Target region positioning and adjusting method and system based on body surface tracking and respiratory gating

Abstract

The embodiment of the invention provides a target area positioning and adjusting method, system and device based on body surface tracking and respiratory gating and a medium, and the method comprises the steps that a breathing time phase is determined based on breathing signal data of a patient; acquiring contour data corresponding to the breathing time phase based on the breathing time phase; the body surface data and the contour data are registered, and the target area position of the patient is determined; in response to the fact that the target area position is not in the target area, pose adjustment is conducted on the patient, and the updated target area position is determined till the updated target area position is located in the target area.

Description

Technical Field

[0001] The present specification relates to the field of medical equipment technology, and in particular to a method and system for adjusting the position of a target area based on body surface tracking and respiratory gating. Background Art

[0002] Radiotherapy is one of the main methods currently used to treat diseases. During radiotherapy, in order to minimize the risk of radiation damage to the patient's healthy tissues, it is necessary to ensure that the radiation is accurately irradiated to the patient's target area. When the target is located in the chest and abdomen of the patient, the target location changes frequently due to the patient's breathing, and may even deviate from the radiation area of ​​the radiation, which will not only prolong the radiotherapy time, but may also affect the effect of radiotherapy.

[0003] Existing methods for locating the target area usually combine information such as the patient's breathing cycle to locate the target area in real time, which requires the patient to maintain a specific breathing posture and breathing rhythm during radiotherapy. This is not suitable for patients with breathing difficulties or who cannot control their breathing. In addition, when the target area deviates from the irradiation area of ​​the radiotherapy rays, existing methods for locating the target area usually cannot actively adjust the target area.

[0004] Therefore, it is necessary to provide a method, system, device and medium for adjusting the position of a target area based on body surface tracking and respiratory gating. Summary of the invention

[0005] One or more embodiments of the present specification provide a method for adjusting the target position based on body surface tracking and respiratory gating, the method comprising: determining the respiratory phase based on the patient's respiratory signal data; acquiring contour data corresponding to the respiratory phase based on the respiratory phase; aligning the body surface data and the contour data to determine the patient's target position; in response to the target position not being within the target area, adjusting the patient's posture and determining an updated target position until the updated target position is within the target area.

[0006] One or more embodiments of the present specification provide a target position positioning and adjustment system based on body surface tracking and respiratory gating, the system comprising a monitoring unit, a posture adjustment unit and a processor: the monitoring unit is configured to obtain respiratory signal data and body surface data of the patient; the posture adjustment unit is configured to adjust the posture of the patient; the processor is configured to: determine the respiratory phase based on the respiratory signal data of the patient; obtain contour data corresponding to the respiratory phase based on the respiratory phase; align the body surface data and the contour data to determine the target position of the patient; in response to the target position not being within the target area, adjust the patient's posture and determine an updated target position until the updated target position is within the target area.

[0007] One or more embodiments of the present specification provide a target area position adjustment device based on body surface tracking and respiratory gating, including a processor, wherein the processor is used to execute a target area position positioning adjustment method based on body surface tracking and respiratory gating.

[0008] A computer-readable storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a target area position positioning adjustment method based on body surface tracking and respiratory gating. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 is a modular schematic diagram of a target area position positioning and adjustment system according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a target area position positioning adjustment method according to some embodiments of this specification;

[0012] Figure 3 is an exemplary schematic diagram of a respiratory signal model according to some embodiments of this specification;

[0013] Figure 4 is an exemplary schematic diagram of determining the target area position of a patient according to some embodiments of this specification;

[0014] Figure 5 It is an exemplary schematic diagram of adjusting the patient's posture according to some embodiments of the present specification. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0016] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0017] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0019] To overcome the shortcomings of the prior art, some embodiments of the present specification provide a method, system, device and medium for target position positioning and adjustment based on body surface tracking and respiratory gating, which can accurately determine the patient's target position in real time, and when the target position deviates from the irradiation area of ​​the radiotherapy rays, the patient's posture can be adjusted in time to improve the continuity of radiotherapy, thereby ensuring the effectiveness of radiotherapy and reducing the radiation dose received by the patient.

