CN115300811B - Dose distribution determining method and device based on machine learning - Google Patents
Dose distribution determining method and device based on machine learning Download PDFInfo
- Publication number
- CN115300811B CN115300811B CN202210947897.3A CN202210947897A CN115300811B CN 115300811 B CN115300811 B CN 115300811B CN 202210947897 A CN202210947897 A CN 202210947897A CN 115300811 B CN115300811 B CN 115300811B
- Authority
- CN
- China
- Prior art keywords
- image
- target
- dose distribution
- dimensional dose
- sample data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000010801 machine learning Methods 0.000 title claims abstract description 45
- 238000011282 treatment Methods 0.000 claims abstract description 147
- 238000001959 radiotherapy Methods 0.000 claims abstract description 53
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 33
- 238000012937 correction Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 13
- 201000010099 disease Diseases 0.000 claims description 19
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 230000002093 peripheral effect Effects 0.000 claims 1
- 210000001519 tissue Anatomy 0.000 description 12
- 230000005855 radiation Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000006073 displacement reaction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 210000000920 organ at risk Anatomy 0.000 description 3
- 210000000988 bone and bone Anatomy 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007408 cone-beam computed tomography Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/08—Volume rendering
-
- 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
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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)
- Biomedical Technology (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Animal Behavior & Ethology (AREA)
- Epidemiology (AREA)
- Radiology & Medical Imaging (AREA)
- Urology & Nephrology (AREA)
- Surgery (AREA)
- Databases & Information Systems (AREA)
- Computer Graphics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radiation-Therapy Devices (AREA)
Abstract
The invention discloses a dose distribution determining method and device based on machine learning, and relates to the field of radiotherapy. The specific scheme comprises the following steps: tumor treatment data of a target user are acquired, wherein the tumor treatment data comprise a planned treatment image, a sketching structure and a positioning guide image, the sketching structure is sketched according to the planned treatment image, and the positioning guide image is a treatment guide image after positioning the target user; registering the planned treatment image and the positioning guide image to determine positioning deviation; obtaining a target residual deviation and a registration image of the positioning deviation after correction of the treatment couch; and processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a preset three-dimensional dose prediction model to determine target three-dimensional dose distribution, wherein the target three-dimensional dose distribution is the dose distribution containing the target residual deviation. The invention can timely and accurately determine the three-dimensional dose distribution containing residual deviation, and improves the treatment efficiency of patients.
Description
Technical Field
The invention relates to the field of radiotherapy, in particular to a dose distribution determining method and device based on machine learning.
Background
Before radiation treatment is carried out on a patient, a planning CT image of the patient is firstly scanned and acquired, and then a doctor performs target area and organ-at-risk delineation based on the planning CT image in a radiotherapy planning system (treatment planning system, TPS) so as to generate a radiotherapy plan of the patient. When radiation therapy is performed on a patient based on a radiation therapy plan, a therapist first positions the patient so that the actual treatment position is as consistent as possible with the treatment position in the planned CT image. But are affected by various factors, resulting in a 6-dimensional positioning deviation (Lng, lat, vrt, rtn, pitch and Roll six directions) after positioning the patient. In order to achieve accurate radiotherapy, image-guided radiotherapy technology (IGRT) is widely used in clinic, and can accurately position a tumor before or during treatment, help a doctor to determine whether a patient is accurately positioned, determine whether the tumor position or shape is changed, and the like, so as to reduce the possibility that normal tissues receive irradiation.
Although IGRT is becoming popular in clinical applications, in actual clinical applications, the positioning deviation of a patient cannot be eliminated even after the on-line correction of a treatment couch due to the influence of the correction accuracy of the treatment couch and the characteristics of non-rigid tissues of the human body, but exists in the form of residual deviation. However, at present, therapists can only complete the positioning correction of the treatment bed through the positioning deviation, and cannot quickly know the influence of the residual deviation on the coverage rate of the target area and the irradiated dose of the surrounding tissues of the tumor.
In the prior art, the residual deviation can be uploaded to the TPS so that the TPS can calculate a three-dimensional dose distribution containing the residual deviation and transmit the three-dimensional dose distribution to a therapist, and the therapist judges the influence of the residual deviation on the coverage rate of a target area and the irradiated dose of the tissue around the tumor based on the three-dimensional dose distribution. This process takes longer, which results in longer treatment times for the patient, and thus lower treatment efficiency.
Disclosure of Invention
The invention provides a dose distribution determining method and device based on machine learning, which can timely and accurately determine three-dimensional dose distribution containing residual deviation, and improve the treatment efficiency of patients.
In order to achieve the above purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a machine learning based dose distribution determining method, the method comprising:
tumor treatment data of a target user are acquired, wherein the tumor treatment data comprise a planned treatment image, a sketching structure and a positioning guide image, the sketching structure is sketched according to the planned treatment image, and the positioning guide image is a treatment guide image after positioning the target user; registering the planned treatment image and the positioning guide image to determine positioning deviation; obtaining a target residual deviation and a registration image of the positioning deviation after correction of the treatment couch; and processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a preset three-dimensional dose prediction model to determine target three-dimensional dose distribution, wherein the target three-dimensional dose distribution is the dose distribution containing the target residual deviation.
In one possible implementation, the processing of the planned treatment image, the delineated structure, the registered image and the target residual deviation using a preset three-dimensional dose prediction model to determine a target three-dimensional dose distribution includes: acquiring a target disease type of a target user; and processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a three-dimensional dose prediction model corresponding to the target disease type, and determining target three-dimensional dose distribution.
