CN115526929A

CN115526929A - Image-based registration method and device

Info

Publication number: CN115526929A
Application number: CN202211196844.9A
Authority: CN
Inventors: 不公告发明人
Original assignee: Suzhou Xiaowei Changxing Robot Co ltd
Current assignee: Suzhou Xiaowei Changxing Robot Co ltd
Priority date: 2022-09-28
Filing date: 2022-09-28
Publication date: 2022-12-27

Abstract

The application relates to an image-based registration method, apparatus, computer device, storage medium and computer program product. The method comprises the following steps: acquiring a three-dimensional model constructed for a target object; acquiring a first two-dimensional medical imaging and a second two-dimensional medical imaging of a target object, wherein the posture of the two-dimensional imaging equipment during imaging to obtain the first two-dimensional medical imaging is orthogonal to the posture of the two-dimensional imaging equipment during imaging to obtain the second two-dimensional medical imaging; acquiring a first conversion matrix between a digital reconstruction two-dimensional image coordinate system and a coordinate system of two-dimensional imaging equipment; acquiring a planning pose of a target object in a coordinate system of the two-dimensional imaging equipment based on an initial pose of the target object in the three-dimensional model and a first conversion matrix; and converting the planned pose into a mechanical arm coordinate system to obtain an expected pose of the target object in the mechanical arm coordinate system. By adopting the method, the precision of the mechanical arm operation can be improved.

Description

Image-based registration method and device

Technical Field

The present application relates to the field of medical device technologies, and in particular, to an image-based registration method and apparatus.

Background

In the operation execution process, the coordinate space of the surgical robot needs to be associated with the coordinate space of the actual pose of the patient, and then the surgical robot is guided by the navigation system to operate in the preoperative planned operation area. The guiding method of the surgical robot generally adopts a navigation method based on optical or magnetic positioning after a target is implanted in bone tissue of a patient. However, mounting the target on the patient's bone tissue can result in additional damage to the patient's bone tissue, reducing surgical safety.

Disclosure of Invention

The application provides an image-based registration method and device capable of improving surgical safety.

In a first aspect, the application provides an image-based registration method, which is applied to a registration system comprising two-dimensional imaging equipment and a mechanical arm, wherein the two-dimensional imaging equipment is fixedly connected with the mechanical arm; the method comprises the following steps:

acquiring a three-dimensional model constructed for a target object based on a three-dimensional medical image shot before an operation;

acquiring a first two-dimensional medical imaging and a second two-dimensional medical imaging of a target object, wherein the posture of the two-dimensional imaging equipment during imaging to obtain the first two-dimensional medical imaging is orthogonal to the posture of the two-dimensional imaging equipment during imaging to obtain the second two-dimensional medical imaging;

acquiring a first conversion matrix between a coordinate system of the digital reconstruction two-dimensional image and a coordinate system of two-dimensional imaging equipment according to imaging parameters of the digital reconstruction two-dimensional image obtained by reconstructing the digital image of the three-dimensional model and respective imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging;

acquiring a planning pose of a target object in a coordinate system of the two-dimensional imaging equipment based on an initial pose of the target object in the three-dimensional model and a first conversion matrix;

and converting the planned pose into a mechanical arm coordinate system to obtain an expected pose of the target object in the mechanical arm coordinate system.

The initial pose of the target object can be converted to the mechanical arm coordinate system through the three-dimensional model constructed for the target object and the first two-dimensional medical imaging and the second two-dimensional medical imaging of the target object, so that the mechanical arm can be guided to operate in an operation area in real time, and the guiding precision of the mechanical arm can be guaranteed by correcting the images in the operation. Moreover, the two-dimensional imaging equipment and the mechanical arm are integrated equipment, so that the real-time initial pose can be converted into a mechanical arm coordinate system, the real-time pose of the target object in the mechanical arm coordinate system is obtained, and the guide precision is improved.

