Image completion method and device, computer equipment and storage medium

Abstract

The invention relates to an image completion method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a measurement radiation field image of a first part of radiation field of a beam in a measurement area of a detector; acquiring a complemented radiation field image of a second part of radiation field outside the measurement area; and complementing the measured radiation field image through the complemented radiation field image to obtain a target radiation field image. By adopting the method, the radiation field image with information loss can be complemented.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to an image completion method and device, computer equipment and a storage medium. BACKGROUND

[0002] In the field of radiotherapy, the body dose monitoring method based on the electronic portal imaging device (EPID) has developed rapidly.

[0003] However, due to mechanical design, too large field or position eccentricity, etc., the EPID detector cannot collect all the field images of the measurement region, that is, there is a situation of missing part of the information of the collected field image.

[0004] Therefore, there is an urgent need for a method for completing the field image with missing information to ensure that a complete field image can be obtained for radiotherapy delivery while ensuring the quality of the field image. SUMMARY

[0005] Therefore, it is necessary to provide an image completion method, device, computer equipment and storage medium to complete the field image with missing information.

[0006] In a first aspect, the present application provides an image completion method, comprising:

[0007] Obtaining a measurement field image of a first part of the field of the beam in the measurement region of the detector;

[0008] Obtaining a completion field image of a second part of the field located outside the measurement region;

[0009] Completing the measurement field image by the completion field image to obtain a target field image. In one embodiment, obtaining the completion field image of the second part of the field located outside the measurement region comprises:

[0010] Obtaining a radiotherapy plan parameter and / or a radiotherapy execution parameter;

[0011] Determining the completion field image according to the radiotherapy plan parameter and / or the radiotherapy execution parameter.

[0012] In one embodiment, determining the completion field image according to the radiotherapy plan parameter and / or the radiotherapy execution parameter comprises:

[0013] Inputting the radiotherapy plan parameter and / or the radiotherapy execution parameter and the measurement field image into an image completion model to output the completion field image.

[0014] In one of the embodiments, the complete field image is determined according to the radiation plan parameters and / or the radiation execution parameters, comprising:

[0015] The expected field image is determined according to the radiation plan parameters;

[0016] The complete field image is predicted according to the expected field image and the radiation execution parameters.

[0017] In one of the embodiments, the target field image is obtained by complementing the measured field image with the complete field image, comprising:

[0018] A plurality of complete points of a complete edge of the complete field image and a plurality of measured points of a complemented edge of the measured field image are obtained;

[0019] Each of the complete points is aligned with the corresponding measured point, and the aligned complete edge and the complemented edge are spliced to obtain the target field image.

[0020] In one of the embodiments, the method further comprises:

[0021] The radiation delivery effect is evaluated according to the radiation plan parameters and the target field image; and / or, the body dose distribution of the measurement region is reconstructed according to the radiation plan parameters and the target field image.

[0022] In one of the embodiments, the radiation treatment effect is evaluated according to the radiation plan parameters and the target field image, comprising:

[0023] The predicted field image corresponding to the measurement region is obtained based on the radiation plan parameters;

[0024] The target field image corresponding to the measurement region is compared with the predicted field image;

[0025] The radiation delivery effect is evaluated according to the comparison result.

[0026] In a second aspect, the present application further provides an image completion device, comprising:

[0027] The acquisition module is configured to obtain a measured field image of a first part of a field in a measurement region of a detector by a beam;

[0028] The obtaining module is configured to obtain a complete field image of a second part of a field outside the measurement region;

[0029] The complementing module is configured to obtain a target field image by complementing the measured field image with the complete field image.

[0030] In a third aspect, the present application also provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the content of any one of the embodiments of the image completion method of the first aspect when executing the computer program.

[0031] In a fourth aspect, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program implements the content of any one of the embodiments of the image completion method of the first aspect when executed by a processor.

[0032] In a fifth aspect, the present application also provides a computer program product, comprising a computer program, and the computer program implements the content of any one of the embodiments of the image completion method of the first aspect when executed by a processor.