In one possible implementation, the method further includes: transmitting the planned treatment image, the sketching structure, the registration image and the target residual deviation to a radiotherapy planning system; receiving real three-dimensional dose distribution sent by a radiotherapy planning system; and optimizing the three-dimensional dose prediction model according to the planned treatment image, the sketching structure, the registration image, the target residual deviation, the target three-dimensional dose distribution and the real three-dimensional dose distribution to obtain an optimized three-dimensional dose prediction model.
In one possible implementation, the method further includes: acquiring a plurality of sample data, wherein one sample data comprises a planning treatment image, a sketching structure and a positioning guide image of a user; registering the planned treatment image and the positioning guide image in each sample data to obtain a positioning deviation corresponding to each sample data; obtaining residual deviation and registration images of the positioning deviation corresponding to each sample data after correction of the treatment couch; transmitting the planned treatment image and the sketching structure in each sample data, and the corresponding registration image and residual deviation of each sample data to a radiotherapy planning system; receiving three-dimensional dose distribution containing residual deviation corresponding to each sample data sent by a radiotherapy planning system; and training the neural network model by taking the planned treatment image and the sketching structure in each sample data and the registration image and the residual deviation corresponding to each sample data as inputs and the three-dimensional dose distribution corresponding to each sample data as outputs to obtain a three-dimensional dose prediction model.
In one possible implementation, the method further comprises, after determining the target three-dimensional dose distribution: determining the coverage rate of the target area and the increment of the irradiated dose of the tissue around the tumor according to the target three-dimensional dose distribution and the three-dimensional dose distribution without positioning deviation, wherein the increment is obtained according to the irradiated dose and the clinical standard dose; and outputting the target three-dimensional dose distribution if the target coverage rate is greater than the first preset value and the increment is smaller than the second preset value.
In one possible implementation, the method further includes: if the target coverage rate is smaller than the first preset value or the increment is larger than the second preset value, outputting prompt information which is used for prompting adjustment of the positioning of the target user.
In a second aspect, the present invention provides a dose distribution determining apparatus based on machine learning, comprising:
the system comprises an acquisition module, a positioning module and a display module, wherein the acquisition module is used for acquiring tumor treatment data of a target user, the tumor treatment data comprises a planned treatment image, a sketching structure and a positioning guide image, the sketching structure is sketched according to the planned treatment image, and the positioning guide image is a treatment guide image after positioning the target user; the registration module is used for registering the planned treatment image and the positioning guide image and determining positioning deviation; the acquisition module is also used for acquiring the target residual deviation and the registration image of the positioning deviation corrected by the treatment couch; the determining module is used for processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a preset three-dimensional dose prediction model to determine target three-dimensional dose distribution, wherein the target three-dimensional dose distribution is the dose distribution containing the target residual deviation.
In one possible implementation manner, the determining module is specifically configured to: acquiring a target disease type of a target user; and processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a three-dimensional dose prediction model corresponding to the target disease type, and determining target three-dimensional dose distribution.
In another possible implementation, the dose distribution determining device further comprises: the device comprises a sending module, a receiving module and an optimizing module. The sending module is used for sending the planned treatment image, the sketching structure, the registration image and the target residual deviation to a radiotherapy planning system; the receiving module is used for receiving the real three-dimensional dose distribution sent by the radiotherapy planning system; and the optimization module is used for optimizing the three-dimensional dose prediction model according to the planned treatment image, the sketching structure, the registration image, the target residual deviation, the target three-dimensional dose distribution and the real three-dimensional dose distribution to obtain an optimized three-dimensional dose prediction model.
In another possible implementation, the dose distribution determining device further comprises: the device comprises a sending module, a receiving module and a training module.
The acquisition module is also used for acquiring a plurality of sample data, wherein one sample data comprises a planned treatment image, a sketching structure and a positioning guide image of a user; the registration module is also used for registering the planned treatment image and the positioning guide image in each sample data to obtain positioning deviation corresponding to each sample data; the acquisition module is also used for acquiring residual deviation and registration images of the positioning deviation corresponding to each sample data after the correction of the treatment couch; the sending module is used for sending the planned treatment image and the sketching structure in each sample data, and the registration image and the residual deviation corresponding to each sample data to the radiotherapy planning system; the receiving module is used for receiving the three-dimensional dose distribution containing residual deviation corresponding to each sample data sent by the radiotherapy planning system; the training module is used for training the neural network model by taking the planned treatment image and the sketching structure in each sample data as well as the registration image and the residual deviation corresponding to each sample data as input and the three-dimensional dose distribution corresponding to each sample data as output to obtain the three-dimensional dose prediction model.
In another possible implementation, the dose distribution determining device further comprises: and a judging module.
The determining module is also used for determining the coverage rate of the target area and the increment of the irradiated dose of the tissue around the tumor according to the target three-dimensional dose distribution and the three-dimensional dose distribution without the positioning deviation, and the increment is obtained according to the irradiated dose and the clinical standard dose; and the judging module is used for outputting target three-dimensional dose distribution if the target coverage rate is larger than a first preset value and the increment is smaller than a second preset value.
In another possible implementation manner, the judging module is further configured to output a prompt message if the target coverage rate is less than the first preset value or the increment is greater than the second preset value, where the prompt message is used to prompt adjustment of the positioning of the target user.
In a third aspect, the present invention provides a computer device comprising: a processor and a memory. The memory is used to store computer program code, which includes computer instructions. When the processor executes the computer instructions, the computer device performs the machine learning based dose distribution determination method as in the first aspect and any one of its possible implementations.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions which, when run on a computer device, cause the computer device to perform a machine learning based dose distribution determination method as in the first aspect and any one of its possible implementations.
