Image processing method and device and storage medium

Abstract

The invention provides an image processing method and device and a storage medium, relates to the technical field of radiotherapy, and is used for solving the problem of poor CBCT image quality. The method comprises the following steps: acquiring a guide image, wherein the guide image is an image generated by an image guide system based on a radiotherapy system; and then, image processing is carried out on the guide image, a target image is generated, and the target image is an electronic computed tomography (CT) simulation image corresponding to the guide image. Wherein the image processing comprises the steps of inputting a guide image into an image conversion model trained based on deep learning; or carrying out deformation registration and forward and backward projection calculation on the guide image.

Description

Technical Field

[0001] The present application relates to the field of radiotherapy technology, and in particular to an image processing method, device and storage medium. Background Art

[0002] Radiotherapy is one of the commonly used treatment methods for tumors. Existing radiotherapy systems are equipped with image guidance devices, which use image guidance technology to assist in determining the tumor target area and help implement the dose, thereby improving the accuracy and efficiency of radiotherapy.

[0003] Image-guided technology generally uses cone beam computed tomography (CBCT) images to guide the human body positioning in radiotherapy. CBCT imaging can achieve rapid imaging, has the characteristics of small size, low cost, and low radiation dose to patients, so it is widely used in positioning correction and image reference during fractionated radiotherapy, that is, to align the planning CT image and the CBCT image of radiotherapy, but the current CBCT image quality is poor, resulting in image registration accuracy. Summary of the invention

[0004] The present application provides an image processing method, device and storage medium for solving the problem of poor CBCT image quality.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, the present application provides an image processing method. In the method, a guide image is obtained, and the guide image is an image generated by an image guidance system based on a radiotherapy system. Afterwards, the guide image is processed to generate a target image, and the target image is a CT simulation image corresponding to the guide image. Among them, the image processing includes: inputting the guide image into an image conversion model trained based on deep learning; or performing deformation registration combined with forward and backward projection calculations on the guide image.

[0007] Based on the above technical solution, after the guidance image is generated by the image guidance system of the radiotherapy system, the processing device can perform image processing on the guidance image to generate a target image, and the target image is a CT simulation image corresponding to the guidance image. Among them, the image processing includes: inputting the guidance image into an image conversion model trained based on deep learning; or performing deformation registration combined with forward and backward projection calculations on the guidance image. Since the CT image has the characteristic of clear image, the present application obtains a CT simulation image through the guidance image, thereby effectively solving the problem of poor CBCT image quality. Moreover, when the clarity of the CT simulation image is high, the image registration accuracy can be effectively improved. In addition, by adopting the technical solution of the present application, there is no need to add special equipment or control the respiratory cycle, thereby improving the efficiency of treatment.

[0008] In a possible design, the guide image is a cone beam computed tomography (CBCT) guide image or a 4D-CBCT guide image.

[0009] In another possible design, the guide image is a CBCT guide image. Image processing includes: inputting the CBCT guide image into an image conversion model trained based on deep learning to obtain a target image, where the target image is a density projection image of a 4D-CT simulation image corresponding to the CBCT guide image.

[0010] In another possible design, the image conversion model uses CBCT images generated by an image-guided system as original images and 4D-CT density projection images as training images.

[0011] In another possible design, generating a CBCT image includes: acquiring at least one CBCT image and performing an average process on the at least one CBCT image to obtain a CBCT density projection image.

[0012] In another possible design, the guide image is a 4D-CBCT guide image. Image processing includes: inputting the 4D-CBCT guide image into an image conversion model trained based on deep learning or performing deformation registration combined with forward and backward projection calculations on the 4D-CBCT guide image to obtain a target image, which is a density projection image of a 4D-CT simulation image corresponding to the 4D-CBCT guide image.

[0013] In another possible design, the image conversion model uses the 4D-CBCT images generated by the image guidance system as the original images and the density projection images of the 4D-CT as the training images.

[0014] In another possible design, the guide image is a 4D-CBCT guide image. Image processing includes: inputting the 4D-CBCT guide image into an image conversion model trained based on deep learning or performing deformation registration combined with forward and backward projection calculation on the 4D-CBCT guide image to obtain a target image, the target image is a 4D-CT simulation image, and the 4D-CT simulation image is a 4D-CT simulation image corresponding to the 4D-CBCT guide image.

[0015] In another possible design, the image processing includes: inputting the 4D-CBCT guide image into an image conversion model trained based on deep learning or performing deformation registration combined with forward and backward projection calculation on the 4D-CBCT guide image to obtain a 4D-CT simulation image. The 4D-CT simulation image is processed to obtain a target image, which is a density projection image of the 4D-CT simulation image.

[0016] In another possible design, the image conversion model uses 4D-CBCT images generated by an image-guided system as original images and 4D-CT images as training images.

[0017] In another possible design, the deformation registration combined with forward and backward projection calculation of the 4D-CBCT guided image specifically includes: obtaining a planned image; the planned image is a planned CT; obtaining a CBCT image of each phase in the 4D-CBCT guided image; performing iterations on the CBCT image of each phase to generate a CT simulation image of each phase; obtaining the CT simulation images of multiple phases to generate a 4D-CT simulation image corresponding to the 4D-CBCT guided image; wherein the iteration of the CBCT image of each phase includes: forward projecting a single-phase planned CT deformation image to obtain a planned CT projection, subtracting the CBCT projection, and reconstructing to obtain an image I1, wherein the single-phase planned CT deformation image of the first iteration is the planned image; the single-phase planned CT deformation image is subtracted from the intermediate reconstructed image I1 to obtain an image I2; the image I2 and the planned CT are deformed and registered to obtain a deformation field, wherein the iteration is stopped if the deformation field meets the deformation requirements; the planned CT deformation image is obtained according to the deformation field, and the planned CT deformation image is the CT simulation image.

[0018] In another possible design, generating a 4D-CBCT image includes: acquiring at least one CBCT image, processing the at least one CBCT image, and generating a 4D-CBCT image, wherein the 4D-CBCT image includes images of different phases of a respiratory cycle.

[0019] In another possible design, the method may also include: displaying the target image.

[0020] In another possible design, before displaying the target image, the method further includes: displaying first information, the first information being used to indicate that the target image is to be displayed. In response to an operation on the first information, the target image is displayed.

[0021] In another possible design, when the target image is a 4D-CT simulation image, displaying the target image includes: responding to different phases and displaying the 4D-CT simulation image corresponding to the phase; or, displaying the phase and the 4D-CT simulation image corresponding to the phase in an animated image.

[0022] In another possible design, the method may further include: acquiring a planning image, which is a 4D-CT density projection image used for formulating a treatment plan, registering the target image with the planning image, and adjusting the patient position, stopping treatment, or adjusting the treatment plan in response to the registration result.

