Image processing method and apparatus

Abstract

The application relates to an image processing method and device. The method comprises the following steps: acquiring a three-dimensional medical image of a target part in a first mode and a four-dimensional medical image of the target part in a second mode; acquiring a surface deformation field of the target part according to the three-dimensional medical image and the four-dimensional medical image; acquiring an internal simulated deformation field of the target part based on the surface deformation field of the target part; and generating a four-dimensional simulated medical image of the target part according to the surface deformation field and the internal simulated deformation field. The method can truly reflect the motion track of an internal interested region of the target part.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and in particular to an image processing method and apparatus. Background Technology

[0002] With the continuous development of medical imaging technology, it has become possible to use medical imaging equipment to image the three-dimensional motion of some parts of the human body.

[0003] In related technologies, a biomechanical model can be constructed using four-dimensional computed tomography (4D-CT) images of the target area, and this biomechanical model can be used to determine the deformation inside the target area. However, 4D-CT images cannot accurately reflect the motion trajectory of the region of interest inside the target area. Summary of the Invention

[0004] Therefore, it is necessary to provide an image processing method and apparatus that can realistically reflect the motion trajectory of the internal region of interest of the target part in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides an image processing method, the method comprising:

[0006] Acquire three-dimensional medical images of the target site in the first modality and four-dimensional medical images in the second modality;

[0007] Based on 3D and 4D medical images, obtain the surface deformation field of the target area;

[0008] Based on the surface deformation field of the target part, obtain the simulated internal deformation field of the target part;

[0009] Based on the surface deformation field and the internal simulated deformation field, a four-dimensional simulated medical image of the target area is generated.

[0010] In one embodiment, the surface deformation field of the target area is obtained based on three-dimensional and four-dimensional medical images, including:

[0011] Based on three-dimensional and four-dimensional medical images, determine the geometric deformation field of the target area;

[0012] The surface deformation field of the target part is determined based on the geometric deformation field.

[0013] In one embodiment, determining the geometric deformation field of the target region based on three-dimensional and four-dimensional medical images includes:

[0014] Acquire a reference 3D medical image from a 4D medical image;

[0015] The reference deformation field is obtained by matching the reference 3D medical image with the 3D medical image.

[0016] Based on four-dimensional medical images and reference deformation fields, the geometric deformation field of the target area is determined.

[0017] In one embodiment, acquiring a reference three-dimensional medical image from a four-dimensional medical image includes:

[0018] Obtain parameter information of the target area in 3D medical images;

[0019] Three-dimensional medical images with the same parameter information as those in four-dimensional medical images are identified as reference three-dimensional medical images.

[0020] In one embodiment, the geometric deformation field of the target region is determined based on four-dimensional medical images and a reference deformation field, including:

[0021] The internal deformation field of the four-dimensional medical image is obtained by matching the other three-dimensional medical images in the four-dimensional medical image with the reference three-dimensional medical image.

[0022] The internal deformation field of a four-dimensional medical image is fused with a reference deformation field to obtain the geometric deformation field of the target area.

[0023] In one embodiment, determining the surface deformation field of the target region based on the geometric deformation field includes:

[0024] Obtain the location information of the target points on the surface of the target area;

[0025] Based on the location information of the target points on the surface, the surface deformation field of the target part is extracted from the geometric deformation field.

[0026] In one embodiment, the internal simulated deformation field of the target region is obtained based on the surface deformation field of the target region, including:

[0027] Obtain a biomechanical model of the target site;

[0028] By using the surface deformation field as the boundary condition of the target part, and simulating the internal deformation of the target part through a biomechanical model, the internal simulated deformation field of the target part is obtained.

[0029] In one embodiment, the surface deformation field is used as the boundary condition of the target part, and the internal deformation of the target part is simulated using a biomechanical model to obtain the simulated internal deformation field of the target part, including:

[0030] Segmenting three-dimensional medical images to generate a three-dimensional mesh structure;

[0031] The surface deformation field is mapped to the surface region of the three-dimensional mesh structure to obtain a three-dimensional mesh structure with boundary conditions;

[0032] The internal deformation of the three-dimensional mesh structure was simulated using a biomechanical model to obtain the simulated internal deformation field of the target part.

[0033] In one embodiment, a four-dimensional simulated medical image of the target region is generated based on the surface deformation field and the internal simulated deformation field, including:

[0034] The surface deformation field and the internal simulated deformation field are analyzed to determine the simulated position information of multiple target points in the target area;

[0035] Based on the simulated location information of each target point, three-dimensional simulated medical images of multiple target areas are generated;

[0036] By combining the various three-dimensional simulated medical images, a four-dimensional simulated medical image of the target area is obtained.

[0037] Secondly, this application also provides an image processing apparatus, which includes:

[0038] The first acquisition module is used to acquire three-dimensional medical images of the target body in the first modality and four-dimensional medical images in the second modality.

[0039] The second acquisition module is used to acquire the surface deformation field of the target area based on the three-dimensional medical images and the four-dimensional medical images.

[0040] The third acquisition module is used to acquire the internal simulated deformation field of the target part based on the surface deformation field of the target part;

[0041] The generation module is used to generate four-dimensional simulated medical images of the target area based on the surface deformation field and the internal simulated deformation field.

[0042] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the content of any of the image processing method embodiments in the first aspect described above.

[0043] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the content of any of the image processing method embodiments described in the first aspect above.

[0044] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the content of any of the image processing method embodiments described in the first aspect above.