In a fifth aspect, the present invention provides a computer program product comprising computer instructions which, when run on a computer device, cause the computer device to perform the machine learning based dose distribution determination method as in the first aspect and any one of its possible implementations.
According to the method provided by the embodiment of the invention, the planned treatment image, the sketching structure, the registration image and the target residual deviation are processed by adopting the preset three-dimensional dose prediction model, so that the target three-dimensional dose distribution is determined, namely, the dose distribution containing the target residual deviation is predicted by the three-dimensional dose prediction model. Therefore, the dose distribution containing the target residual deviation can be almost obtained in real time in the treatment process of the patient, and compared with the prior art that the dose distribution containing the target residual deviation is obtained by uploading the data of the patient to a TPS system for calculation and then transmitting the calculation result back, the three-dimensional dose distribution containing the residual deviation can be timely and accurately determined, and the treatment efficiency of the patient is improved.
Drawings
Fig. 1 is a schematic view of an application scenario of a dose distribution determining method based on machine learning according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for determining a dose distribution based on machine learning according to an embodiment of the present invention;
FIG. 3 is a second flowchart of a method for determining a dose distribution based on machine learning according to an embodiment of the present invention;
FIG. 4 is a third flowchart of a method for determining a dose distribution based on machine learning according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a dose distribution determining apparatus based on machine learning according to an embodiment of the present invention;
fig. 6 is a schematic diagram of another dose distribution determining apparatus based on machine learning according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "first" and "second" are used below for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the embodiments of the present disclosure, unless otherwise indicated, the meaning of "a plurality" is two or more. In addition, the use of "based on" or "according to" is intended to be open and inclusive in that a process, step, calculation, or other action "based on" or "according to" one or more of the stated conditions or values may in practice be based on additional conditions or beyond the stated values.
Fig. 1 is a schematic diagram of an application scenario of a dose distribution determining method based on machine learning according to an embodiment of the present invention. As shown in fig. 1, the application scenario includes a computer device 101 and a radiotherapy planning system 102. The computer device 101 communicates with the radiation therapy planning system 102 by wired or wireless communication.
The computer device 101 is mainly used for performing radiation treatment on a patient according to a radiation treatment plan generated by the radiation treatment planning system 102. Firstly, registering a planned treatment image and a sketching structure of a patient with a positioning guide image to obtain positioning deviation, then, according to the positioning deviation obtained by registration, a therapist adjusts a treatment couch to correct the positioning deviation, and the computer equipment 101 can obtain a residual deviation and a registration image after registration movement. Finally, the computer device 101 obtains a three-dimensional dose distribution containing residual deviations from the planned treatment image, the delineated structure, the registered image and the residual deviations, and determines in real time whether repositioning of the patient is required according to the three-dimensional dose distribution containing residual deviations.
The radiotherapy planning system 102 is mainly used for acquiring a plan treatment image of a patient, and then acquiring a sketching structure by a doctor according to the acquired image and sketching a tumor target area and tumor surrounding tissues of the patient in the radiotherapy planning system 102. The radiation therapy planning system 102 models the radiation source and the patient, simulates radiation therapy delivered by the plan based on the patient's tumor target volume positioned by the delineated structure, and generates a radiation therapy plan. The radiation therapy planning system 102 is also configured to calculate a three-dimensional dose distribution absorbed in the patient using one or more algorithms, the calculation being made available to the radiation therapy planning therapist.
Fig. 2 is a flowchart of a dose distribution determining method based on machine learning according to an embodiment of the present invention. As shown in fig. 2, the machine learning based dose distribution determination method may comprise the following steps 201-204.
201. Tumor treatment data of a target user is acquired, wherein the tumor treatment data comprises a planned treatment image, a sketching structure and a positioning guide image.
The sketching structure is sketched according to the planned treatment image, and the positioning guide image is a treatment guide image after positioning the target user.
The target user is typically a patient in need of radiation treatment, and the planned treatment image in the tumor treatment data is obtained on a simulator and sent to the radiation treatment planning system. The simulator may be a CT simulator or an MR simulator, and the planned treatment image may be a CT image or an MR image.
The sketching structure is obtained by sketching a tumor target area and a jeopardy organ of a patient in a radiotherapy planning system according to a planned treatment image and is sent to computer equipment. The sketching structure can also be obtained through intelligent sketching of an algorithm and sent to the computer equipment. The delineating structure mainly delineates the tumor target area and the outline of the organs at risk. The delineating structure in the radiotherapy is a basic guarantee of accurate radiotherapy, and the accuracy of the delineating structure directly determines the reliability of the radiotherapy dose distribution.
The positioning guide image is a patient treatment image acquired based on an image-guided radiotherapy technology when a therapist finishes positioning the patient according to a designated position, and can be a CT image, an MR image or a CBCT image.
202. Registering the planned treatment image and the positioning guide image, and determining positioning deviation.
Registration may employ a rigid registration method, for example, rigid registration may be performed based on the planned treatment image and the bone structure in the positioning guide image. Registration may also employ non-rigid registration methods. It will be appreciated that as radiation therapy progresses or time passes, the volume and shape of the tumor changes, thereby changing the location and shape of certain tissues, organs surrounding it. But typically the body's rigid structure, such as bone structure, does not change. The registration in this embodiment is therefore preferably a rigid registration.
The positioning deviation in this embodiment is an offset obtained after registering the planned treatment image and the positioning guide image. Because there are 6-dimensional positioning deviations (Lng, lat, vrt, rtn, pitch and Roll six directions) after positioning of the patient, the positioning deviations may include six latitude values, such as 2.15cm,1.45cm,3.46cm,1 degree, 0.8 degree, 0.5 degree.
