Lung Image Registration Method, Device, Computer Equipment and Storage Medium

Abstract

This application relates to a lung image registration method, apparatus, computer device, and storage medium. The method includes: acquiring enhanced data and plain scan data of a target object's lungs; registering the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea within the lung; determining lung deformation information based on the deformation information of the lung surface and the deformation information of the trachea within the lung; and registering the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result. Using this method can improve the registration effect.

Description

Technical Field

[0001] The present application relates to the technical field of image processing, and particularly to a lung image registration method, apparatus, computer device, and storage medium. Background Art

[0002] CT (Computed Tomography) uses precisely collimated X-ray beams, gamma rays, ultrasonic waves, etc., together with highly sensitive detectors to perform one cross-sectional scan after another around a certain part of the human body. It has the characteristics of fast scanning time and clear images. Therefore, it has become an indispensable technical means in medical diagnosis.

[0003] Currently, when patients are seeing a doctor, they undergo enhanced lung CT, and before undergoing interventional surgery after hospitalization, they undergo plain lung CT. The image data obtained from the enhancement can provide anatomical structure information such as lung blood vessels and lesions, while the image data obtained from the plain scan lacks anatomical structure information such as lung blood vessels and lesions. In order to avoid lung blood vessels and determine the target point during the surgical path planning of lung interventional surgery, the image data obtained from the enhancement is often registered to the image data obtained from the plain scan.

[0004] However, since registration requires the image data from the enhancement and the image data from the plain scan to be information-symmetric, in the case where the information of the two sets of image data is asymmetric, the registration effect is often poor, unable to meet the high-accuracy requirements of actual interventional surgery. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a lung image registration method, apparatus, computer device, and storage medium that can improve the registration effect and meet the high-accuracy requirements of actual interventional surgery.

[0006] In a first aspect, a lung image registration method is provided, and the method includes:

[0007] Obtain enhanced data and plain scan data of the lungs of a target object;

[0008] Register the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea inside the lung;

[0009] Determine lung deformation information based on the deformation information of the lung surface and the deformation information of the trachea inside the lung;

[0010] Based on the lung deformation information, register the enhanced data to the plain scan data to obtain a target registration result.

[0011] In one of the embodiments, the registering the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea inside the lung includes:

[0012] Mask extraction is performed on the enhanced data and the plain scan data respectively to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung;

[0013] Based on the enhanced data mask and the plain scan data mask of the lung parenchyma, registration is performed to obtain the deformation information of the lung surface;

[0014] Based on the enhanced data mask and the plain scan data mask of the trachea in the lung, registration is performed to obtain the deformation information of the trachea in the lung.

[0015] In one embodiment, the above-mentioned registration based on the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the deformation information of the lung surface includes:

[0016] Surface reconstruction processing is respectively performed on the enhanced data mask and the plain scan data mask of the lung parenchyma to generate a reticular image of the enhanced data and a reticular image of the plain scan data of the lung surface;

[0017] Rigid registration is performed on the reticular image of the enhanced data and the reticular image of the plain scan data of the lung surface to obtain the rigid registration relationship of the lung surface;

[0018] The reticular image of the enhanced data of the lung surface is transformed by using the rigid registration relationship of the lung surface to obtain a transformed image of the enhanced data of the lung surface;

[0019] Elastic registration is performed on the transformed image of the enhanced data of the lung surface and the reticular image of the plain scan data of the lung surface to obtain the deformation information of the lung surface.

[0020] In one embodiment, the above-mentioned registration based on the enhanced data mask and the plain scan data mask of the trachea in the lung to obtain the deformation information of the trachea in the lung includes:

[0021] Surface reconstruction processing is respectively performed on the enhanced data mask and the plain scan data mask of the trachea in the lung to generate a reticular image of the enhanced data and a reticular image of the plain scan data of the trachea in the lung;

[0022] Rigid registration is performed on the reticular image of the enhanced data and the reticular image of the plain scan data of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung;

[0023] The reticular image of the enhanced data of the trachea in the lung is transformed by using the rigid registration relationship of the trachea in the lung to obtain a transformed image of the enhanced data of the trachea in the lung;

[0024] Elastic registration is performed on the transformed image of the enhanced data of the trachea in the lung and the reticular image of the plain scan data of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0025] In one embodiment, the above-mentioned registration based on the enhanced data mask and the plain scan data mask of the trachea in the lung to obtain the deformation information of the trachea in the lung includes:

[0026] Surface reconstruction processing is respectively performed on the enhanced data mask and the non-enhanced data mask of the trachea in the lung to generate a reticular image of the enhanced data of the trachea in the lung and a reticular image of the non-enhanced data of the trachea in the lung;

[0027] Rigid registration is performed on the reticular image of the enhanced data of the trachea in the lung and the reticular image of the non-enhanced data of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung;

[0028] An enhanced data image of the trachea centerline and a non-enhanced data image of the trachea centerline are generated according to the enhanced data mask and the non-enhanced data mask of the trachea in the lung;

[0029] The enhanced data image of the trachea centerline is transformed by using the rigid registration relationship of the trachea in the lung to obtain a transformed image of the enhanced data of the trachea in the lung;

[0030] The transformed image of the enhanced data of the trachea in the lung and the non-enhanced data image of the trachea centerline are matched to obtain the deformation information of the trachea in the lung.

[0031] In one embodiment, determining the deformation information of the lung according to the deformation information of the lung surface and the deformation information of the trachea in the lung includes:

[0032] Determining the deformation information inside the lung according to the deformation information of the trachea in the lung;

[0033] Determining the deformation information of the lung according to the deformation information inside the lung and the deformation information of the lung surface.

[0034] In one embodiment, determining the deformation information of the lung according to the deformation information inside the lung and the deformation information of the lung surface includes:

[0035] Establishing a finite element model of the lung according to the enhanced data mask of the lung parenchyma;

[0036] Solving the finite element model of the lung according to the deformation information inside the lung and the deformation information of the lung surface to obtain the first node deformation relationship corresponding to the finite element model of the lung;

[0037] Performing interpolation processing according to the first node deformation relationship to obtain the deformation information of the lung.

[0038] In one embodiment, registering the enhanced data and the non-enhanced data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung includes:

[0039] Mask extraction is respectively performed on the enhanced data and the non-enhanced data to obtain the enhanced data mask and the non-enhanced data mask of the lung parenchyma and the trachea in the lung;

[0040] Registration is performed according to the enhanced data mask and the non-enhanced data mask of the lung parenchyma and the trachea in the lung to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0041] In one embodiment, the above-mentioned registration of the enhanced data mask and the non-enhanced data mask of the lung parenchyma and the trachea within the lung to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung includes:

[0042] Perform surface reconstruction processing on the enhanced data mask and the non-enhanced data mask of the lung parenchyma and the trachea within the lung respectively to generate a meshed image of the enhanced data of the lung parenchyma and the trachea within the lung and a meshed image of the non-enhanced data;

[0043] Perform rigid body registration on the meshed image of the enhanced data and the meshed image of the non-enhanced data of the lung parenchyma and the trachea within the lung to obtain the rigid body registration relationship of the lung surface;

[0044] Use the rigid body registration relationship of the lung surface to transform the meshed image of the enhanced data of the lung parenchyma and the trachea within the lung to obtain a transformed image of the enhanced data of the lung parenchyma and the trachea within the lung;

[0045] Perform elastic registration on the transformed image of the enhanced data of the lung parenchyma and the trachea within the lung and the meshed image of the non-enhanced data of the lung parenchyma and the trachea within the lung to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung.