[0020] Figure 1 It is a schematic diagram of an application scenario of the target area position positioning adjustment system shown in some embodiments of this specification. The application scenario of the target area position positioning adjustment system involved in the embodiments of this specification will be described in detail below. It should be noted that the following embodiments are only used to explain this application and do not constitute a limitation on this application.

[0021] In some embodiments, the target area positioning and adjustment system can be used in a variety of scenarios, such as accurately positioning the patient's tumor and other target areas based on the system during radiotherapy to ensure the accuracy and effectiveness of the treatment, and using the system to adjust the position of the operating table in real time during surgery to facilitate surgical operations. Figure 1 As shown, the application scenario of the target area position positioning and adjustment system may include a monitoring unit 110, a posture adjustment unit 120, a processor 130, a diagnosis and treatment device 140, and a patient 150, etc.

[0022] The monitoring unit is configured as a device for collecting respiratory signal data and body surface data of the patient. In some embodiments, the monitoring unit 110 includes but is not limited to respiratory monitors, body sensing cameras and other equipment.

[0023] The posture adjustment unit is configured as a device for adjusting the patient's posture. In some embodiments, the posture adjustment unit includes but is not limited to electric beds, rotary lifting platforms, and other equipment. The posture adjustment unit can translate and / or rotate along six degrees of freedom to flexibly adjust the patient's position.

[0024] The processor is configured as a key component for executing program instructions and processing data. The processor can process and execute one or more functions described in this specification. For example, the processor can determine the respiratory phase and the corresponding contour data of the respiratory phase based on the patient's respiratory signal data. In some embodiments, the processor can also align the body surface data and the contour data to determine the target area position of the patient.

[0025] In some embodiments, in response to the target area position not being within the target region, the processor may further adjust the patient's posture and determine an updated target area position until the updated target area position is within the target region.

[0026] The diagnostic and therapeutic equipment is configured as a device for diagnosing and / or treating a patient. In some embodiments, the diagnostic and therapeutic equipment includes but is not limited to a linear accelerator, a heavy ion therapy device, and the like.

[0027] Patient refers to an individual who needs to be diagnosed and / or treated. In some embodiments, patients include but are not limited to cancer patients receiving radiation therapy, surgical patients undergoing surgery, etc.

[0028] The above description is for illustrative purposes only, and actual application scenarios may vary.

[0029] It should be noted that the above description of the candidate display, determination system and its modules is only for convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem connected to other modules without deviating from this principle. In some embodiments, each module can share a storage module, or each module can have its own storage module. Such variations are all within the scope of protection of this specification.

[0030] Figure 2 is an exemplary flow chart of a method for adjusting the position of a target area according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be executed by a processor of the target area position positioning adjustment system.

[0031] Step 210 , determining the respiratory phase based on the patient's respiratory signal data.

[0032] The respiratory signal data may reflect changes in the patient's breathing. In some embodiments, the respiratory signal data includes the patient's respiratory frequency and breathing pattern. The breathing pattern may include the patient's inspiratory volume, expiratory volume, inspiratory rate, and expiratory rate, etc. The processor may obtain the respiratory signal data through the monitoring unit.

[0033] The respiratory phase can reflect the different stages of the patient's breathing. In some embodiments, the respiratory phase includes an inspiratory phase (e.g., early inspiratory phase, mid-inspiratory phase, late inspiratory phase, etc.) and an expiratory phase (e.g., early expiratory phase, mid-expiratory phase, late expiratory phase, etc.).

[0034] In some embodiments, the processor can determine the respiratory phase in a variety of ways. Taking the determination of the inspiratory phase as an example, the processor can determine the rate of change of the patient's inspiratory rate. When the patient's inspiratory rate is increasing, it is the early stage of inspiration; when the patient's inspiratory rate is stable, it is the middle stage of inspiration; when the patient's inspiratory rate is negatively increasing, it is the end of inspiration. The processor can determine the expiratory phase in a similar manner.