[0045] The aforementioned image processing method, apparatus, computer equipment, storage medium, and program product acquire a three-dimensional medical image of a target body part in a first modality and a four-dimensional medical image in a second modality. Based on the three-dimensional and four-dimensional medical images, the surface deformation field of the target body part is acquired. Based on the surface deformation field of the target body part, an internal simulated deformation field of the target body part is acquired. Based on the surface deformation field and the internal simulated deformation field, a four-dimensional simulated medical image of the target body part is generated. This method combines the three-dimensional medical image in the first modality and the four-dimensional medical image in the second modality. Using the four-dimensional medical image in the second modality, the actual surface deformation field of the target body part can be acquired. Based on this surface deformation field, the internal simulated deformation field of the target body part can be accurately determined. Thus, a four-dimensional simulated medical image of the target body part in the first modality can be obtained based on the internal simulated deformation field. Furthermore, the four-dimensional simulated medical image in the first modality can more realistically reflect the motion trajectory of the region of interest inside the target body part. Attached Figure Description

[0046] Figure 1 This is an application environment diagram of an image processing method in one embodiment;

[0047] Figure 2 This is a flowchart illustrating an image processing method in one embodiment;

[0048] Figure 3 This is a flowchart illustrating an image processing method in one embodiment;

[0049] Figure 4 This is a flowchart illustrating an image processing method in one embodiment;

[0050] Figure 5 This is a flowchart illustrating an image processing method in one embodiment;

[0051] Figure 6 This is a flowchart illustrating an image processing method in one embodiment;

[0052] Figure 7 This is a flowchart illustrating an image processing method in one embodiment;

[0053] Figure 8 This is a flowchart illustrating an image processing method in one embodiment;

[0054] Figure 9 This is a flowchart illustrating an image processing method in one embodiment;

[0055] Figure 10 This is a flowchart illustrating an image processing method in one embodiment;

[0056] Figure 11This is a flowchart illustrating an image processing method in one embodiment;

[0057] Figure 12 This is a flowchart illustrating an image processing method in one embodiment;

[0058] Figure 13 This is a structural block diagram of an image processing device in one embodiment. Detailed Implementation

[0059] 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.

[0060] Before providing a detailed introduction to the technical solution of this application, let me first briefly introduce the technical background of this application.

[0061] With the continuous development of medical imaging technology, it has become possible to image the three-dimensional motion of certain parts of the human body using medical imaging equipment. When the medical imaging equipment is a computed tomography (CT) device, the CT device can perform a single scan of the target area to obtain a three-dimensional tomographic image with high spatial resolution. This three-dimensional tomographic image is considered the gold standard for displaying the internal structure of the target area. Gated 4D-CT devices are typically used to image the three-dimensional motion of a target area within a respiratory cycle, especially for medical procedures involving that area. However, the high radiation during the CT scan is not suitable for long-term scans. Even when using CT, the subject needs to cooperate to acquire 4D-CT images of a normal respiratory process without motion artifacts. The 4D-CT device acquires the average three-dimensional motion of each stage of the respiratory process, meaning that this three-dimensional motion cannot reflect the real-time three-dimensional motion of the target area.

[0062] Magnetic Resonance Imaging (MRI) equipment can also scan target areas to obtain MRI images. Compared with CT equipment, MRI equipment does not involve ionizing radiation, meaning it does not expose the human body to radiation during the scanning process. Therefore, MRI equipment can image target areas for extended periods over several respiratory cycles, determining continuous three-dimensional motion of the target area over time. Taking the lungs as an example, without contrast agents, the visualization of anatomical details in 4D-MRI images is limited. This is because the proton density inside the lungs is low, resulting in a relatively lower spatial resolution for 4D-MRI images compared to CT. In other words, while 4D-MRI images can reflect real-time three-dimensional motion within the target area, their lower resolution prevents them from clearly depicting the anatomical details during this real-time three-dimensional motion.

[0063] To address the aforementioned issues, this application provides an image processing method that integrates the advantages of MRI and CT images. Specifically, it combines the high spatial resolution of CT with the three-dimensional motion information of 4D-MRI, resulting in a simulated 4D-CT image that encompasses the three-dimensional volume of several respiratory cycles. In essence, it combines the continuous three-dimensional motion provided by 4D-MRI images with a single static 3D-CT image to generate a 4D-CT image, thus reflecting the actual motion and deformation within the lungs.

[0064] The image processing method provided in this application embodiment can be applied to, for example... Figure 1The application environment shown is as follows. For example, the computer device can be a server, personal computer, laptop, smartphone, tablet, mobile phone, etc. The computer device may include a processor, memory, and network interface connected via a system bus or wirelessly. The processor of the computer device provides computing and control capabilities. The memory of the computer device may include non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device stores data during image processing. The network interface of the computer device is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements an image processing method. The computer device can be implemented using a standalone computer device or a cluster of multiple computer devices. It is important to note that the memory of the computer device is not limited to the above-mentioned memory and may also include high-speed random access memory, volatile solid-state memory, etc. Furthermore, the architecture of the computer device is not limited to the above-described cases; some components may be added or omitted.

[0065] In one embodiment, such as Figure 2 As shown, an image processing method is provided, which is applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0066] S201, acquire three-dimensional medical images of the target site in the first modality and four-dimensional medical images in the second modality.

[0067] The target area can be any part of the human body that moves during respiration, such as the lungs, liver, and spleen during free breathing. Three-dimensional medical imaging is obtained by scanning the target area using medical equipment in the first modality. Four-dimensional medical imaging is obtained by continuously acquiring multiple frames of three-dimensional medical images over time using medical equipment in the second modality. This medical equipment could be a CT scanner, MRI scanner, or medical ultrasound scanner. The first and second modalities refer to different types of medical equipment, and the radiation levels to the target area differ depending on the type of equipment. Assuming the radiation generated during the first modality scanning or imaging process is greater than that generated during the second modality scanning or imaging process, only one moment's three-dimensional image is acquired during the first modality scan. This reduces the time the target area is exposed to high radiation, avoiding prolonged scanning time in the first modality. For example, the radiation level of a CT scanner is higher than that of an MRI scanner.

[0068] Optionally, the computer device can search for historical 3D medical images with the same identification information from a 3D medical image database based on the identification information of the target area, and use the historical 3D medical images with the same identification information as the 3D medical images of the target area; and, it can search for historical 4D medical images with the same identification information from 4D medical images, and use the historical 4D medical images with the same identification information as the 4D medical images of the target area. Optionally, the computer device can send a scanning command to the medical device, and after receiving the scanning command, the medical device scans the target area to obtain 3D and 4D medical images of the target area. This embodiment does not limit the method of obtaining 3D and 4D medical images of the target area.