[0023] In another possible design, registering the target image with the planning image specifically includes: displaying the target image, which is a density projection image of the 4D-CT simulation image, and the target image includes a tumor density projection. Displaying the planning image, which includes a tumor contour. Registering the tumor density projection of the target image and the tumor contour of the planning image, and adjusting the patient position, stopping treatment, or adjusting the treatment plan in response to the registration result.

[0024] In another possible design, registering the target image with the planning image specifically includes: displaying the target image at different phases of the respiratory cycle, the target image being a 4D-CT simulation image. Displaying the planning image, the planning image including the tumor contour. Registering the 4D-CT simulation image of any phase with the tumor contour of the planning image, and adjusting the patient position, stopping treatment, or adjusting the treatment plan in response to the registration result. Or, registering the 4D-CT simulation image of each phase with the tumor contour of the planning image, and adjusting the patient position, stopping treatment, or adjusting the treatment plan in response to the registration result.

[0025] In another possible design, when the density projection of the target image deviates from the tumor outline of the planning image on one side, the patient position is adjusted. When the density projection of the target image deviates from the tumor outline of the planning image on both opposite sides, the treatment is stopped or the treatment plan is adjusted.

[0026] In another possible design, the density projection image includes a maximum intensity projection MIP image or an average intensity projection AIP image.

[0027] In a second aspect, the present application provides an image processing device, which includes: a processor and a memory; the processor and the memory are coupled; the memory is used to store one or more programs, and the one or more programs include computer execution instructions. When the image processing device is running, the processor executes the computer execution instructions stored in the memory to implement the image processing method described in the first aspect and any possible implementation method of the first aspect.

[0028] In a third aspect, the present application provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a computer, the computer executes the image processing method described in the above-mentioned first aspect and any possible implementation of the first aspect.

[0029] In a fourth aspect, the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run a computer program or instructions to implement an image processing method as described in the first aspect and any possible implementation of the first aspect.

[0030] In the above scheme, the technical problems that can be solved and the technical effects achieved by the image processing device, computer equipment, computer storage medium or chip can refer to the technical problems and technical effects solved by the above-mentioned first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1A A schematic diagram of a radiotherapy system provided in an embodiment of the present application;

[0032] Figure 1B An example diagram of a tumor motion trajectory within a respiratory cycle provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of a flow chart of an image processing method provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of a flow chart of another image processing method provided in an embodiment of the present application;

[0035] Figure 4 An example diagram of an image processing method provided in an embodiment of the present application;

[0036] Figure 5-Figure 11 A schematic diagram of a flow chart of another image processing method provided in an embodiment of the present application;

[0037] Fig.12 An example diagram of a display image provided in an embodiment of the present application;

[0038] Fig.13 An example diagram of a prompt information provided in an embodiment of the present application;

[0039] Fig.14A An example diagram of a display image provided in an embodiment of the present application;

[0040] Fig. 14B An example diagram of another prompt information provided in an embodiment of the present application;

[0041] Fig.15A A schematic diagram of a flow chart of another image processing method provided in an embodiment of the present application;

[0042] Fig. 15B A schematic diagram of a flow chart of another image processing method provided in an embodiment of the present application;

[0043] Fig.16 A schematic diagram of a flow chart of another image processing method provided in an embodiment of the present application;

[0044] Fig.17 A schematic diagram of a flow chart of another image processing method provided in an embodiment of the present application;

[0045] Fig.18 A schematic diagram of the structure of an image processing device provided in an embodiment of the present application;

[0046] Fig.19 A conceptual partial view of a computer program product provided for an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] In this article, the character " / " generally indicates that the objects before and after are in an "or" relationship. For example, A / B can be understood as A or B.

[0049] The terms “first” and “second” in the description and claims of the present application are used to distinguish different objects rather than to describe a specific order of the objects.

[0050] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include other steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0051] In addition, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present concepts in a specific way.

[0052] Before introducing the image processing method of the embodiment of the present application in detail, the implementation environment and application scenarios of the embodiment of the present application are first introduced.

[0053] First, the application scenarios of the embodiments of the present application are introduced.

[0054] Figure 1A A schematic diagram of a radiotherapy system 100 provided in an embodiment of the present disclosure is provided, and the radiotherapy system 100 may include a radiotherapy device 110 and a data processing device 200. The radiotherapy device 110 may include a patient support device 113, a rotating gantry 112, a radiation source 111 disposed on the rotating gantry 112, and a group of image acquisition components.

[0055] The radiation source 111 is used to generate a high energy level (eg, megavoltage level) beam 114 (electron beam or X-ray) to treat a target area (including a tumor).

[0056] The patient support device 113 can support the patient P, and can also move and position the patient P. Exemplarily, the patient support device 113 can be a three-dimensional, four-dimensional, five-dimensional, or six-dimensional treatment bed or treatment chair.

[0057] The rotating frame 112 can drive the tube 115 and the detector 116 to rotate around the axis Y. The rotating frame 112 can be a ring frame, a C-arm frame, a drum frame, etc. The present disclosure does not limit the structure of the rotating frame, and only uses the example shown in the accompanying drawings as an example for illustration.

[0058] Figure 1AA group of image acquisition components arranged on the rotating frame 112 is shown in FIG. Each group of image acquisition components includes a tube 115 and a detector 116 arranged opposite to each other, which are used for CBCT imaging. In some embodiments, the tube 115 is a ray emission source, which can also be called a ray tube, or an imaging source. The tube 115 can be used to emit a cone imaging beam (for example, KV-level X-rays). The tube 115 may include a linear accelerator. The detector 116 can be a flat-panel detector or a curved surface detector. The detector 116 is used to receive the imaging beam emitted by the tube 115. The detector 116 can generate a corresponding two-dimensional image or a three-dimensional image based on the received imaging beam emitted by the tube 115. In some embodiments, the detector 116 can be, for example, a CT (Computed Tomography) device, a cone-beam CT device, a PET (positronemission tomography) device, a volume CT device, or the like, or a combination thereof.

[0059] The data processing device 200 is in communication with the detector 116. It is typically set at a location away from the linear radiotherapy equipment 110, usually in a different room from the radiotherapy equipment 110, so as to protect the operator from radiation. The data processing device 200 may include a computer (or a mobile phone, a tablet computer, a laptop computer, etc.) for controlling the radiotherapy system 100, and may also receive a projection image from the detector 116 and process the projection image. The data processing unit 30 may include an input device (such as a keyboard) to facilitate receiving input information, and may also include a display for displaying information before or during radiotherapy. In some embodiments, the data processing device 200 is a computer device with a graphical user interface (GUI), and the computer device includes: one or more processors, a memory, and one or more applications.