[0046] In one embodiment, the above-mentioned determination of the lung deformation information based on the deformation information of the lung surface and the deformation information of the trachea within the lung includes:

[0047] Establish a finite element model of the lung according to the enhanced data mask of the lung parenchyma and the trachea within the lung;

[0048] Solve the finite element model of the lung according to the deformation information of the lung surface and the deformation information of the trachea within the lung to obtain the second node deformation relationship corresponding to the finite element model of the lung;

[0049] Perform interpolation processing according to the second node deformation relationship to obtain the deformation relationship of the lung.

[0050] In one embodiment, the above-mentioned registration of the enhanced data and the non-enhanced data to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung includes:

[0051] Perform voxel rigid body registration on the enhanced data and the non-enhanced data to obtain the rigid body registration relationship of the lung surface;

[0052] Use the rigid body registration relationship of the lung surface to transform the enhanced data to obtain transformed data;

[0053] Perform voxel elastic registration on the transformed data and the non-enhanced data to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung.

[0054] In one embodiment, the above-mentioned determination of the lung deformation information based on the deformation information of the lung surface and the deformation information of the trachea within the lung includes:

[0055] Establish a finite element model of the lung based on enhanced data;

[0056] Solve the finite element model of the lung according to the deformation information of the lung surface and the deformation information of the trachea in the lung to obtain the third node deformation relationship corresponding to the finite element model of the lung;

[0057] Perform interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lung.

[0058] In one embodiment, the above-mentioned registration of the enhanced data to the non-contrast data based on the lung deformation information to obtain the target registration result includes:

[0059] Use the pre-obtained rigid body registration relationship of the lung surface and the lung deformation information to transform the enhanced data in sequence to obtain the target registration result of registering the enhanced data to the non-contrast data.

[0060] In a second aspect, a lung image registration device is provided, and the device includes:

[0061] A data acquisition module, configured to acquire enhanced data and non-contrast data of the lungs of a target object;

[0062] A first deformation determination module, configured to register the enhanced data and the non-contrast data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0063] A second deformation determination module, configured to determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0064] A registration module, configured to register the enhanced data to the non-contrast data based on the lung deformation information to obtain the target registration result.

[0065] In one embodiment, the above-mentioned first deformation determination module includes:

[0066] A first mask extraction sub-module, configured to perform mask extraction on the enhanced data and the non-contrast data respectively to obtain an enhanced data mask of the lung parenchyma and the trachea in the lung and a non-contrast data mask;

[0067] A lung surface deformation determination sub-module, configured to register according to the enhanced data mask and the non-contrast data mask of the lung parenchyma to obtain the deformation information of the lung surface;

[0068] A trachea deformation determination sub-module, configured to register according to the enhanced data mask and the non-contrast data mask of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0069] In one embodiment, the above-mentioned lung surface deformation determination sub-module is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma respectively to generate an enhanced data mesh image and a plain scan data mesh image of the lung surface; perform rigid registration on the enhanced data mesh image and the plain scan data mesh image of the lung surface to obtain the rigid registration relationship of the lung surface; use the rigid registration relationship of the lung surface to transform the enhanced data mesh image of the lung surface to obtain the enhanced data transformed image of the lung surface; perform elastic registration on the enhanced data transformed image of the lung surface and the plain scan data mesh image of the lung surface to obtain the deformation information of the lung surface.

[0070] In one embodiment, the above-mentioned trachea deformation determination sub-module is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung respectively to generate an enhanced data mesh image and a plain scan data mesh image of the trachea in the lung; perform rigid registration on the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung; use the rigid registration relationship of the trachea in the lung to transform the enhanced data mesh image of the trachea in the lung to obtain the enhanced data transformed image of the trachea in the lung; perform elastic registration on the enhanced data transformed image of the trachea in the lung and the plain scan data mesh image of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0071] In one embodiment, the above-mentioned trachea deformation determination sub-module is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung respectively to generate an enhanced data mesh image and a plain scan data mesh image of the trachea in the lung; perform rigid registration on the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung; generate a trachea centerline enhanced data image and a trachea centerline plain scan data image according to the enhanced data mask and the plain scan data mask of the trachea in the lung; use the rigid registration relationship of the trachea in the lung to transform the trachea centerline enhanced data image to obtain the enhanced data transformed image of the trachea in the lung; perform matching on the enhanced data transformed image of the trachea in the lung and the trachea centerline plain scan data image to obtain the deformation information of the trachea in the lung.

[0072] In one embodiment, the above-mentioned second deformation determination module includes:

[0073] A lung internal deformation determination sub-module, configured to determine the deformation information inside the lung according to the deformation information of the trachea in the lung;

[0074] A lung deformation determination sub-module, configured to determine the lung deformation information according to the deformation information inside the lung and the deformation information of the lung surface.

[0075] In one embodiment, the above-mentioned lung deformation determination sub-module is specifically configured to establish a lung finite element model based on the enhanced data mask of the lung parenchyma; solve the lung finite element model according to the deformation information inside the lung and the deformation information on the lung surface to obtain the first node deformation relationship corresponding to the lung finite element model; perform interpolation processing according to the first node deformation relationship to obtain the lung deformation information.

[0076] In one embodiment, the above-mentioned first deformation determination module includes:

[0077] A second mask extraction sub-module, configured to perform mask extraction on the enhanced data and the plain scan data respectively to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea inside the lung;

[0078] A lung and trachea deformation determination sub-module, configured to perform registration on the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea inside the lung to obtain the deformation information on the lung surface and the deformation information of the trachea inside the lung.

[0079] In one embodiment, the above-mentioned lung and trachea deformation determination sub-module is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea inside the lung respectively to generate the enhanced data mesh images and the plain scan data mesh images of the lung parenchyma and the trachea inside the lung; perform rigid body registration on the enhanced data mesh images and the plain scan data mesh images of the lung parenchyma and the trachea inside the lung to obtain the rigid body registration relationship on the lung surface; use the rigid body registration relationship on the lung surface to transform the enhanced data mesh images of the lung parenchyma and the trachea inside the lung to obtain the enhanced data transformation images of the lung parenchyma and the trachea inside the lung; perform elastic registration on the enhanced data transformation images of the lung parenchyma and the trachea inside the lung and the plain scan data mesh images of the lung parenchyma and the trachea inside the lung to obtain the deformation information on the lung surface and the deformation information of the trachea inside the lung.

[0080] In one embodiment, the above-mentioned second deformation determination module is specifically configured to establish a lung finite element model based on the enhanced data mask of the lung parenchyma and the trachea inside the lung; solve the lung finite element model according to the deformation information on the lung surface and the deformation information of the trachea inside the lung to obtain the second node deformation relationship corresponding to the lung finite element model; perform interpolation processing according to the second node deformation relationship to obtain the deformation relationship of the lung.

[0081] In one embodiment, the above-mentioned first deformation determination module is specifically configured to perform rigid body registration of voxels on the enhanced data and the plain scan data to obtain the rigid body registration relationship on the lung surface; use the rigid body registration relationship on the lung surface to transform the enhanced data to obtain the transformed data; perform elastic registration of voxels on the transformed data and the plain scan data to obtain the deformation information on the lung surface and the deformation information of the trachea inside the lung.

[0082] In one embodiment, the second deformation determination module is specifically configured to establish a finite element model of the lungs based on the enhanced data; solve the finite element model of the lungs according to the deformation information of the lung surface and the deformation information of the trachea in the lungs to obtain a third node deformation relationship corresponding to the finite element model of the lungs; perform interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lungs.