[0069] S202, based on three-dimensional and four-dimensional medical images, obtain the surface deformation field of the target area.

[0070] Among them, the surface deformation field represents the transformation direction and displacement of points on the surface region of the target part.

[0071] In this embodiment, a CT scanner is used to represent the medical equipment corresponding to three-dimensional medical images, and an MRI scanner is used to represent the medical equipment corresponding to four-dimensional medical images. Three-dimensional medical images acquired by a CT scanner have high spatial resolution, while MRI can acquire continuous magnetic resonance images of the target area that change over time. A computer can convert these continuous magnetic resonance images over time into the coordinate system of the three-dimensional medical images to obtain high-resolution, continuous CT scan images of the target area that change over time, i.e., the deformation field of the target area. The computer can then extract the surface deformation field from the deformation field of the target area based on points on the surface region of the target area.

[0072] S203, based on the surface deformation field of the target part, obtain the internal simulated deformation field of the target part.

[0073] In this embodiment, after obtaining the surface deformation field of the target area, the computer device can use the surface deformation field as a boundary constraint and simulate the internal deformation field of the target area using a biomechanical model to obtain the simulated internal deformation field of the target area. Alternatively, the computer device can train a neural network model using a large number of surface deformation field samples and corresponding simulated internal deformation fields. The surface deformation field of the target area is then input into the trained neural network model, which analyzes the surface deformation field and outputs the simulated internal deformation field of the target area.

[0074] S204 generates a four-dimensional simulated medical image of the target area based on the surface deformation field and the internal simulated deformation field.

[0075] In this embodiment, the deformation field of the target area is composed of a surface deformation field and an internal simulated deformation field. The computer device can fuse the surface deformation field and the internal simulated deformation field to obtain multiple three-dimensional simulated medical images of the target area, and determine the four-dimensional image composed of multiple three-dimensional simulated medical images as the four-dimensional simulated medical image of the target area. This four-dimensional simulated medical image refers to the simulated four-dimensional medical image of the first mode.

[0076] It is important to emphasize that although the embodiments of this application limit the dimensions of the first and second modal medical images—that is, the first modal medical image is a three-dimensional medical image and the second modal medical image is a four-dimensional medical image—in essence, the second modal medical image is only different from the first modal medical image by adding a time dimension. Therefore, as science and technology continue to develop, when five-dimensional, six-dimensional, or higher-dimensional images appear in the future, the image processing method of this application can also be applied.

[0077] The following section explains some special cases. In one scenario, the acquisition speed of the first modality of medical images is slow and time-consuming, resulting in low acquisition efficiency. The acquisition speed of the second modality of medical images is faster and the time is relatively shorter, resulting in higher acquisition efficiency. Therefore, scanning a four-dimensional medical image in the first modality takes a long time. However, in this application, acquiring only the three-dimensional medical image of the first modality takes relatively less time. By fusing the faster four-dimensional medical image of the second modality with the three-dimensional medical image of the first modality, a four-dimensional simulated medical image corresponding to the three-dimensional medical image of the first modality can be acquired more quickly. This improves the efficiency of acquiring the four-dimensional simulated medical image of the first modality.

[0078] In another scenario, the first modality itself is not suitable for generating four-dimensional medical images, but can only generate three-dimensional medical images. However, in practical applications, there are situations where four-dimensional medical images of the first modality are required. In this application embodiment, the three-dimensional medical images of the first modality and the four-dimensional medical images of the second modality are combined to generate a four-dimensional simulated medical image of the first modality.

[0079] In the aforementioned image processing method, a three-dimensional medical image of the target area in a first modality and a four-dimensional medical image in a second modality are acquired. Based on the three-dimensional and four-dimensional medical images, the surface deformation field of the target area is acquired. Based on the surface deformation field of the target area, the internal simulated deformation field of the target area is acquired. Based on the surface deformation field and the internal simulated deformation field, a four-dimensional simulated medical image of the target area is generated. This method combines the three-dimensional medical image in the first modality and the four-dimensional medical image in the second modality. The four-dimensional medical image in the second modality can be used to acquire the true surface deformation field of the target area. Based on this surface deformation field, the internal simulated deformation field of the target area can be accurately determined. Thus, a four-dimensional simulated medical image of the target area in the first modality can be obtained based on the internal simulated deformation field. Furthermore, the four-dimensional simulated medical image in the first modality more realistically reflects the motion trajectory of the region of interest inside the target area.

[0080] Based on the above embodiments, this embodiment is... Figure 2 The relevant content of step S102, "obtaining the surface deformation field of the target area based on three-dimensional and four-dimensional medical images," will be introduced and explained.

[0081] like Figure 3 As shown, as a non-limiting example, step S102 above may include the following:

[0082] S301, based on three-dimensional and four-dimensional medical images, determines the geometric deformation field of the target area.

[0083] In this embodiment, the three-dimensional medical image is a three-dimensional CT image, and the four-dimensional medical image is an magnetic resonance imaging (MRI) image, as an example. A four-dimensional medical image includes multiple MRI images. For any given MRI image, the computer device can perform image matching with the three-dimensional CT image to obtain the displacement information of the target area in various directions. The displacement information in all directions is then fused, and the fusion result is used as the geometric deformation field of the target area. Alternatively, the computer device can select an MRI image belonging to the same respiratory stage as the three-dimensional CT image from among the multiple MRI images, perform image matching with the three-dimensional CT image, and perform image matching with other MRI images. Based on the two image matching results, the geometric deformation field of the target area is determined.

[0084] S302, Based on the geometric deformation field, determine the surface deformation field of the target part.

[0085] In this embodiment, after obtaining the geometric deformation field of the target part, the deformation field corresponding to the surface target point can be extracted from the geometric deformation field based on the surface target point in the target part, and the deformation field corresponding to the surface deformation field can be determined as the surface deformation field of the target part.