[0060] It should be noted that Figure 1A The scene diagram of the image-guided radiotherapy system shown is only an example. The image-guided radiotherapy system and the scene described in the embodiment of the present disclosure are intended to more clearly illustrate the technical solution of the embodiment of the present disclosure, and do not constitute a limitation on the technical solution provided by the embodiment of the present disclosure. Those skilled in the art will appreciate that with the evolution of the image-guided radiotherapy system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present disclosure is also applicable to similar technical problems.

[0061] The image processing method of the embodiment of the present application is applied to the scenario of CBCT image processing. Radiotherapy is one of the commonly used treatment methods for tumor treatment. Existing radiotherapy systems are equipped with image guidance devices, which use image guidance technology to assist in determining the tumor target area and help implement the dose, thereby improving the accuracy and efficiency of radiotherapy.

[0062] Image-guided technology generally uses CBCT to guide the positioning of the human body in radiotherapy. CBCT imaging can achieve rapid imaging, has the characteristics of small size, low cost, and low radiation dose to patients, so it is widely used for positioning correction and image reference during fractionated radiotherapy, that is, to align the planning CT image and the CBCT image of radiotherapy. However, the current CBCT image quality is poor, resulting in image registration accuracy.

[0063] In addition, respiratory motion is one of the most important factors in the accuracy of radiotherapy images. Since the lungs and abdomen move with every breath, radiotherapy needs to consider the impact of this motion on radiation. For example, Figure 1B As shown, the tumor is located in area 101 during the exhalation cycle, and in area 102 during the inhalation cycle. Currently, in order to ensure that the radiation can accurately irradiate the tumor area, doctors usually use special equipment to track the respiratory movement of the lungs, such as respiratory gating and deep breath holding techniques. These technologies allow patients to maintain deep inhalation or hold their breath during radiotherapy, thereby reducing respiratory movement interference during treatment. However, this method is cumbersome and can only be irradiated in fixed time periods, which increases the patient's treatment time.

[0064] In order to solve the above problems, an embodiment of the present application provides an image processing method. In this method, a processing device (i.e., the above-mentioned data processing device 200) can obtain a guide image, which is an image generated by an image guidance system based on a radiotherapy system. Afterwards, the processing device can perform image processing on the guide image to generate a target image, which is a CT simulation image corresponding to the guide image. Among them, the image processing includes: inputting the guide image into an image conversion model trained based on deep learning; or performing deformation registration combined with forward and backward projection calculations on the guide image. Since CT images have the characteristic of clear images, the present application obtains a CT simulation image through a guide image, thereby effectively solving the problem of poor CBCT image quality. Moreover, when the clarity of the CT simulation image is high, the image registration accuracy can be effectively improved. In addition, by adopting the technical solution of the present application, there is no need to add special equipment or control the respiratory cycle, thereby improving the efficiency of treatment.

[0065] The embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0066] like Figure 2As shown, a method for processing an image provided by an embodiment of the present application includes:

[0067] S201: Acquire a guidance image.

[0068] The guidance image is an image generated by an image guidance system based on the radiotherapy system.

[0069] It should be noted that the guidance images are used to guide the positioning of the human body during radiotherapy.

[0070] In a possible design, the guide image is a CBCT guide image or a 4-dimensional (4D)-CBCT guide image. In an embodiment of the present application, the 4D-CBCT guide image is used to indicate the movement trajectory of the tumor within the respiratory cycle. The 4D-CBCT guide image may include: CBCT images of different phases of a respiratory cycle. Exemplarily, if 1-2 seconds is the inhalation cycle and 3-4 seconds is the exhalation cycle, the 4D-CBCT guide image may include: a CBCT image of the inhalation cycle within the 1st to 2nd seconds, and a CBCT image of the exhalation cycle within the 3rd to 4th seconds.

[0071] S202, performing image processing on the guide image to generate a target image. The target image is a CT simulation image corresponding to the guide image. That is, in the embodiment of the present application, the generated target image is a CT simulation image. It can be understood that the clarity of the CT image is relatively high, and the defect of the poor image quality of the guide image can be compensated by generating the CT simulation image through the guide image.

[0072] In an embodiment of the present application, image processing may include: inputting the guide image into an image conversion model trained based on deep learning; or performing deformation registration combined with forward and backward projection calculations on the guide image.

[0073] That is, in the technical solution of the present application, the processing device can input the guide image into the trained image conversion model to obtain the target image. Alternatively, the processing device can perform deformation registration combined with forward and backward projection calculation on the guide image to obtain the target image.

[0074] It should be noted that the embodiments of the present application do not limit deep learning. For example, deep learning may include: convolutional neural network, recursive neural network, or generative adversarial network, etc.

[0075] It should be noted that in the embodiments of the present application, the guide image is a CBCT guide image or a 44D-CBCT guide image, and different guide images obtain different target images. Specifically, when the guide image is a CBCT guide image, the target image can be a density projection image of a 4D-CT simulation image (which can be referred to as implementation mode one). When the guide image is a 4D-CBCT guide image, the target image can be a 4D-CT simulation image (which can be referred to as implementation mode two). Alternatively, when the guide image is a 4D-CBCT guide image, the target image can be a density projection image of a 4D-CT simulation image (which can be referred to as implementation mode three). The above three situations (i.e., implementation mode one, implementation mode two, and implementation mode three) are introduced below.

[0076] In the first embodiment provided by the present application, a density projection image of a 4D-CT simulation image can be obtained through a CBCT guided image, which improves the image quality relative to the guided image, and the density projection image of the 4D-CT simulation image corresponding to the CBCT guided image can be used for image registration or target area delineation. If the simulation image corresponding to the guided image is used for target area delineation to formulate a treatment plan, the accuracy of the treatment plan can be improved because the guided image is based on the current image of the patient being treated.

[0077] For example, Figure 3 As shown, the density projection images of the 4D-CT simulation images obtained by the CBCT guided images include:

[0078] S301, obtaining a CBCT guidance image. The CBCT guidance image may also be obtained by an image acquisition component of the radiotherapy system 100. For example, obtaining a CBCT guidance image includes: obtaining a CBCT guidance image, and performing an average process on the CBCT guidance image to obtain a CBCT density projection guidance image.

[0079] S302, inputting the CBCT guided image into the image conversion model trained based on deep learning to obtain a target image, where the target image is a density projection image of the 4D-CT simulation image corresponding to the CBCT guided image. In other words, when the guided image is a CBCT guided image, the target image is a density projection image of the 4D-CT simulation image corresponding to the CBCT guided image.

[0080] For example, Figure 4 As shown, the above step S302 includes: inputting the CBCT image 401 into the input layer of the trained image conversion model. Then, the input layer inputs the CBCT image 401 into the hidden layer (i.e., the image conversion network) to obtain a density projection image 402 of the 4D-CT simulation image. Then, the output layer outputs the density projection image 402 of the 4D-CT simulation image.