[0083] In one embodiment, the registration module is specifically configured to sequentially transform the enhanced data by using the pre-obtained rigid body registration relationship of the lung surface and the lung deformation information to obtain a target registration result of registering the enhanced data to the plain scan data.

[0084] In a third aspect, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0085] Obtain enhanced data and plain scan data of the lungs of a target object;

[0086] Register the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea in the lungs;

[0087] Determine lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lungs;

[0088] Register the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result.

[0089] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0090] Obtain enhanced data and plain scan data of the lungs of a target object;

[0091] Register the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea in the lungs;

[0092] Determine lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lungs;

[0093] Register the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result.

[0094] The above-mentioned lung image registration method, device, computer device, and storage medium obtain enhanced data and plain scan data of the lungs of a target object; register the enhanced data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lungs; determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lungs; and register the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result. Through the embodiments of the present disclosure, by using the influence of the deformation of the trachea in the lungs on the internal deformation of the lungs, more accurate lung deformation information can be determined, and then the enhanced data can be transformed according to the lung deformation information, which can improve the registration effect and thus meet the high-accuracy requirements of actual interventional surgeries. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] Figure 1 FIG. is an application environment diagram of the lung image registration method in an embodiment;

[0096] Figure 2 FIG. is a schematic flowchart of the lung image registration method in an embodiment;

[0097] Figure 3 FIG. is a schematic flowchart of the lung image registration method in another embodiment;

[0098] Figure 4a FIG. is a schematic diagram of a mesh image in an embodiment;

[0099] Figure 4b FIG. is a schematic diagram of the trachea registration in the lungs in an embodiment;

[0100] Figure 4c FIG. is a schematic diagram of the trachea centerline registration in an embodiment;

[0101] Figure 4d FIG. is a schematic diagram of the finite element solution in an embodiment;

[0102] Figure 4e FIG. is one of the schematic diagrams of the node deformation relationship obtained by solving in an embodiment;

[0103] Figure 4f FIG. is another schematic diagram of the node deformation relationship obtained by solving in an embodiment;

[0104] Figure 5 FIG. is a schematic flowchart of the lung image registration method in yet another embodiment;

[0105] Figure 6a FIG. is a schematic diagram of a mask in an embodiment;

[0106] Figure 6b FIG. is a schematic diagram of a mesh image in an embodiment;

[0107] Figure 6cSchematic diagram before elastic registration in an embodiment;

[0108] Figure 6d Schematic diagram after elastic registration in an embodiment;

[0109] Figure 7 Flow schematic diagram of a lung image registration method in yet another embodiment;

[0110] Figure 8 Structural block diagram of a lung image registration device in an embodiment;

[0111] Figure 9 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0112] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0113] The lung image registration method provided by the present application can be applied to an application environment as shown in Figure 1 The application environment may include a terminal 101 and a medical scanning device 102. Among them, the terminal 101 can communicate with the medical scanning device 102 through a network. The above terminal 101 can be, but is not limited to, various personal computers, laptop computers and tablet computers. The above medical scanning device 102 can be, but is not limited to, CT (Computed Tomography) devices and PET (Positron Emission Computed Tomography)-CT devices.

[0114] The application environment may further include a PACS (Picture Archiving and Communication Systems) server 103. Both the terminal 101 and the medical scanning device 102 can communicate with the PACS server 103 through a network. The above PACS server 103 can be implemented by an independent server or a server cluster composed of multiple servers.

[0115] In one embodiment, as shown in Figure 2 A lung image registration method is provided. Taking the method applied to the terminal in Figure 1 as an example, the method includes the following steps:

[0116] Step 201, obtain enhanced data and plain scan data of the lungs of the target object.

[0117] The terminal can respectively obtain the enhanced data and plain scan data of the lungs of the target object from a medical scanning device. For example, obtain the enhanced data and plain scan data of the lungs of the target object from a CT device. The terminal can also respectively obtain the enhanced data and plain scan data of the lungs of the target object from a PACS server. The embodiments of the present disclosure do not limit this.

[0118] Step 202: Register the enhanced data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0119] Both the enhanced data and the plain scan data of the lungs of the target object include both the information of the lungs and the information of the trachea in the lung. By registering the enhanced data and the plain scan data, the terminal can obtain the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0120] The above registration can be performed in various ways. For example, the terminal performs rigid registration on the enhanced data and the plain scan data; or, the terminal first performs rigid registration on the enhanced data and the plain scan data and then performs surface elastic registration. The embodiments of the present disclosure do not limit the registration method and can be set according to the actual situation.

[0121] Step 203: Determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0122] Since the pulmonary arteriovenous vessels are mainly distributed around the trachea in the lung, the deformation of the trachea in the lung will affect the deformation of the lungs. Therefore, after obtaining the deformation information of the lung surface and the deformation information of the trachea in the lung, combining the deformation information of the trachea in the lung with the deformation information of the lung surface can correct the deformation information of the lungs to obtain more accurate lung deformation information. The embodiments of the present disclosure do not limit the correction method and can be set according to the actual situation.

[0123] Step 204: Register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result.

[0124] After determining the lung deformation information, by performing transformation processing on the enhanced data using the lung deformation information, the target registration result of registering the enhanced data to the plain scan data can be obtained. Among them, the transformation processing can include at least one of translation and rotation.

[0125] In the above lung image registration method, enhanced data and plain scan data of the lungs of the target object are obtained; the enhanced data and the plain scan data are registered to obtain the deformation information of the lung surface and the deformation information of the trachea in the lungs; the lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the trachea in the lungs; based on the lung deformation information, the enhanced data is registered to the plain scan data to obtain the target registration result. Through the embodiments of the present disclosure, by using the influence of the deformation of the trachea in the lungs on the internal deformation of the lungs, more accurate lung deformation information can be determined, and then the enhanced data can be transformed according to the lung deformation information, which can improve the registration effect, thereby meeting the high-accuracy requirements of actual interventional surgery.

[0126] In one embodiment, as Figure 3 shown, an implementation manner of registering the enhanced data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lungs, and determining the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lungs is provided. The embodiments of the present disclosure may include the following steps:

[0127] Step 301, obtain the enhanced data and the plain scan data of the lungs of the target object.

[0128] Step 302, perform mask extraction on the enhanced data and the plain scan data respectively to obtain the enhanced data mask of the lung parenchyma and the trachea in the lungs and the plain scan data mask.

[0129] The terminal performs mask extraction on the enhanced data to respectively obtain the enhanced data mask of the lung parenchyma and the enhanced data mask of the trachea in the lungs. The terminal performs mask extraction on the plain scan data to respectively obtain the enhanced data mask of the lung parenchyma and the plain scan data mask of the trachea in the lungs.

[0130] In practical applications, deep learning algorithms or other algorithms can be used to automatically perform mask extraction, or manual delineation can be used for mask extraction. The embodiments of the present disclosure do not limit the mask extraction method.

[0131] Step 303, perform registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the deformation information of the lung surface.

[0132] After the mask is extracted, rigid registration can be performed on the enhanced data mask and the plain scan data mask of the lung parenchyma first, and then surface elastic registration can be performed to obtain the deformation information of the lung surface. Among them, the deformation information of the lung surface includes the position change information of each point on the lung surface after registration and before registration.

[0133] In one of the embodiments, the registration may include the following steps:

[0134] Step 1: Perform surface reconstruction on the enhanced data mask and the non-contrast data mask of the lung parenchyma respectively to generate a mesh image of the enhanced data on the lung surface and a mesh image of the non-contrast data. Among them, the generated mesh image is as shown in Figure 4a shown.