[0086] In the aforementioned image processing method, the geometric deformation field of the target area is determined based on 3D and 4D medical images, and then the surface deformation field of the target area is determined based on this geometric deformation field. This method, through 3D and 4D medical images, can obtain a more accurate geometric deformation field of the target area, not only avoiding high radiation during the scanning process but also solving the problem of low resolution in 4D medical images. Therefore, the surface deformation field obtained based on this geometric deformation field more closely approximates the actual surface deformation process of the target area.

[0087] Based on the above embodiments, this embodiment is... Figure 3 The relevant content of step S301, "Determine the geometric deformation field of the target area based on three-dimensional and four-dimensional medical images," will be introduced and explained.

[0088] like Figure 4 As shown, as a non-limiting example, step S301 above may include the following:

[0089] S401, acquire the reference 3D medical image from the 4D medical image.

[0090] Among them, the reference three-dimensional medical image refers to the image that belongs to a similar respiratory stage as the three-dimensional medical image. For example, when the three-dimensional medical image belongs to the end-expiratory image in a similar respiratory stage, the end-expiratory image in the four-dimensional medical image can be used as the reference three-dimensional medical image.

[0091] In this embodiment, to ensure effective image matching, a reference 3D medical image belonging to a similar respiratory stage to the 3D medical image needs to be selected from the 4D medical images. The computer device can select an image from the 4D medical images that is similar to the respiratory stage of the 3D medical image, based on the respiratory stage of the 3D medical image, and use this image as the reference 3D medical image. It should be noted that when the 4D medical images include images of multiple respiratory stages of the target area, i.e., when there are multiple images in the 4D medical images that belong to similar respiratory stages to the 3D medical image, then any image belonging to a similar respiratory stage to the 3D medical image will be used as the reference 3D medical image.

[0092] S402, perform image matching between the reference 3D medical image and the 3D medical image to obtain the reference deformation field.

[0093] The reference deformation field refers to the transformation direction and displacement from the reference three-dimensional medical image to the three-dimensional medical image.

[0094] In this embodiment, since the reference 3D medical image and the 3D medical image belong to similar respiratory stages, the computer device can use an image matching algorithm to perform image matching between the reference 3D medical image and the 3D medical image to obtain the transformation direction and displacement between the reference 3D medical image and the 3D medical image, and use this transformation direction and displacement as a reference deformation field. Still taking the example that the 3D medical image is a 3D CT image and the 4D medical image is a magnetic resonance imaging (MRI) image, assuming that the reference MRI image in the 4D MRI image is represented as... 3D CT images are represented as The reference deformation field obtained after image matching can be represented as r CT-MRI Image matching algorithms can include mean absolute difference algorithms, normalized product correlation algorithms, local grayscale encoding algorithms, etc.

[0095] S403, based on four-dimensional medical images and reference deformation fields, determines the geometric deformation field of the target area.

[0096] In this embodiment, after the computer device obtains the reference strain field between the reference three-dimensional medical image and the three-dimensional medical image, the computer device can perform image matching between other three-dimensional medical images in the four-dimensional medical image and the reference three-dimensional medical image to obtain the transformation direction and displacement between the other three-dimensional medical images and the reference three-dimensional medical image, and determine the geometric deformation field of the target part based on the matching result and the reference deformation field.

[0097] In the aforementioned image processing method, a reference 3D medical image is acquired from the 4D medical image. The reference 3D medical image is then matched with the 3D medical image to obtain a reference deformation field. Based on the 4D medical image and the reference deformation field, the geometric deformation field of the target area is determined. This method selects reference 3D medical images from the 4D medical image that are at a similar respiratory stage to the 3D medical image. This makes the image matching process between the reference 3D medical image and the 3D medical image more accurate, resulting in a more accurate reference deformation field and thus a more precise geometric deformation field for the target area.

[0098] Based on the above embodiments, this embodiment is... Figure 4 The following section describes and explains the relevant content of step S401, "Acquiring a reference 3D medical image from a 4D medical image." Figure 5 As shown, as a non-limiting example, step S401 above may include the following:

[0099] S501, acquire parameter information of the target area in the three-dimensional medical image; the parameter information includes location information and / or height information.

[0100] The parameter information for the target location can be the parameter value of any point within that location. For example, if the target location is the lung, the parameter information could be the height of the lung, which could be the height value of the lung at its highest point, the height value of the lung at its lowest point, or the relative height value between the highest and lowest points. If the target location is the liver, the parameter information could be the location information of the liver.

[0101] In this embodiment, the computer device can extract report information related to the target area from the image report of the three-dimensional medical image, and obtain parameter information of the target area from the report information related to the target area.

[0102] S502, designate the three-dimensional medical image with the same parameter information in the four-dimensional medical image as the reference three-dimensional medical image.

[0103] In this embodiment, images with the same parameters represent images of similar respiratory stages. The computer device can acquire an image report corresponding to the four-dimensional medical image, extract multiple parameter information of the target area from the image report, and select the parameter information that is the same as the parameter information of the target area in the three-dimensional medical image. Alternatively, it can select the parameter information that is closest to the parameter information of the target area in the three-dimensional medical image from the multiple parameter information, and use the three-dimensional medical image corresponding to the parameter information as a reference three-dimensional medical image.

[0104] In the image processing method described above, parameter information of the target area in the three-dimensional medical image is obtained, and the three-dimensional medical image with the same parameter information in the four-dimensional medical image is identified as the reference three-dimensional medical image. Based on the parameter information of the target area in the three-dimensional medical image, this method can more accurately filter out reference three-dimensional medical images from the four-dimensional medical image that are at a similar respiratory stage to the three-dimensional medical image.

[0105] Based on the above embodiments, this embodiment is... Figure 5 The following describes the relevant content of step S502, "matching the reference three-dimensional medical image with the three-dimensional medical image to obtain the reference deformation field." As a non-limiting example, step S502 may include the following: obtaining the displacement information of the target part in the reference three-dimensional medical image and the three-dimensional medical image in various directions, and determining the displacement information as the reference deformation field.

[0106] In this embodiment, the computer device acquires reference position information of multiple target points in a reference three-dimensional medical image, and acquires scan position information of multiple target points in the three-dimensional medical image. The reference position information of each target point is subtracted from the scan position information, and the position difference of each target point obtained by subtraction is used as the displacement information of the target part in each direction. The position information is determined as the reference deformation field.