[0033] The image completion method, device, computer device and storage medium described above acquire a measurement field image of a first part of a field of view in a measurement region of a detector; acquire a completion field image of a second part of the field of view outside the measurement region; and complete the measurement field image by using the completion field image to obtain a target field image. For a measurement field image with a small measurement region, the method can complete the measurement field image by using the completion field image of the second part of the field of view outside the measurement region, so that the integrity of the field image information can be ensured, and more abundant image information can be provided for subsequent image processing. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0035] Figure 1 An application environment diagram of the image completion method in an embodiment;

[0036] Figure 2 A flowchart of the image completion method in an embodiment;

[0037] Figure 3 A schematic diagram of a measurement field image in an embodiment;

[0038] Figure 4 A flowchart of the image completion method in an embodiment;

[0039] Figure 5 A flowchart of the image completion method in an embodiment;

[0040] Figure 6This is a flowchart illustrating an image completion method in one embodiment;

[0041] Figure 7 This is a flowchart illustrating an image completion method in one embodiment;

[0042] Figure 8 This is a flowchart illustrating an image processing method in one embodiment;

[0043] Figure 9 This is a schematic diagram of the image completion device in one embodiment. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0045] The image completion method provided in this application embodiment can be applied to, for example, Figure 1 The application environment shown is a computer device that can be a server, personal computer, laptop, smartphone, tablet, or mobile phone. This computer device may include a processor, memory, and network interface connected via a system bus or wirelessly. The processor provides computing and control capabilities. The memory may include non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data used in the image completion process. The network interface is used to communicate with external terminals via a network connection, and the computer program, when executed by the processor, implements an image completion method.

[0046] In one exemplary embodiment, such as Figure 2 As shown, an image completion method is provided, which is applied to... Figure 1 The following steps, 201 to 203, are used as an example of computer equipment.

[0047] S201, acquire the measurement field image of the first part of the field of the beam within the measurement area of ​​the detector.

[0048] The first part of the radiation field refers to the range (e.g., irradiation range, coverage area, etc.) of the beam emitted by the detector in the radiation delivery equipment (e.g., radiotherapy equipment, radiation processing equipment) from the detector. During image acquisition, the first part of the radiation field within the measurement area cannot completely cover the region of interest; that is, the measured radiation field image is acquired when the detector's radiation field range exceeds part of the region of interest. Therefore, the measured radiation field image of the first part of the radiation field has some missing information. The region of interest can refer to the area where the patient needs to undergo radiation delivery (e.g., radiation delivery can be radiotherapy, pre-radiotherapy radiation simulation verification, radiation processing, etc.). For example, the region of interest can be the tumor area or the area including the area surrounding the tumor area. The detector can be an electronic radiation field imaging device, a fluorescence detector, a solid-state detector, a liquid ionization chamber detector, a charge-coupled device (CCD) camera, etc.

[0049] In this embodiment, the computer device can send an image acquisition signal to the detector. After receiving the image acquisition signal, the detector acquires an image of the region of interest to obtain a measurement field image of the measurement area. It should be noted that since the detector's measurement area may be smaller than the region of interest, the measurement field image only contains a portion of the measurement area.

[0050] For example, Figure 3 This diagram illustrates the measurement of the field of view. The irregular areas represent the regions of interest (ROIs). The largest quadrilateral represents the detector's maximum measurement area, within which all information about the ROI can be acquired. However, due to various limitations, the detector's actual measurement area is limited to the interior of a smaller quadrilateral. As clearly seen in the diagram, a portion of the ROI exists between the interior of the largest quadrilateral and the exterior of the smallest quadrilateral. The image corresponding to the area inside the smaller quadrilateral cannot completely cover the ROI; that is, the image corresponding to this smaller quadrilateral is an image of the ROI that exceeds the field of view.

[0051] S202, Obtain the complete field image of the second part of the field located outside the measurement area.

[0052] The measurement area refers to the measurement area of ​​the detector, as referenced. Figure 3 The region inside the smaller quadrilateral in the measurement area. The region outside the measurement area refers to... Figure 3 The region between the interior of the larger quadrilateral and the exterior of the smaller quadrilateral can be one region or multiple regions.

[0053] The area outside the measurement area can be multiple areas. Correspondingly, the second part of the field of view can be any one or any multiple areas outside the measurement area, and the number of completed field images can also be multiple, that is, the number of completed field images is the same as the number of the second part of the field of view. Alternatively, the second part of the field of view can also be all areas outside the measurement area.