[0135] In practical applications, MeshLab can be used for surface reconstruction. For example, input the enhanced mask data of the lung parenchyma into MeshLab, and use the pre-set surface reconstruction algorithm in MeshLab to generate a mesh image (Mesh) of the enhanced data on the lung surface. The embodiments of the present disclosure do not limit the surface processing method.

[0136] Step 2: Perform rigid registration on the mesh image of the enhanced data on the lung surface and the mesh image of the non-contrast data to obtain the rigid registration relationship on the lung surface. Among them, the rigid registration relationship can be represented by a rigid transformation matrix.

[0137] Step 3: Transform the mesh image of the enhanced data on the lung surface using the rigid registration relationship on the lung surface to obtain a transformed image of the enhanced data on the lung surface. Among them, the transformation can include at least one of translation and rotation.

[0138] Step 4: Perform elastic registration on the transformed image of the enhanced data on the lung surface and the mesh image of the non-contrast data on the lung surface to obtain the deformation information of the lung surface.

[0139] Step 304: Perform registration on the enhanced data mask and the non-contrast data mask of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0140] After extracting the mask, rigid registration can be performed on the enhanced data mask and the non-contrast data mask of the trachea in the lung first, and then elastic registration can be performed to obtain the deformation information of the trachea in the lung. Among them, the deformation information of the trachea in the lung includes the position change information of each point on the surface of the trachea in the lung after registration compared with before registration.

[0141] In one of the embodiments, the registration process may include: performing surface reconstruction on the enhanced data mask and the non-contrast data mask of the trachea in the lung respectively to generate a mesh image of the enhanced data of the trachea in the lung and a mesh image of the non-contrast data; performing rigid registration on the mesh image of the enhanced data of the trachea in the lung and the mesh image of the non-contrast data to obtain the rigid registration relationship of the trachea in the lung; using the rigid registration relationship of the trachea in the lung to transform the mesh image of the enhanced data of the trachea in the lung to obtain a transformed image of the enhanced data of the trachea in the lung; performing elastic registration on the transformed image of the enhanced data of the trachea in the lung and the mesh image of the non-contrast data of the trachea in the lung to obtain the deformation information of the trachea in the lung, as shown in Figure 4b shown.

[0142] In one embodiment, the registration process may include: respectively performing surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung to generate a meshed image of the enhanced data of the trachea in the lung and a meshed image of the plain scan data of the trachea in the lung; performing rigid registration on the meshed image of the enhanced data of the trachea in the lung and the meshed image of the plain scan data of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung; generating an enhanced data image of the trachea centerline and a plain scan data image of the trachea centerline according to the enhanced data mask and the plain scan data mask of the trachea in the lung; transforming the enhanced data image of the trachea centerline by using the rigid registration relationship of the trachea in the lung to obtain a transformed enhanced data image of the trachea in the lung; and matching the transformed enhanced data image of the trachea in the lung and the plain scan data image of the trachea centerline to obtain the deformation information of the trachea in the lung.

[0143] The above matching of the transformed enhanced data image of the trachea in the lung and the plain scan data image of the trachea centerline may include: using a preset algorithm to match each branch or branch bifurcation point of the trachea centerline, as Figure 4c shown. The preset algorithm may include a tree matching algorithm, a deep learning algorithm. The embodiments of the present disclosure do not limit the matching method.

[0144] Step 305, determining the deformation information inside the lung according to the deformation information of the trachea in the lung.

[0145] After determining the deformation information of the trachea in the lung, the terminal may use the deformation information of the trachea in the lung as the deformation information inside the lung.

[0146] Alternatively, the terminal may first perform nearest point matching between the trachea in the lung and the lung parenchyma, find a pair of nodes where the lung parenchyma and the trachea in the lung match each other, and use the deformation information of the nodes of the trachea in the lung as the deformation information of the nodes of the lung parenchyma, so as to obtain the deformation information inside the lung.

[0147] In practical applications, other methods may also be used to determine the deformation information inside the lung, and the embodiments of the present disclosure do not limit this.

[0148] Step 306, determining the deformation information of the lung according to the deformation information inside the lung and the deformation information of the lung surface.

[0149] After determining the deformation information inside the lung and the deformation information of the lung surface, the deformation information of the lung may be solved by using a finite element model. Specifically, a finite element model of the lung is established according to the enhanced data mask of the lung parenchyma; the finite element model of the lung is solved according to the deformation information inside the lung and the deformation information of the lung surface to obtain the first node deformation relationship corresponding to the finite element model of the lung; and interpolation processing is performed according to the first node deformation relationship to obtain the deformation information of the lung.

[0150] In practical applications, TetGen (an open-source finite element mesh generation software) can be used to establish a finite element model of the lungs. Among them, the enhanced data mask of the lung parenchyma or the enhanced data mesh image generated according to the enhanced data mask of the lung parenchyma can provide the boundary for establishing the finite element model of the lungs.

[0151] The finite element model can be solved using FeBio (a biomechanical simulation software): Import the established finite element model of the lungs into FeBio, set the material properties, and use the deformation information inside the lungs and the deformation information on the lung surface as the constraint conditions for solving the finite element. The solving process is as Figure 4d shown, and the obtained nodal deformation relationship is as Figure 4e shown, and the cross-section of this nodal deformation relationship is as Figure 4f shown.

[0152] Step 307: Register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result.

[0153] In the above embodiments, first obtain the enhanced data and plain scan data of the lungs of the target object; then perform mask extraction on the enhanced data and plain scan data respectively to obtain the enhanced data mask of the lung parenchyma and the trachea inside the lungs and the plain scan data mask; then, perform registration based on the enhanced data mask and plain scan data mask of the lung parenchyma to obtain the deformation information of the lung surface, and perform registration based on the enhanced data mask and plain scan data mask of the trachea inside the lungs to obtain the deformation information of the trachea inside the lungs; then, determine the deformation information inside the lungs according to the deformation information of the trachea inside the lungs, and determine the lung deformation information according to the deformation information inside the lungs and the deformation information of the lung surface; finally, register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result. In the embodiments of the present disclosure, relatively accurate deformation information of the lung surface and the trachea inside the lungs is obtained through rigid registration and surface elastic registration respectively; then, by using the influence of the trachea inside the lungs on the deformation inside the lungs, more accurate lung deformation information is obtained. In the registration methods of the prior art, the influence of the trachea inside the lungs is often ignored, and the deformation of the trachea inside the lungs is not used to correct the deformation inside the lungs. Therefore, compared with the prior art, the embodiments of the present disclosure can improve the registration effect, thereby meeting the requirements of high accuracy in actual interventional surgeries.

[0154] In one embodiment, as Figure 5 shown, there is also provided an implementation method for registering the enhanced data and the plain scan data to obtain the deformation information of the lung surface and the trachea inside the lungs, and determining the lung deformation information according to the deformation information of the lung surface and the trachea inside the lungs. The embodiments of the present disclosure may include the following steps:

[0155] Step 401: Obtain the enhanced data and plain scan data of the lungs of the target object.

[0156] Step 402: Perform mask extraction on the enhanced data and the plain scan data respectively to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung.

[0157] The terminal performs mask extraction on the enhanced data. The obtained enhanced data mask includes both the lung parenchyma and the trachea in the lung, as Figure 6a shown. The terminal performs mask extraction on the plain scan data. The obtained plain scan data mask includes both the lung parenchyma and the trachea in the lung. The mask extraction method can refer to the above embodiments, and the embodiments of the present disclosure do not limit this.

[0158] Step 403: Perform registration based on the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0159] The terminal can first perform rigid registration on the extracted enhanced data mask and plain scan data mask of the lung parenchyma and the trachea in the lung, and then perform surface elastic registration to obtain the deformation information including the lung surface and the trachea in the lung.