[0035] In some embodiments, the processor may also determine the inspiratory phase based on the patient's lung air volume. Taking the determination of the inspiratory phase as an example, the processor may preset a first inspiratory threshold and a second inspiratory threshold in advance. When the patient inhales, when the lung air volume is less than the first inspiratory threshold, it is the early inspiratory stage; when the lung air volume is greater than the first inspiratory threshold and less than the second inspiratory threshold, it is the middle inspiratory stage; when the lung air volume is greater than the second inspiratory threshold, it is the end inspiratory stage. The processor may preset the first exhalation threshold and the second exhalation threshold in advance in a similar manner to determine the exhalation phase.

[0036] In some embodiments, the processor may also determine the respiratory phase by using a respiratory signal model. Figure 3 and its related contents.

[0037] Step 220, based on the respiratory phase, obtain the contour data corresponding to the respiratory phase.

[0038] Contour data refers to the patient's body surface data collected in advance before diagnosis and treatment, which can reflect the patient's anatomical structure and physiological characteristics. Contour data can be represented as a human body model of the patient in a three-dimensional coordinate system.

[0039] In some embodiments, the processor can obtain the contour data of the patient in a variety of ways. For example, the processor can obtain the contour data through a treatment plan.

[0040] A treatment plan is a treatment plan for a patient to receive radiotherapy. The treatment plan includes the corresponding human body data and isocenter information at different breathing times.

[0041] In some embodiments, the processor continuously collects the patient's respiratory signal data and determines the respiratory phase through a respiratory monitor and other equipment, and continuously scans the patient through a CT scanner and other equipment to obtain the patient's CT data corresponding to different respiratory phases. The processor can model the scanned CT data in a three-dimensional coordinate system and determine the modeling result as the human body data in the treatment plan. The processor can determine the human body data in the treatment plan as contour data.

[0042] The isocenter information is the isocenter point of the patient's tumor or other pathological tissue, which can be expressed as coordinates in a three-dimensional coordinate system. In some embodiments, the processor can send the human body data to medical staff for diagnosis, and obtain the isocenter information corresponding to different respiratory phases uploaded by the medical staff.

[0043] Step 230: align the body surface data and the contour data to determine the target area position of the patient.

[0044] Body surface data refers to the patient's appearance data collected in real time. In some embodiments, the processor scans the patient through a device such as a body sensing camera to obtain the patient's body surface data corresponding to different breathing times. The processor can model the scanned body surface data in a three-dimensional coordinate system and determine the modeling result as the body surface data.

[0045] The target area refers to the area where the patient needs to be treated.

[0046] Registration refers to the operation of spatially aligning body surface data and contour data. The processor can register body surface data and contour data with the same respiratory phase in a variety of ways. For example, the processor can register by rigid body registration, elastic registration, and other methods.

[0047] In some embodiments, the processor can divide the respiratory stage into six respiratory phases, and determine the contour data of the patient in the six respiratory phases through a CT scanner or other equipment before the diagnosis and treatment begins. When radiotherapy begins, the processor can obtain the patient's current body surface data and respiratory phase based on a body sensing camera or other equipment, and select the contour data of the same respiratory phase from the six contour data for registration to obtain the registered contour data.

[0048] In some embodiments, the processor may also perform registration based on a rigid body registration network method.

[0049] The rigid body registration network method is a method for registration through rigid body transformation. In some embodiments, the rigid body registration network method at least includes a DeepVCP (Deep Volumetric Correspondence Prediction) network method.

[0050] In some embodiments, the DeepVCP network method includes a deep feature extraction layer, a weighting layer, a Kalman filter, and a generation layer.