[0107] In the image processing method described above, displacement information of the target area in the reference 3D medical image and the 3D medical image in various directions is obtained, and this displacement information is determined as the reference deformation field. By obtaining displacement information in various directions corresponding to the two images, this method can more accurately obtain the surface deformation field between the reference 3D medical image and the 3D medical image.

[0108] Based on the above embodiments, this embodiment is... Figure 4 The following section describes and explains step S403, "Determining the geometric deformation field of the target area based on four-dimensional medical images and a reference deformation field." Figure 6 As shown, as a non-limiting example, step S403 above may include the following:

[0109] S601, perform image matching between the four-dimensional medical images other than the reference three-dimensional medical image and the reference three-dimensional medical image to obtain the internal deformation field of the four-dimensional medical image.

[0110] In this embodiment, for any other 3D medical image besides the reference 3D medical image in a 4D medical image, the computer device can use an image matching algorithm to perform image matching between the other 3D medical image and the reference 3D medical image, obtain the transformation direction and displacement between the other 3D medical image and the reference 3D medical image, and use all the transformation directions and displacements as the internal deformation field of the 4D medical image of the target area. Still taking the 3D medical image as a 3D CT image and the 4D medical image as an MRI image as an example, the internal deformation field of the 4D medical image can be represented as...

[0111] S602 fuses the internal deformation field of the four-dimensional medical image with the reference deformation field to obtain the geometric deformation field of the target area.

[0112] In this embodiment, the reference deformation field refers to the transformation direction and displacement when a reference 3D medical image is converted to a 3D medical image, and the internal deformation field of the 4D medical image refers to the transformation direction and displacement when other 3D medical images are converted to the reference 3D medical image. Therefore, the transformation direction and displacement when other 3D medical images are converted to a 3D medical image should be the result of fusing the internal deformation field of the 4D medical image with the reference deformation field. A computer device can fuse the internal deformation field of the 4D medical image with the reference deformation field to obtain the geometric deformation field of the target area. Taking the 3D medical image as a 3D CT image and the 4D medical image as an MRI image as an example, the geometric deformation field of the target area can be represented as follows:

[0113] In the aforementioned image processing method, image matching is performed between the four-dimensional medical image and other three-dimensional medical images (excluding the reference three-dimensional medical image) to obtain the internal deformation field of the four-dimensional medical image. This internal deformation field is then fused with the reference deformation field to obtain the geometric deformation field of the target area. This method, by matching other three-dimensional medical images with the reference three-dimensional medical image, can accurately obtain the internal deformation field of the four-dimensional medical image. Furthermore, fusing this internal deformation field with the reference deformation field yields a more accurate geometric deformation field.

[0114] Based on the above embodiments, this embodiment is... Figure 3 The relevant content of step S302, "Determining the surface deformation field of the target part based on the geometric deformation field," will be introduced and explained. For example... Figure 7 As shown, as a non-limiting example, step S302 above may include the following:

[0115] S701, Obtain the position information of the surface target point of the target part.

[0116] In this embodiment, the computer device can use any point in the three-dimensional medical image of the target area as a reference point to determine the image coordinate system corresponding to the three-dimensional medical image, obtain the relative position of the pixel point where the surface target point is located and the reference point, and thus obtain the position information of the surface target point in the image coordinate system.

[0117] S702 extracts the surface deformation field of the target part from the geometric deformation field based on the position information of the target point on the surface.

[0118] In this embodiment, the computer device can determine the deformation field corresponding to the position information of each surface target point from the geometric deformation field based on the position information of each surface target point. These deformation fields are the surface deformation fields of the target part.

[0119] In the above image processing method, by obtaining the position information of the surface target points of the target part, the deformation field corresponding to these position information can be accurately found from the geometric deformation field based on the position information of the surface target points, so as to make the obtained surface deformation field of the target part more accurate.

[0120] Based on the above embodiments, this embodiment is... Figure 2 The following section describes and explains step S203, "Obtaining the simulated internal deformation field of the target part based on its surface deformation field." Figure 8 As shown, as a non-limiting example, step S203 above may include the following:

[0121] S801, Obtain the biomechanical model of the target area; the biomechanical model is a model used to represent the deformation rules of the target area.

[0122] In this embodiment, the computer device can search for the deformation rule corresponding to the identification information of the target part from the database, and use this deformation rule as the deformation rule of the target part. The biomechanical model is the model determined based on the deformation rule of the target part. It should be noted that different target parts correspond to different deformation rules, and therefore different biomechanical models.

[0123] S802 uses the surface deformation field as the boundary condition of the target part, and simulates the internal deformation of the target part through a biomechanical model to obtain the simulated internal deformation field of the target part.

[0124] In this embodiment, the surface deformation field is the real deformation field formed by the change of the surface area of ​​the target part over time. Using this real deformation field as a boundary condition, the simulated internal deformation of the target part is closer to the real internal deformation field. The computer device can input the surface deformation field as a boundary condition into the biomechanical model. Using this biomechanical model, the internal deformation of the target part can be simulated more accurately, resulting in a more accurate simulated internal deformation field.

[0125] In the image processing method described above, a biomechanical model of the target region is obtained, and the surface deformation field is used as the boundary condition of the target region. The internal deformation of the target region is simulated through the biomechanical model to obtain the simulated internal deformation field of the target region. This method uses the real surface deformation field of the target region as the boundary condition. During the simulation of the internal deformation of the target region, it can simulate a more accurate internal deformation field based on the surface deformation field, making the obtained simulated internal deformation field closer to the real internal deformation field of the target region.

[0126] Based on the above embodiments, this embodiment is... Figure 8 The following section describes and explains step S802, which involves "using the surface deformation field as the boundary condition of the target part, simulating the internal deformation of the target part through a biomechanical model, and obtaining the simulated internal deformation field of the target part." Figure 9 As shown, as a non-limiting example, step S802 above may include the following:

[0127] S901 segments three-dimensional medical images and generates a three-dimensional mesh structure.