[0160] In one of the embodiments, the following steps may be included:

[0161] Step 1: Perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung respectively to generate the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the trachea in the lung. Among them, the mesh image is as Figure 6b shown, and the surface of the trachea in the lung is used as the inner surface of the lung.

[0162] Step 2: Perform rigid registration on the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the trachea in the lung to obtain the rigid registration relationship of the lung surface. Among them, the rigid registration relationship can be represented by a rigid transformation matrix.

[0163] Step 3: Use the rigid registration relationship of the lung surface to transform the enhanced data mesh image of the lung parenchyma and the trachea in the lung to obtain the enhanced data transformed image of the lung parenchyma and the trachea in the lung. Among them, the transformation includes at least one of translation and rotation.

[0164] Step 4: Perform elastic registration on the enhanced data transformed image of the lung parenchyma and the trachea in the lung and the plain scan data mesh image of the lung parenchyma and the trachea in the lung to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung. Before elastic registration, it is as Figure 6c shown, and after elastic registration, it is as shown in 6d. The black is the floating image (the enhanced data transformed image of the lung parenchyma and the trachea in the lung), and the white is the reference image (the plain scan data mesh image of the lung parenchyma and the trachea in the lung).

[0165] Step 404: Determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0166] After determining the deformation information of the lung interior and the deformation information of the lung surface, the finite element model can be used to solve for the lung deformation information. Specifically, a finite element model of the lung is established based on the enhanced data masks of the lung parenchyma and the trachea within the lung; the finite element model of the lung is solved according to the deformation information of the lung surface and the deformation information of the trachea within the lung to obtain the second node deformation relationship corresponding to the finite element model of the lung; interpolation processing is performed according to the second node deformation relationship to obtain the deformation relationship of the lung.

[0167] The process of finite element solution for the lung can refer to the above embodiment, and the embodiments of the present disclosure will not be elaborated here.

[0168] Step 405, register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result.

[0169] In the above embodiment, first obtain the enhanced data and the plain scan data of the lungs of the target object; then perform mask extraction on the enhanced data and the plain scan data respectively to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea within the lung; then, perform registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea within the lung to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung, and determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea within the lung; finally, register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result. The embodiments of the present disclosure obtain relatively accurate deformation information of the lung surface and the deformation information of the trachea within the lung through rigid registration and surface elastic registration, and moreover, when determining the lung deformation information, the deformation of the lung surface and the deformation of the trachea within the lung are considered simultaneously. Therefore, the obtained lung deformation information is relatively accurate, and using this lung deformation information to register the enhanced data and the plain scan data can also obtain a relatively accurate target registration result, thereby improving the registration effect.

[0170] In one embodiment, as Figure 7 shown, there is also provided an implementation method for registering the enhanced data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung, and determining the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea within the lung. The embodiments of the present disclosure may include the following steps:

[0171] Step 501, obtain the enhanced data and the plain scan data of the lungs of the target object.

[0172] Step 502, perform voxel rigid registration on the enhanced data and the plain scan data to obtain the rigid registration relationship of the lung surface.

[0173] The terminal performs voxel rigid registration on the enhanced data and the plain scan data to obtain the rigid registration relationship of the lung surface. Among them, the rigid registration relationship can be represented by a rigid transformation matrix.

[0174] Step 503: Transform the enhanced data using the rigid registration relationship on the lung surface to obtain transformed data.

[0175] The terminal transforms the enhanced data using a rigid transformation matrix to obtain the transformed data corresponding to the enhanced data. Among them, the transformation includes at least one of translation and rotation.

[0176] Step 504: Perform voxel-based elastic registration on the transformed data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0177] Step 505: Determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0178] After determining the deformation information of the inside of the lung and the deformation information of the lung surface, the lung deformation information can be solved using a finite element model. Specifically, it may include: establishing a lung finite element model according to the enhanced data; solving the lung finite element model according to the deformation information of the lung surface and the deformation information of the trachea in the lung to obtain the third node deformation relationship corresponding to the lung finite element model; performing interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lung.

[0179] The establishment of the lung finite element model and the finite element solution process can refer to the above embodiments, and the embodiments of the present disclosure will not be elaborated herein.

[0180] Step 506: Register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result.

[0181] In the above embodiments, first obtain the enhanced data and the plain scan data of the lungs of the target object; then perform voxel-based rigid registration on the enhanced data and the plain scan data to obtain the rigid registration relationship of the lung surface; then, use the rigid registration relationship of the lung surface to transform the enhanced data to obtain the transformed data, and perform voxel-based elastic registration on the transformed data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung; then, determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung; finally, register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result. The embodiments of the present disclosure obtain relatively accurate deformation information of the lung surface and the deformation information of the trachea in the lung through rigid registration and surface elastic registration respectively; and, considering the deformation of the lung surface and the deformation of the trachea in the lung at the same time, relatively accurate lung deformation information is obtained. Different from the prior art that does not consider the influence of the deformation of the trachea in the lung, the present disclosure uses the lung deformation information to register the enhanced data and the plain scan data, and can obtain a relatively accurate target registration result, thereby improving the registration effect.

[0182] In one embodiment, the above-mentioned registration of the enhanced data to the non-contrast data based on the lung deformation information to obtain the target registration result may further include: sequentially transforming the enhanced data by using the pre-obtained rigid body registration relationship of the lung surface and the lung deformation information to obtain the target registration result of registering the enhanced data to the non-contrast data.

[0183] During the rigid body registration process, the rigid body registration relationship of the lung surface can be obtained. In practical applications, the enhanced data can be first transformed once by using the rigid body registration relationship of the lung surface; then, the transformed enhanced data is transformed again by using the lung deformation information, and the transformation result is used as the target registration result of registering the enhanced data to the non-contrast data.

[0184] In the above embodiment, the enhanced data is sequentially transformed by using the pre-obtained rigid body registration relationship of the lung surface and the lung deformation information to obtain the target registration result of registering the enhanced data to the non-contrast data. Through the embodiments of the present disclosure, the lung surface is roughly registered by using the rigid body registration relationship first, and then the fine registration is performed by using the lung deformation relationship, which can effectively improve the registration effect, thereby meeting the requirements of high accuracy in actual interventional surgery.

[0185] It should be understood that although Figures 2 to 7 the steps in the flowchart are shown sequentially according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limitation, and these steps can be executed in other orders. Moreover, Figures 2 to 7 at least a part of the steps in

[0186] In one embodiment, as Figure 8 shown, a lung image registration device is provided, including:

[0187] A data acquisition module 601, configured to acquire the enhanced data and the non-contrast data of the lungs of the target object;

[0188] A first deformation determination module 602, configured to register the enhanced data and the non-contrast data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0189] A second deformation determination module 603, configured to determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0190] A registration module 604, configured to register the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result.

[0191] In one embodiment, the first deformation determination module 602 includes:

[0192] A first mask extraction sub-module, configured to perform mask extraction on the enhanced data and the plain scan data respectively to obtain an enhanced data mask and a plain scan data mask of the lung parenchyma and the trachea in the lung;

[0193] A lung surface deformation determination sub-module, configured to perform registration on the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the deformation information of the lung surface;

[0194] A trachea deformation determination sub-module, configured to perform registration on the enhanced data mask and the plain scan data mask of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0195] In one embodiment, the lung surface deformation determination sub-module is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma respectively to generate an enhanced data mesh image and a plain scan data mesh image of the lung surface; perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the lung surface to obtain a rigid body registration relationship of the lung surface; use the rigid body registration relationship of the lung surface to transform the enhanced data mesh image of the lung surface to obtain an enhanced data transformed image of the lung surface; perform elastic registration on the enhanced data transformed image of the lung surface and the plain scan data mesh image of the lung surface to obtain the deformation information of the lung surface.