In one embodiment, acquiring a three-dimensional model constructed for a target object based on a three-dimensional medical image taken before an operation includes:

and sequentially carrying out interpolation processing, noise reduction processing and contrast enhancement processing on the three-dimensional medical image, and carrying out three-dimensional reconstruction on the basis of the processed three-dimensional medical image to obtain a three-dimensional model constructed for the target object.

The influence of noise on a three-dimensional reconstruction result can be reduced by carrying out noise reduction processing on the interpolated three-dimensional medical image; the contrast enhancement processing is carried out on the three-dimensional medical image after the noise reduction, so that the difference between the interested part and other parts in the three-dimensional medical image can be increased.

In one embodiment, acquiring a first transformation matrix between a coordinate system of a digitally reconstructed two-dimensional image and a coordinate system of a two-dimensional imaging device according to imaging parameters of the digitally reconstructed two-dimensional image obtained by reconstructing a digital image of a three-dimensional model and respective imaging parameters of a first two-dimensional medical imaging and a second two-dimensional medical imaging includes:

registering the digital reconstructed two-dimensional image with the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively to obtain digital reconstructed two-dimensional images which are respectively and correspondingly registered in the first two-dimensional medical imaging and the second two-dimensional medical imaging;

and determining a first conversion matrix according to the respective imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging and the respective digital reconstruction imaging parameters of the digital reconstruction two-dimensional image correspondingly registered in the first two-dimensional medical imaging and the digital reconstruction imaging parameter correspondingly registered in the second two-dimensional medical imaging.

The real-time pose of the target object in the coordinate system of the mechanical arm can be obtained by the first two-dimensional medical imaging and the second two-dimensional medical imaging which are collected in the operation and are registered with the digital reconstruction two-dimensional image, and the first conversion matrix is determined according to the registration result, so that the accuracy of the mechanical arm in operation can be improved.

In one embodiment, a two-dimensional imaging device includes a C-arm and an X-ray tube; when a first two-dimensional medical imaging is obtained through X-ray tube imaging, the C-shaped arm is in a first posture; the C-arm assumes a second pose when a second two-dimensional medical image is obtained by X-ray tube imaging.

By means of the first and second two-dimensional medical imaging, a digitally reconstructed two-dimensional image registered with the first and second two-dimensional medical imaging can be determined from the plurality of digitally reconstructed two-dimensional images, so that a first transformation matrix between a coordinate system of the digitally reconstructed two-dimensional image and a coordinate system of the two-dimensional imaging device can be determined.

In one embodiment, the registering the digitally reconstructed two-dimensional image with the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively to obtain the digitally reconstructed two-dimensional image with the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively registered correspondingly comprises:

carrying out digital image reconstruction on the three-dimensional model to obtain at least one digital reconstruction two-dimensional image;

registering the first two-dimensional medical imaging and the second two-dimensional medical imaging with the digital reconstruction two-dimensional images respectively, updating digital image reconstruction parameters and reconstructing digital images of the three-dimensional model under the condition that the corresponding registered digital reconstruction two-dimensional images are not determined by the first two-dimensional medical imaging or the second two-dimensional medical imaging, re-obtaining a plurality of digital reconstruction two-dimensional images and re-registering, repeating the updating, reconstructing and registering processes until the corresponding registered digital reconstruction two-dimensional images are determined by the first two-dimensional medical imaging and the second two-dimensional medical imaging, and obtaining the corresponding registered digital reconstruction two-dimensional images of the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively.

The image registered with the first two-dimensional medical imaging and the second two-dimensional medical imaging is determined through an image registration algorithm, and a first conversion matrix between a preoperative image coordinate system and a two-dimensional imaging equipment coordinate system can be determined, so that the real-time pose of the target object under the preoperative image coordinate system can be converted into the real-time pose under the mechanical arm coordinate system, an additional target is prevented from being installed at the target object, the safety of the target object is improved, and the recovery time of the target object is shortened.

