Lung image registration method, computer equipment and storage medium

Abstract

The invention relates to a lung image registration method, computer equipment and a storage medium. The method comprises the following steps: acquiring enhanced data and plain scanning data of a lung of a target object; registering the enhanced data and the flat scanning data to obtain deformation information of the lung surface and deformation information of the trachea in the lung; determining lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung; and registering the enhanced data to the flat scanning data based on the lung deformation information to obtain a target registration result. By adopting the method, the registration effect can be improved.

Description

[0001] This application is a divisional application of the application with the application date of November 19, 2021, the application number of 202111398523.2, and the invention name of "Lung image registration method, device, computer equipment and storage medium". TECHNICAL FIELD

[0002] The present application relates to the technical field of image processing, in particular to a lung image registration method, computer equipment and storage medium. BACKGROUND

[0003] CT (Computed Tomography, electronic computer tomography) is a scanning technology that uses precisely collimated X-ray beams, gamma rays, ultrasonic waves, etc., together with a highly sensitive detector to make one after another cross-sectional scans around a certain part of the human body. It has the characteristics of fast scanning time and clear image, and therefore has become an indispensable technology in medical diagnosis.

[0004] At present, patients perform lung CT enhancement when seeing a doctor, and perform lung CT plain scan before interventional surgery. The image data obtained by enhancement can provide anatomical structure information of lung blood vessels and lesions, while the image data obtained by plain scan lacks anatomical structure information of lung blood vessels and lesions. In order to avoid lung blood vessels and determine the target point in the surgical path planning of lung interventional surgery, the image data obtained by enhancement is often registered to the image data obtained by plain scan.

[0005] However, since the registration requires the information of the enhanced image data and the plain scan image data to be symmetrical, in the case of asymmetrical two sets of image data information, the registration effect is often poor, which cannot meet the high accuracy requirement of actual interventional surgery. SUMMARY

[0006] Therefore, it is necessary to provide a lung image registration method, device, computer equipment and storage medium which can improve the registration effect and meet the high accuracy requirement of actual interventional surgery.

[0007] In a first aspect, a lung image registration method is provided, the method comprising:

[0008] obtaining enhanced data and plain scan data of a lung of a target object;

[0009] registering the enhanced data and the plain scan data to obtain deformation information of a lung surface and deformation information of an intrapulmonary bronchus;

[0010] determining lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus;

[0011] The enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result.

[0012] In one of the embodiments, the registration of the enhanced data and the plain scan data to obtain the lung surface deformation information and the lung airway deformation information comprises:

[0013] 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 lung airway;

[0014] Registration is performed according to the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the lung surface deformation information;

[0015] Registration is performed according to the enhanced data mask and the plain scan data mask of the lung airway to obtain the lung airway deformation information.

[0016] In one of the embodiments, the registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain the lung surface deformation information comprises:

[0017] Surface reconstruction is performed 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;

[0018] Rigid body registration is performed 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;

[0019] The enhanced data mesh image of the lung surface is transformed using the rigid body registration relationship of the lung surface to obtain the enhanced data transformed image of the lung surface;

[0020] Elastic registration is performed on the enhanced data transformed image of the lung surface and the plain scan data mesh image of the lung surface to obtain the lung surface deformation information.

[0021] In one of the embodiments, the registration according to the enhanced data mask and the plain scan data mask of the lung airway to obtain the lung airway deformation information comprises:

[0022] Surface reconstruction is performed on the enhanced data mask and the plain scan data mask of the lung airway respectively to generate the enhanced data mesh image and the plain scan data mesh image of the lung airway;

[0023] Rigid body registration is performed on the enhanced data mesh image and the plain scan data mesh image of the lung airway to obtain the rigid body registration relationship of the lung airway;

[0024] The enhanced data mesh image of the lung airway is transformed using the rigid body registration relationship of the lung airway to obtain the enhanced data transformed image of the lung airway;

[0025] The enhanced data transformed image of the trachea in the lung is elastically registered with the reticulation image of the trachea in the lung in the plain scan data to obtain the deformation information of the trachea in the lung.

[0026] In one of the embodiments, the deformation information of the trachea in the lung is obtained by registering the enhanced data mask and the plain scan data mask of the trachea in the lung, including:

[0027] The enhanced data mask and the plain scan data mask of the trachea in the lung are respectively subjected to surface reconstruction processing to generate the enhanced data reticulation image and the plain scan data reticulation image of the trachea in the lung;

[0028] The enhanced data reticulation image and the plain scan data reticulation image of the trachea in the lung are subjected to rigid body registration to obtain the rigid body registration relationship of the trachea in the lung;

[0029] The enhanced data mask and the plain scan data mask of the trachea in the lung are used to generate the trachea center line enhanced data image and the trachea center line plain scan data image;

[0030] The trachea center line enhanced data image is transformed using the rigid body registration relationship of the trachea in the lung to obtain the enhanced data transformed image of the trachea in the lung;

[0031] The enhanced data transformed image of the trachea in the lung and the trachea center line plain scan data image are matched to obtain the deformation information of the trachea in the lung.

[0032] In one of the embodiments, the lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the trachea in the lung, including:

[0033] The deformation information inside the lung is determined according to the deformation information of the trachea in the lung;

[0034] The lung deformation information is determined according to the deformation information inside the lung and the deformation information of the lung surface.

[0035] In one of the embodiments, the lung deformation information is determined according to the deformation information inside the lung and the deformation information of the lung surface, including:

[0036] A lung finite element model is established according to the enhanced data mask of the lung parenchyma;

[0037] The lung finite element model is solved according to the deformation information inside the lung and the deformation information of the lung surface to obtain a first node deformation relationship corresponding to the lung finite element model;

[0038] The lung deformation information is obtained by interpolation processing according to the first node deformation relationship.

[0039] In one of the embodiments, the deformation information of the lung surface and the deformation information of the trachea in the lung are obtained by registering the enhanced data and the plain scan data, including:

[0040] Mask extraction is performed 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 intrapulmonary air tube;

[0041] Registration is performed according to the enhanced data mask and the plain scan data mask of the lung parenchyma and the intrapulmonary air tube to obtain deformation information of the lung surface and deformation information of the intrapulmonary air tube.

[0042] In one embodiment, the registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma and the intrapulmonary air tube to obtain deformation information of the lung surface and deformation information of the intrapulmonary air tube includes:

[0043] Surface reconstruction is performed on the enhanced data mask and the plain scan data mask of the lung parenchyma and the intrapulmonary air tube to generate an enhanced data mesh image and a plain scan data mesh image of the lung parenchyma and the intrapulmonary air tube;

[0044] Rigid body registration is performed on the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the intrapulmonary air tube to obtain a rigid body registration relationship of the lung surface;

[0045] The enhanced data mesh image of the lung parenchyma and the intrapulmonary air tube is transformed using the rigid body registration relationship of the lung surface to obtain an enhanced data transformed image of the lung parenchyma and the intrapulmonary air tube;

[0046] Elastic registration is performed on the enhanced data transformed image of the lung parenchyma and the intrapulmonary air tube and the plain scan data mesh image of the lung parenchyma and the intrapulmonary air tube to obtain deformation information of the lung surface and deformation information of the intrapulmonary air tube.