[0196] In one embodiment, the trachea deformation determination sub-module is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung respectively to generate an enhanced data mesh image and a plain scan data mesh image of the trachea in the lung; perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung to obtain a rigid body registration relationship of the trachea in the lung; use the rigid body registration relationship of the trachea in the lung to transform the enhanced data mesh image of the trachea in the lung to obtain an enhanced data transformed image of the trachea in the lung; perform elastic registration on the enhanced data transformed image of the trachea in the lung and the plain scan data mesh image of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0197] In one embodiment, the above tracheal deformation determination sub-module is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung respectively to generate an enhanced data mesh image and a plain scan data mesh image of the trachea in the lung; perform rigid registration on the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung; generate an enhanced data image of the tracheal centerline and a plain scan data image of the tracheal centerline according to the enhanced data mask and the plain scan data mask of the trachea in the lung; use the rigid registration relationship of the trachea in the lung to transform the enhanced data image of the tracheal centerline to obtain an enhanced data transformed image of the trachea in the lung; match the enhanced data transformed image of the trachea in the lung and the plain scan data image of the tracheal centerline to obtain the deformation information of the trachea in the lung.

[0198] In one embodiment, the above second deformation determination module 603 includes:

[0199] The lung internal deformation determination sub-module is used to determine the lung internal deformation information according to the tracheal deformation information in the lung;

[0200] The lung deformation determination sub-module is used to determine the lung deformation information according to the lung internal deformation information and the lung surface deformation information.

[0201] In one embodiment, the above lung deformation determination sub-module is specifically configured to establish a lung finite element model according to the enhanced data mask of the lung parenchyma; solve the lung finite element model according to the lung internal deformation information and the lung surface deformation information to obtain the first node deformation relationship corresponding to the lung finite element model; perform interpolation processing according to the first node deformation relationship to obtain the lung deformation information.

[0202] In one embodiment, the above first deformation determination module 601 includes:

[0203] The second mask extraction sub-module is used to perform mask extraction on the enhanced data and the plain scan data respectively to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung;

[0204] The lung and trachea deformation determination sub-module is used to perform registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung to obtain the lung surface deformation information and the tracheal deformation information in the lung.

[0205] In one embodiment, the above-mentioned lung and trachea deformation determination sub-module is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea within the lung respectively to generate a mesh image of the enhanced data and a mesh image of the plain scan data of the lung parenchyma and the trachea within the lung; perform rigid registration on the mesh image of the enhanced data and the mesh image of the plain scan data of the lung parenchyma and the trachea within the lung to obtain the rigid registration relationship of the lung surface; use the rigid registration relationship of the lung surface to transform the mesh image of the enhanced data of the lung parenchyma and the trachea within the lung to obtain a transformed image of the enhanced data of the lung parenchyma and the trachea within the lung; perform elastic registration on the transformed image of the enhanced data of the lung parenchyma and the trachea within the lung and the mesh image of the plain scan data of the lung parenchyma and the trachea within the lung to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung.

[0206] In one embodiment, the above-mentioned second deformation determination module 602 is specifically configured to establish a lung finite element model according to the enhanced data mask of the lung parenchyma and the trachea within the lung; solve the lung finite element model according to the deformation information of the lung surface and the deformation information of the trachea within the lung to obtain a second nodal deformation relationship corresponding to the lung finite element model; perform interpolation processing according to the second nodal deformation relationship to obtain the deformation relationship of the lung.

[0207] In one embodiment, the above-mentioned first deformation determination module 601 is specifically configured to perform rigid registration of voxels on the enhanced data and the plain scan data to obtain the rigid registration relationship of the lung surface; use the rigid registration relationship of the lung surface to transform the enhanced data to obtain transformed data; perform elastic registration of voxels on the transformed data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung.

[0208] In one embodiment, the above-mentioned second deformation determination module 602 is specifically configured to establish a lung finite element model according to the enhanced data; solve the lung finite element model according to the deformation information of the lung surface and the deformation information of the trachea within the lung to obtain a third nodal deformation relationship corresponding to the lung finite element model; perform interpolation processing according to the third nodal deformation relationship to obtain the deformation relationship of the lung.

[0209] In one embodiment, the above-mentioned registration module 604 is specifically configured to sequentially transform the enhanced data by using the pre-obtained rigid registration relationship of the lung surface and the lung deformation information to obtain a target registration result of registering the enhanced data to the plain scan data.

[0210] For the specific limitations of the lung image registration device, reference can be made to the limitations of the lung image registration method in the foregoing text, which will not be elaborated herein. Each module in the above lung image registration device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0211] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structural diagram can be as Figure 9 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a lung image registration method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0212] Those skilled in the art can understand that Figure 9 the structure shown in

[0213] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0213] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0214] Obtain enhanced data and plain scan data of the lungs of the target object;

[0215] Register the enhanced data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0216] Determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0217] Register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result.

[0218] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0219] Perform mask extraction on the enhanced data and the plain scan data respectively to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung;

[0220] Perform registration based on the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the deformation information of the lung surface;

[0221] Perform registration based on the enhanced data mask and the plain scan data mask of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0222] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0223] Perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma respectively to generate the enhanced data mesh image and the plain scan data mesh image of the lung surface;

[0224] Perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the lung surface to obtain the rigid body registration relationship of the lung surface;

[0225] Use the rigid body registration relationship of the lung surface to transform the enhanced data mesh image of the lung surface to obtain the enhanced data transformed image of the lung surface;

[0226] Perform elastic registration on the enhanced data transformed image of the lung surface and the plain scan data mesh image of the lung surface to obtain the deformation information of the lung surface.

[0227] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0228] Perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung respectively to generate the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung;

[0229] Perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung to obtain the rigid body registration relationship of the trachea in the lung;

[0230] Use the rigid body registration relationship of the trachea in the lung to transform the enhanced data mesh image of the trachea in the lung to obtain the enhanced data transformed image of the trachea in the lung;

[0231] Perform elastic registration on the enhanced data transformed image of the trachea in the lung and the plain scan data mesh image of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0232] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0233] Perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung respectively to generate a mesh image of the enhanced data of the trachea in the lung and a mesh image of the plain scan data of the trachea in the lung;

[0234] Perform rigid registration on the mesh image of the enhanced data of the trachea in the lung and the mesh image of the plain scan data of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung;

[0235] Generate an enhanced data image of the trachea centerline and a plain scan data image of the trachea centerline according to the enhanced data mask and the plain scan data mask of the trachea in the lung;

[0236] Transform the enhanced data image of the trachea centerline by using the rigid registration relationship of the trachea in the lung to obtain a transformed image of the enhanced data of the trachea in the lung;

[0237] Match the transformed image of the enhanced data of the trachea in the lung and the plain scan data image of the trachea centerline to obtain the deformation information of the trachea in the lung.

[0238] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0239] Determine the deformation information inside the lung according to the deformation information of the trachea in the lung;

[0240] Determine the deformation information of the lung according to the deformation information inside the lung and the deformation information of the lung surface.

[0241] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0242] Establish a finite element model of the lung according to the enhanced data mask of the lung parenchyma;

[0243] Solve the finite element model of the lung according to the deformation information inside the lung and the deformation information of the lung surface to obtain the first node deformation relationship corresponding to the finite element model of the lung;

[0244] Perform interpolation processing according to the first node deformation relationship to obtain the deformation information of the lung.