203. And obtaining a target residual deviation and a registration image of the positioning deviation after the treatment couch correction.
The registration image is an IGRT image obtained after correcting the treatment couch according to the positioning deviation obtained by registration.
The target residual error is obtained by computer equipment after correcting the treatment couch according to the positioning deviation. Due to the accuracy of the automatic displacement of the couch, rotational deviations and sub-millimeter translational deviations are typically left behind, which are then the target residual deviations.
The radiotherapy bed generally comprises a six-dimensional bed and a three-dimensional bed, and because the error is six-dimensional value, the six-dimensional bed is recommended to be used in the image-guided radiotherapy technology, and the six-dimensional bed is corrected according to the positioning deviation obtained by registration, so that the dose transfer precision in the radiotherapy can be effectively improved. However, in practical clinical application, the three-dimensional bed is still the radiation therapy bed with the most wide clinical application due to the influence of price limitation, practicability and the like. When using a three-dimensional couch as a couch, the couch is generally only capable of automatic displacement adjustment of three dimensional values in the positioning offset.
For example, patient treatment with a deviation of 2.15cm,1.45cm,3.46cm,1 degree, 0.8 degree, 0.5 degree, displacement of the three-dimensional couch would allow the therapist to confirm the displacement of 2cm,1cm,3cm. After the automatic displacement of the treatment couch is completed, the target residual error is 0.15cm,0.45cm,0.46cm,1 degree, 0.8 degree, 0.5 degree.
204. And processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a preset three-dimensional dose prediction model, and determining the target three-dimensional dose distribution.
Wherein the target three-dimensional dose distribution is a dose distribution containing a target residual deviation.
It will be appreciated that the three-dimensional dose prediction model is based on machine deep learning training, and the machine learning model may be a neural network model based on a Unet or CNN framework. The trained three-dimensional dose prediction model outputs target three-dimensional dose distribution after the planned treatment image, the sketching structure, the registration image and the target residual deviation are input. The target three-dimensional dose distribution includes a dose distribution of a tumor target region and a dose distribution of an organ at risk.
Optionally, in the embodiment of the present invention, the computer device processes the planned treatment image, the sketching structure, the registration image and the target residual deviation by using a preset three-dimensional dose prediction model, and determines a target three-dimensional dose distribution, and the specific process may be: the computer equipment firstly acquires the target disease type of the target user, and adopts a three-dimensional dose prediction model corresponding to the target disease type to process the planned treatment image, the sketching structure, the registration image and the target residual deviation, so as to determine the target three-dimensional dose distribution. In this way, by training the three-dimensional dose prediction model corresponding to the disease type according to the disease type and adopting the three-dimensional dose prediction model corresponding to the disease type when predicting the dose distribution, different treatments of different disease types are realized, and the accuracy of dose prediction is improved.
According to the method provided by the embodiment of the invention, the planned treatment image, the sketching structure, the registration image and the target residual deviation are processed by adopting the preset three-dimensional dose prediction model, so that the target three-dimensional dose distribution is determined, namely, the dose distribution containing the target residual deviation is predicted by the three-dimensional dose prediction model. Therefore, the dose distribution containing the target residual deviation can be almost obtained in real time in the treatment process of the patient, and compared with the prior art that the dose distribution containing the target residual deviation is obtained by uploading the data of the patient to a TPS system for calculation and then transmitting the calculation result back, the three-dimensional dose distribution containing the residual deviation can be timely and accurately determined, and the treatment efficiency of the patient is improved.
Optionally, in an embodiment of the present invention, after determining the target three-dimensional dose distribution in the step 204, the computer device may send a planned treatment image, a sketching structure, a registration image and a target residual deviation to the radiotherapy planning system, receive a real three-dimensional dose distribution sent by the radiotherapy planning system, and optimize the three-dimensional dose prediction model according to the planned treatment image, the sketching structure, the registration image, the target residual deviation, the target three-dimensional dose distribution and the real three-dimensional dose distribution, so as to obtain an optimized three-dimensional dose prediction model.
Thus, after predicting the three-dimensional dose distribution using the three-dimensional dose prediction model, the computer device can obtain a true value of the three-dimensional dose distribution from the radiotherapy planning system, and dynamically optimize the three-dimensional dose prediction model based on the model input data, the predicted dose distribution (i.e., the target three-dimensional dose distribution), and the true value (i.e., the true three-dimensional dose distribution) to ensure the accuracy of the target three-dimensional dose distribution predicted by the three-dimensional dose prediction model.
Optionally, a three-dimensional dose prediction model may be trained prior to performing steps 201-204 described above. Specifically, referring to fig. 2, as shown in fig. 3, the method for determining a dose distribution based on machine learning according to an embodiment of the present invention may further include the following steps 205 to 210.
205. A plurality of sample data is acquired, wherein one sample data comprises a planned treatment image, a sketching structure and a positioning guide image of a user.
206. Registering the planned treatment image and the positioning guide image in each sample data to obtain positioning deviation corresponding to each sample data.
207. And acquiring residual deviation and registration images of the positioning deviation corresponding to each sample data after the correction of the treatment couch.
It will be appreciated that the specific descriptions of the steps 205-207 may refer to the descriptions of the steps 201-203 in the foregoing embodiments, and are not repeated herein.
208. The planned treatment image and the delineated structure in each sample data, as well as the corresponding registration image and residual deviation for each sample data, are sent to a radiotherapy planning system.
