the preset similarity, and the third dose distribution data is used for representing dose distribution information in an actual radiotherapy plan corresponding to the historical case.
9. A computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to control the radiotherapy-based dose distribution data processing apparatus of any one of claims 1 to 8.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to control the radiotherapy-based dose distribution data processing apparatus of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310338802.2A CN116052840B (en) | 2023-03-31 | 2023-03-31 | Dose distribution data processing device based on radiotherapy, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310338802.2A CN116052840B (en) | 2023-03-31 | 2023-03-31 | Dose distribution data processing device based on radiotherapy, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116052840A CN116052840A (en) | 2023-05-02 |
| CN116052840B true CN116052840B (en) | 2023-06-13 |
Family
ID=86127676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310338802.2A Active CN116052840B (en) | 2023-03-31 | 2023-03-31 | Dose distribution data processing device based on radiotherapy, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116052840B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274235B (en) * | 2023-11-09 | 2024-02-27 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Determination device for radiotherapy curative effect, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201818996A (en) * | 2016-10-11 | 2018-06-01 | 日商三菱電機股份有限公司 | Radiation treatment method and radiation treatment planning system for determining dose of radiation |
| CN109621228A (en) * | 2018-12-12 | 2019-04-16 | 上海联影医疗科技有限公司 | The calculating unit and storage medium of radiological dose |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11449208B2 (en) * | 2017-07-06 | 2022-09-20 | Varian Medical Systems International Ag | Interactive and intuitive method to shape 3D dose distribution during optimization of IMRT plans |
| CN110141801B (en) * | 2019-05-17 | 2021-04-27 | 天津大学 | Intelligent dose planning method for close-range intra-particle radiotherapy operation |
| CN110232964B (en) * | 2019-06-04 | 2023-11-14 | 苏州雷泰智能科技有限公司 | Plan implementation method and device based on predicted dose guidance and Gaussian process optimization |
| CN111241331A (en) * | 2020-01-14 | 2020-06-05 | 平安科技（深圳）有限公司 | Image searching method, device, equipment and medium based on artificial intelligence |
| CN111388879B (en) * | 2020-03-19 | 2022-06-14 | 上海联影医疗科技股份有限公司 | Radiation dose determination system, radiation dose determination device and storage medium |
| CN115100185A (en) * | 2022-07-22 | 2022-09-23 | 深圳市联影高端医疗装备创新研究院 | Image processing method, image processing device, computer equipment and storage medium |
-
2023
- 2023-03-31 CN CN202310338802.2A patent/CN116052840B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201818996A (en) * | 2016-10-11 | 2018-06-01 | 日商三菱電機股份有限公司 | Radiation treatment method and radiation treatment planning system for determining dose of radiation |
| CN109621228A (en) * | 2018-12-12 | 2019-04-16 | 上海联影医疗科技有限公司 | The calculating unit and storage medium of radiological dose |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116052840A (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11386557B2 (en) | Systems and methods for segmentation of intra-patient medical images | |
| US11413474B2 (en) | System and method for modelling of dose calculation in radiotherapy treatment planning | |
| CN108778416B (en) | Systems, methods, and media for pseudo-CT generation from MR data using tissue parameter estimation | |
| RU2675678C1 (en) | Motion control in linear accelerator (linac) controlled with mri | |
| EP2992819B1 (en) | Weighted surface-to-surface mapping | |
| CN109906470A (en) | Use the image segmentation of neural network method | |
| CN116052840B (en) | Dose distribution data processing device based on radiotherapy, electronic equipment and storage medium | |
| CN111462916B (en) | Method and device for predicting dose volume histogram of organ at risk of radiotherapy plan | |
| CN106682409B (en) | Sampling method, radiotherapy plan optimization method and dose calculation method | |
| CN116072263A (en) | Planning parameter prediction device based on radiotherapy | |
| CN115938591A (en) | Radiotherapy-based dose distribution interval determination device and electronic equipment | |
| JP2018108284A (en) | Information processing device, information processing method, and computer program | |
| CN111494815B (en) | Three-dimensional dose calculation method, device and medium based on mixed variable-scale model | |
| WO2009040497A1 (en) | Image enhancement method | |
| CN116785601A (en) | Method and system for robust radiotherapy treatment planning with dose mapping uncertainty | |
| CN118574659A (en) | Basic dose calculation | |
| EP3888745A1 (en) | Computer-implemented method for radiotherapy treatment planning, computer program product and computer system for performing the method | |
| WO2021197893A1 (en) | Computer-implemented method for radiotherapy treatment planning, computer program product and computer system for performing the method | |
| CN116153465B (en) | Radiotherapy plan generation device based on reference DVH, electronic equipment and storage medium | |
| EP3751524A1 (en) | Method, computer program product and computer system for providing an approximate image | |
| CN113841204A (en) | System and method for training a machine learning model and for providing estimated internal images of a patient | |
| CN104866928B (en) | Optimization method and system for adaptive radiation therapy | |
| JP2022182902A (en) | Treatment planning system, treatment plan creation method, and computer program | |
| CN117717723A (en) | Portal information determining device, processor and electronic equipment | |
| CN117482411A (en) | Adjustment method of dosage parameters |
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 |