[0245] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0246] Perform mask extraction on the enhanced data and the plain scan data respectively to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung;

[0247] Perform registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0248] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0249] Perform surface reconstruction processing on the enhanced data masks and non-contrast data masks of the lung parenchyma and the trachea within the lung respectively to generate enhanced data mesh images and non-contrast data mesh images of the lung parenchyma and the trachea within the lung;

[0250] Perform rigid registration on the enhanced data mesh images and non-contrast data mesh images of the lung parenchyma and the trachea within the lung to obtain the rigid registration relationship of the lung surface;

[0251] Transform the enhanced data mesh images of the lung parenchyma and the trachea within the lung by using the rigid registration relationship of the lung surface to obtain enhanced data transformed images of the lung parenchyma and the trachea within the lung;

[0252] Perform elastic registration on the enhanced data transformed images of the lung parenchyma and the trachea within the lung and the non-contrast data mesh images of the lung parenchyma and the trachea within the lung to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung.

[0253] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0254] Establish a finite element model of the lung based on the enhanced data masks of the lung parenchyma and the trachea within the lung;

[0255] Solve the finite element model of the lung according to the deformation information of the lung surface and the deformation information of the trachea within the lung to obtain the second node deformation relationship corresponding to the finite element model of the lung;

[0256] Perform interpolation processing according to the second node deformation relationship to obtain the deformation relationship of the lung.

[0257] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0258] Perform rigid registration of the voxels of the enhanced data and the non-contrast data to obtain the rigid registration relationship of the lung surface;

[0259] Transform the enhanced data by using the rigid registration relationship of the lung surface to obtain transformed data;

[0260] Perform elastic registration on the transformed data and the non-contrast data to obtain the deformation information of the lung surface and the deformation information of the trachea within the lung.

[0261] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0262] Establish a finite element model of the lung based on the enhanced data;

[0263] Solve the finite element model of the lung according to the deformation information of the lung surface and the deformation information of the trachea in the lung to obtain the third node deformation relationship corresponding to the finite element model of the lung;

[0264] Perform interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lung.

[0265] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0266] Use the pre-obtained rigid body registration relationship of the lung surface and the lung deformation information to transform the enhanced data in sequence to obtain the target registration result of registering the enhanced data to the plain scan data.

[0267] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0268] Obtain the enhanced data and plain scan data of the lungs of the target object;

[0269] Register the enhanced data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0270] Determine the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0271] Register the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result.

[0272] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0273] Perform mask extraction on the enhanced data and the plain scan data respectively to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea in the lung;

[0274] Register according to the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the deformation information of the lung surface;

[0275] Register according to the enhanced data mask and the plain scan data mask of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0276] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0277] Perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma respectively to generate the enhanced data mesh image and the plain scan data mesh image of the lung surface;

[0278] Perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the lung surface to obtain the rigid body registration relationship of the lung surface;

[0279] Transform the enhanced data mesh image of the lung surface using the rigid registration relationship on the lung surface to obtain the enhanced data transformed image of the lung surface;

[0280] Perform elastic registration on the enhanced data transformed image of the lung surface and the plain scan data mesh image of the lung surface to obtain the deformation information of the lung surface.

[0281] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

[0282] Perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung respectively to generate the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung;

[0283] Perform rigid registration on the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung;

[0284] Transform the enhanced data mesh image of the trachea in the lung using the rigid registration relationship of the trachea in the lung to obtain the enhanced data transformed image of the trachea in the lung;

[0285] Perform elastic registration on the enhanced data transformed image of the trachea in the lung and the plain scan data mesh image of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0286] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

[0287] Perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea in the lung respectively to generate the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung;

[0288] Perform rigid registration on the enhanced data mesh image and the plain scan data mesh image of the trachea in the lung to obtain the rigid registration relationship of the trachea in the lung;

[0289] Generate the enhanced data image of the trachea centerline and the plain scan data image of the trachea centerline according to the enhanced data mask and the plain scan data mask of the trachea in the lung;

[0290] Transform the enhanced data image of the trachea centerline using the rigid registration relationship of the trachea in the lung to obtain the enhanced data transformed image of the trachea in the lung;

[0291] Match the enhanced data transformed image of the trachea in the lung and the plain scan data image of the trachea centerline to obtain the deformation information of the trachea in the lung.

[0292] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

[0293] Determine the deformation information inside the lung according to the deformation information of the trachea in the lung;

[0294] Determine the lung deformation information based on the deformation information inside the lung and the deformation information on the lung surface.

[0295] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0296] Establish a lung finite element model based on the enhanced data mask of the lung parenchyma;

[0297] Solve the lung finite element model according to the deformation information inside the lung and the deformation information on the lung surface to obtain the first node deformation relationship corresponding to the lung finite element model;

[0298] Perform interpolation processing according to the first node deformation relationship to obtain the lung deformation information.

[0299] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0300] Respectively perform mask extraction on the enhanced data and the plain scan data to obtain the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea inside the lung;

[0301] Perform registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea inside the lung to obtain the deformation information on the lung surface and the deformation information of the trachea inside the lung.

[0302] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0303] Respectively perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma and the trachea inside the lung to generate the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the trachea inside the lung;

[0304] Perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the trachea inside the lung to obtain the rigid body registration relationship on the lung surface;

[0305] Use the rigid body registration relationship on the lung surface to transform the enhanced data mesh image of the lung parenchyma and the trachea inside the lung to obtain the enhanced data transformed image of the lung parenchyma and the trachea inside the lung;

[0306] Perform elastic registration on the enhanced data transformed image of the lung parenchyma and the trachea inside the lung and the plain scan data mesh image of the lung parenchyma and the trachea inside the lung to obtain the deformation information on the lung surface and the deformation information of the trachea inside the lung.

[0307] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0308] Establish a lung finite element model based on the enhanced data mask of the lung parenchyma and the trachea inside the lung;

[0309] Solve the finite element model of the lung according to the deformation information of the lung surface and the deformation information of the trachea in the lung to obtain the second node deformation relationship corresponding to the finite element model of the lung;

[0310] Perform interpolation processing according to the second node deformation relationship to obtain the deformation relationship of the lung.

[0311] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0312] Perform rigid body registration of voxels on the enhanced data and the plain scan data to obtain the rigid body registration relationship of the lung surface;

[0313] Transform the enhanced data by using the rigid body registration relationship of the lung surface to obtain transformed data;

[0314] Perform elastic registration of voxels on the transformed data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea in the lung.

[0315] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0316] Establish a finite element model of the lung according to the enhanced data;

[0317] Solve the finite element model of the lung according to the deformation information of the lung surface and the deformation information of the trachea in the lung to obtain the third node deformation relationship corresponding to the finite element model of the lung;

[0318] Perform interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lung.

[0319] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0320] Use the pre-obtained rigid body registration relationship of the lung surface and the lung deformation information to sequentially transform the enhanced data to obtain the target registration result of registering the enhanced data to the plain scan data.

[0321] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0322] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0323] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A lung image registration method, characterized in that, The method includes: Obtaining enhanced data and plain scan data of the lungs of a target object; Registering the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea inside the lungs; Determining lung deformation information based on the deformation information of the lung surface and the deformation information of the trachea inside the lungs; Registering the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result; Wherein, the registering the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea inside the lungs includes: Performing rigid body registration of voxels on the enhanced data and the plain scan data to obtain a rigid body registration relationship of the lung surface; Transforming the enhanced data by using the rigid body registration relationship of the lung surface to obtain transformed data; Performing elastic registration of voxels on the transformed data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the trachea inside the lungs.