[0047] In one embodiment, the determination of the lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary air tube includes:

[0048] A lung finite element model is established according to the enhanced data mask of the lung parenchyma and the intrapulmonary air tube;

[0049] The lung finite element model is solved according to the deformation information of the lung surface and the deformation information of the intrapulmonary air tube to obtain a second node deformation relationship corresponding to the lung finite element model;

[0050] Interpolation is performed according to the second node deformation relationship to obtain a deformation relationship of the lung.

[0051] In one embodiment, the registration of the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the intrapulmonary air tube includes:

[0052] Rigid body registration is performed on the enhanced data and the plain scan data in the voxel to obtain a rigid body registration relationship of the lung surface;

[0053] The enhanced data is transformed using the rigid body registration relationship of the lung surface to obtain transformed data.

[0054] The transform data and the plain scan data are voxel-registered to obtain deformation information of a lung surface and deformation information of a bronchus in the lung.

[0055] In one embodiment, the lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the bronchus in the lung, including:

[0056] A lung finite element model is established according to the enhanced data;

[0057] The lung finite element model is solved according to the deformation information of the lung surface and the deformation information of the bronchus in the lung to obtain a third node deformation relationship corresponding to the lung finite element model;

[0058] The third node deformation relationship is interpolated to obtain a lung deformation relationship.

[0059] In one embodiment, the enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result, including:

[0060] The enhanced data is transformed according to the pre-obtained rigid registration relationship of the lung surface and the lung deformation information in sequence to obtain the target registration result of registering the enhanced data to the plain scan data.

[0061] In a second aspect, a lung image registration device is provided, including:

[0062] A data acquisition module is configured to acquire enhanced data and plain scan data of a lung of a target object;

[0063] A first deformation determination module is configured to register the enhanced data and the plain scan data to obtain deformation information of a lung surface and deformation information of a bronchus in the lung;

[0064] A second deformation determination module is configured to determine lung deformation information according to the deformation information of the lung surface and the deformation information of the bronchus in the lung;

[0065] A registration module is configured to register the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result.

[0066] In one embodiment, the first deformation determination module includes:

[0067] A first mask extraction sub-module is configured to extract masks from the enhanced data and the plain scan data respectively to obtain enhanced data masks and plain scan data masks of lung parenchyma and a bronchus in the lung;

[0068] A lung surface deformation determination sub-module is configured to register the enhanced data masks and the plain scan data masks of the lung parenchyma to obtain deformation information of the lung surface;

[0069] The trachea deformation determination submodule is configured to: perform surface reconstruction 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; perform transformation on the enhanced data mesh image of the trachea in the lung by using the rigid body registration relationship of the trachea in the lung to obtain an enhanced data transformed image of the trachea in the lung; and 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 deformation information of the trachea in the lung.

[0070] In one of the embodiments, the lung surface deformation determination submodule is specifically configured to: perform surface reconstruction 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; perform transformation on the enhanced data mesh image of the lung surface by using the rigid body registration relationship of the lung surface to obtain an enhanced data transformed image of the lung surface; and 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 deformation information of the lung surface.

[0071] In one of the embodiments, the trachea deformation determination submodule is specifically configured to: perform surface reconstruction 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; perform transformation on the enhanced data mesh image of the trachea in the lung by using the rigid body registration relationship of the trachea in the lung to obtain an enhanced data transformed image of the trachea in the lung; and 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 deformation information of the trachea in the lung.

[0072] In one of the embodiments, the trachea deformation determination submodule is specifically configured to: perform surface reconstruction 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; generate a trachea center line enhanced data image and a trachea center line plain scan data image according to the enhanced data mask and the plain scan data mask of the trachea in the lung; perform transformation on the trachea center line enhanced data image by using the rigid body registration relationship of the trachea in the lung to obtain an enhanced data transformed image of the trachea in the lung; and perform matching on the enhanced data transformed image of the trachea in the lung and the trachea center line plain scan data image to obtain deformation information of the trachea in the lung.

[0073] In one of the embodiments, the second deformation determination module comprises:

[0074] The internal lung deformation determination submodule is configured to determine deformation information of an internal lung according to the deformation information of the trachea in the lung.

[0075] The lung deformation determination submodule is configured to determine lung deformation information according to the deformation information of the internal lung and the deformation information of the lung surface.

[0076] In one of the embodiments, the lung deformation determining submodule 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 deformation information of the lung and the deformation information of the lung surface to obtain a first node deformation relationship corresponding to the lung finite element model; and perform interpolation processing according to the first node deformation relationship to obtain the lung deformation information.

[0077] In one of the embodiments, the first deformation determining module comprises:

[0078] The second mask extraction submodule is 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 intrapulmonary airway.

[0079] The lung and airway deformation determining submodule is configured to perform registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma and the intrapulmonary airway to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary airway.

[0080] In one of the embodiments, the lung and airway deformation determining submodule 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 intrapulmonary airway respectively to generate an enhanced data mesh image and a plain scan data mesh image of the lung parenchyma and the intrapulmonary airway; perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the intrapulmonary airway to obtain a rigid body registration relationship of the lung surface; transform the enhanced data mesh image of the lung parenchyma and the intrapulmonary airway 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 airway; and perform elastic registration on the enhanced data transformed image of the lung parenchyma and the intrapulmonary airway and the plain scan data mesh image of the lung parenchyma and the intrapulmonary airway to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary airway.

[0081] In one of the embodiments, the second deformation determining 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 deformation information of the lung surface and the deformation information of the intrapulmonary airway to obtain a second node deformation relationship corresponding to the lung finite element model; and perform interpolation processing according to the second node deformation relationship to obtain the deformation relationship of the lung.

[0082] In one of the embodiments, the first deformation determining module is specifically configured to perform rigid body registration on voxels of the enhanced data and the plain scan data to obtain a rigid body registration relationship of the lung surface; transform the enhanced data by using the rigid body registration relationship of the lung surface to obtain transformed data; and perform elastic registration on voxels of the transformed data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary airway.

[0083] In one of the embodiments, the second deformation determining module 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 intrapulmonary bronchus to obtain a third node deformation relationship corresponding to the lung finite element model; and perform interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lung.

[0084] In one of the embodiments, the registration module is specifically configured to transform the enhanced data in sequence to obtain a target registration result of registering the enhanced data to the plain scan data by using the rigid registration relationship of the lung surface and the lung deformation information obtained in advance.

[0085] In a third aspect, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0086] obtaining enhanced data and plain scan data of a lung of a target object;

[0087] registering the enhanced data and the plain scan data to obtain deformation information of a lung surface and deformation information of an intrapulmonary bronchus;

[0088] determining lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus;

[0089] registering the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result.

[0090] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0091] obtaining enhanced data and plain scan data of a lung of a target object;

[0092] registering the enhanced data and the plain scan data to obtain deformation information of a lung surface and deformation information of an intrapulmonary bronchus;

[0093] determining lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus;

[0094] registering the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result.