[0054] In this embodiment, the computer device can analyze the measured field image of the first part of the field using a preset image completion model to determine the completed field image of the second part of the field. Alternatively, the computer device can predict the completed field image of the second part of the field outside the measurement area based on the imaging parameters of the detector displayed on the accelerator. Or, the computer device can calculate and determine the completed field image of the second part of the field outside the measurement area based on an image completion algorithm. For example, the image completion algorithm can be depth-based image completion. For example, it can be based on the device's historical field data, machine operating parameters (e.g., the motion and / or position data of the collimator used to adjust the beam size, the angle and / or position of the beam when it exits the device, etc.). Alternatively, the completed field image can be obtained by measuring the detector by adjusting or changing the position and / or orientation of the detector. This embodiment does not limit the method of obtaining the completed field image of the second part of the field outside the measurement area.

[0055] S203, by completing the measurement field image, the target field image is obtained.

[0056] You can refer to this. Figure 3 Further explanation of each shooting field image: measuring shooting field images refers to... Figure 3 The smaller quadrilateral's interior region corresponds to the field image; completing the field image refers to... Figure 3 The target field image refers to the area between the interior of the larger quadrilateral and the exterior of the smaller quadrilateral. Figure 3 The field image corresponding to the irregular area in the middle, that is, the target field image is composed of the measured field image and the completed field image.

[0057] In this embodiment, after obtaining the completed field image of the second part of the field outside the detector's measurement area, a computer device or user can determine the edges that need to be stitched from the completed field image and the measured field image, align and stitch the edges, and use the stitched measured field image as the target field image. If there are multiple completed field images, the target field image is obtained by stitching the multiple completed field images with the measured field image respectively. However, this is not limited to this; other methods can also be used to complete the measured field image using the completed field image to obtain the target field image, and no limitation is made here. For example, when the completed field image is obtained by extending the edges of the measured field image, the target field image can be obtained directly by combining them without image alignment and stitching.

[0058] In the aforementioned image completion method, a measured field image of the first portion of the field within the detector's measurement area is acquired; a completed field image of the second portion of the field outside the measurement area is acquired; and the measured field image is completed using the completed field image to obtain the target field image. This method is suitable for measured field images with small measurement areas, as it can be completed using the completed field image of the second portion of the field outside the measurement area. This ensures the integrity of the field image information and provides richer image information for subsequent image processing.

[0059] The completed field images mentioned above can be determined in two ways. The first way is through treatment plans and historical image sequences. The second way is through the imaging parameters of a detector (e.g., an electronic field imaging device). These two methods will be described below.

[0060] First, in one embodiment, such as Figure 4 As shown, the first method will be introduced first. The above-mentioned method of obtaining the complete field image of the second part of the field outside the measurement area includes the following steps:

[0061] S301, Obtain radiation planning parameters and / or radiation execution parameters.

[0062] Both radiation planning parameters and radiation execution parameters are stored in the accelerator's log files, the log files of external monitoring devices that monitor the accelerator's operating status, and / or other files. Radiation planning parameters refer to planned, pre-execution parameters. For example, radiation planning parameters could be specific values ​​for radiation dose or planned radiation locations. Radiation execution parameters refer to the parameters or results of actual execution; for example, radiation execution parameters could be the detector's initial position, movement trajectory, etc., during the actual execution process.

[0063] In this embodiment of the application, after receiving a radiotherapy instruction, the computer device can search for and obtain the radiotherapy plan parameters and / or radiotherapy execution parameters corresponding to the treatment instruction from the accelerator's log file, the record file of the external monitoring device that monitors the accelerator's operating status, and / or other files.

[0064] S302, determine the complete radiation field image based on radiation planning parameters and / or radiation execution parameters.

[0065] In this embodiment, the computer device can use a preset image completion model to analyze radiation planning parameters and / or radiation execution parameters, and the measured radiation field image, to predict the image of a second part of the radiation field outside the measurement area, and use the prediction result as the completed radiation field image. Figure 3 The radiation field image corresponds to the region between the interior of the larger quadrilateral and the exterior of the smaller quadrilateral. Alternatively, the computer device can determine the desired radiation field image based on radiation plan parameters, and predict the completed radiation field image based on the desired radiation field image and radiation execution parameters to obtain the completed radiation field image. This application does not limit the method of obtaining the completed radiation field image.