2. The method according to claim 1, characterized in that, The registering the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea inside the lungs includes: Performing mask extraction on the enhanced data and the plain scan data respectively to obtain an enhanced data mask and a plain scan data mask of the lung parenchyma and an enhanced data mask and a plain scan data mask of the trachea inside the lungs; Performing registration based on the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the deformation information of the lung surface; Performing registration based on the enhanced data mask and the plain scan data mask of the trachea inside the lungs to obtain the deformation information of the trachea inside the lungs.

3. The method according to claim 2, wherein The performing registration based on the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the deformation information of the lung surface includes: Performing surface reconstruction processing on the enhanced data mask and the plain scan data mask of the lung parenchyma respectively to generate a reticular image of the enhanced data of the lung surface and a reticular image of the plain scan data of the lung surface; Performing rigid body registration on the reticular image of the enhanced data of the lung surface and the reticular image of the plain scan data of the lung surface to obtain a rigid body registration relationship of the lung surface; Transforming the reticular image of the enhanced data of the lung surface by using the rigid body registration relationship of the lung surface to obtain a transformed image of the enhanced data of the lung surface; Performing elastic registration on the transformed image of the enhanced data of the lung surface and the reticular image of the plain scan data of the lung surface to obtain the deformation information of the lung surface.

4. The method according to claim 2, wherein The performing registration based on the enhanced data mask and the plain scan data mask of the trachea inside the lungs to obtain the deformation information of the trachea inside the lungs includes: Performing surface reconstruction processing on the enhanced data mask and the plain scan data mask of the trachea inside the lungs respectively to generate a reticular image of the enhanced data of the trachea inside the lungs and a reticular image of the plain scan data of the trachea inside the lungs; Performing rigid body registration on the reticular image of the enhanced data of the trachea inside the lungs and the reticular image of the plain scan data of the trachea inside the lungs to obtain a rigid body registration relationship of the trachea inside the lungs; Transforming the reticular image of the enhanced data of the trachea inside the lungs by using the rigid body registration relationship of the trachea inside the lungs to obtain a transformed image of the enhanced data of the trachea inside the lungs; Performing elastic registration on the transformed image of the enhanced data of the trachea inside the lungs and the reticular image of the plain scan data of the trachea inside the lungs to obtain the deformation information of the trachea inside the lungs.

5. The method according to claim 2, characterized in that, Performing registration on the enhanced data mask and the non-contrast data mask of the intrapulmonary trachea to obtain the deformation information of the intrapulmonary trachea includes: Performing surface reconstruction processing on the enhanced data mask and the non-contrast data mask of the intrapulmonary trachea respectively to generate a mesh image of the enhanced data of the intrapulmonary trachea and a mesh image of the non-contrast data of the intrapulmonary trachea; Performing rigid body registration on the mesh image of the enhanced data of the intrapulmonary trachea and the mesh image of the non-contrast data of the intrapulmonary trachea to obtain the rigid body registration relationship of the intrapulmonary trachea; Generating an enhanced data image of the tracheal centerline and a non-contrast data image of the tracheal centerline according to the enhanced data mask and the non-contrast data mask of the intrapulmonary trachea; Transforming the enhanced data image of the tracheal centerline by using the rigid body registration relationship of the intrapulmonary trachea to obtain an enhanced data transformed image of the intrapulmonary trachea; Matching the enhanced data transformed image of the intrapulmonary trachea and the non-contrast data image of the tracheal centerline to obtain the deformation information of the intrapulmonary trachea.

6. The method according to claim 2, wherein Determining the lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary trachea includes: Determining the deformation information inside the lung according to the deformation information of the intrapulmonary trachea; Determining the lung deformation information according to the deformation information inside the lung and the deformation information of the lung surface.

7. The method according to claim 6, characterized in that, Determining the lung deformation information according to the deformation information inside the lung and the deformation information of the lung surface includes: Establishing a lung finite element model according to the enhanced data mask of the lung parenchyma; Solving the lung finite element model according to the deformation information inside the lung and the deformation information of the lung surface to obtain the first node deformation relationship corresponding to the lung finite element model; Performing interpolation processing according to the first node deformation relationship to obtain the lung deformation information.

8. The method according to claim 1, characterized in that Performing registration on the enhanced data and the non-contrast data to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary trachea includes: Performing mask extraction on the enhanced data and the non-contrast data respectively to obtain an enhanced data mask and a non-contrast data mask that include both the lung parenchyma and the intrapulmonary trachea; Performing registration on the enhanced data mask and the non-contrast data mask of the lung parenchyma and the intrapulmonary trachea to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary trachea.

9. The method according to claim 8, wherein Performing registration on the enhanced data mask and the non-contrast data mask of the lung parenchyma and the intrapulmonary trachea to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary trachea includes: Performing surface reconstruction processing on the enhanced data mask and the non-contrast data mask of the lung parenchyma and the intrapulmonary trachea respectively to generate a mesh image of the enhanced data of the lung parenchyma and the intrapulmonary trachea and a mesh image of the non-contrast data of the lung parenchyma and the intrapulmonary trachea; Performing rigid body registration on the mesh image of the enhanced data of the lung parenchyma and the intrapulmonary trachea and the mesh image of the non-contrast data of the lung parenchyma and the intrapulmonary trachea to obtain the rigid body registration relationship of the lung surface; Transforming the mesh image of the enhanced data of the lung parenchyma and the intrapulmonary trachea by using the rigid body registration relationship of the lung surface to obtain an enhanced data transformed image of the lung parenchyma and the intrapulmonary trachea; Perform elastic registration on the enhanced data-transformed image of the lung parenchyma and the intrapulmonary airways and the non-enhanced data mesh image of the lung parenchyma and the intrapulmonary airways to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary airways.

10. The method according to claim 9, characterized in that, Determining the lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary airways includes: Establish a lung finite element model according to the enhanced data mask of the lung parenchyma and the intrapulmonary airways; Solve the lung finite element model according to the deformation information of the lung surface and the deformation information of the intrapulmonary airways to obtain the second node deformation relationship corresponding to the lung finite element model; Perform interpolation processing according to the second node deformation relationship to obtain the deformation relationship of the lung.

11. The method according to claim 1, characterized in that, Determining the lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary airways includes: Establish a lung finite element model according to the enhanced data; Solve the lung finite element model according to the deformation information of the lung surface and the deformation information of the intrapulmonary airways to obtain the third node deformation relationship corresponding to the lung finite element model; Perform interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lung.

12. The method according to any one of claims 1-11, characterized in that, Registering the enhanced data to the non-enhanced data based on the lung deformation information to obtain a target registration result includes: Use the pre-obtained rigid body registration relationship of the lung surface and the lung deformation information to transform the enhanced data in sequence to obtain the target registration result of registering the enhanced data to the non-enhanced data.

13. An image registration device, characterized in that, The device includes: A data acquisition module for acquiring enhanced data and non-enhanced data of the lungs of a target object; A first deformation determination module for registering the enhanced data and the non-enhanced data to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary airways; A second deformation determination module for determining the lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary airways; A registration module for registering the enhanced data to the non-enhanced data based on the lung deformation information to obtain a target registration result; Among them, the first deformation determination module is specifically used to perform rigid body registration of voxels on the enhanced data and the non-enhanced data to obtain the rigid body registration relationship of the lung surface; use the rigid body registration relationship of the lung surface to transform the enhanced data to obtain transformed data; perform elastic registration of voxels on the transformed data and the non-enhanced data to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary airways.

14. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 12 are implemented.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images