[0095] The lung image registration method, device, computer device and storage medium, obtain enhanced data and plain scan data of a lung of a target object; registration is performed on the enhanced data and the plain scan data to obtain deformation information of a lung surface and deformation information of a trachea in the lung; lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the trachea in the lung; the enhanced data is registered to the plain scan data based on the lung deformation information, and a target registration result is obtained. Through the embodiment of the present disclosure, the influence of the deformation of the trachea in the lung on the deformation of the lung is utilized, more accurate lung deformation information can be determined, and the enhanced data is transformed according to the lung deformation information, which can improve the registration effect, thereby meeting the high accuracy requirement of actual interventional surgery. BRIEF DESCRIPTION OF DRAWINGS

[0096] Figure 1 An application environment diagram of the lung image registration method in one embodiment;

[0097] Figure 2 A flowchart of the lung image registration method in one embodiment;

[0098] Figure 3 A flowchart of the lung image registration method in another embodiment;

[0099] Figure 4a A diagram of a mesh image in one embodiment;

[0100] Figure 4b A diagram of trachea registration in a lung in one embodiment;

[0101] Figure 4c A diagram of trachea centerline registration in one embodiment;

[0102] Figure 4d A diagram of finite element solving in one embodiment;

[0103] Figure 4e One of diagrams of node deformation relationships obtained by solving in one embodiment;

[0104] Figure 4f Another diagram of node deformation relationships obtained by solving in one embodiment;

[0105] Figure 5 A flowchart of the lung image registration method in yet another embodiment;

[0106] Figure 6a A diagram of a mask in one embodiment;

[0107] Figure 6b A diagram of a mesh image in one embodiment;

[0108] Figure 6cA schematic diagram of a lung image registration method in another embodiment;

[0109] Figure 6d A schematic diagram of a lung image registration method in another embodiment;

[0110] Figure 7 A schematic diagram of a lung image registration method in another embodiment;

[0111] Figure 8 A schematic diagram of a lung image registration method in another embodiment;

[0112] Figure 9 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0113] In order to make the purposes, technical solutions and advantages of the present application clearer, 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 should not be used to limit the present application.

[0114] 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 can include a terminal 101 and a medical scanning device 102. The terminal 101 can communicate with the medical scanning device 102 through a network. The terminal 101 can be, but is not limited to, various personal computers, notebook computers and tablet computers, and the medical scanning device 102 can be, but is not limited to, a CT (Computed Tomography, i.e. electronic computed tomography) device and a PET (Positron Emission Computed Tomography, positron emission computed tomography)-CT device.

[0115] The application environment can also include a PACS (Picture Archiving and Communication Systems, image archiving and communication system) server 103, and the terminal 101 and the medical scanning device 102 can communicate with the PACS server 103 through a network. The PACS server 103 can be implemented by an independent server or a server cluster composed of multiple servers.

[0116] In an embodiment, as shown in Figure 2 , a lung image registration method is provided. Taking the terminal in Figure 1 as an example, the method includes the following steps:

[0117] Step 201, obtaining enhanced data and plain scan data of a lung of a target object.

[0118] The terminal can acquire the enhanced data and the plain scan data of the lung of the target object from a medical scanning device respectively. For example, the enhanced data and the plain scan data of the lung of the target object are acquired from a CT device respectively. The terminal can also acquire the enhanced data and the plain scan data of the lung of the target object from a PACS server respectively. The embodiments of the present disclosure do not limit this.

[0119] In step 202, the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus are obtained by registering the enhanced data and the plain scan data.

[0120] The enhanced data and the plain scan data of the lung of the target object both include information of the lung and information of the intrapulmonary bronchus. The terminal can obtain the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus by registering the enhanced data and the plain scan data.

[0121] The registration can be performed in various ways. For example, the terminal can perform rigid registration on the enhanced data and the plain scan data. Alternatively, the terminal can first perform rigid registration on the enhanced data and the plain scan data and then perform surface elasticity registration. The embodiments of the present disclosure do not limit the registration method, which can be set according to actual conditions.

[0122] In step 203, the lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus.

[0123] Since the arterial and venous blood vessels in the lung are mainly distributed around the intrapulmonary bronchus, the deformation of the intrapulmonary bronchus will affect the deformation of the lung. Therefore, after the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus are obtained, the deformation information of the intrapulmonary bronchus can be combined with the deformation information of the lung surface to correct the lung deformation information, so that more accurate lung deformation information is obtained. The embodiments of the present disclosure do not limit the correction method, which can be set according to actual conditions.

[0124] In step 204, the enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result.

[0125] After the lung deformation information is determined, the enhanced data is transformed using the lung deformation information, so that the target registration result of registering the enhanced data to the plain scan data is obtained. The transformation can include at least one of translation and rotation.

[0126] In the lung image registration method, enhanced data and plain scan data of a lung of a target object are obtained; registration is performed on the enhanced data and the plain scan data to obtain deformation information of a lung surface and deformation information of a trachea in the lung; lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the trachea in the lung; and the enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result. By using the influence of the deformation of the trachea in the lung on the deformation of the lung, more accurate lung deformation information can be determined, and the enhanced data is transformed according to the lung deformation information, so that the registration effect can be improved, thereby meeting the high accuracy requirement of actual interventional surgery.

[0127] In one embodiment, as shown in Figure 3 An implementation manner for registering enhanced data and plain scan data to obtain deformation information of a lung surface and deformation information of a trachea in the lung, and determining lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung is provided. The embodiment of the present disclosure can include the following steps:

[0128] In step 301, enhanced data and plain scan data of a lung of a target object are obtained.

[0129] In step 302, mask extraction is performed on the enhanced data and the plain scan data respectively to obtain enhanced data masks of lung parenchyma and a trachea in the lung and plain scan data masks.

[0130] The terminal performs mask extraction on the enhanced data, and can obtain enhanced data masks of lung parenchyma and a trachea in the lung respectively. The terminal performs mask extraction on the plain scan data, and can obtain enhanced data masks of lung parenchyma and plain scan data masks of a trachea in the lung respectively.

[0131] In actual application, mask extraction can be automatically performed by using a deep learning algorithm or other algorithms, or can be performed by manual delineation. The embodiment of the present disclosure does not limit the mask extraction manner.

[0132] In step 303, registration is performed according to the enhanced data masks of lung parenchyma and the plain scan data masks to obtain deformation information of a lung surface.

[0133] After the masks are extracted, rigid body registration can be performed on the enhanced data masks of lung parenchyma and the plain scan data masks, and then surface elasticity registration is performed to obtain deformation information of a lung surface. The deformation information of the lung surface includes position change information of each point of the lung surface before and after registration.

[0134] In one embodiment, the registration can include the following steps:

[0135] Step one, respectively, the enhanced data mask and plain scan data mask of lung parenchyma are subjected to surface reconstruction processing, and the enhanced data mesh image and the plain scan data mesh image of lung surface are generated. Wherein, the generated mesh image is as shown in Figure 4a

[0136] In practical application, MeshLab can be used for surface reconstruction processing. For example, the enhanced mask data of lung parenchyma is input into MeshLab, and the enhanced data mesh image of lung surface is generated by using the pre-set surface reconstruction algorithm in MeshLab. The surface processing mode is not limited in the embodiments of the present disclosure.