[0081] In an embodiment of the present application, the density projection image may include: a maximum intensity projection (maximal intensity projection, MIP) image or an average intensity projection (Average Intensity Projection, AIP) image. It should be noted that the above-mentioned MIP finally presents a light and dark image, in which the highlight portion represents the maximum gray value along that direction, which is used to indicate the location of a blood vessel, artery or other structure. The gray value of the above-mentioned AIP image is the average of all gray values ​​in the guide image, so the AIP image is relatively smoother and closer to the actual object morphology.

[0082] In the following embodiments of the present application, only the density projection image being an AIP image is used as an example for illustration. For the case where the density projection image is an MIP, reference can be made to the AIP image, and the present application will not list the embodiments separately.

[0083] For example, Figure 5 In the illustrated embodiment, the image conversion model uses the CBCT image generated by the image guidance system as the original image and the 4D-CT density projection image as the training image. For example, the CBCT image can also be acquired by the image acquisition component of the radiotherapy system 100 .

[0084] In a possible implementation, the CBCT image generated based on the image guidance system may include:

[0085] S501. Acquire at least one CBCT image.

[0086] S502: Perform average processing on at least one CBCT image to obtain a CBCT density projection image, where, for example, the CBCT density projection image is an AIP image.

[0087] For example, Figure 5 In the illustrated embodiment, when the guide image is a CBCT guide image, the processing device can train the image conversion model based on the CBCT density projection image and the 4D-CT density projection image to obtain a trained image conversion model. For example, for the specific introduction of the process of training the image conversion model based on deep learning, reference can be made to the description of the model training process in conventional technology, which will not be repeated here.

[0088] An embodiment provided by the present application obtains a CBCT guidance image generated by an image guidance system, and generates a density projection image of a 4D-CT simulation image corresponding to the CBCT guidance image through image processing. The density projection image of the 4D-CT simulation image has higher clarity than the guidance image, and can be further used for registration (improving registration accuracy) and target area delineation. Since the guidance image is the patient's current image, the density projection image of the 4D-CT simulation image converted from the guidance image has high clarity. The density projection image of the 4D-CT simulation image is used to delineate the target area and formulate or modify the treatment plan to achieve precise treatment.

[0089] In an embodiment of the present application, the density projection image of the 4D-CT simulation image includes a set of all movement positions of the tumor during the respiratory cycle. Therefore, the density projection image of the 4D-CT simulation image can be used for image registration to achieve precise irradiation of the tumor's respiratory movement.

[0090] In the second implementation mode provided in the present application, a 4D-CT simulation image can be obtained by performing image processing on the 4D-CBCT guided image, which improves the image quality relative to the 4D-CBCT guided image, and the 4D-CT simulation image corresponding to the 4D-CBCT guided image can be used for three-dimensional image registration.

[0091] In a possible design, the 4D-CBCT guided image is processed to obtain a 4D-CT simulation image, which can be obtained by Figure 6-Figure 7 Two different implementations (Implementation 2 (a) - Implementation 2 (b)) are shown.

[0092] For example, Figure 6 As shown, by performing image processing on the 4D-CBCT guided image, a 4D-CT simulation image (i.e., implementation mode 2 (a)) is obtained, including:

[0093] S601: Acquire a 4D-CBCT guidance image. For example, acquiring a 4D-CBCT guidance image includes acquiring multiple CBCT guidance images, processing the multiple CBCT guidance images, and generating guidance images including different phases in a respiratory cycle, i.e., a 4D-CBCT guidance image. Alternatively, the method for generating a 4D-CBCT image can refer to the method for generating a 4D-CBCT image in conventional technology, which will not be described in detail here.

[0094] S602: Input the 4D-CBCT guided image into the image conversion model trained based on deep learning to obtain a target image, where the target image is a 4D-CT simulation image. In an embodiment of the present application, the image conversion model uses the 4D-CBCT image generated based on the image guidance system as the original image and the 4D-CT image as the training image. That is, when the guided image is a 4D-CBCT guided image, the processing device can train the image conversion model based on the generated 4D-CBCT image and the 4D-CT image to obtain a trained image conversion model.

[0095] In the embodiment of the present application, the image conversion model uses the 4D-CBCT image generated by the image guidance system as the original image and the 4D-CT image as the training image. That is, when the guidance image is the 4D-CBCT guidance image, the processing device can train the image conversion model based on the generated 4D-CBCT image and the 4D-CT image to obtain the trained image conversion model.

[0096] In the second implementation mode provided in this application, Figure 7 As shown, by performing image processing on the 4D-CBCT guided image to obtain a 4D-CT simulation image (i.e., implementation mode 2 (b)), the method may further include:

[0097] S701, obtaining a 4D-CBCT guidance image. For example, obtaining a 4D-CBCT guidance image includes obtaining multiple CBCT guidance images, processing the multiple CBCT guidance images, and generating guidance images including different phases in the respiratory cycle, that is, a 4D-CBCT guidance image. For example, the method of generating a 4D-CBCT image can refer to the method of generating a 4D-CBCT image in conventional technology, which is not described in detail here.

[0098] S702 , performing deformation registration combined with forward and backward projection calculation on the 4D-CBCT guided image to obtain a target image, where the target image is a 4D-CT simulation image corresponding to the 4D-CBCT guided image.

[0099] The following introduces the process of the processing device performing deformation registration combined with forward and backward projection calculation on the 4D-CBCT guided image.

[0100] In a possible design, deformable registration combined with forward and backward projection calculation of 4D-CBCT guided images specifically includes:

[0101] A planning image is acquired. For example, the planning image is a planning CT.

[0102] Acquire CBCT projection images at each phase in the 4D-CBCT guided images.

[0103] For each phase the following iterations are performed:

[0104] S1. The single-phase planned CT deformation image is forward-projected to obtain a planned CT projection, and the CBCT projection is subtracted to reconstruct an image I1, wherein the single-phase planned CT deformation image of the first iteration is the planned image.

[0105] S2, the single-phase planned CT deformation image minus the intermediate reconstructed image I1 to obtain image I2.

[0106] S3, image I2 and planned CT deformation registration to obtain a deformation field. If the deformation field meets the deformation requirement, the iteration is stopped.

[0107] S4, obtaining a planned CT deformation image according to the deformation field. The planned CT deformation image is the CT simulation image.

[0108] When the iteration is performed for the first time, the single-phase planned CT is the planned CT, and the planned CT deformation image is obtained through the above steps S1-S4. The above steps S1-S4 are performed again with the first generated planned CT deformation image, and the above steps S1-S4 are iteratively repeated until the deformation field changes meet the requirements, and the iteration is stopped. The final planned CTt deformation image is the CT simulation image of the CBCT guided image.

[0109] The CT simulation images of multiple phases are obtained to generate a 4D-CT simulation image corresponding to the 4D-CBCT guided image.