In one embodiment, the digital image reconstruction of the three-dimensional model to obtain at least one digitally reconstructed two-dimensional image includes:

acquiring digital reconstruction imaging parameters, wherein the digital reconstruction imaging parameters comprise the position of an analog light source and the projection angle of the analog light source to the three-dimensional model;

according to the projection angle and the position, the light is emitted to the three-dimensional model through the simulation light source, and the intersection point coordinate between the light emitted by the simulation light source and the three-dimensional model when the light passes through the three-dimensional model is calculated;

obtaining a gray value obtained by performing trilinear interpolation on intersection point coordinates corresponding to each ray, and accumulating the gray value of the intersection point coordinates corresponding to each ray;

and giving the gray value accumulation result corresponding to each light ray to the intersection point between each light ray and the digital imaging plane to obtain a digital reconstruction two-dimensional image corresponding to the digital reconstruction imaging parameters.

By performing digital image reconstruction on the three-dimensional model, a plurality of digitally reconstructed two-dimensional images may be obtained, such that the digitally reconstructed two-dimensional images may be registered with the intraoperative first and second two-dimensional medical images.

In a second aspect, the present application further provides an image-based registration apparatus. The method is applied to a registration system comprising two-dimensional imaging equipment and a mechanical arm, wherein the two-dimensional imaging equipment is fixedly connected with the mechanical arm; the device comprises:

the first acquisition module is used for acquiring a three-dimensional model constructed for a target object based on a three-dimensional medical image shot before an operation;

the second acquisition module is used for acquiring a first two-dimensional medical image and a second two-dimensional medical image of the target object, and the posture of the two-dimensional imaging equipment during imaging to obtain the first two-dimensional medical image is orthogonal to the posture of the two-dimensional imaging equipment during imaging to obtain the second two-dimensional medical image;

the reconstruction module is used for acquiring a first conversion matrix between a coordinate system of the digital reconstruction two-dimensional image and a coordinate system of the two-dimensional imaging equipment according to imaging parameters of the digital reconstruction two-dimensional image obtained by reconstructing the digital image of the three-dimensional model and respective imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging;

the third acquisition module is used for acquiring the planning pose of the target object in the coordinate system of the two-dimensional imaging equipment based on the initial pose of the target object in the three-dimensional model and the first conversion matrix;

and the configuration module is used for converting the planned pose into a mechanical arm coordinate system and obtaining the expected pose of the target object in the mechanical arm coordinate system.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

acquiring a planning pose of a target object in a coordinate system of two-dimensional imaging equipment based on an initial pose and a first conversion matrix of the target object in the three-dimensional model;

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:

acquiring a first conversion matrix between a coordinate system of the digital reconstructed two-dimensional image and a coordinate system of two-dimensional imaging equipment according to imaging parameters of the digital reconstructed two-dimensional image obtained by reconstructing the digital image of the three-dimensional model and respective imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging;

The image-based registration method, the image-based registration device, the computer equipment, the storage medium and the computer program product acquire the three-dimensional model constructed for the target object through the three-dimensional medical image shot before the operation; acquiring a first two-dimensional medical imaging and a second two-dimensional medical imaging of a target object, wherein the posture of the two-dimensional imaging equipment during imaging to obtain the first two-dimensional medical imaging is orthogonal to the posture of the two-dimensional imaging equipment during imaging to obtain the second two-dimensional medical imaging; acquiring a first conversion matrix between a coordinate system of the digital reconstruction two-dimensional image and a coordinate system of two-dimensional imaging equipment according to imaging parameters of the digital reconstruction two-dimensional image obtained by reconstructing the digital image of the three-dimensional model and respective imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging; acquiring a planning pose of a target object in a coordinate system of the two-dimensional imaging equipment based on an initial pose of the target object in the three-dimensional model and a first conversion matrix; the planning pose is converted into a mechanical arm coordinate system, the expected pose of the target object in the mechanical arm coordinate system is obtained, and by adopting the method, a target does not need to be implanted at the target object, so that the safety of the target object is improved, and meanwhile, the recovery time of the target object can be shortened; and the images in the real-time acquisition operation are registered, so that the precision of the mechanical arm operation can be improved.