[0137] Step two, the enhanced data mesh image and the plain scan data mesh image of lung surface are subjected to rigid body registration to obtain the rigid body registration relationship of lung surface. Wherein, the rigid body registration relationship can be expressed by rigid body transformation matrix.

[0138] Step three, the enhanced data mesh image of lung surface is transformed by using the rigid body registration relationship of lung surface, and the enhanced data transformed image of lung surface is obtained. Wherein, the transformation can include at least one of translation and rotation.

[0139] Step four, the enhanced data transformed image of lung surface and the plain scan data mesh image of lung surface are subjected to elastic registration to obtain the deformation information of lung surface.

[0140] Step 304, the deformation information of the intrapulmonary airway is obtained by registration according to the enhanced data mask and the plain scan data mask of the intrapulmonary airway.

[0141] After the mask is extracted, the enhanced data mask and the plain scan data mask of the intrapulmonary airway can be subjected to rigid body registration first, and then subjected to elastic registration to obtain the deformation information of the intrapulmonary airway. Wherein, the deformation information of the intrapulmonary airway includes the position change information of each point on the surface of the intrapulmonary airway before and after registration.

[0142] In one of the embodiments, the registration process can include: respectively, the enhanced data mask and the plain scan data mask of the intrapulmonary airway are subjected to surface reconstruction processing, and the enhanced data mesh image and the plain scan data mesh image of the intrapulmonary airway are generated; the enhanced data mesh image and the plain scan data mesh image of the intrapulmonary airway are subjected to rigid body registration to obtain the rigid body registration relationship of the intrapulmonary airway; the enhanced data mesh image of the intrapulmonary airway is transformed by using the rigid body registration relationship of the intrapulmonary airway, and the enhanced data transformed image of the intrapulmonary airway is obtained; the enhanced data transformed image of the intrapulmonary airway and the plain scan data mesh image of the intrapulmonary airway are subjected to elastic registration to obtain the deformation information of the intrapulmonary airway, as shown in Figure 4b

[0143] ​​In one of the embodiments, the registration process can include: performing surface reconstruction 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; performing 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; generating a trachea center line enhanced data image and a trachea center line plain scan data image according to the enhanced data mask and the plain scan data mask of the trachea in the lung; transforming the trachea center line enhanced data image according to the rigid body registration relationship of the trachea in the lung to obtain an enhanced data transformed image of the trachea in the lung; and matching the enhanced data transformed image of the trachea in the lung and the trachea center line plain scan data image to obtain deformation information of the trachea in the lung.

[0144] The matching of the enhanced data transformed image of the trachea in the lung and the trachea center line plain scan data image can include: matching each branch or branch bifurcation point of the trachea center line according to a preset algorithm, such as shown in the following table. Figure 4c The preset algorithm can include a tree matching algorithm and a deep learning algorithm. The matching manner is not limited in the embodiments of the present disclosure.

[0145] In step 305, the deformation information of the lung is determined according to the deformation information of the trachea in the lung.

[0146] After the deformation information of the trachea in the lung is determined, the terminal can take the deformation information of the trachea in the lung as the deformation information of the lung.

[0147] Alternatively, the terminal can first perform nearest point matching on the trachea in the lung and the lung parenchyma, find a pair of nodes matched with each other between the lung parenchyma and the trachea in the lung, and take the deformation information of the node of the trachea in the lung as the deformation information of the node of the lung parenchyma, so as to obtain the deformation information of the lung.

[0148] In actual application, other ways can also be used to determine the deformation information of the lung, which is not limited in the embodiments of the present disclosure.

[0149] In step 306, the lung deformation information is determined according to the deformation information of the lung and the deformation information of the lung surface.

[0150] After the deformation information of the lung and the deformation information of the lung surface are determined, the lung deformation information can be solved by using a finite element model. Specifically, a lung finite element model is established according to the enhanced data mask of the lung parenchyma; the lung finite element model is solved according to the deformation information of the lung and the deformation information of the lung surface to obtain a first node deformation relationship corresponding to the lung finite element model; and interpolation processing is performed according to the first node deformation relationship to obtain the lung deformation information.

[0151] In practical applications, TetGen (an open-source finite element meshing software) can be used to establish a lung finite element model. 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 a boundary for establishing the lung finite element model.

[0152] The finite element model can be solved by using FeBio (a biomechanical simulation software). The established lung finite element model is imported into FeBio, material properties are set, and the deformation information inside the lung and the deformation information on the surface of the lung are used as constraint conditions for finite element solving. The solving process is as shown in Figure 4d The node deformation relationship obtained by solving is as shown in Figure 4e The cross section of the node deformation relationship is as shown in Figure 4f

[0153] In step 307, the enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result.

[0154] In the above embodiment, the enhanced data and the plain scan data of the lung of a target object are first obtained. The enhanced data mask and the plain scan data mask of the lung parenchyma and the intrapulmonary bronchus are obtained by performing mask extraction on the enhanced data and the plain scan data, respectively. Then, the deformation information of the lung surface is obtained by registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma, and the deformation information of the intrapulmonary bronchus is obtained by registration according to the enhanced data mask and the plain scan data mask of the intrapulmonary bronchus. Next, the deformation information inside the lung is determined according to the deformation information of the intrapulmonary bronchus, and the lung deformation information is determined according to the deformation information inside the lung and the deformation information on the surface of the lung. Finally, the enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result. In the present embodiment, the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus are obtained by rigid registration and surface elasticity registration, respectively. Then, the influence of the intrapulmonary bronchus on the deformation inside the lung is used to obtain more accurate lung deformation information. The registration method of the prior art often ignores the influence of the intrapulmonary bronchus and does not correct the deformation inside the lung by using the deformation of the intrapulmonary bronchus. Therefore, compared with the prior art, the present embodiment can improve the registration effect, thereby meeting the demand for high accuracy in actual interventional surgery.

[0155] In one embodiment, as shown in Figure 5 An implementation manner 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 intrapulmonary bronchus, and determining the lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus is also provided. The present embodiment can include the following steps:

[0156] In step 401, the enhanced data and the plain scan data of the lung of a target object are obtained.

[0157] ​Step 402, respectively, mask extraction is performed on the enhanced data and the plain scan data, to obtain the enhanced data mask of the lung parenchyma and the intrapulmonary air tube and the plain scan data mask.

[0158] The terminal performs mask extraction on the enhanced data, and the obtained enhanced data mask includes both the lung parenchyma and the intrapulmonary air tube, as shown in FIG. 6a. Figure 6a The terminal performs mask extraction on the plain scan data, and the obtained plain scan data mask includes both the lung parenchyma and the intrapulmonary air tube. The mask extraction manner can refer to the above embodiment, and the embodiment of the present disclosure is not limited thereto.

[0159] Step 403, registration is performed according to the enhanced data mask of the lung parenchyma and the intrapulmonary air tube and the plain scan data mask, to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary air tube.

[0160] The terminal can first perform rigid body registration on the extracted enhanced data mask and the plain scan data mask of the lung parenchyma and the intrapulmonary air tube, and then perform surface elasticity registration, to obtain the deformation information of the lung surface and the intrapulmonary air tube.