[0128] In this context, the 3D mesh structure represents the volumetric mesh of the target region's geometry and is used for subsequent internal deformation simulation. Compared to 3D medical images, the 3D mesh structure offers higher spatial resolution.

[0129] In this embodiment, the computer device can use an active contour-based segmentation method to interactively segment the 3D medical image to obtain an initial surface mesh. Since the initial surface mesh may contain irrelevant elements, it needs to be continuously smoothed and extracted to improve mesh quality while reducing the number of surface meshes, thereby improving simulation efficiency. The smoothed and extracted mesh is used as the 3D mesh structure of the target region. Other segmentation methods can also be used to obtain the 3D mesh structure of the target region, such as mapping, rasterization, node-linked element method, and topological decomposition. After obtaining the 3D mesh structure, finite element simulation needs to be performed. In the finite element simulation, the 3D mesh structure corresponding to the target region uses a homogeneous, isotropic, and hyperelastic material.

[0130] S902 maps the surface deformation field to the surface region of the three-dimensional mesh structure, resulting in a three-dimensional mesh structure carrying boundary conditions.

[0131] In this embodiment, the computer device can obtain the mapping relationship between the surface deformation field and the surface region of the three-dimensional mesh structure. Using this mapping relationship, the surface deformation field is mapped to the surface region of the three-dimensional mesh structure. At this time, the surface region of the three-dimensional mesh structure is the surface deformation field, and the internal region has no deformation field. Alternatively, the computer device can use the position information of the surface target point corresponding to the surface deformation field to map the surface deformation field to the surface region of the three-dimensional mesh structure to obtain a three-dimensional mesh structure with boundary conditions.

[0132] S903 uses a biomechanical model to simulate the internal deformation of a three-dimensional mesh structure, obtaining the simulated internal deformation field of the target part.

[0133] In this embodiment, the computer device can use the biomechanical model generated by the deformation rules of the target part to simulate the internal deformation, determine the deformation field inside the target part, and use the obtained internal deformation field as the internal simulated deformation field.

[0134] It should be noted that during the finite element modeling of the target area, the strain energy function (Mooeny-Rivlin) is used to describe the deformation inside the target area. This strain energy function can be expressed as:

[0135]

[0136] Where c1 and c2 are the material coefficients of the strain energy function. Right Cauchy-Green deformation tensor The first and second invariants are K, the penalty parameter is J, and the determinant of the deformable gradient tensor is J. This right Cauchy-Green deformable tensor can be expressed as:

[0137]

[0138] in, The selection of c1 and c2 makes the elastic model of the target part approximately E = 250 Pa.

[0139] Taking the lungs as the target area as an example, assuming no other external force acts on the lungs, r CT The surface deformation field of the lungs, r REM The deformation field inside the lungs can be represented by the following global equilibrium equation, which can be expressed as:

[0140]

[0141] Among them, K u and K p In this scheme, K is the external force acting on the interior and surface of the lungs. u and K p If the value is 0, then the deformation field r inside the lung is... REM It can be represented as:

[0142] [K u ]{r FEM}=F u -[K up ]{r CT}

[0143] In the aforementioned image processing method, a three-dimensional medical image is segmented to generate a three-dimensional mesh structure. The surface deformation field is mapped onto the surface region of the three-dimensional mesh structure to obtain a three-dimensional mesh structure with boundary conditions. A biomechanical model is then used to simulate the internal deformation of the three-dimensional mesh structure, yielding the simulated internal deformation field of the target area. This method, by mapping the surface deformation field to the surface region of the segmented three-dimensional mesh, can constrain the boundaries of the three-dimensional network structure. Based on these boundary conditions, the biomechanical model can accurately simulate internal deformation, resulting in a more accurate simulated internal deformation field.

[0144] Based on the above embodiments, this embodiment is... Figure 2 The following section describes and explains step S204, "Generating a four-dimensional simulated medical image of the target area based on the surface deformation field and the internal simulated deformation field." Figure 10 As shown, as a non-limiting example, step S204 above may include the following:

[0145] S1001 analyzes the surface deformation field and the internal simulated deformation field to determine the simulated position information of multiple target points in the target area.

[0146] In this embodiment, the surface deformation field represents the displacement information of target points in various directions in the surface region of the target area, and the internal simulated deformation field represents the displacement information of target points in various directions in the internal region of the target area. A computer device can acquire the initial positions of multiple target points on a three-dimensional medical image. Based on these initial positions and the displacement information in various directions within a preset time interval, simulated position information of multiple target points in the target area can be obtained. For example, if the initial position of target point A in the three-dimensional medical image in the three-dimensional coordinate system is (10, 12, 30), and the displacement information of target point A in various directions is: displacement of 5 on the X-axis, displacement of 10 on the Y-axis, and displacement of 3 on the Z-axis, then the simulated position information of target point A is (15, 15, 33).

[0147] S1002 generates three-dimensional simulated medical images of multiple target sites based on the simulated location information of each target point.

[0148] In this embodiment, during the deformation process of each target point, each respiratory stage corresponds to a simulated position information, meaning one target point corresponds to multiple simulated position information. The computer device can divide the simulated position information of each target point according to the respiratory stage, grouping similar respiratory stages together. For any group of simulated position information, each target point is set on its corresponding simulated position information, generating a three-dimensional simulated medical image of the target area during that respiratory stage. Following this method, multiple three-dimensional simulated medical images of the target area can be generated.

[0149] S1003 combines the various three-dimensional simulated medical images to obtain a four-dimensional simulated medical image of the target area.

[0150] Among them, the four-dimensional simulated medical image is obtained by arranging multiple three-dimensional simulated medical images in sequence.

[0151] In this embodiment, each three-dimensional simulated medical image corresponds to a respiratory stage. The computer device can arrange the three-dimensional simulated medical images according to the respiratory stage and determine the three-dimensional simulated medical images in the time sequence of the arrangement as the four-dimensional simulated medical images of the target area.