[0066] The above-mentioned method obtains radiation planning parameters and / or radiation execution parameters, and determines the complete radiation field image based on these parameters. This method, through the planning and execution parameters prior to radiotherapy, can accurately simulate the radiation process, thereby accurately obtaining the complete radiation field image.

[0067] In one embodiment, obtaining a completed radiation field image can be achieved through an image completion model. Specifically, radiation planning parameters and / or radiation execution parameters, along with the measured radiation field image, are input into the image completion model, which outputs a completed radiation field image.

[0068] In this embodiment, the computer device can input radiation planning parameters and / or radiation execution parameters, as well as the measured radiation field image, as input signals into a preset image completion model. The image completion model extracts feature information of the measured radiation field image and, based on the feature information of the measured radiation field image, radiation planning parameters and / or radiation execution parameters, predicts the completed radiation field image of the second part of the radiation field outside the measurement area.

[0069] The aforementioned preset image completion model can be a deep neural network (DNN), a recurrent neural network (RNN), or a convolutional neural network (CNN), etc. CNN networks can be ResNet series networks, CPN networks, SimpleBaseline networks, Posefix networks, High-Resolution Networks (HRNet), etc. The image completion model can be a single network or a combination of multiple networks.

[0070] During the training of the image completion model, radiation planning parameters and radiation execution parameters, multiple sample measured radiation field images, and corresponding true completed radiation field images are acquired. The radiation planning parameters, radiation execution parameters, and multiple sample measured radiation field images are fed into the initial image completion model. The initial image completion model is used to analyze each sample measured radiation field image to obtain a predicted completed radiation field image. Based on the difference between the predicted and true completed radiation field images, the parameters of the initial image completion model are adjusted until the difference between the predicted and true completed radiation field images output by the initial image completion model is less than a preset threshold. The initial image completion model training is then complete, and the image completion model is obtained.

[0071] In the aforementioned image completion method, radiation planning parameters and / or radiation execution parameters, along with the measured radiation field image, are input into the image completion model, and the completed radiation field image is output. This method analyzes the radiation planning parameters and / or radiation execution parameters, as well as the measured radiation field image, through the image completion model. This allows for the determination of the characteristic information of the second part of the radiation field outside the measurement area, thereby accurately obtaining the completed radiation field image of the second part of the radiation field.

[0072] In one embodiment, such as Figure 5 As shown, the above-mentioned determination of the complete radiation field image based on radiation planning parameters and / or radiation execution parameters includes the following steps:

[0073] S401, determine the desired radiation field image based on radiation plan parameters.

[0074] The expected field image refers to the field image predicted based on the radiation plan parameters.

[0075] In this embodiment, the computer device can analyze multiple historical radiation plan parameters and corresponding historical measurement field images to determine the correspondence between the radiation plan parameters and the measurement field images. Then, based on the correspondence between the radiation plan parameters and the measurement field images, the computer device can analyze the radiation plan parameters, predict the corresponding field image, and use the predicted field image as the desired field image.

[0076] Understandably, computer equipment can also determine the beam shape and angle of the detector based on radiation planning parameters / radiation execution parameters. Combined with known information or information included in the radiation planning parameters / radiation execution parameters regarding the detector's placement and orientation, it can acquire the radiation field outside the measurement area, i.e., the second radiation field. Then, the image of the second radiation field is used to predict the desired radiation field image.

[0077] S402 predicts and completes the field image based on the desired field image and the radiation execution parameters.

[0078] In this embodiment, after acquiring the desired radiation field image, the computer device can adjust the desired radiation field image based on the radiation execution parameters. Then, it can determine the image outside the measurement area on the adjusted desired radiation field image and use this image as the completed radiation field image. Alternatively, the computer device can first determine the image outside the measurement area on the desired radiation field image and use this image as the initial completed radiation field image. Then, it can adjust the initial completed radiation field image using the radiation execution parameters to obtain the predicted completed radiation field image.

[0079] Understandably, after adjusting the initial completed field image, it can be further adjusted by combining historical image sequences to make the resulting completed field image more accurate. For example, since the feature information of patterns or pixels in historical images needs to be reflected in the completed image, the initial completed field image can be adjusted using the feature information of patterns or pixels in historical images.