Drawings

FIG. 1 is a schematic flow diagram of an image-based registration method in one embodiment;

FIG. 2 is a schematic diagram of obtaining a digitally reconstructed two-dimensional image according to one embodiment;

FIG. 3 is a schematic representation of a three-dimensional reconstruction in one embodiment;

FIG. 4 is a schematic flow chart illustrating the preprocessing of CT images according to one embodiment;

FIG. 5 is a schematic view of a preoperative plan in one embodiment;

FIG. 6 is a schematic diagram of registration in one embodiment;

FIG. 7 is a schematic view of a scene in which a first X-ray image is acquired in one embodiment;

FIG. 8 is a schematic view of a scene in which a second X-ray image is acquired in one embodiment;

FIG. 9 is a schematic illustration of acquisition of knee joint X-ray imaging in one embodiment;

FIG. 10 is a schematic flow chart of image registration in one embodiment;

FIG. 11 is a schematic flow chart illustrating the acquisition of a DRR image according to one embodiment;

FIG. 12 is a flow diagram illustrating digital image reconstruction of a three-dimensional model according to one embodiment;

FIG. 13 is a schematic view of the configuration of a surgical system in one embodiment;

FIG. 14 is a block diagram of a system architecture in one embodiment;

FIG. 15 is a schematic flow chart of coordinate transformation in one embodiment;

FIG. 16 is a flow diagram of an image-based registration method in one embodiment;

FIG. 17 is a block diagram of an embodiment of an image-based registration apparatus;

FIG. 18 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The application provides an image-based registration method, which does not need to install an additional target on a target object, improves the safety of the target object and shortens the recovery time of the target object; moreover, the precision of the mechanical arm operation can be improved by using the real-time operation area image acquired in the operation through image registration and coordinate conversion; in addition, the method and the device do not need an additional calibration device, so that the cost can be reduced, and the preoperative preparation steps can be simplified.

As shown in fig. 1, an image-based registration method is provided, which is applied to a registration system including a two-dimensional imaging device and a mechanical arm, where the two-dimensional imaging device is fixedly connected to the mechanical arm. In this embodiment, the method includes the steps of:

101. acquiring a three-dimensional model constructed for a target object based on a three-dimensional medical image shot before an operation;

102. acquiring a first two-dimensional medical imaging and a second two-dimensional medical imaging of a target object, wherein the posture of the two-dimensional imaging equipment during imaging to obtain the first two-dimensional medical imaging is orthogonal to the posture of the two-dimensional imaging equipment during imaging to obtain the second two-dimensional medical imaging;

103. acquiring a first conversion matrix between a coordinate system of the digital reconstruction two-dimensional image and a coordinate system of two-dimensional imaging equipment according to imaging parameters of the digital reconstruction two-dimensional image obtained by reconstructing the digital image of the three-dimensional model and respective imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging;

104. acquiring a planning pose of a target object in a coordinate system of the two-dimensional imaging equipment based on an initial pose of the target object in the three-dimensional model and a first conversion matrix;

105. and converting the planned pose into a mechanical arm coordinate system to obtain an expected pose of the target object in the mechanical arm coordinate system.

Wherein, the three-dimensional medical image can be a CT image; the target object refers to a tissue or organ of a diseased part, such as a knee joint, determined after diagnosis by a doctor. The initial pose of the target object may be one pose or an ordered or unordered set of poses formed by multiple poses. For example, the initial pose of the target object may be a set of all poses within the surgical field determined by the surgeon, or the poses corresponding to the surgical procedure steps determined by the surgeon. The initial pose of the target object is a pose obtained within the digitally reconstructed two-dimensional image coordinate system (or the coordinate system in which the three-dimensional model is located). A two-dimensional imaging device refers to a device that photographs a target object under surgery to obtain a two-dimensional medical image.