[0152] In the aforementioned image processing method, the surface deformation field and the internal simulated deformation field are analyzed to determine the simulated position information of multiple target points in the target area. Based on the simulated position information of each target point, multiple three-dimensional simulated medical images of the target area are generated. These three-dimensional simulated medical images are then combined to obtain a four-dimensional simulated medical image of the target area. This method analyzes both the surface deformation field and the internal simulated deformation field separately, accurately determining the simulated position information of multiple target points in the target area. Based on this simulated position information, multiple three-dimensional simulated medical images of the target area can be generated. These multiple three-dimensional simulated medical images can then be combined to create a four-dimensional simulated medical image that realistically reflects the motion and deformation of the target area.

[0153] In one embodiment, the image processing method is described in detail below, such as... Figure 11 As shown, as a non-limiting example, the method may include:

[0154] S1101, acquire three-dimensional medical images of the target area in the first mode and four-dimensional medical images in the second mode;

[0155] S1102, Obtain parameter information of the target area in the three-dimensional medical image;

[0156] S1103, Identify the three-dimensional medical image with the same parameter information in the four-dimensional medical image as the reference three-dimensional medical image;

[0157] S1104, perform image matching between the reference 3D medical image and the 3D medical image to obtain the reference deformation field;

[0158] S1105, perform image matching between the three-dimensional medical images other than the reference three-dimensional medical image in the four-dimensional medical image and the reference three-dimensional medical image to obtain the internal deformation field of the four-dimensional medical image.

[0159] S1106, fuses the internal deformation field of the four-dimensional medical image with the reference deformation field to obtain the geometric deformation field of the target area;

[0160] S1107, Obtain the position information of the surface target point of the target part;

[0161] S1108, Based on the position information of the target point on the surface, extract the surface deformation field of the target part from the geometric deformation field;

[0162] S1109, Obtain the biomechanical model of the target site;

[0163] S1110, segments three-dimensional medical images and generates a three-dimensional mesh structure;

[0164] S1111 maps the surface deformation field to the surface region of the three-dimensional mesh structure to obtain a three-dimensional mesh structure with boundary conditions;

[0165] S1112, the internal deformation of the three-dimensional mesh structure is simulated using a biomechanical model to obtain the simulated internal deformation field of the target part;

[0166] S1113, Analyze the surface deformation field and the internal simulated deformation field to determine the simulated position information of multiple target points in the target part;

[0167] S1114, Based on the simulated location information of each target point, generate three-dimensional simulated medical images of multiple target parts;

[0168] S1115 combines the three-dimensional simulated medical images of each target area to obtain a four-dimensional simulated medical image of the target area.

[0169] Figure 12 The diagram illustrates the image processing method, which includes the following steps: S1201: Acquire four-dimensional magnetic resonance images of the target area using an MRI device; S1202: Acquire three-dimensional tomographic images of the target area using a CT device; S1203: Match the four-dimensional magnetic resonance images with the three-dimensional tomographic images to obtain the geometric deformation field of the target area; S1204: Extract the surface deformation field from the geometric deformation field; S1205: Segment the three-dimensional tomographic images to obtain a three-dimensional mesh structure of the target area; S1206: Map the surface deformation field from the geometric deformation field to the surface region of the three-dimensional mesh structure to obtain a three-dimensional mesh structure with boundary conditions; S1207: Simulate the internal deformation of the three-dimensional mesh structure using a biomechanical model to obtain the internal simulated deformation field of the target area; S1208: Generate a four-dimensional simulated tomographic image of the target area based on the obtained surface deformation field and internal simulated deformation field. This method acquires three-dimensional tomographic images and four-dimensional magnetic resonance images using imaging equipment, and matches the three-dimensional tomographic images and four-dimensional magnetic resonance images. This not only obtains a more realistic geometric deformation field of the target area, but also avoids the high radiation caused by long-term scanning of CT equipment. The surface deformation field extracted from the geometric deformation field can also more realistically reflect the displacement of points on the surface of the target area in various directions. The internal simulated deformation field obtained based on the surface deformation field can more realistically reflect the real motion deformation inside the target area, so that the generated four-dimensional simulated tomographic images can realistically reflect the motion trajectory of the region of interest inside the target area.

[0170] 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.

[0171] Based on the same inventive concept, this application also provides an image processing apparatus for implementing the image processing 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 processing apparatus embodiments provided below can be found in the limitations of the image processing method described above, and will not be repeated here.

[0172] In one embodiment, such as Figure 13 As shown, an image processing apparatus is provided, comprising: a first acquisition module 11, a second acquisition module 12, a third acquisition module 13, and a generation module 14, wherein:

[0173] The first acquisition module 11 is used to acquire three-dimensional medical images of the target body in a first mode and four-dimensional medical images in a second mode.

[0174] The second acquisition module 12 is used to acquire the surface deformation field of the target area based on the three-dimensional medical image and the four-dimensional medical image.

[0175] The third acquisition module 13 is used to acquire the internal simulated deformation field of the target part based on the surface deformation field of the target part;

[0176] The generation module 14 is used to generate a four-dimensional simulated medical image of the target area based on the surface deformation field and the internal simulated deformation field.

[0177] In one embodiment, the second acquisition module 12 includes: a first determining unit and a second determining unit, wherein:

[0178] The first determining unit is used to determine the geometric deformation field of the target area based on the three-dimensional medical images and the four-dimensional medical images.

[0179] The second determining unit is used to determine the surface deformation field of the target part based on the geometric deformation field.

[0180] In one embodiment, the first determining unit is further configured to acquire a reference three-dimensional medical image in a four-dimensional medical image; perform image matching between the reference three-dimensional medical image and the three-dimensional medical image to obtain a reference deformation field; and determine the geometric deformation field of the target part based on the four-dimensional medical image and the reference deformation field.

[0181] In one embodiment, the first determining unit is further configured to acquire parameter information of the target site in the three-dimensional medical image; and to determine the three-dimensional medical image in the four-dimensional medical image that has the same parameter information as the reference three-dimensional medical image.