209. And receiving the three-dimensional dose distribution containing residual deviation corresponding to each sample data sent by the radiotherapy planning system.
210. And training the neural network model by taking the planned treatment image and the sketching structure in each sample data and the registration image and the residual deviation corresponding to each sample data as inputs and the three-dimensional dose distribution corresponding to each sample data as outputs to obtain a three-dimensional dose prediction model.
Optionally, in an embodiment of the present invention, the computer device may acquire a disease type corresponding to each of the plurality of sample data, and train the three-dimensional dose prediction model corresponding to the disease type for sample data of a different disease type.
In this way, the three-dimensional dose prediction model is trained by acquiring a plurality of sample data and acquiring true values of the three-dimensional dose distribution containing residual deviations corresponding to each sample data from the radiotherapy planning system, so as to ensure the accuracy of the three-dimensional dose distribution predicted by the three-dimensional dose prediction model.
Optionally, as shown in fig. 4 in conjunction with fig. 3, after the above step 204 is performed, the method for determining a dose distribution based on machine learning according to an embodiment of the present invention may further include the following steps 211 to 213.
211. And determining the coverage rate of the target area and the increment of irradiated dose of the tissue around the tumor according to the target three-dimensional dose distribution and the three-dimensional dose distribution without positioning deviation.
The increment is obtained according to the irradiated dose and the clinical standard dose, and the difference value between the current irradiated dose and the clinical standard dose and the percentage of the clinical standard dose are the increment of the irradiated dose. Clinical labeling dose of tumor surrounding tissue refers to the dose irradiated without positioning deviation.
212. And outputting the target three-dimensional dose distribution if the target coverage rate is greater than the first preset value and the increment is smaller than the second preset value.
The computer device outputs a target three-dimensional dose distribution, which indicates that the dose distribution of the target area part and the dose distribution of the tissue surrounding the tumor meet the requirements.
213. If the target coverage rate is smaller than the first preset value or the increment is larger than the second preset value, outputting prompt information which is used for prompting adjustment of the positioning of the target user.
In this way, by predicting the three-dimensional dose distribution containing the residual deviation, the influence of the positioning residual deviation on the three-dimensional dose distribution can be quickly prompted.
The scheme provided by the embodiment of the invention is mainly described in the view of equipment. It will be appreciated that the apparatus, in order to achieve the above-described functions, comprises hardware structures and/or software modules corresponding to the execution of the respective functions. Those of skill in the art will readily appreciate that the various illustrative algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Fig. 5 shows a schematic diagram of one possible composition of the machine learning based dose distribution determining apparatus referred to in the above embodiment, as shown in fig. 5, which may include: an acquisition module 51, a registration module 52 and a determination module 53.
The obtaining module 51 is configured to obtain tumor treatment data of a target user, where the tumor treatment data includes a planned treatment image, a sketching structure and a positioning guide image, the sketching structure is sketched according to the planned treatment image, and the positioning guide image is a treatment guide image after positioning the target user;
a registration module 52 for registering the planned treatment image and the positioning guide image to determine a positioning deviation;
the acquiring module 51 is further configured to acquire a target residual deviation and a registration image after the positioning deviation is corrected by the treatment couch;
the determining module 53 is configured to process the planned treatment image, the delineated structure, the registration image and the target residual deviation by using a preset three-dimensional dose prediction model, and determine a target three-dimensional dose distribution, where the target three-dimensional dose distribution is a dose distribution containing the target residual deviation.
Optionally, the determining module 53 is specifically configured to:
acquiring a target disease type of a target user;
and processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a three-dimensional dose prediction model corresponding to the target disease type, and determining target three-dimensional dose distribution.
Optionally, as shown in fig. 6, the dose distribution determining apparatus based on machine learning may further include: a transmitting module 54, a receiving module 55 and an optimizing module 56.
A transmission module 54 for transmitting the planned treatment image, the delineation structure, the registration image and the target residual deviation to the radiotherapy planning system;
the receiving module 55 is used for receiving the real three-dimensional dose distribution sent by the radiotherapy planning system;
the optimizing module 56 is configured to optimize the three-dimensional dose prediction model according to the planned treatment image, the sketched structure, the registration image, the target residual deviation, the target three-dimensional dose distribution and the real three-dimensional dose distribution, and obtain an optimized three-dimensional dose prediction model.
Optionally, as shown in fig. 6, the dose distribution determining apparatus based on machine learning may further include: training module 57.
The acquiring module 51 is further configured to acquire a plurality of sample data, where one sample data includes a planned treatment image, a sketching structure, and a positioning guide image of a user;
the registration module 52 is further configured to register the planned treatment image and the positioning guide image in each sample data according to the sketching structure in each sample data, so as to obtain a positioning deviation corresponding to each sample data;
the acquiring module 51 is further configured to acquire a residual deviation and a registration image of the positioning deviation corresponding to each sample data after the correction of the treatment couch;
the sending module 54 is further configured to send the planned treatment image and the delineating structure in each sample data, and the registered image and the residual deviation corresponding to each sample data, to the radiotherapy planning system;
the receiving module 55 is further configured to receive a three-dimensional dose distribution containing residual deviation corresponding to each sample data sent by the radiotherapy planning system;
the training module 57 is configured to train the neural network model to obtain a three-dimensional dose prediction model by taking the planned treatment image and the delineating structure in each sample data, and the registration image and the residual deviation corresponding to each sample data as inputs, and the three-dimensional dose distribution corresponding to each sample data as outputs.
Optionally, as shown in fig. 6, the dose distribution determining apparatus based on machine learning may further include: a decision block 58.