[0161] In one of the embodiments, the following steps can be included:

[0162] Step one, surface reconstruction is performed on the enhanced data mask and the plain scan data mask of the lung parenchyma and the intrapulmonary air tube, respectively, to generate the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the intrapulmonary air tube. As shown in FIG. 6b, the surface of the intrapulmonary air tube is taken as the inner surface of the lung. Figure 6b

[0163] Step two, rigid body registration is performed on the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the intrapulmonary air tube, to obtain the rigid body registration relationship of the lung surface. The rigid body registration relationship can be expressed by a rigid body transformation matrix.

[0164] Step three, the enhanced data mesh image of the lung parenchyma and the intrapulmonary air tube is transformed by using the rigid body registration relationship of the lung surface, to obtain the enhanced data transformed image of the lung parenchyma and the intrapulmonary air tube. The transformation includes at least one of translation and rotation.

[0165] Step four, elasticity registration is performed on the enhanced data transformed image of the lung parenchyma and the intrapulmonary air tube and the plain scan data mesh image of the lung parenchyma and the intrapulmonary air tube, to obtain the deformation information of the lung surface and the intrapulmonary air tube. As shown in FIG. 6c before the elasticity registration, and as shown in FIG. 6d after the elasticity registration, the black color is the floating image (the enhanced data transformed image of the lung parenchyma and the intrapulmonary air tube), and the white color is the reference image (the plain scan data mesh image of the lung parenchyma and the intrapulmonary air tube). Figure 6c

[0166] Step 404, the lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the intrapulmonary air tube.​​

[0167] After determining the deformation information inside and on the surface of the lung, the lung deformation information can be solved using a finite element model. Specifically, a finite element model of the lung is established based on enhanced data masks of the lung parenchyma and the trachea within the lung; the finite element model of the lung is solved based on the deformation information of the lung surface and the trachea within the lung to obtain the deformation relationship of the second node corresponding to the lung finite element model; interpolation is performed based on the deformation relationship of the second node to obtain the deformation relationship of the lung.

[0168] The process of solving the lung finite element problem can be referred to in the above embodiments, and will not be repeated here.

[0169] Step 405: Based on lung deformation information, the enhanced data is registered to the plain scan data to obtain the target registration result.

[0170] In the above embodiments, enhanced and plain scan data of the lungs of the target object are first acquired; then, masks are extracted from the enhanced and plain scan data respectively to obtain enhanced data masks and plain scan data masks of the lung parenchyma and intrapulmonary trachea; subsequently, the enhanced data masks and plain scan data masks of the lung parenchyma and intrapulmonary trachea are registered to obtain deformation information of the lung surface and deformation information of the intrapulmonary trachea, and lung deformation information is determined based on the deformation information of the lung surface and the intrapulmonary trachea; finally, the enhanced data is registered to the plain scan data based on the lung deformation information to obtain the target registration result. This embodiment of the present disclosure obtains relatively accurate deformation information of the lung surface and intrapulmonary trachea through rigid body registration and surface elastic registration. Furthermore, when determining the lung deformation information, the deformation of the lung surface and the deformation of the intrapulmonary trachea are considered simultaneously. Therefore, the obtained lung deformation information is relatively accurate. Using this lung deformation information to register the enhanced and plain scan data can also obtain a relatively accurate target registration result, thereby improving the registration effect.

[0171] In one embodiment, such as Figure 7 As shown, a method is also provided for registering enhanced data and plain scan data to obtain deformation information of the lung surface and the trachea within the lung, and for determining lung deformation information based on the deformation information of the lung surface and the trachea within the lung. Embodiments of this disclosure may include the following steps:

[0172] Step 501: Obtain enhanced and plain scan data of the lungs of the target object.

[0173] Step 502: Perform rigid body registration of voxels on the enhanced data and plain scan data to obtain the rigid body registration relationship of the lung surface.

[0174] The terminal performs rigid body registration of voxels on the enhanced data and plain scan data to obtain the rigid body registration relationship of the lung surface. The rigid body registration relationship can be represented by a rigid body transformation matrix.

[0175] In step 503, the enhanced data is transformed by using the rigid body registration relationship of the lung surface to obtain transformed data.

[0176] The terminal transforms the enhanced data by using the rigid body transformation matrix to obtain transformed data corresponding to the enhanced data. The transformation includes at least one of translation and rotation.

[0177] In step 504, the transformed data and the plain scan data are elastically registered in voxels to obtain deformation information of the lung surface and deformation information of the air tube in the lung.

[0178] In step 505, the lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the air tube in the lung.

[0179] After the deformation information inside the lung and the deformation information of the lung surface are determined, the lung deformation information can be solved by using a finite element model. Specifically, the lung deformation information can be obtained by: 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 air tube in the lung to obtain a third node deformation relationship corresponding to the lung finite element model; and performing interpolation processing according to the third node deformation relationship to obtain the lung deformation relationship.

[0180] The establishment of the lung finite element model and the solving process of the finite element can refer to the above embodiments, and will not be described here again.

[0181] In step 506, the enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result.

[0182] In the above embodiments, the enhanced data and the plain scan data of the lung of the target object are first obtained; then the enhanced data and the plain scan data are rigidly registered in voxels to obtain a rigid body registration relationship of the lung surface; then the enhanced data is transformed by using the rigid body registration relationship of the lung surface to obtain transformed data, and the transformed data and the plain scan data are elastically registered in voxels to obtain deformation information of the lung surface and deformation information of the air tube in the lung; then the lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the air tube in the lung; and finally, the enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result. The deformation information of the lung surface and the deformation information of the air tube in the lung obtained by the rigid body registration and the surface elastic registration are relatively accurate; and the lung deformation information obtained by simultaneously considering the deformation of the lung surface and the deformation of the air tube in the lung is relatively accurate. In the prior art, the deformation of the air tube in the lung is not considered, and the lung deformation information is used to register the enhanced data and the plain scan data in the present embodiment, so that a relatively accurate target registration result can be obtained, thereby improving the registration effect.

[0183] In one embodiment, the registration of the enhanced data to the plain scan data based on the lung deformation information to obtain the target registration result further comprises: sequentially transforming the enhanced data by using the pre-obtained rigid registration relationship of the lung surface and the lung deformation information to obtain the target registration result of the registration of the enhanced data to the plain scan data.

[0184] In the rigid registration, the rigid registration relationship of the lung surface can be obtained. In actual application, the enhanced data can be transformed once by using the rigid 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 taken as the target registration result of the registration of the enhanced data to the plain scan data.

[0185] In the above embodiment, the enhanced data is sequentially transformed by using the pre-obtained rigid registration relationship of the lung surface and the lung deformation information to obtain the target registration result of the registration of the enhanced data to the plain scan data. According to the embodiment of the present disclosure, the lung surface is coarsely registered by using the rigid registration relationship, and then finely registered by using the lung deformation relationship, which can effectively improve the registration effect, thereby meeting the requirement of high accuracy in actual interventional surgery.