[0051] In some embodiments, the depth feature extraction layer is used to extract depth features from surface data and contour data; the weighted layer is used to determine key points in the surface data and corresponding candidate points in the contour data; the Kalman filter is used to embed the depth features into the key points and candidate points to obtain high-dimensional features for corresponding relationship prediction; the generation layer is used to predict corresponding relationships based on high-dimensional features, filter out key points of surface data from candidate points, and perform network alignment.

[0052] In some embodiments, the processor can extract deep features from the body surface data and contour data based on the DeepVCP network method, and screen out N body surface data key points based on the deep features of the body surface data. The processor can obtain N*C contour data candidate points based on the deep features of the contour data through similarity matching and other methods. Based on the Kalman filter, the deep features of the body surface data are embedded into the body surface data key points, and the deep features of the contour data are embedded into the contour data candidate points. Based on the generation layer, N contour data candidate points are screened out from the N*C contour data candidate points through constraint conditions as contour data key points. And network alignment is performed based on the body surface data key points and the corresponding contour data key points, so as to achieve alignment of the body surface data and the contour data. Among them, the constraint conditions may include global geometric constraint loss and local similarity loss.

[0053] In some embodiments of this specification, since the real-time collected body surface data and the contour data of the treatment plan may have positional differences, the body surface data and the contour data may not be accurately matched. By using the DeepVCP network method to align the body surface data and the contour data, and by combining the use of global geometric constraint loss and local similarity loss as constraint conditions, it is helpful to finely adjust the matching of local areas while maintaining the accuracy of global registration, thereby improving the registration accuracy in complex real scenes with noise and improving the robustness of the registered data.

[0054] In some embodiments, the processor may correct the body surface data based on the patient's real-time posture information and standard posture information, and align the corrected body surface data with the contour data.

[0055] The posture information can reflect the patient's position and body posture. The posture information includes real-time posture information and standard posture information. The standard posture information is the posture information when the patient's contour data is collected, and the real-time posture information refers to the patient's current posture information. The processor can obtain the patient's posture information through devices such as depth cameras and ultra-wideband (UWB) sensors.

[0056] In some embodiments, the processor corrects the patient's body surface data based on the difference between the real-time posture information and the standard posture information. For example, when the processor finds that the patient's position in the real-time posture information is offset by 1 mm in a certain direction compared to the standard posture information, the processor can move the patient's body surface data by 1 mm in the opposite direction to offset the patient's posture change.

[0057] In some embodiments, the processor obtains the corrected body surface data based on the correction model. The correction model includes any one or combination of a neural network (NN) model, a deep neural network (DNN) model, or other custom model structures.

[0058] In some embodiments, the input of the correction model includes real-time posture information, standard posture information and body surface data of the patient, and the output of the correction model includes corrected body surface data.

[0059] In some embodiments, the correction model can be obtained based on a large number of first training samples with a first label. The first training sample includes sample real-time posture information, sample standard posture information and sample surface data, and the first label includes sample corrected surface data corresponding to the first training sample. The first training sample with the first label can be obtained by simulation fitting. For example, the processor can pre-build a human body model (for example, a simulation model) under the sample standard posture and collect posture information and surface data as sample standard posture information and sample surface data, adjust the posture of the human body model, and use the posture information and surface data after the posture adjustment as sample real-time posture information and sample corrected surface data. By repeating the above steps, several groups of first training samples with the first label are obtained.

[0060] In some embodiments, the training process of the correction model includes: obtaining multiple first training samples with first labels to form a first training sample set, and performing multiple rounds of iterations based on the first training sample set. Among them, at least one round of iteration includes: selecting one or more first training samples from the first training data set, inputting one or more first training samples into the initial correction model, and obtaining the model prediction output corresponding to one or more first training samples; substituting the model prediction output corresponding to one or more first training samples and the first labels corresponding to one or more first training samples into the formula of a predefined loss function to calculate the value of the loss function; according to the value of the loss function, iteratively updating the model parameters in the initial correction model until the iteration end condition is met, and the iteration is terminated to obtain a trained correction model. Among them, the iterative update of the model parameters of the initial correction model can be performed by a variety of methods, for example, it can be updated based on the gradient descent method. The iteration end condition may include the convergence of the loss function or the number of iterations reaching the iteration number threshold.