[0182] In one embodiment, the first determining unit is further configured to perform image matching between the other three-dimensional medical images in the four-dimensional medical image (excluding the reference three-dimensional medical image) and the reference three-dimensional medical image to obtain the internal deformation field of the four-dimensional medical image; and to fuse the internal deformation field of the four-dimensional medical image with the reference deformation field to obtain the geometric deformation field of the target part.

[0183] In one embodiment, the second determining unit is further configured to acquire the position information of the surface target points of the target part; and extract the surface deformation field of the target part from the geometric deformation field based on the position information of the surface target points.

[0184] In one embodiment, the third acquisition module includes: an acquisition unit and a simulation unit, wherein:

[0185] Acquisition unit, used to acquire biomechanical models of the target site;

[0186] The simulation unit is used to use the surface deformation field as the boundary condition of the target part, and simulates the internal deformation of the target part through a biomechanical model to obtain the internal simulated deformation field of the target part.

[0187] In one embodiment, the simulation unit further includes: segmenting the three-dimensional medical image to generate a three-dimensional mesh structure; mapping the surface deformation field to the surface region of the three-dimensional mesh structure to obtain a three-dimensional mesh structure carrying boundary conditions; and simulating the internal deformation of the three-dimensional mesh structure using a biomechanical model to obtain the internal simulated deformation field of the target part.

[0188] In one embodiment, the above-mentioned generation module includes: an analysis unit, a generation unit, and a combination unit, wherein:

[0189] The analysis unit is used to analyze the surface deformation field and the internal simulated deformation field to determine the simulated position information of multiple target points in the target area;

[0190] The generation unit is used to generate three-dimensional simulated medical images of multiple target parts based on the simulated location information of each target point;

[0191] The combination unit is used to combine the three-dimensional simulated medical images of each target area to obtain a four-dimensional simulated medical image of the target area.

[0192] Each module in the aforementioned image processing 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.

[0193] In one 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 processing methods.

[0194] 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 of the embodiments of the above image processing methods.

[0195] 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 processing methods.

[0196] 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.

[0197] 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, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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, etc., and are not limited to these.

[0198] 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 specification.

[0199] 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 processing method, characterized in that, The method includes: Acquire three-dimensional medical images of the target site in the first modality and four-dimensional medical images in the second modality; Based on the three-dimensional medical image and the four-dimensional medical image, the surface deformation field of the target area is obtained; Based on the surface deformation field of the target part, the internal simulated deformation field of the target part is obtained; The surface deformation field and the internal simulated deformation field are analyzed to determine the simulated position information of multiple target points in the target part; Based on the simulated location information of each target point, three-dimensional simulated medical images of multiple target sites are generated; The three-dimensional simulated medical images are combined to obtain a four-dimensional simulated medical image of the target area.

2. The method according to claim 1, characterized in that, The step of obtaining the surface deformation field of the target region based on the three-dimensional medical image and the four-dimensional medical image includes: Based on the three-dimensional medical images and the four-dimensional medical images, determine the geometric deformation field of the target area; Based on the geometric deformation field, the surface deformation field of the target part is determined.

3. The method according to claim 2, characterized in that, Determining the geometric deformation field of the target region based on the three-dimensional medical image and the four-dimensional medical image includes: Obtain a reference three-dimensional medical image from the four-dimensional medical image; The reference three-dimensional medical image is matched with the three-dimensional medical image to obtain the reference deformation field; The geometric deformation field of the target region is determined based on the four-dimensional medical image and the reference deformation field.

4. The method according to claim 3, characterized in that, The acquisition of the reference three-dimensional medical image from the four-dimensional medical image includes: Obtain parameter information of the target area in the three-dimensional medical image; The three-dimensional medical image with the same parameter information in the four-dimensional medical image is identified as the reference three-dimensional medical image.

5. The method according to claim 3, characterized in that, Determining the geometric deformation field of the target region based on the four-dimensional medical image and the reference deformation field includes: The internal deformation field of the four-dimensional medical image is obtained by performing image matching between the three-dimensional medical images other than the reference three-dimensional medical image in the four-dimensional medical image and the reference three-dimensional medical image. The internal deformation field of the four-dimensional medical image is fused with the reference deformation field to obtain the geometric deformation field of the target area.

6. The method according to any one of claims 2-5, characterized in that, Determining the surface deformation field of the target region based on the geometric deformation field includes: Obtain the position information of the surface target points of the target region; Based on the location information of the target point on the surface, the surface deformation field of the target part is extracted from the geometric deformation field.

7. The method according to any one of claims 1-5, characterized in that, The step of obtaining the internal simulated deformation field of the target part based on the surface deformation field of the target part includes: Obtain a biomechanical model of the target site; Using the surface deformation field as the boundary condition of the target part, the internal deformation of the target part is simulated by the biomechanical model to obtain the simulated internal deformation field of the target part.

8. The method according to claim 7, characterized in that, The step of using the surface deformation field as the boundary condition of the target part, and simulating the internal deformation of the target part through the biomechanical model to obtain the simulated internal deformation field of the target part includes: The three-dimensional medical image is segmented to generate a three-dimensional mesh structure; The surface deformation field is mapped onto the surface region of the three-dimensional mesh structure to obtain a three-dimensional mesh structure carrying boundary conditions; The internal deformation of the three-dimensional mesh structure is simulated using the biomechanical model to obtain the simulated internal deformation field of the target part.

9. The method according to any one of claims 1-5, characterized in that, The surface deformation field represents the direction of change and displacement of points on the surface region of the target part.

10. An image processing apparatus, characterized in that, The device includes: The first acquisition module is used to acquire three-dimensional medical images of the target body in the first modality and four-dimensional medical images in the second modality. The second acquisition module is used to acquire the surface deformation field of the target part based on the three-dimensional medical image and the four-dimensional medical image. The third acquisition module is used to acquire the internal simulated deformation field of the target part based on the surface deformation field of the target part; The generation module is used to analyze the surface deformation field and the internal simulated deformation field to determine the simulated position information of multiple target points in the target area; based on the simulated position information of each target point, generate multiple three-dimensional simulated medical images of the target area; and combine the three-dimensional simulated medical images to obtain a four-dimensional simulated medical image of the target area.

Images