[0186] It should be understood that, although Figures 2 to 7 the steps in the flowchart of FIG. 1 are shown in sequence according to the arrows, these steps are not necessarily executed in sequence according to the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, Figures 2 to 7 at least part of the steps in the flowchart of FIG. 1 can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0187] In one embodiment, as shown in FIG. 1, Figure 8 a lung image registration apparatus is provided, comprising:

[0188] The data acquisition module 601 is configured to acquire enhanced data and plain scan data of a lung of a target object.

[0189] The first deformation determination module 602 is configured to register the enhanced data and the plain scan data to obtain deformation information of a lung surface and deformation information of an intrapulmonary airway.

[0190] The second deformation determination module 603 is configured to determine lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary airway.

[0191] The registration module 604 is configured to register the enhanced data to the plain scan data based on the lung deformation information, to obtain a target registration result.

[0192] In one of the embodiments, the first deformation determination module 602 includes:

[0193] The first mask extraction sub-module is 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 lung parenchyma and intrapulmonary trachea.

[0194] The lung surface deformation determination sub-module is configured to determine the deformation information of the lung surface according to the enhanced data mask and the plain scan data mask of the lung parenchyma.

[0195] The trachea deformation determination sub-module is configured to determine the deformation information of the intrapulmonary trachea according to the enhanced data mask and the plain scan data mask of the intrapulmonary trachea.

[0196] In one of the embodiments, 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; perform transformation on the enhanced data mesh image of the lung surface by using the rigid body registration relationship of the lung surface, to obtain an enhanced data transformed image of the lung surface; and 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.

[0197] In one of the embodiments, 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 intrapulmonary trachea respectively, to generate an enhanced data mesh image and a plain scan data mesh image of the intrapulmonary trachea; perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the intrapulmonary trachea to obtain a rigid body registration relationship of the intrapulmonary trachea; perform transformation on the enhanced data mesh image of the intrapulmonary trachea by using the rigid body registration relationship of the intrapulmonary trachea, to obtain an enhanced data transformed image of the intrapulmonary trachea; and perform elastic registration on the enhanced data transformed image of the intrapulmonary trachea and the plain scan data mesh image of the intrapulmonary trachea, to obtain the deformation information of the intrapulmonary trachea.

[0198] In one of the embodiments, the airway deformation determination submodule is specifically configured to perform surface reconstruction processing on the enhanced data mask and the plain scan data mask of the airway in the lung respectively to generate an enhanced data mesh image and a plain scan data mesh image of the airway in the lung; perform rigid body registration on the enhanced data mesh image and the plain scan data mesh image of the airway in the lung to obtain a rigid body registration relationship of the airway in the lung; generate an airway center line enhanced data image and an airway center line plain scan data image according to the enhanced data mask and the plain scan data mask of the airway in the lung; transform the airway center line enhanced data image by using the rigid body registration relationship of the airway in the lung to obtain an enhanced data transformed image of the airway in the lung; and perform matching on the enhanced data transformed image of the airway in the lung and the airway center line plain scan data image to obtain the deformation information of the airway in the lung.

[0199] In one of the embodiments, the second deformation determination module 603 includes:

[0200] The internal lung deformation determination submodule is configured to determine the deformation information of the internal lung according to the deformation information of the airway in the lung.

[0201] The lung deformation determination submodule is configured to determine the lung deformation information according to the deformation information of the internal lung and the deformation information of the lung surface.

[0202] In one of the embodiments, the lung deformation determination submodule is specifically configured to establish a lung finite element model according to the enhanced data mask of the lung parenchyma; perform solving on the lung finite element model according to the deformation information of the internal lung and the deformation information of the lung surface to obtain a first node deformation relationship corresponding to the lung finite element model; and perform interpolation processing according to the first node deformation relationship to obtain the lung deformation information.

[0203] In one of the embodiments, the first deformation determination module 601 includes:

[0204] The second mask extraction submodule is 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 airway in the lung.

[0205] The lung and airway deformation determination submodule is configured to perform registration according to the enhanced data mask and the plain scan data mask of the lung parenchyma and the airway in the lung to obtain the deformation information of the lung surface and the deformation information of the airway in the lung.

[0206] In one of the embodiments, the lung and airway deformation determination submodule is specifically configured to perform surface reconstruction on the enhanced data mask and the plain scan data mask of the lung parenchyma and the airway in the lung respectively to generate an enhanced data mesh image and a plain scan data mesh image of the lung parenchyma and the airway in the lung; perform rigid registration on the enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the airway in the lung to obtain a rigid registration relationship of the lung surface; perform transformation on the enhanced data mesh image of the lung parenchyma and the airway in the lung by using the rigid registration relationship of the lung surface to obtain an enhanced data transformed image of the lung parenchyma and the airway in the lung; and perform elastic registration on the enhanced data transformed image of the lung parenchyma and the airway in the lung and the plain scan data mesh image of the lung parenchyma and the airway in the lung to obtain the deformation information of the lung surface and the deformation information of the airway in the lung.

[0207] In one of the embodiments, the 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 airway in the lung; solve the lung finite element model according to the deformation information of the lung surface and the deformation information of the airway in the lung to obtain a second node deformation relationship corresponding to the lung finite element model; and perform interpolation processing according to the second node deformation relationship to obtain the deformation relationship of the lung.

[0208] In one of the embodiments, the first deformation determination module 601 is specifically configured to perform rigid registration on voxels of the enhanced data and the plain scan data to obtain a rigid registration relationship of the lung surface; perform transformation on the enhanced data by using the rigid registration relationship of the lung surface to obtain transformed data; and perform elastic registration on voxels of the transformed data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the airway in the lung.

[0209] In one of the embodiments, the 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 airway in the lung to obtain a third node deformation relationship corresponding to the lung finite element model; and perform interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lung.

[0210] In one of the embodiments, the registration module 604 is specifically configured to perform transformation on the enhanced data in sequence 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.

[0211] The specific limitations of the lung image registration device can refer to the limitations of the lung image registration method described above, which will not be repeated here. Each module in the above lung image registration device can be realized by software, hardware and their combination. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor calls and executes the operations of the above modules.

[0212] In one embodiment, a computer device, which can be a terminal, is provided, and an internal structure diagram of the computer device can be as shown in Figure 9 The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. 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 operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved by WIFI, operator network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement 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 overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0213] Those skilled in the art can understand that Figure 9 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0214] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0215] obtaining enhanced data and plain scan data of the lung of the target object;

[0216] registering the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the intrapulmonary bronchus;

[0217] determining lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus;

[0218] The enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result.

[0219] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0220] Mask extraction is respectively performed on the enhanced data and the plain scan data to obtain an enhanced data mask and a plain scan data mask of lung parenchyma and intrapulmonary bronchus;

[0221] Registration is performed according to the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain deformation information of a lung surface;

[0222] Registration is performed according to the enhanced data mask and the plain scan data mask of the intrapulmonary bronchus to obtain deformation information of the intrapulmonary bronchus.

[0223] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0224] Surface reconstruction processing is respectively performed on the enhanced data mask and the plain scan data mask of the lung parenchyma to generate an enhanced data mesh image and a plain scan data mesh image of the lung surface;

[0225] Rigid body registration is performed 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;

[0226] The enhanced data mesh image of the lung surface is transformed using the rigid body registration relationship of the lung surface to obtain an enhanced data transformed image of the lung surface;

[0227] Elastic registration is performed 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.