[0061] For the steps of registering the corrected body surface data and contour data, please refer to the relevant content of registering body surface data and contour data above.

[0062] In some embodiments of the present specification, since the patient may change his or her posture, when registering the body surface data and the contour data, the posture corresponding to the body surface data may be different from the posture corresponding to the contour data, resulting in reduced accuracy of registration. By correcting the body surface data, the accuracy of registering the body surface data and the contour data can be effectively improved, thereby facilitating accurate positioning of the target area.

[0063] In some embodiments, in response to the registration being completed, the processor may determine the registered isocenter based on the registered contour data, and determine the registered isocenter as the target area position of the patient.

[0064] In some embodiments, the processor can also determine the target area position based on the body surface data and the contour data. Figure 4 Related instructions.

[0065] Step 240 , in response to the target area position not being within the target region, adjusting the patient's posture and determining an updated target area position until the updated target area position is within the target region.

[0066] The target area is the effective treatment area of ​​the diagnostic equipment, and the patient's target position needs to be within the target area.

[0067] In some embodiments, the target area includes the radiation beam irradiation range of a radiation device (e.g., a linear accelerator), the effective detection range of a diagnostic device, etc. The target area can be pre-determined, and the processor can also determine the target area based on factory reports, operating instructions, and other information of the relevant equipment.

[0068] Posture adjustment refers to the step of adjusting the patient's body posture. The processor can adjust the patient's posture by moving, rotating, pitching, and tilting the bed based on the posture adjustment unit.

[0069] In some embodiments, the processor may dynamically detect the updated target area position by real-time adjustment until the updated target area position is located in the target area.

[0070] In some embodiments, the processor may further adjust the patient's posture based on the posture adjustment parameters. Figure 5 Related instructions.

[0071] In some embodiments of the present specification, by adjusting the patient's position to ensure that the updated target area is located in the target area, the target area position can be adjusted flexibly and dynamically, reducing the frequent changes in the target area position due to the patient's breathing, thereby reducing the radiotherapy efficiency and the negative impact caused by the expansion of the irradiated area due to untimely adjustment of the target area position. This helps to improve the accuracy of radiotherapy and reduce the time consumption, thereby reducing the damage of radiation to healthy tissues.

[0072] is an exemplary schematic diagram of a respiratory signal model according to some embodiments of the present specification.

[0073] In some embodiments, the processor may determine the respiratory phase 370 through the respiratory signal model 300 based on the respiratory signal data 310 .

[0074] The breathing signal model 300 is a model for determining the breathing phase. In some embodiments, the breathing signal model comprises a machine learning model.

[0075] In some embodiments, the respiratory signal model 300 includes a data processing layer 340 and a data analysis layer 360. The data processing layer may be a Kalman filter (KF), and the data analysis layer may be a long short-term memory network (LSTM).

[0076] In some embodiments, the input of the data processing layer is the respiratory signal data 310 , and the output is the pre-processed data 350 . The output of the data processing layer can be used as the input of the data analysis layer, and the output of the data analysis layer is the respiratory phase 370 .

[0077] In some embodiments, the input of the respiratory signal model also includes the patient's real-time posture information 320 and body surface data 330. For more information about posture information and body surface data, see Figure 2 and related instructions.

[0078] In some embodiments of the present specification, by incorporating the patient's real-time posture information and body surface data into the input of the respiratory signal model, the respiratory signal model can further consider the impact of respiratory data deviations caused by the different relative positions of the patient and the monitoring unit, thereby helping to improve the accuracy of predicting the respiratory phase.

[0079] In some embodiments, the data processing layer and the data analysis layer can be obtained through joint training.