The determining module 53 is further configured to determine, according to the target three-dimensional dose distribution and the three-dimensional dose distribution without positioning deviation, a coverage rate of the target area and an increment of an irradiated dose of the tissue surrounding the tumor, where the increment is obtained according to the irradiated dose and a clinical standard dose;
the judging module 58 is configured to output the target three-dimensional dose distribution if the target coverage is greater than the first preset value and the increment is smaller than the second preset value.
Optionally, the judging module 58 is further configured to output a prompt message if the target coverage rate is less than the first preset value or the increment is greater than the second preset value, where the prompt message is used to prompt adjustment of the positioning of the target user.
Of course, the dose distribution determining device based on machine learning provided by the embodiment of the invention includes, but is not limited to, the above module.
The dose distribution determining device based on machine learning provided by the embodiment of the invention is used for executing the dose distribution determining method based on machine learning, so that the same effects as those of the dose distribution determining method based on machine learning can be achieved.
Another embodiment of the present invention also provides a computer readable storage medium having stored therein computer instructions which, when executed on a computer device, cause the computer device to perform the steps of the machine learning based dose distribution determination method of any one of the method flows shown in the above method embodiments.
Another embodiment of the present invention also provides a computer program product comprising computer instructions which, when run on a computer device, cause the computer device to perform the steps of the machine learning based dose distribution determination method of any one of the method flows shown in the method embodiments described above.
The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the present invention is not limited thereto, but any changes or substitutions within the technical scope of the present invention should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A method of determining a dose distribution based on machine learning, comprising:
tumor treatment data of a target user are acquired, wherein the tumor treatment data comprise a planned treatment image, a sketching structure and a positioning guide image, the sketching structure is sketched according to the planned treatment image, and the positioning guide image is a treatment guide image after positioning the target user;
registering the planned treatment image and the positioning guide image to determine positioning deviation;
obtaining a target residual deviation and a registration image of the positioning deviation after correction of the treatment couch;
processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a preset three-dimensional dose prediction model to determine target three-dimensional dose distribution, wherein the target three-dimensional dose distribution is the dose distribution containing the target residual deviation;
the machine learning based dose distribution determination method further comprises:
transmitting the planned treatment image, the delineation structure, the registration image, and the target residual deviation to a radiotherapy planning system;
receiving the real three-dimensional dose distribution sent by the radiotherapy planning system;
optimizing the three-dimensional dose prediction model according to the planned treatment image, the sketching structure, the registration image, the target residual deviation, the target three-dimensional dose distribution and the real three-dimensional dose distribution to obtain an optimized three-dimensional dose prediction model;
the machine learning based dose distribution determination method further comprises:
acquiring a plurality of sample data, wherein one sample data comprises a planning treatment image, a sketching structure and a positioning guide image of a user;
registering the planned treatment image and the positioning guide image in each sample data to obtain positioning deviation corresponding to each sample data;
obtaining residual deviation and registration images of the positioning deviation corresponding to each sample data after the correction of the treatment couch;
transmitting the planned treatment image and the sketching structure in each sample data, and the corresponding registration image and residual deviation of each sample data to a radiotherapy planning system;
receiving three-dimensional dose distribution containing residual deviation corresponding to each sample data sent by a radiotherapy planning system;
and training the neural network model by taking the planned treatment image and the sketching structure in each sample data as input and the registration image and the residual deviation corresponding to each sample data as output to obtain the three-dimensional dose prediction model.
2. The machine learning based dose distribution determination method of claim 1 wherein said processing said planned treatment image, said delineating structure, said registration image and said target residual deviation using a preset three-dimensional dose prediction model to determine a target three-dimensional dose distribution comprises:
acquiring a target disease type of the target user;
and processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a three-dimensional dose prediction model corresponding to the target disease type, and determining the target three-dimensional dose distribution.
3. The machine learning based dose distribution determination method according to claim 1 or 2, further comprising, after determining the target three-dimensional dose distribution:
determining the coverage rate of a target area and the increment of irradiated dose of peripheral tissues of the tumor according to the target three-dimensional dose distribution and the three-dimensional dose distribution without positioning deviation, wherein the increment is obtained according to the irradiated dose and clinical standard dose;
and outputting the target three-dimensional dose distribution if the target coverage rate is greater than a first preset value and the increment is smaller than a second preset value.
4. A machine learning based dose distribution determination method according to claim 3, characterized in that the machine learning based dose distribution determination method further comprises:
and if the target coverage rate is smaller than the first preset value or the increment is larger than the second preset value, outputting prompt information, wherein the prompt information is used for prompting and adjusting the positioning of the target user.