[0110] In the second implementation mode provided in the present application, a 4D-CBCT guided image is used to obtain a 4D-CT simulation image corresponding to the 4D-CBCT guided image in different ways. The 4D-CT simulation image has higher clarity than the 4D-CBCT guided image, and the 4D-CT simulation image can be used for image registration to improve the registration accuracy.

[0111] In the third implementation mode provided in the present application, the density projection image of the 4D-CT simulation image can be obtained by performing image processing on the 4D-CBCT guide image, thereby improving the image quality relative to the guide image. The density projection image of the 4D-CT simulation image corresponding to the 4D-CBCT guide image can be used for alignment or target area delineation.

[0112] For example, the 4D-CBCT guided image is processed to obtain a density projection image of the 4D-CT simulation image, which can be obtained by Figure 8-Figure 11 The four different implementations (Implementation 3 (a) - Implementation 3 (d)) are shown.

[0113] For example, Figure 8As shown, by performing image processing on the 4D-CBCT guided image, a density projection image of the 4D-CT simulation image (i.e., implementation method three (a)) is obtained, including:

[0114] S801, obtaining a 4D-CBCT guidance image. For example, obtaining a 4D-CBCT guidance image includes obtaining multiple CBCT guidance images, processing the multiple CBCT guidance images, and generating guidance images including different phases in the respiratory cycle, that is, a 4D-CBCT guidance image. For example, the method of generating a 4D-CBCT image can refer to the method of generating a 4D-CBCT image in conventional technology, which is not described in detail here.

[0115] S802 , input the 4D-CBCT guided image into an image conversion model trained based on deep learning to obtain a target image, where the target image is a density projection image of the 4D-CT simulation image corresponding to the 4D-CBCT guided image.

[0116] In an embodiment of the present application, the image conversion model uses the 4D-CBCT image generated based on the image guidance system as the original image and the density projection image of the 4D-CT as the training image. That is, the processing device can train the image conversion model based on the generated 4D-CBCT image and the density projection image of the 4D-CT to obtain the trained image conversion model. By way of example, the generated 4D-CBCT image includes: acquiring at least one CBCT image. Thereafter, processing the at least one CBCT image to generate a 4D-CBCT image. By way of example, the method for generating a 4D-CBCT image can refer to the method for generating a 4D-CBCT image in conventional technology, which will not be described in detail here.

[0117] In the third implementation mode provided in this application, Fig. 9 As shown, by performing image processing on the 4D-CBCT guided image, a density projection image of the 4D-CT simulation image is obtained (i.e., implementation mode three (b)), which may also include:

[0118] S901, obtaining a 4D-CBCT guidance image. For example, obtaining a 4D-CBCT guidance image includes obtaining multiple CBCT guidance images, processing the multiple CBCT guidance images, and generating guidance images including different phases in the respiratory cycle, i.e., a 4D-CBCT guidance image. It should be noted that the method for generating a 4D-CBCT image can refer to the method for generating a 4D-CBCT image in conventional technology, which will not be described in detail here.

[0119] S902, inputting the 4D-CBCT guided image into the image conversion model trained based on deep learning to obtain a 4D-CT simulation image;

[0120] S903, processing the 4D-CT simulation image to obtain a target image, where the target image is a density projection image of the 4D-CT simulation image. For example, the processing device may first obtain a 4D-CT simulation image through a model, and then perform average processing on the 4D-CT simulation image to obtain a density projection image of the 4D-CT simulation image.

[0121] In the third implementation mode provided in this application, Fig.10 As shown, by performing image processing on the 4D-CBCT guided image, a density projection image of the 4D-CT simulation image (i.e., implementation mode three (c)) is obtained, which may also include:

[0122] S1001, obtaining a 4D-CBCT guidance image. For example, obtaining a 4D-CBCT guidance image includes obtaining multiple CBCT guidance images, processing the multiple CBCT guidance images, and generating guidance images including different phases in the respiratory cycle, that is, a 4D-CBCT guidance image. For example, the method of generating a 4D-CBCT image can refer to the method of generating a 4D-CBCT image in conventional technology, which is not described in detail here.

[0123] S1002 , performing deformation registration combined with forward and backward projection calculation on the 4D-CBCT guided image to obtain a target image, where the target image is a density projection image of the 4D-CT simulation image corresponding to the 4D-CBCT guided image.

[0124] In the third implementation mode provided in this application, Fig.11 As shown, by performing image processing on the 4D-CBCT guided image, a density projection image of the 4D-CT simulation image (i.e., implementation method three (d)) is obtained, including:

[0125] S1101, obtaining a 4D-CBCT guidance image. For example, obtaining a 4D-CBCT guidance image includes obtaining multiple CBCT guidance images, processing the multiple CBCT guidance images, and generating guidance images including different phases in the respiratory cycle, that is, a 4D-CBCT guidance image. For example, the method of generating a 4D-CBCT image can refer to the method of generating a 4D-CBCT image in conventional technology, which is not described in detail here.

[0126] S1102 , performing deformation registration combined with forward and backward projection calculation on the 4D-CBCT guided image to obtain a 4D-CT simulation image.

[0127] S1103, processing the 4D-CT simulation image to obtain a target image, where the target image is a density projection image of the 4D-CT simulation image. That is, the processing device may first obtain the 4D-CT simulation image by registration projection calculation, and then perform average processing on the 4D-CT simulation image to obtain a density projection image of the 4D-CT simulation image. The specific processing method is referred to the above embodiment, which will not be described here.

[0128] The image processing method provided in the embodiment of the present application can convert the 4D-CBCT guide image into a density projection image of a 4D-CT simulation image through an image conversion model or deformation registration combined with forward and backward projection calculations. Alternatively, the image processing method provided in the embodiment of the present application can convert the 4D-CBCT guide image into a corresponding 4D-CT simulation image through an image conversion model or deformation registration combined with forward and backward projection calculations, and then process the 4D-CT simulation image to obtain a density projection image of the 4D-CT simulation image. The density projection image of the 4D-CT simulation image has a higher definition than the guide image, and can be further used for registration (improving registration accuracy) and target area delineation. Since the guide image is the patient's current image, the density projection image of the 4D-CT simulation image converted from the guide image has a high definition, and the density projection image of the 4D-CT simulation image is used to delineate the target area and formulate or modify the treatment plan to achieve precise treatment.

[0129] In an embodiment of the present application, the density projection image of the 4D-CT simulation image includes a set of all movement positions of the tumor during the respiratory cycle. Therefore, the density projection image of the 4D-CT simulation image can be used for image registration to achieve precise irradiation of the tumor's respiratory movement.

[0130] In some embodiments, after obtaining the target image, the processing device may display the target image.