[0080] In some embodiments, the processor can pre-acquire a trained data processing layer, and in the joint training process of the data processing layer and the determination layer, keep the model parameters of the trained data processing layer unchanged, and continue to train the model parameters of the data analysis layer. The second training sample of the joint training includes sample respiratory signal data, and the second label is the sample respiratory phase corresponding to the sample respiratory signal data. In some embodiments, the second training sample can be acquired based on historical data, and the second label can be determined by manual annotation.

[0081] Exemplarily, the joint training process includes: inputting the sample respiratory signal data into the trained data processing layer to obtain preprocessed data; randomly dividing the preprocessed data into two parts, one of which is used as a training set and the other as a test set, and inputting the preprocessed data in the training set into the initial data analysis layer to obtain the respiratory phase output by the initial data analysis layer. Based on the respiratory phase output by the prediction layer and the second label, a loss function is constructed to update the model parameters of the initial data analysis layer, while keeping the parameters of the trained data processing layer unchanged. When the loss function of the initial data analysis layer meets the preset conditions, the model training is completed to obtain the preliminary trained respiratory signal model; the preprocessed data in the test set is input into the preliminary trained respiratory signal model to obtain the output result of the preliminary trained respiratory signal model, and the output result is compared with the sample respiratory phase corresponding to the preprocessed data in the test set. When the comparison requirements are met, the joint training is completed. If the requirements are not met, the model parameters are iteratively updated and retrained until the joint training is completed. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.; meeting the comparison requirements can be: the error between the output result and the sample respiratory phase is less than the preset error threshold.

[0082] In some embodiments of the present specification, the respiratory phase is predicted by a respiratory signal model, and the data analysis and processing capabilities of the respiratory signal model can be utilized to quickly and accurately determine the respiratory phase, thereby improving the response speed and prediction accuracy of the target area position positioning and adjustment system.

[0083] Figure 4 is an exemplary schematic diagram of determining the target area position of a patient according to some embodiments of the present specification.

[0084] In some embodiments, the processor may sample the body surface data 330 to determine the sampled data.

[0085] Sampling refers to the operation of extracting and filtering the body surface data 330. The sampled data 330 is the data obtained after filtering the body surface data.

[0086] In some embodiments, the sampling method includes but is not limited to random sampling, uniform sampling, cluster sampling, etc. For example, the processor may divide the body surface data into several regions, select the same number of sampling points from each region, and determine the body surface data corresponding to the sampling points as the sampling data.

[0087] In some embodiments, the processor may determine a primary target area position 430 based on the sampling data 410 and the contour position 420 .

[0088] The primary target area position 430 refers to the target area position that has been initially positioned. The positioning accuracy of the primary target area position is lower than that of the target area position.

[0089] In some embodiments, the step of determining the primary target area position based on the sampling data and the contour position by the processor is similar to the step of determining the target area position of the patient by registering the body surface data and the contour data, which can be seen in Figure 1 Related instructions.

[0090] In some embodiments, in response to the primary target area position not being within the target area, the processor may perform a preliminary posture adjustment 440 based on the primary target area position and the target area position.

[0091] The preliminary posture adjustment 440 refers to a posture adjustment based on the primary target area position, and the preliminary posture adjustment may include adjustment ranges for each of the six degrees of freedom.

[0092] In some embodiments, the processor may determine the adjustment range of each of the six degrees of freedom in a variety of ways. For example, the processor may determine the isocenters that respectively determine the primary target area position and the target area position, and determine the relative positional relationship between the primary target area position and the target area position based on the isocenters.

[0093] In some embodiments, the processor may determine the adjustment range of each of the six degrees of freedom based on a first preset table. The processor may construct a first preset table based on historical relative position relationships and historical adjustment ranges. The first preset table includes a correspondence between different historical relative position relationships and different historical adjustment ranges. The processor may determine the adjustment range of each of the six degrees of freedom by querying the first preset table based on the current relative position relationship.