[0228] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0229] Surface reconstruction processing is respectively performed on the enhanced data mask and the plain scan data mask of the intrapulmonary bronchus to generate an enhanced data mesh image and a plain scan data mesh image of the intrapulmonary bronchus;

[0230] Rigid body registration is performed on the enhanced data mesh image and the plain scan data mesh image of the intrapulmonary bronchus to obtain a rigid body registration relationship of the intrapulmonary bronchus;

[0231] The enhanced data mesh image of the intrapulmonary bronchus is transformed using the rigid body registration relationship of the intrapulmonary bronchus to obtain an enhanced data transformed image of the intrapulmonary bronchus;

[0232] Elastic registration is performed on the enhanced data transformed image of the intrapulmonary bronchus and the plain scan data mesh image of the intrapulmonary bronchus to obtain the deformation information of the intrapulmonary bronchus.

[0233] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0234] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mesh image and a plain scan data mesh image of the intrapulmonary trachea;

[0235] The enhanced data mesh image and the plain scan data mesh image of the intrapulmonary trachea are subjected to rigid body registration to obtain a rigid body registration relationship of the intrapulmonary trachea;

[0236] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0237] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0238] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0239] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0240] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0241] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0242] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0243] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0244] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0245] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0246] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0247] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0248] The enhanced data mask and the plain scan data mask of the intrapulmonary trachea are respectively subjected to surface reconstruction processing to generate an enhanced data mask and a plain scan data mask of the intrapulmonary trachea;

[0249] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0250] The enhanced data mask and the plain scan data mask of the lung parenchyma and the intrapulmonary bronchus are respectively subjected to surface reconstruction processing to generate an enhanced data mesh image and a plain scan data mesh image of the lung parenchyma and the intrapulmonary bronchus;

[0251] The enhanced data mesh image and the plain scan data mesh image of the lung parenchyma and the intrapulmonary bronchus are subjected to rigid body registration to obtain a rigid body registration relationship of the lung surface;

[0252] The enhanced data mesh image of the lung parenchyma and the intrapulmonary bronchus is transformed using the rigid body registration relationship of the lung surface to obtain an enhanced data transformed image of the lung parenchyma and the intrapulmonary bronchus;

[0253] The enhanced data transformed image of the lung parenchyma and the intrapulmonary bronchus and the plain scan data mesh image of the lung parenchyma and the intrapulmonary bronchus are subjected to elastic registration to obtain deformation information of the lung surface and deformation information of the intrapulmonary bronchus.

[0254] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0255] A lung finite element model is established according to the enhanced data mask of the lung parenchyma and the intrapulmonary bronchus;

[0256] The lung finite element model is solved according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus to obtain a second node deformation relationship corresponding to the lung finite element model;

[0257] Interpolation processing is performed according to the second node deformation relationship to obtain a deformation relationship of the lung.

[0258] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0259] The enhanced data and the plain scan data are subjected to rigid body registration of voxels to obtain a rigid body registration relationship of the lung surface;

[0260] The enhanced data is transformed using the rigid body registration relationship of the lung surface to obtain transformed data;

[0261] The transformed data and the plain scan data are subjected to elastic registration of voxels to obtain deformation information of the lung surface and deformation information of the intrapulmonary bronchus.

[0262] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0263] A lung finite element model is established according to the enhanced data;

[0264] According to the deformation information of the lung surface and the deformation information of the trachea in the lung, the lung finite element model is solved to obtain a third node deformation relationship corresponding to the lung finite element model;

[0265] According to the third node deformation relationship, interpolation processing is performed to obtain the deformation relationship of the lung.

[0266] In one embodiment, the processor also implements the following steps when executing the computer program:

[0267] The pre-obtained rigid body registration relationship of the lung surface and the lung deformation information are used to sequentially transform the enhanced data to obtain a target registration result of registering the enhanced data to the plain scan data.

[0268] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:

[0269] Obtaining enhanced data and plain scan data of a target object lung;

[0270] Registering the enhanced data and the plain scan data to obtain deformation information of the lung surface and deformation information of the trachea in the lung;

[0271] Determining the lung deformation information according to the deformation information of the lung surface and the deformation information of the trachea in the lung;

[0272] Registering the enhanced data to the plain scan data based on the lung deformation information to obtain a target registration result.

[0273] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0274] Mask extraction is performed on the enhanced data and the plain scan data respectively to obtain enhanced data masks and plain scan data masks of the lung parenchyma and the trachea in the lung;

[0275] Registration is performed according to the enhanced data masks and the plain scan data masks of the lung parenchyma to obtain the deformation information of the lung surface;

[0276] Registration is performed according to the enhanced data masks and the plain scan data masks of the trachea in the lung to obtain the deformation information of the trachea in the lung.

[0277] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0278] Surface reconstruction processing is performed on the enhanced data masks and the plain scan data masks of the lung parenchyma respectively to generate enhanced data mesh images and plain scan data mesh images of the lung surface;

[0279] Rigid body registration is performed on the enhanced data mesh images and the plain scan data mesh images of the lung surface to obtain a rigid body registration relationship of the lung surface;

[0280] transform the enhanced data mesh image of the lung surface using the rigid body registration relationship of the lung surface to obtain an enhanced data transformed image of the lung surface;

[0281] perform elastic registration on the enhanced data transformed image of the lung surface and the mesh image of the lung surface in the plain scan to obtain deformation information of the lung surface.

[0282] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0283] 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;

[0284] 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;

[0285] transform the enhanced data mesh image of the trachea in the lung using the rigid body registration relationship of the trachea in the lung to obtain an enhanced data transformed image of the trachea in the lung;

[0286] perform elastic registration on the enhanced data transformed image of the trachea in the lung and the mesh image of the trachea in the lung in the plain scan to obtain deformation information of the trachea in the lung.

[0287] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0288] 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;

[0289] 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;

[0290] 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;

[0291] transform the trachea centerline enhanced data image using the rigid body registration relationship of the trachea in the lung to obtain an enhanced data transformed image of the trachea in the lung;

[0292] perform matching on the enhanced data transformed image of the trachea in the lung and the trachea centerline plain scan data image to obtain deformation information of the trachea in the lung.

[0293] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0294] determine deformation information inside the lung according to the deformation information of the trachea in the lung.

[0295] determine the lung deformation information according to the deformation information of the lung interior and the deformation information of the lung surface.

[0296] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0297] establish a lung finite element model according to the lung parenchyma enhanced data mask;

[0298] solve the lung finite element model according to the deformation information of the lung interior and the deformation information of the lung surface to obtain a first node deformation relationship corresponding to the lung finite element model;

[0299] perform interpolation processing according to the first node deformation relationship to obtain the lung deformation information.

[0300] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0301] respectively perform mask extraction on the enhanced data and the plain scan data to obtain lung parenchyma and intrapulmonary bronchus enhanced data masks and plain scan data masks;

[0302] perform registration according to the lung parenchyma and intrapulmonary bronchus enhanced data masks and plain scan data masks to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus.