[0131] For example, the processing device can display the AIP image of the 4D-CT simulation image or the 4D-CT simulation image. It is understandable that by displaying the target image, and the target image is the electronic computer tomography CT simulation image corresponding to the guide image. In this way, a clearer image can be displayed to the user. For example, Fig.12 As shown, the AIP image showing the 4D-CT simulation image can be a cross-section, a coronal plane and a sagittal plane. For example, the positions of the cross-section, the coronal plane and the sagittal plane can be adjusted according to user needs. The size and position of each view are not limited in this application. Only the example shown in the accompanying drawings is used for example. For example, the three different views can also be arranged in parallel.

[0132] In a possible implementation, before displaying the target image, the processing device may display first information, where the first information is used to instruct to display the target image. Thereafter, in response to an operation on the first information, the processing device may display the target image.

[0133] For example, Fig.13 As shown, the screen 1301 of the processing device can display a prompt message 1302, and the prompt message 1302 can be "Display 4D-CT simulation image". Optionally, the processing device can also display a "Yes" button and a "No" button. It can be understood that by displaying the first information, the user's selectivity is increased, thereby improving the user experience. This application does not limit the content of the prompt display, for example, it can also be "Display the density projection image of the 4D-CT simulation image" or other text descriptions.

[0134] For example, when the target image is a 4D-CT simulation image, the processing device may display the target image by: static display or dynamic display.

[0135] Static display, in response to different phases, displays the 4D-CT simulation image corresponding to the phase. That is, according to the phase selected by the user, the 4D-CT simulation image of the phase is displayed. For example, Fig.14A As shown, if the user specifies phase 1, the three views display an image 1401 corresponding to phase 1. If the user specifies phase 2, the three views display an image 1402 corresponding to phase 2. If the user specifies phase 3, the three views display an image 1403 corresponding to phase 3. For example, the display is performed in three views, which are the same as the above display, namely, the coronal plane, the sagittal plane and the cross-section. The positions of the three views can be adjusted according to the user's needs, which will not be described in detail here.

[0136] Dynamic display, dynamically display the 4D-CT simulation image corresponding to the phase. For example, the phase and the 4D-CT simulation image corresponding to the phase can be dynamically displayed. The user can determine whether to display the static image or the animated image. When the user confirms to display the dynamic image, after receiving the dynamic display treatment, the phase and the 4D-CT simulation image of the phase are synchronously displayed dynamically. The example tag image file format (TIF) is displayed. For example, Fig.14A As shown, the user can select dynamic display on the interface. When the user selects dynamic display, there is no need to use the mouse to select the phase, and the processor automatically synchronizes the phase and the view under the phase.

[0137] Exemplarily, the processing device may display a 4D-CT simulation image of a respiratory cycle (i.e., an image of an exhalation cycle and an image of an inhalation cycle). Alternatively, the processing device may display an image of the first second of an exhalation cycle and / or an image of the second second of an inhalation cycle.

[0138] Optionally, the processing device may display second information and third information, wherein the second information is used to indicate the display of a 4D-CT simulation image of at least one respiratory cycle, and the third information is used to indicate the display of a 4D-CT simulation image of different phases of a respiratory cycle. In response to the operation of the second information and / or the third information, the target image is displayed.

[0139] For example, Fig. 14B As shown, the screen 1404 of the processing device can display an "inhalation cycle" option, an "expiratory cycle" option, and a "breathing cycle" option. In response to the operation of the button, the processing device can display one or more images. For example, if the "expiratory cycle" option is operated, an image of the exhalation cycle can be displayed.

[0140] It is understandable that when the target image is a 4D-CT simulation image, a 4D-CT simulation image of at least one respiratory cycle can be displayed; and / or 4D-CT simulation images of different phases of the respiratory cycle can be displayed. In this way, the diversity of displayed images is enriched, and the judgment basis can be increased, thereby improving the accuracy of user judgment.

[0141] In one embodiment provided in the present application, after obtaining a target image, the target image can be registered with an image used for formulating a treatment plan, thereby improving the registration accuracy and the treatment precision. For example, the following example describes the registration using a target image that is a 4D-CT simulation image and a target image that is a density projection image. Figure 7 The 4D-CT simulation images and Figure 8 The density projection image generated by the method shown is taken as an example, and other methods can be executed for reference, which will not be described in detail here.

[0142] For example, Fig.15A As shown, after obtaining the target image, the target image is registered with the image used for formulating the treatment plan, which may also include:

[0143] S1501a, obtaining a 4D-CBCT guided image. For details, please refer to the description of step S701 in other embodiments of the present application.

[0144] S1502a, performing deformation registration combined with forward and backward projection calculation on the 4D-CBCT guided image to obtain a target image (4D-CT simulation image). For details, please refer to the description of step S702 in other embodiments of the present application.

[0145] S1503a, obtaining a planning image. The planning image is a 4D-CT density projection image used to formulate a treatment plan.

[0146] S1504a, register the target image with the planned image. For specific registration, please refer to other embodiments of the present application.

[0147] S1505a. Adjust the patient position, stop treatment, or adjust the treatment plan in response to the registration result.

[0148] In one possible design, the treatment plan can be used to guide the radiotherapy equipment to deliver radiation. The radiotherapy equipment includes: a radiation source for emitting a treatment beam, a frame for carrying the radiation source, and a beam collimation unit for regulating the beam shape. The treatment plan is used to guide the irradiation position, irradiation duration, movement trajectory of the radiation source, size / shape / position of the beam collimation unit, etc. Under the guidance of the treatment plan, the radiotherapy equipment delivers the dose distribution specified in the treatment plan to the target area according to the irradiation position and movement trajectory.

[0149] For example, Fig. 15B As shown, after the target image is obtained, the target image is registered with the image used to formulate the treatment plan, which specifically includes:

[0150] S1501b, obtaining a 4D-CBCT guided image. For details, refer to the description of other embodiments of the present application.

[0151] S1502b, input the 4D-CBCT guided image into the image conversion model trained based on deep learning to obtain the target image (density projection image of the 4D-CT simulation image). For details, please refer to the description of other embodiments of this application.

[0152] S1503b, obtaining a planning image. The planning image is a 4D-CT density projection image used to formulate a treatment plan.

[0153] S1504b, register the target image with the planned image. For specific registration, please refer to other embodiments of the present application.

[0154] S1505b. Adjust the patient position, stop treatment, or adjust the treatment plan in response to the registration result.

[0155] For example, please refer to the description in S1505a for details, which will not be repeated here.

[0156] It is understandable that after acquiring the planning image, the target image is registered with the planning image. Since the guide image is the current image of the patient, the target image is generated based on the guide image, and the clarity of the target image is high, and the imaging effect is good. In this way, a more accurate registration result can be obtained, so as to accurately adjust the patient's position, and stop treatment or adjust the treatment plan accordingly.