[0080] In the image completion method described above, the desired radiation field image is determined based on radiation plan parameters; the completed radiation field image is then predicted based on the desired radiation field image and radiation execution parameters. Since the radiation field image is obtained after radiation based on the radiation plan parameters and radiation execution parameters, the desired radiation field image is determined by analyzing the radiation plan parameters, thereby accurately predicting the completed radiation field image based on the desired radiation field parameters.

[0081] The following embodiment will describe the specific method for completing the measured field image to obtain the target field image by completing the field image, as follows: Figure 6 As shown, the specific method includes the following:

[0082] S501, obtain multiple completion points of the completion edge of the completed field image and multiple measurement points of the corresponding completed edge of the measured field image.

[0083] The completed edge can be any side of the field image, and the edge being completed can be an edge of the measured field image corresponding to the completed edge. For example, if the completed edge completes the left side of the field image, then the edge being completed is the right side of the measured field image; if the completed edge completes the top side of the field image, then the edge being completed is the bottom side of the measured field image. (Reference) Figure 3 As shown, the edge to be completed in the measured field image is at the bottom of the measured field image. Correspondingly, the edge to be completed in the completed field image is at the top of the completed field image. During the completion process, the bottom edge of the measured field image and the top edge of the completed field image need to be spliced ​​together.

[0084] In this embodiment, the computer device can stitch any side of the completed field image and the measured field image together, and determine the completed edge of the completed field image and the completed edge of the measured field image based on the stitching result. Alternatively, the computer device can determine the completed edge of the completed field image and the completed edge of the measured field image based on the size information of the completed field image and the measured field image.

[0085] Furthermore, the computer device can set multiple points on the completed edge and the edge to be completed as reference points in the subsequent splicing process. The reference point on the completed edge is the completed point, and the reference point on the edge to be completed is the completed point. For example, the endpoints and center points of the two edges on the completed edge and the edge to be completed can be used as reference points.

[0086] S502, align each completion point with its corresponding measurement point, and then stitch the aligned completion edge and the completed edge together to obtain the target firing field image.

[0087] In this embodiment, before stitching the completed edge and the edge to be completed, multiple completion points of the completed edge are first matched with multiple measurement points in the edge to be completed. It is important to ensure that the matching relationships are accurate to avoid stitching the front side of the measured field image with the back side of the completed field image. After alignment, the computer device can stitch the completed edge and the edge to be completed based on each aligned completion point and its corresponding measurement point to obtain the stitched image.

[0088] Furthermore, since measurement errors may exist during the detector's measurement process, the computer equipment can adjust the stitched image based on the detector's measurement errors, thus avoiding the impact of measurement errors on the completion process and making the target field image more accurate.

[0089] In the image completion method described above, multiple completion points of the completed edge of the completed field image and multiple measurement points of the corresponding completed edge of the measured field image are obtained. Each completion point is aligned with its corresponding measurement point, and the aligned completed edge and the completed edge are then stitched together to obtain the target field image. During the completion process, this method ensures alignment between the completed field image and the measured field image by determining multiple completion points of the completed edge of the completed field image and multiple measurement points of the corresponding completed edge of the measured field image. This results in better quality of the target field image.

[0090] After image completion, the effectiveness of radiotherapy can be evaluated during radiotherapy, and the volume dose distribution of the patient's measurement area can be reconstructed based on the completed image. In one embodiment, the process after image completion will be described below.

[0091] Evaluate radiation delivery effectiveness based on radiation plan parameters and target field images; and / or reconstruct the volume dose distribution of the measurement area based on radiation plan parameters and target field images.

[0092] In this embodiment, after image completion, the computer device can predict the images during radiotherapy based on radiation planning parameters and radiation execution parameters to obtain a predicted radiation field image. By comparing the predicted radiation field image with the target radiation field image, the radiotherapy effect can be accurately determined. Simultaneously, since the target radiation field image can be the image formed after the beam passes through the patient's measurement area, the X-ray emission dose can be determined based on the radiation planning parameters, and the body dose distribution of the patient's measurement area can be reconstructed based on the X-ray emission dose, the target radiation field image, and the radiation execution parameters.