[0303] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0304] respectively perform surface reconstruction processing on the lung parenchyma and intrapulmonary bronchus enhanced data masks and plain scan data masks to generate lung parenchyma and intrapulmonary bronchus enhanced data mesh images and plain scan data mesh images;

[0305] perform rigid body registration on the lung parenchyma and intrapulmonary bronchus enhanced data mesh images and plain scan data mesh images to obtain a rigid body registration relationship of the lung surface;

[0306] transform the lung parenchyma and intrapulmonary bronchus enhanced data mesh images using the rigid body registration relationship of the lung surface to obtain lung parenchyma and intrapulmonary bronchus enhanced data transformed images;

[0307] perform elastic registration on the lung parenchyma and intrapulmonary bronchus enhanced data transformed images and the lung parenchyma and intrapulmonary bronchus plain scan data mesh images to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus.

[0308] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0309] establish a lung finite element model according to the lung parenchyma and intrapulmonary bronchus enhanced data mask;

[0310] solving the lung finite element model according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus to obtain a second node deformation relationship corresponding to the lung finite element model;

[0311] performing interpolation processing according to the second node deformation relationship to obtain the deformation relationship of the lung.

[0312] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0313] 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;

[0314] transforming the enhanced data using the rigid body registration relationship of the lung surface to obtain transformed data;

[0315] 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 intrapulmonary bronchus.

[0316] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0317] establishing a lung finite element model according to the enhanced data;

[0318] solving the lung finite element model according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus to obtain a third node deformation relationship corresponding to the lung finite element model;

[0319] performing interpolation processing according to the third node deformation relationship to obtain the deformation relationship of the lung.

[0320] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0321] transforming the enhanced data using the pre-obtained rigid body registration relationship of the lung surface and the lung deformation information in sequence to obtain a target registration result of registering the enhanced data to the plain scan data.

[0322] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0323] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of each technical feature in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0324] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within 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 by, The method comprises: obtaining enhanced data and plain scan data of a lung of a target object; mask extraction is performed on the enhanced data and the plain scan data respectively to obtain enhanced data mask and plain scan data mask of lung parenchyma and intrapulmonary bronchus; registration is performed according to the enhanced data mask and the plain scan data mask of the lung parenchyma to obtain deformation information of the lung surface; surface reconstruction is performed on the enhanced data mask and the plain scan data mask of the intrapulmonary bronchus respectively to generate enhanced data mesh image and plain scan data mesh image of the intrapulmonary bronchus; rigid body registration is performed on the enhanced data mesh image and the plain scan data mesh image of the intrapulmonary bronchus to obtain rigid body registration relationship of the intrapulmonary bronchus; bronchus center line enhanced data image and bronchus center line plain scan data image are generated according to the enhanced data mask and the plain scan data mask of the intrapulmonary bronchus; the bronchus center line enhanced data image is transformed according to the rigid body registration relationship of the intrapulmonary bronchus to obtain enhanced data transformed image of the intrapulmonary bronchus; matching is performed on the enhanced data transformed image of the intrapulmonary bronchus and the bronchus center line plain scan data image to obtain deformation information of the intrapulmonary bronchus; lung deformation information is determined according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus; the enhanced data is registered to the plain scan data based on the lung deformation information to obtain a target registration result.

2. The method of claim 1, wherein, The 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 comprises: surface reconstruction is performed on the enhanced data mask and the plain scan data mask of the lung parenchyma respectively to generate enhanced data mesh image and plain scan data mesh image of the lung surface; rigid body registration is performed on the enhanced data mesh image and the plain scan data mesh image of the lung surface to obtain rigid body registration relationship of the lung surface; the enhanced data mesh image of the lung surface is transformed according to the rigid body registration relationship of the lung surface to obtain enhanced data transformed image of the lung surface; elastic registration is performed 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.

3. The method of claim 1, wherein, The registration according to the enhanced data mask and the plain scan data mask of the intrapulmonary bronchus to obtain the deformation information of the intrapulmonary bronchus comprises: surface reconstruction is performed on the enhanced data mask and the plain scan data mask of the intrapulmonary bronchus respectively to generate enhanced data mesh image and plain scan data mesh image of the intrapulmonary bronchus; rigid body registration is performed on the enhanced data mesh image and the plain scan data mesh image of the intrapulmonary bronchus to obtain rigid body registration relationship of the intrapulmonary bronchus; the enhanced data mesh image of the intrapulmonary bronchus is transformed according to the rigid body registration relationship of the intrapulmonary bronchus to obtain enhanced data transformed image of the intrapulmonary bronchus; elastic registration is performed on the enhanced data transformed image of the intrapulmonary bronchus and the plain scan data mesh image of the intrapulmonary bronchus to obtain the deformation information of the intrapulmonary bronchus.

4. The method of claim 1, wherein, The determination of the lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary bronchus comprises: the deformation information of the intrapulmonary bronchus is determined according to the deformation information of the intrapulmonary bronchus. Determine the lung deformation information according to the deformation information of the lung interior and the deformation information of the lung surface.

5. The method of claim 4, wherein, The determination of the lung deformation information according to the deformation information of the lung interior and the deformation information of the lung surface comprises: Establish a lung finite element model according to the lung parenchyma enhancement data mask; Solve the lung finite element model according to the deformation information of the lung interior and the deformation information of the lung surface to obtain a 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.

6. The method of claim 1, wherein, The registration of the enhancement data and the plain scan data to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary trachea comprises: Mask extraction is performed on the enhancement data and the plain scan data respectively to obtain the lung parenchyma and intrapulmonary trachea enhancement data mask and plain scan data mask; Registration is performed on the lung parenchyma and intrapulmonary trachea enhancement data mask and plain scan data mask to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary trachea.

7. The method of claim 6, wherein, The registration of the lung parenchyma and intrapulmonary trachea enhancement data mask and plain scan data mask to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary trachea comprises: Surface reconstruction processing is performed on the lung parenchyma and intrapulmonary trachea enhancement data mask and plain scan data mask respectively to generate the lung parenchyma and intrapulmonary trachea enhancement data mesh image and plain scan data mesh image; Rigid body registration is performed on the lung parenchyma and intrapulmonary trachea enhancement data mesh image and plain scan data mesh image to obtain a rigid body registration relationship of the lung surface; The lung parenchyma and intrapulmonary trachea enhancement data mesh image is transformed using the rigid body registration relationship of the lung surface to obtain an enhancement data transformed image of the lung parenchyma and intrapulmonary trachea; Elastic registration is performed on the enhancement data transformed image of the lung parenchyma and intrapulmonary trachea and the plain scan data mesh image of the lung parenchyma and intrapulmonary trachea to obtain the deformation information of the lung surface and the deformation information of the intrapulmonary trachea.

8. The method of claim 7, wherein, The determination of the lung deformation information according to the deformation information of the lung surface and the deformation information of the intrapulmonary trachea comprises: Establish a lung finite element model according to the lung parenchyma enhancement data mask; Solve the lung finite element model according to the deformation information of the lung surface and the deformation information of the intrapulmonary trachea to obtain a second node deformation relationship corresponding to the lung finite element model; Perform interpolation processing according to the second node deformation relationship to obtain the lung deformation relationship. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the method in any one of claims 1 to 8.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 8.

Images