5. A machine learning based dose distribution determining device, comprising:
the system comprises an acquisition module, a positioning module and a display module, wherein the acquisition module is used for acquiring tumor treatment data of a target user, the tumor treatment data comprises a planned treatment image, a sketching structure and a positioning guide image, the sketching structure is sketched according to the planned treatment image, and the positioning guide image is a treatment guide image after positioning the target user;
the registration module is used for registering the planned treatment image and the positioning guide image and determining positioning deviation;
the acquisition module is also used for acquiring the target residual deviation and the registration image of the positioning deviation corrected by the treatment couch;
the determining module is used for processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a preset three-dimensional dose prediction model to determine target three-dimensional dose distribution, wherein the target three-dimensional dose distribution is the dose distribution containing the target residual deviation;
the machine learning based dose distribution determining device further comprises:
the sending module is used for sending the planned treatment image, the sketching structure, the registration image and the target residual deviation to the radiotherapy planning system;
the receiving module is used for receiving the real three-dimensional dose distribution sent by the radiotherapy planning system;
the optimizing module is used for optimizing the three-dimensional dose prediction model according to the planned treatment image, the sketching structure, the registration image, the target residual deviation, the target three-dimensional dose distribution and the real three-dimensional dose distribution to obtain an optimized three-dimensional dose prediction model;
the machine learning based dose distribution determining device further comprises:
the acquisition module is also used for acquiring a plurality of sample data, wherein one sample data comprises a planned treatment image, a sketching structure and a positioning guide image of a user;
the registration module is also used for registering the planned treatment image and the positioning guide image in each sample data according to the sketching structure in each sample data to obtain positioning deviation corresponding to each sample data;
the acquisition module is also used for acquiring residual deviation and registration images of the positioning deviation corresponding to each sample data after the correction of the treatment couch;
the sending module is also used for sending the planned treatment image and the sketching structure in each sample data, and the registration image and the residual deviation corresponding to each sample data to the radiotherapy planning system;
the receiving module is also used for receiving the three-dimensional dose distribution containing residual deviation corresponding to each sample data sent by the radiotherapy planning system;
the training module is used for training the neural network model by taking the planned treatment image and the sketching structure in each sample data as well as the registration image and the residual deviation corresponding to each sample data as input and the three-dimensional dose distribution corresponding to each sample data as output to obtain a three-dimensional dose prediction model.
6. The machine learning based dose distribution determining device according to claim 5, characterized in that the determining module is specifically configured to:
acquiring a target disease type of the target user;
and processing the planned treatment image, the sketching structure, the registration image and the target residual deviation by adopting a three-dimensional dose prediction model corresponding to the target disease type, and determining the target three-dimensional dose distribution.
7. A computer device, the computer device comprising: a processor and a memory; the memory is used for storing computer program codes, and the computer program codes comprise computer instructions; the computer device, when executing the computer instructions, performs the machine learning based dose distribution determination method of any of claims 1-4.
8. A computer readable storage medium comprising computer instructions which, when run on a computer device, cause the computer device to perform the machine learning based dose distribution determination method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210947897.3A CN115300811B (en) | 2022-08-08 | 2022-08-08 | Dose distribution determining method and device based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210947897.3A CN115300811B (en) | 2022-08-08 | 2022-08-08 | Dose distribution determining method and device based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115300811A CN115300811A (en) | 2022-11-08 |
| CN115300811B true CN115300811B (en) | 2024-01-05 |
Family
ID=83861000
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210947897.3A Active CN115300811B (en) | 2022-08-08 | 2022-08-08 | Dose distribution determining method and device based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115300811B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102824693A (en) * | 2012-08-02 | 2012-12-19 | 李宝生 | System and method for verifying radiotherapy plan before online therapy |
| CN104548372A (en) * | 2015-01-07 | 2015-04-29 | 上海联影医疗科技有限公司 | Radiotherapy planning method and device, radiotherapy dose determining method and device and radiotherapy quality guaranteeing method and device |
| CN107441637A (en) * | 2017-08-30 | 2017-12-08 | 南方医科大学 | The intensity modulated radiation therapy Forecasting Methodology of 3-dimensional dose distribution and its application in the works |
| CN109011221A (en) * | 2018-09-04 | 2018-12-18 | 东莞东阳光高能医疗设备有限公司 | A kind of the neutron capture therapy system and its operating method of dosage guidance |
| CN109771842A (en) * | 2017-11-10 | 2019-05-21 | 北京连心医疗科技有限公司 | Cloud radiotherapy method of quality control, equipment and storage medium based on machine learning |
| CN110292723A (en) * | 2019-06-25 | 2019-10-01 | 上海联影医疗科技有限公司 | Dosage guidance pendulum position device, dosage monitoring device, radiotherapy system and medium |
| CN111028914A (en) * | 2019-12-04 | 2020-04-17 | 北京连心医疗科技有限公司 | Artificial intelligence guided dose prediction method and system |