[0093] In the aforementioned image completion method, the radiation delivery effect is evaluated based on radiation plan parameters and target radiation field images; and / or, the volume dose distribution of the measurement area is reconstructed based on radiation plan parameters and target radiation field images. This method, through image completion, enriches the information in the measurement radiation field images, and based on the target radiation field images, can accurately complete the process of evaluating radiation delivery effect and reconstructing volume dose distribution.

[0094] The following describes the process of evaluating the effectiveness of radiotherapy based on radiation plan parameters and target field images. In one embodiment, such as... Figure 7 As shown, the process includes the following:

[0095] S601, based on radiation plan parameters, acquires the predicted radiation field image corresponding to the measurement area.

[0096] In this embodiment, the computer device can input radiation plan parameters into the image prediction model, analyze the radiation plan parameters through the image prediction model, and determine the feature information of the measurement area. Based on this feature information, a predicted radiation field image of the measurement area is output. It should be noted that the training method of the image prediction model is completely consistent with that of the aforementioned image completion model; the only difference is that the image completion model only predicts the image of the region of interest outside the measurement area, while the image prediction model needs to predict the entire image of the region of interest.

[0097] S602 compares the target field image corresponding to the measurement area with the predicted field image.

[0098] In this embodiment of the application, the computer device can compare the target field image and the predicted field image corresponding to the measurement area to determine the difference information between the target field image and the predicted field image.

[0099] S603, Evaluate the effectiveness of radiation delivery based on the comparison results.

[0100] In this embodiment, if the difference between the target radiation field image and the predicted radiation field image is greater than or equal to a preset difference threshold, the radiotherapy effect is determined to be poor; if the difference between the target radiation field image and the predicted radiation field image is less than the preset difference threshold, the radiotherapy effect is determined to be good.

[0101] In the aforementioned image completion method, a predicted radiation field image corresponding to the measurement area is obtained based on radiation planning parameters; the target radiation field image corresponding to the measurement area is compared with the predicted radiation field image; and the radiation delivery effect is evaluated based on the comparison result. This method analyzes radiation planning parameters through prediction to obtain a predicted radiation field image, and based on the comparison result between the predicted radiation field image and the target radiation field image, the dose penetrating the measurement area during radiotherapy can be accurately determined, thereby accurately evaluating the radiation delivery effect.

[0102] As a specific embodiment of this application, such as Figure 8 As shown, image completion methods include:

[0103] S701, acquire the measurement field image of the first part of the field of the beam within the measurement area of ​​the detector;

[0104] S702, Obtain radiation planning parameters and / or radiation execution parameters;

[0105] S703 takes radiation planning parameters and / or radiation execution parameters, as well as measured radiation field images, as input to the image completion model and outputs a completed radiation field image.

[0106] S704, Determine the desired radiation field image based on radiation plan parameters;

[0107] S705 predicts and completes the field image based on the desired field image and the radiation execution parameters;

[0108] S706, obtain multiple completion points of the completion edge of the completed field image and multiple measurement points of the corresponding completed edge of the measured field image;

[0109] S707, align each completion point with the corresponding measurement point, and stitch the aligned completion edge and the completed edge together to obtain the target firing field image;

[0110] S708, evaluate the radiation delivery effect based on radiation plan parameters and target field images; and / or, reconstruct the volume dose distribution of the measurement area based on radiation plan parameters and target field images.

[0111] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0112] Based on the same inventive concept, this application also provides an image completion apparatus for implementing the image completion method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more image completion apparatus embodiments provided below can be found in the limitations of the image completion method described above, and will not be repeated here.

[0113] In one exemplary embodiment, such as Figure 9 As shown, an image completion device is provided, including: a first acquisition module 11, a second acquisition module 12, and a completion module 13, wherein:

[0114] The first acquisition module 11 is used to acquire a measurement field image of the first part of the field of the beam within the measurement area of ​​the detector.

[0115] The second acquisition module 12 is used to acquire the complete field image of the second part of the field located outside the measurement area;

[0116] The completion module 13 is used to complete the measured field image by completing the field image to obtain the target field image.

[0117] In one embodiment, the second acquisition module 12 includes: a first acquisition unit and a determination unit, wherein:

[0118] The first acquisition unit is used to acquire radiation planning parameters and / or radiation execution parameters;

[0119] The determination unit is used to determine the complete radiation field image based on radiation planning parameters and / or radiation execution parameters.