[0157] In one possible implementation, Fig.16 As shown, the target image is registered with the planned image, specifically including:

[0158] S1601, displaying a target image and a planned image. For example, the target image is a density projection image of a 4D-CT simulation image, the target image includes a tumor density projection, and the planned image includes a tumor contour.

[0159] S1602: Register the tumor density projection of the target image and the tumor contour of the planning image, and adjust the patient position, stop treatment, or adjust the treatment plan in response to the registration result.

[0160] In another possible implementation, Fig.17 As shown, registering the target image with the planned image specifically includes:

[0161] S1701, displaying target images and planned images at different phases of the respiratory cycle, wherein the target image is a 4D-CT simulation image.

[0162] S1702: Register the 4D-CT simulation image of any phase with the tumor contour of the planning image.

[0163] Alternatively, S1703, the 4D-CT simulation images of all phases are registered with the tumor contour of the planning image.

[0164] That is, after executing S1701, S1702 and S1704 may be executed. Alternatively, after executing S1701, S1703 and S1704 may be executed.

[0165] S1704. Adjust the patient position, stop treatment, or adjust the treatment plan in response to the registration result.

[0166] Exemplarily, the 4D-CT simulation image includes: phase a-phase d images, and the processing device can align the phase a (or phase b, etc.) image with the tumor contour of the planned image and perform corresponding tasks according to the alignment result.

[0167] Alternatively, the processing device may register the 4D-CT simulation image of each phase with the tumor contour of the planning image, and adjust the patient position, stop treatment, or adjust the treatment plan in response to the registration result.

[0168] Exemplarily, the 4D-CT simulation image includes: phase a-phase d images, and the processing device can align each image in the phase a-phase d images with the tumor contour of the planned image to obtain multiple alignment results, and perform corresponding tasks based on the multiple alignment results.

[0169] In a possible design, when one side of the density projection of the target image deviates from the tumor outline of the planning image, the patient position is adjusted. It should be noted that the one side of the density projection of the target image can be any side of the target image (such as the left side, the right side, the upper side, the lower side, etc.).

[0170] It is understandable that if the density projection of the target image deviates from the tumor contour of the planning image on only one side, it means that the density projection of the target image is close to the position in the planning image. In this way, the treatment plan can be executed by simply adjusting the patient position accordingly.

[0171] In another possible design, when the density projection of the target image deviates from the tumor outline of the planning image on both sides, the treatment is stopped or the treatment plan is adjusted. The relative two sides refer to the direction of one side of the two sides being opposite to the direction of the other side. Exemplarily, the two sides include: the left side and the right side, or the upper side and the lower side. It is understandable that if the density projection of the target image deviates from the tumor outline of the planning image on both sides, it means that the density projection of the target image deviates greatly from the position in the planning image, and the registration effect cannot be achieved by adjusting the patient's position. Therefore, the treatment plan can be adjusted to improve the accuracy of the treatment. Alternatively, the treatment plan is stopped to avoid causing additional harm.

[0172] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. It is understandable that the image processing device or electronic device (or server) includes a hardware structure and / or software module corresponding to each function in order to realize the above functions. Those skilled in the art should easily realize that, in combination with the steps of the image processing methods of each example described in the embodiments disclosed in this application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0173] The embodiment of the present application also provides an image processing device, which can be a computer device, a CPU in the computer device, a processing module in the computer device for processing images, or a client in the computer device for processing images.

[0174] The embodiment of the present application can divide the image processing device into functional modules or functional units according to the above method example. For example, each functional module or functional unit can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules or functional units. Among them, the division of modules or units in the embodiment of the present application is schematic, which is only a logical function division. There may be other division methods in actual implementation.

[0175] Fig.18 1 is a schematic diagram of a hardware structure of an image processing device according to an exemplary embodiment. The image processing device may include a processor 1802, and the processor 1802 is used to execute application code to implement the image processing method in this application.

[0176] The processor 1802 may be a central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0177] like Fig.18 As shown, the image processing device may further include a memory 1803. The memory 1803 is used to store application program codes for executing the solution of the present application, and the execution is controlled by the processor 1802.

[0178] The memory 1803 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 1803 may exist independently and be connected to the processor 1802 via the bus 1804. The memory 1803 may also be integrated with the processor 1802.

[0179] like Fig.18 As shown, the image processing apparatus may further include a communication interface 1801, wherein the communication interface 1801, the processor 1802, and the memory 1803 may be coupled to each other, for example, via a bus 1804. The communication interface 1801 is used to perform information exchange with other devices, for example, to support information exchange between the image processing apparatus and other devices.

[0180] It should be pointed out that Fig.18 The device structure shown in the figure does not constitute a limitation on the image processing device, except Fig.18 In addition to the components shown, the image processing device may include more or fewer components than shown, or combine certain components, or have a different arrangement of components.

[0181] The present application also provides a computer-readable storage medium, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by a processor of a computer device, the computer can execute the image processing method provided in the above-mentioned embodiment. For example, the computer-readable storage medium may be a memory 1803 including instructions, and the above instructions may be executed by a processor 1802 of a computer device to complete the above method. Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, a non-temporary computer-readable storage medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0182] Fig.19A conceptual partial view of a computer program product provided by an embodiment of the present application is schematically shown, where the computer program product includes a computer program for executing a computer process on a computing device.

[0183] In one embodiment, the computer program product is provided using a signal bearing medium 1900. The signal bearing medium 1900 may include one or more program instructions that, when executed by one or more processors, may provide the above-described Figure 2-Figure 3 , Figure 5-Figure 11 , Figure 15A-Figure 17 Thus, for example, reference to Figure 2 In the embodiment shown in , one or more features of S201-S202 may be undertaken by one or more instructions associated with the signal bearing medium 1900. In addition, Fig.19 The program instructions in also describe example instructions.

[0184] In some examples, signal bearing medium 1900 may include computer readable medium 1901, such as, but not limited to, a hard drive, a compact disk (CD), a digital video disk (DVD), a digital tape, a memory, a read-only memory (ROM), or a random access memory (RAM), and the like.

[0185] In some implementations, the signal bearing medium 1900 may include a computer recordable medium 1902 such as, but not limited to, a memory, a read / write (R / W) CD, a R / W DVD, or the like.

[0186] In some embodiments, signal bearing medium 1900 may include communication medium 1903 such as, but not limited to, digital and / or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0187] The signal bearing medium 1900 may be communicated by a wireless form of communication medium 1903. The one or more program instructions may be, for example, computer executable instructions or logic implemented instructions.

[0188] In some examples, such as for Fig.18 The described image processing apparatus may be configured to provide various operations, functions, or actions in response to one or more program instructions via computer-readable medium 1901 , computer-recordable medium 1902 , and / or communication medium 1903 .