| CN111584034A (en) * | 2020-04-14 | 2020-08-25 | 四川省肿瘤医院 | Radiation therapy implementation quality control method and system based on artificial intelligence |
| CN112843503A (en) * | 2021-01-29 | 2021-05-28 | 中国人民解放军陆军军医大学第二附属医院 | Radiotherapy in-vivo dose monitoring method |
| CN113096766A (en) * | 2021-04-08 | 2021-07-09 | 济南大学 | Three-dimensional dose prediction method and system in personalized accurate radiotherapy plan |
| CN113674834A (en) * | 2021-08-16 | 2021-11-19 | 于金明 | Radiotherapy target region establishing and correcting method based on dose distribution preview system |
| CN113679960A (en) * | 2021-08-11 | 2021-11-23 | 中科超精(南京)科技有限公司 | Multi-mode guiding radiotherapy device integrating three-dimensional online dose guiding |
| WO2022032528A1 (en) * | 2020-08-12 | 2022-02-17 | 西安大医集团股份有限公司 | Image display control method and apparatus, electronic device, and computer storage medium |
| WO2022077828A1 (en) * | 2020-10-15 | 2022-04-21 | 上海市肺科医院 | Repeated positioning method and system |
| CN114558251A (en) * | 2022-01-27 | 2022-05-31 | 苏州雷泰医疗科技有限公司 | Automatic positioning method and device based on deep learning and radiotherapy equipment |
| CN114707742A (en) * | 2022-04-15 | 2022-07-05 | 中国医学科学院肿瘤医院 | Artificial intelligence prediction method and system for adaptive radiotherapy strategy |
| WO2022142770A1 (en) * | 2020-12-28 | 2022-07-07 | 北京医智影科技有限公司 | Automatic radiation treatment planning system and method, and computer program product |
| CN114796891A (en) * | 2017-06-05 | 2022-07-29 | 西安大医集团股份有限公司 | Radiotherapy system |
-
2022
- 2022-08-08 CN CN202210947897.3A patent/CN115300811B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102824693A (en) * | 2012-08-02 | 2012-12-19 | 李宝生 | System and method for verifying radiotherapy plan before online therapy |
| CN104548372A (en) * | 2015-01-07 | 2015-04-29 | 上海联影医疗科技有限公司 | Radiotherapy planning method and device, radiotherapy dose determining method and device and radiotherapy quality guaranteeing method and device |
| CN114796891A (en) * | 2017-06-05 | 2022-07-29 | 西安大医集团股份有限公司 | Radiotherapy system |
| CN107441637A (en) * | 2017-08-30 | 2017-12-08 | 南方医科大学 | The intensity modulated radiation therapy Forecasting Methodology of 3-dimensional dose distribution and its application in the works |
| CN109771842A (en) * | 2017-11-10 | 2019-05-21 | 北京连心医疗科技有限公司 | Cloud radiotherapy method of quality control, equipment and storage medium based on machine learning |
| CN109011221A (en) * | 2018-09-04 | 2018-12-18 | 东莞东阳光高能医疗设备有限公司 | A kind of the neutron capture therapy system and its operating method of dosage guidance |
| CN110292723A (en) * | 2019-06-25 | 2019-10-01 | 上海联影医疗科技有限公司 | Dosage guidance pendulum position device, dosage monitoring device, radiotherapy system and medium |
| CN111028914A (en) * | 2019-12-04 | 2020-04-17 | 北京连心医疗科技有限公司 | Artificial intelligence guided dose prediction method and system |
| CN111584034A (en) * | 2020-04-14 | 2020-08-25 | 四川省肿瘤医院 | Radiation therapy implementation quality control method and system based on artificial intelligence |
| WO2022032528A1 (en) * | 2020-08-12 | 2022-02-17 | 西安大医集团股份有限公司 | Image display control method and apparatus, electronic device, and computer storage medium |
| WO2022077828A1 (en) * | 2020-10-15 | 2022-04-21 | 上海市肺科医院 | Repeated positioning method and system |
| WO2022142770A1 (en) * | 2020-12-28 | 2022-07-07 | 北京医智影科技有限公司 | Automatic radiation treatment planning system and method, and computer program product |
| CN112843503A (en) * | 2021-01-29 | 2021-05-28 | 中国人民解放军陆军军医大学第二附属医院 | Radiotherapy in-vivo dose monitoring method |
| CN113096766A (en) * | 2021-04-08 | 2021-07-09 | 济南大学 | Three-dimensional dose prediction method and system in personalized accurate radiotherapy plan |
| CN113679960A (en) * | 2021-08-11 | 2021-11-23 | 中科超精(南京)科技有限公司 | Multi-mode guiding radiotherapy device integrating three-dimensional online dose guiding |
| CN113674834A (en) * | 2021-08-16 | 2021-11-19 | 于金明 | Radiotherapy target region establishing and correcting method based on dose distribution preview system |
| CN114558251A (en) * | 2022-01-27 | 2022-05-31 | 苏州雷泰医疗科技有限公司 | Automatic positioning method and device based on deep learning and radiotherapy equipment |
| CN114707742A (en) * | 2022-04-15 | 2022-07-05 | 中国医学科学院肿瘤医院 | Artificial intelligence prediction method and system for adaptive radiotherapy strategy |
Non-Patent Citations (2)
| Title |
|---|
| Multi-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapy;Qi, MK 等;《MEDICAL PHYSICS》;第47卷(第4期);1880-1894 * |
| 基于神经网络学习方法的放疗计划三维剂量分布预测;孔繁图;麦燕华;亓孟科;吴艾茜;郭芙彤;贾启源;李永宝;宋婷;周凌宏;;南方医科大学学报(06);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115300811A (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111068187B (en) | System for performing an automated workflow of an adaptive radiation therapy session | |
| US12011613B2 (en) | Systems and methods for automatic treatment planning and optimization | |
| CN105825073B (en) | A kind of online radiotherapy planning quality control system | |
| CN106039576B (en) | Portal dosimetry system, device and method | |
| CN107072624B (en) | System and method for automated treatment planning | |
| US20230044983A1 (en) | Sequential monoscopic tracking | |
| US11801024B2 (en) | Apparatus and method for maintaining image quality while minimizing x-ray dosage of a patient | |
| JP6496813B2 (en) | Method, computer program and system for radiation therapy dose calculation | |
| CN110947108A (en) | System, method and apparatus for automatic target volume generation | |
| CN111386555A (en) | Image guidance method and device, medical equipment and computer readable storage medium | |
| CN115485019A (en) | Automatically planned radiation-based treatment | |
| US9014454B2 (en) | Method and apparatus pertaining to images used for radiation-treatment planning | |
| CN109872804B (en) | Automatic radiotherapy planning system and using method thereof | |
| JP2014212820A (en) | Radiotherapy system | |
| CN107847758A (en) | Use the radiation therapy system of multiple disposal plans | |
| CN115300811B (en) | Dose distribution determining method and device based on machine learning | |
| US11690581B2 (en) | Tumor position determination | |
| US9919165B2 (en) | Systems and methods for fiducial to plan association | |
| CN114344737A (en) | Tumor radiotherapy control system and storage medium | |
| CN113853636A (en) | Method, computer program product and computer system for providing an approximate image |
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 |