[0120] In one embodiment, the determining unit is further configured to input radiation plan parameters and / or radiation execution parameters, as well as the measured radiation field image, into the image completion model, and output the completed radiation field image.

[0121] In one embodiment, the determining unit is further configured to determine the desired radiation field image based on radiation plan parameters; and to predict and complete the radiation field image based on the desired radiation field image and radiation execution parameters.

[0122] In one embodiment, the completion module includes: a second acquisition unit and a splicing unit, wherein:

[0123] The second acquisition unit is used to acquire multiple completion points of the completion edge of the completed shooting field image and multiple measurement points of the corresponding completed edge of the measured shooting field image.

[0124] The stitching unit is used to align each completion point with the corresponding measurement point, and stitch the aligned completion edge and the completed edge together to obtain the target firing field image.

[0125] In one embodiment, the image completion device further includes a processing module, wherein:

[0126] The processing module is used to evaluate the radiation delivery effect based on radiation plan parameters and target field images; and / or to reconstruct the volume dose distribution of the measurement area based on radiation plan parameters and target field images.

[0127] In one embodiment, the above processing module includes: a third acquisition unit, a comparison unit, and an evaluation unit, wherein:

[0128] The third acquisition unit is used to acquire the predicted radiation field image corresponding to the measurement area based on the radiation plan parameters;

[0129] The comparison unit is used to compare the target field image corresponding to the measurement area with the predicted field image.

[0130] The evaluation unit is used to assess the effectiveness of radiation delivery based on comparison results.

[0131] Each module in the aforementioned image completion device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0132] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the content of any of the embodiments of the above-described image completion methods.

[0133] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the content of any one embodiment of the above-described image completion method.

[0134] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the content of any one of the embodiments of the above-described image completion method.

[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0136] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0137] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0138] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An image completion method characterized by, The method comprises: acquiring a measurement field image of a first partial field of the beam in a measurement region of a detector; acquiring a complementary field image of a second partial field outside the measurement region; complementing the measurement field image with the complementary field image to obtain a target field image.

2. The method of claim 1, wherein, The acquiring of the complementary field image of the second partial field outside the measurement region comprises: acquiring radiation plan parameters and / or radiation execution parameters; determining the complementary field image according to the radiation plan parameters and / or the radiation execution parameters.

3. The method of claim 2, wherein, The determining of the complementary field image according to the radiation plan parameters and / or the radiation execution parameters comprises: inputting the radiation plan parameters and / or the radiation execution parameters and the measurement field image into an image complementing model to output the complementary field image.

4. The method of claim 2, wherein, The determining of the complementary field image according to the radiation plan parameters and / or the radiation execution parameters comprises: determining an expected field image according to the radiation plan parameters; predicting the complementary field image according to the expected field image and the radiation execution parameters.

5. The method of claim 1, wherein, The complementing of the measurement field image with the complementary field image to obtain the target field image comprises: acquiring a plurality of complementary points of a complementary edge of the complementary field image and a plurality of measurement points of a complemented edge of the measurement field image corresponding to the complementary points; aligning each complementary point with a corresponding measurement point and splicing the aligned complementary edge and the complemented edge to obtain the target field image.

6. The method of claim 1, wherein, Further comprising: evaluating radiation delivery effect according to radiation plan parameters and the target field image; and / or, reconstructing a volume dose distribution of the measurement region according to the radiation plan parameters and the target field image.

7. The method of claim 6, wherein, The evaluating of the radiation delivery effect according to the radiation plan parameters and the target field image comprises: acquiring a predicted field image corresponding to the measurement region based on the radiation plan parameters; comparing the target field image corresponding to the measurement region with the predicted field image; evaluating the radiation delivery effect according to a comparison result.

8. An image completion apparatus characterized by comprising: The device comprises: an acquisition module configured to acquire a measurement field image of a first partial field of the beam in a measurement region of a detector; an acquisition module configured to acquire a complementary field image of a second partial field outside the measurement region; a complementing module configured to complement the measurement field image with the complementary field image to obtain a target field image. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the image complementing method of any one of claims 1 to 7.

Images