[0094] In some embodiments, during the preliminary posture adjustment 440 , the processor may determine the target area position 450 based on the body surface data 330 and the contour data 460 .

[0095] In some embodiments, since it takes time to determine the target area, if the posture adjustment is performed after the target area is determined, it will take a long time. Therefore, the primary target area can be determined first and the preliminary posture adjustment can be performed. The target area can be determined during the preliminary posture adjustment process. After the target area is determined, the posture adjustment can be performed until the target area is located at the target area.

[0096] For more information on determining the target area position based on the body surface data and the contour data, please refer to Figure 2 Relevant part.

[0097] In some embodiments of the present specification, by first determining the primary target area position, performing a quick preliminary posture adjustment, and determining the target area position during the preliminary posture adjustment process to perform a more precise posture adjustment, the waiting time for posture adjustment can be reduced and the efficiency of posture adjustment can be improved.

[0098] Figure 5 It is an exemplary schematic diagram of adjusting the patient's posture according to some embodiments of the present specification.

[0099] In some embodiments, the processor may determine a posture adjustment parameter 530 based on the target area position 450 , the target area position 510 and the patient's real-time posture information 520 ; and perform a posture adjustment 540 on the patient based on the posture adjustment parameter 530 .

[0100] The target region position 510 refers to the spatial position of the target region. The target region position can be represented by a coordinate region in a three-dimensional coordinate system.

[0101] The patient's real-time posture information 520 may reflect the patient's current spatial position. The patient's real-time posture information may be represented by six degrees of freedom.

[0102] The posture adjustment parameter 530 is a parameter for controlling the posture adjustment unit to adjust the patient's position. In some embodiments, the posture adjustment parameter includes the adjustment direction and adjustment amplitude of the electric bed in six degrees of freedom, for example, [(X:0); (Y:+3); (Z:-2); (α:0); (β:+3°); (γ:0)], which means that the electric bed first moves 3 units along the positive direction of the Y axis, moves 2 units along the negative direction of the Z axis, and rotates 3 degrees clockwise along the Y axis.

[0103] In some embodiments, the processor may determine the posture adjustment parameter through a posture adjustment parameter model. The posture adjustment parameter model may be a machine learning model, such as any one or combination of a NN model, a DNN model, or other custom model structures.

[0104] In some embodiments, the input of the posture adjustment parameter model includes the target area position, the target region position and the patient's real-time posture information, and the output includes the posture adjustment parameters.

[0105] In some embodiments, the processor can train a posture adjustment parameter model through a third training sample with a third training label. The third training sample includes a sample target area position, a sample target area position and a sample real-time posture information, and the third training label includes a sample posture adjustment parameter corresponding to the third training sample.

[0106] The third training sample of the third training label can be obtained by simulation fitting. For example, the processor can pre-construct a human body model (for example, a simulation model or a real person), and collect the target area position, the target area position and the real-time posture information of the human body model as a set of third training samples, and perform multiple posture adjustments in parallel until the target area position is located in the target area. The processor can select the posture adjustment parameters with the smallest adjustment amplitude and the least number of repeated alignments from the multiple posture adjustment records as the third training label corresponding to the group of third training samples. By changing the target area position, the target area position and the real-time posture information of the human body model and repeating the above steps, several groups of third training samples with third labels can be obtained.

[0107] In some embodiments of the present specification, by using a posture adjustment parameter model to determine posture adjustment parameters to adjust the patient's posture, it is possible to avoid discomfort to the patient due to excessive posture adjustment times and large amplitudes, and improve the efficiency of posture adjustment.

[0108] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0109] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0110] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0111] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0112] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0113] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0114] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for adjusting the position of a target area based on body surface tracking and respiratory gating, the method comprising: determining a respiratory phase based on the patient's respiratory signal data; Based on the respiratory phase, acquiring contour data corresponding to the respiratory phase; Registering body surface data and the contour data to determine the target area position of the patient; In response to the target area position not being within the target region, the patient's posture is adjusted and an updated target area position is determined until the updated target area position is within the target region.