[0189] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0190] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0191] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0192] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0193] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes various media that can store program codes, such as-U disk, mobile hard disk, ROM, RAM, disk or CD.

[0194] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An image processing method, characterized in that: Acquire a guidance image, where the guidance image is an image generated by an image guidance system based on the radiotherapy system; Performing image processing on the guide image to generate a target image, wherein the target image is a computer tomography (CT) simulation image corresponding to the guide image; Among them, the image processing includes: inputting the guide image into an image conversion model trained based on deep learning; or performing deformation registration combined with forward and backward projection calculations on the guide image.

2. The method according to claim 1, characterized in that The guide image is a cone beam computed tomography (CBCT) guide image or a 4D-CBCT guide image.

3. The method according to claim 1, characterized in that The guiding image is a CBCT guiding image; The image processing includes: inputting the CBCT guided image into an image conversion model trained based on deep learning to obtain a target image, wherein the target image is a density projection image of a 4D-CT simulation image corresponding to the CBCT guided image.

4. The method according to claim 3, characterized in that The image conversion model uses the CBCT image generated based on the image guidance system as the original image and the 4D-CT density projection image as the training image.

5. The method according to claim 4, characterized in that The generated CBCT image comprises: acquiring at least one CBCT image; The at least one CBCT image is averaged to obtain a CBCT density projection image.

6. The method according to claim 1, characterized in that The guiding image is a 4D-CBCT guiding image; The image processing includes: inputting the 4D-CBCT guided image into an image conversion model trained based on deep learning or performing deformation registration combined with forward and backward projection calculations on the 4D-CBCT guided image to obtain a target image, wherein the target image is a density projection image of a 4D-CT simulation image corresponding to the 4D-CBCT guided image.

7. The method according to claim 6, characterized in that The image conversion model uses the 4D-CBCT image generated based on the image guidance system as the original image and the density projection image of the 4D-CT as the training image.

8. The method according to claim 1, characterized in that The guiding image is a 4D-CBCT guiding image; The image processing includes: inputting the 4D-CBCT guided image into an image conversion model based on deep learning training or performing deformation registration combined with forward and backward projection calculations on the 4D-CBCT guided image to obtain a target image, wherein the target image is a 4D-CT simulation image, and the 4D-CT simulation image is a 4D-CT simulation image corresponding to the 4D-CBCT guided image.

9. The method according to claim 8, characterized in that The image processing comprises: Input the 4D-CBCT guided image into an image conversion model trained based on deep learning or perform deformation registration combined with forward and backward projection calculation on the 4D-CBCT guided image to obtain a 4D-CT simulation image; The 4D-CT simulation image is processed to obtain the target image, where the target image is a density projection image of the 4D-CT simulation image.

10. The method according to claim 8 or 9, characterized in that: The image conversion model uses the 4D-CBCT image generated based on the image guidance system as the original image and the 4D-CT image as the training image.

11. The method according to claim 6 or 8, characterized in that: The deformable registration combined with forward and backward projection calculation of the 4D-CBCT guided image specifically includes: Acquire a planned image; the planned image is a planned CT; Acquire a CBCT image of each phase in the 4D-CBCT guided image; Iterating the CBCT image of each phase to generate a CT simulation image of each phase; Obtaining the CT simulation images of multiple phases to generate a 4D-CT simulation image corresponding to the 4D-CBCT guided image; The CBCT image of each phase is iterated and includes: The single-phase planned CT deformation image is forward-projected to obtain a planned CT projection, and the CBCT projection is subtracted to reconstruct an image I1, wherein the single-phase planned CT deformation image of the first iteration is the planned image; The single-phase planned CT deformation image is subtracted from the intermediate reconstructed image I1 to obtain an image I2; The image I2 and the planned CT are deformed and registered to obtain a deformation field, wherein the iteration is stopped when the deformation field meets the deformation requirement; A planned CT deformation image is obtained according to the deformation field, and the planned CT deformation image is the CT simulation image.

12. The method according to claim 6 or 8, characterized in that: The generated 4D-CBCT image includes: acquiring at least one CBCT image; The at least one CBCT image is processed to generate a 4D-CBCT image, wherein the 4D-CBCT image includes images of different phases of a respiratory cycle.

13. The method according to claim 1, characterized in that Also includes: The target image is displayed.

14. The method according to claim 13, characterized in that Before displaying the target image, the method further includes: displaying first information, where the first information is used to instruct to display the target image; The displaying of the target image comprises: In response to an operation on the first information, the target image is displayed.

15. The method according to claim 8, characterized in that When the target image is a 4D-CT simulation image, displaying the target image includes: In response to different phases, display the 4D-CT simulation image corresponding to the phase; or, The animated image shows the phase-corresponding 4D-CT simulation image.

16. The method according to claim 1, characterized in that The method further comprises: Acquire a planning image, wherein the planning image is a 4D-CT density projection image used for formulating a treatment plan; registering the target image with the planned image; Adjust patient position, stop treatment, or adjust treatment plan in response to registration results.

17. The method according to claim 16, characterized in that The registering the target image with the planned image specifically comprises: Displaying the target image, wherein the target image is a density projection image of a 4D-CT simulation image, and the target image includes a tumor density projection; displaying the planning image, wherein the planning image includes a tumor outline; The tumor density projection of the target image and the tumor contour of the planning image are registered, and the patient position is adjusted, treatment is stopped, or the treatment plan is adjusted in response to the registration result.

18. The method according to claim 17, characterized in that The registering the target image with the planned image specifically comprises: Display target images at different phases of the respiratory cycle, wherein the target images are 4D-CT simulation images; displaying the planning image, wherein the planning image includes a tumor outline; Registering the 4D-CT simulation image of any phase with the tumor contour of the planning image, and adjusting the patient position, stopping treatment or adjusting the treatment plan in response to the registration result; or, The 4D-CT simulation image of each phase is registered with the tumor contour of the planning image, and the patient position is adjusted, treatment is stopped, or the treatment plan is adjusted in response to the registration result.

19. The method according to any one of claims 16 to 18, characterized in that: When one side of the density projection of the target image deviates from the tumor outline of the planning image, adjusting the patient position; When the density projection of the target image deviates from the tumor contour of the planning image on both sides, the treatment is stopped or the treatment plan is adjusted.

20. The method according to any one of claims 3-7 and 11, characterized in that: The density projection image includes a maximum intensity projection MIP image or an average intensity projection AIP image.

21. An image processing device, characterized in that: include: Processor and memory; The processor is coupled to the memory; The memory is used to store one or more programs, which include computer-executable instructions. When the image processing device is running, the processor executes the computer-executable instructions stored in the memory to enable the image processing device to perform the method as described in any one of claims 1-20.

22. A computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, characterized in that: When a computer executes the instruction, the computer performs the method according to any one of claims 1 to 20.

Images