2. The method according to claim 1, characterized in that Determining the patient's respiratory phase based on the respiratory signal data includes: Based on the respiratory signal data, the respiratory phase is determined by a respiratory signal model, wherein the respiratory signal model includes a data processing layer and a data analysis layer, and the respiratory signal model is a machine learning model.

3. The method according to claim 2, characterized in that The input of the respiratory signal model includes the patient's real-time posture information and body surface data.

4. The method according to claim 1, characterized in that: The registering the body surface data and the contour data comprises: The registration is performed based on a rigid body registration network method, and the rigid body registration network method at least includes a DeepVCP (DeepVolumetric Correspondence Prediction) network method.

5. The method according to claim 1, characterized in that The registering the body surface data and the contour data comprises: Correcting the body surface data based on the real-time posture information and standard posture information of the patient; The corrected body surface data and the contour data are registered.

6. The method according to claim 1, characterized in that The posture adjustment of the patient comprises: Determining posture adjustment parameters based on the target area position, the target region position and the patient's real-time posture information; The posture of the patient is adjusted based on the posture adjustment parameters.

7. The method according to claim 1, characterized in that The registering of the body surface data and the contour data to determine the target area position of the patient comprises: Sampling the body surface data to determine sampled data; Determining a primary target area position based on the sampling data and the contour position; In response to the primary target area position not being within the target area, performing preliminary posture adjustment based on the primary target area position and the target area position; During the initial posture adjustment process, the target area position is determined based on the body surface data and the contour data.

8. A target area position positioning and adjustment system based on body surface tracking and respiratory gating, characterized in that: The system comprises: A monitoring unit configured to obtain respiratory signal data and body surface data of the patient; A posture adjustment unit, configured to adjust the posture of the patient; The processor is configured as: determining a respiratory phase based on the patient's respiratory signal data; Based on the respiratory phase, acquiring contour data corresponding to the respiratory phase; Registering body surface data and the contour data to determine the target area position of the patient; In response to the target area position not being within the target region, the patient's posture is adjusted and an updated target area position is determined until the updated target area position is within the target region.

9. The system according to claim 8, characterized in that The processor is further configured to: Based on the respiratory signal data, the respiratory phase is determined by a respiratory signal model, wherein the respiratory signal model includes a data processing layer and a data analysis layer, and the respiratory signal model is a machine learning model.

10. The system according to claim 9, characterized in that The input of the respiratory signal model includes the patient's real-time posture information and body surface data.

11. The system according to claim 8, characterized in that The processor is further configured to: The registration is performed based on a rigid body registration network method, and the rigid body registration network method at least includes a DeepVCP (DeepVolumetric Correspondence Prediction) network method.

12. The system according to claim 8, characterized in that The processor is further configured to: Correcting the body surface data based on the real-time posture information and standard posture information of the patient; The corrected body surface data and the contour data are registered.

13. The system according to claim 8, characterized in that The processor is further configured to: Determining posture adjustment parameters based on the target area position, the target region position and the patient's real-time posture information; The posture adjustment unit is further configured as follows: Based on the posture adjustment parameters, the posture of the patient is adjusted.

14. The system according to claim 8, characterized in that The processor is further configured to: Sampling the body surface data to determine sampled data; Determining a primary target area position based on the sampling data and the contour position; In response to the primary target area position not being within the target area, performing preliminary posture adjustment based on the primary target area position and the target area position; During the initial posture adjustment process, the target area position is determined based on the body surface data and the contour data.

15. A target area position positioning and adjustment device based on body surface tracking and respiratory gating, comprising a processor, wherein the processor is used to execute the target area position positioning and adjustment method according to any one of claims 1 to 7.

16. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the target area position positioning and adjustment method based on body surface tracking and respiratory gating as described in any one of claims 1 to 7.

Images