The method comprises the steps that a fixed geometric position relation exists between two-dimensional imaging equipment and a mechanical arm, a second conversion matrix between a coordinate system of the two-dimensional imaging equipment and a coordinate system of the mechanical arm is determined, a conversion matrix between a digital reconstruction two-dimensional image coordinate system where a digital reconstruction two-dimensional image is located and the two-dimensional imaging equipment coordinate system where the two-dimensional imaging equipment is located serves as a first conversion matrix, the conversion matrix between the two-dimensional imaging equipment coordinate system and the mechanical arm coordinate system serves as a second conversion matrix, an initial pose of a target object under the digital reconstruction two-dimensional image coordinate system where the digital reconstruction two-dimensional image is located can be converted into the two-dimensional imaging equipment coordinate system where the two-dimensional imaging equipment is located through the first conversion matrix, the planning pose of the target object in the two-dimensional imaging equipment coordinate system can be converted into the mechanical arm coordinate system where the mechanical arm is located through the second conversion matrix, and the expected pose of the target object in the mechanical arm coordinate system can be obtained.

The determination process of the second conversion matrix comprises the following steps: with P _c Representing the coordinates of any point in the two-dimensional imaging device coordinate system by P _r Representing a point P in a two-dimensional imaging device coordinate system _c Coordinates in the arm coordinate system, (x) ₁ ，y ₁ ，z ₁ ) Representing the deviation of the origin of the two-dimensional imaging device coordinate system relative to the origin of the mechanical arm coordinate system in the directions of the x axis, the y axis and the z axis respectively when the mechanical arm coordinate system is taken as a reference coordinate system; when a two-dimensional imaging device coordinate system and a mechanical arm coordinate system are set, the x axis, the y axis and the z axis of the two-dimensional imaging device coordinate system and the x axis, the y axis and the z axis corresponding to the mechanical arm coordinate system are set to be the same coordinate axis direction, and only the translation transformation between the two-dimensional imaging device coordinate system and the mechanical arm coordinate system needs to be considered when the coordinate system is transformed, so that the transformation relation between the two-dimensional imaging device coordinate system and the mechanical arm coordinate system is as follows: p _r ＝D*P _c (ii) a Where D is a translation operator, expressed as:

the orthogonal posture of the two-dimensional imaging device when the two-dimensional imaging device obtains the first two-dimensional medical imaging and the orthogonal posture of the two-dimensional imaging device when the two-dimensional imaging device obtains the second two-dimensional medical imaging means that the orthogonal posture of the two-dimensional imaging device when the two-dimensional imaging device shoots the first two-dimensional medical imaging and the orthogonal posture of the two-dimensional imaging device when the two-dimensional imaging device shoots the second two-dimensional medical imaging, for example, the two-dimensional imaging device obtains the first two-dimensional medical imaging by shooting from the front side of the target object, and the two-dimensional imaging device obtains the first two-dimensional medical imaging by shooting from the side of the target object.

If the Digitally Reconstructed two-dimensional image is obtained by an X-ray imaging device, the Digitally Reconstructed two-dimensional image obtained by processing a Digital Reconstructed Radio (DRR) is also referred to as a Digitally Reconstructed radiographic image, and at this time, the imaging parameters of the Digitally Reconstructed two-dimensional image include a projection distance and a projection angle, where the projection distance refers to a distance between the X-ray source and the three-dimensional model. In one example, a schematic diagram of a digital reconstruction of a three-dimensional model to obtain a digital reconstruction of a two-dimensional image is shown in fig. 2, and according to the three-dimensional model and the imaging principle of an analog X-ray system, a digital reconstruction of a two-dimensional image is generated on an analog DRR imaging plane by changing the distance between an analog X-ray source and the three-dimensional model and the projection angle.

Specifically, three-dimensional reconstruction is performed on three-dimensional medical image data acquired by a target object before an operation to obtain a three-dimensional model of the target object, and digital image reconstruction is performed on the three-dimensional model to obtain a plurality of digital reconstructed two-dimensional images and image parameters corresponding to each digital reconstructed two-dimensional image. In the operation, two-dimensional medical images (namely, a first two-dimensional medical image and a second two-dimensional medical image) of a target object under two postures are acquired in real time through a two-dimensional imaging device, and imaging parameters corresponding to the first two-dimensional medical image and the second two-dimensional medical image are acquired respectively. And obtaining a first conversion matrix between a digital reconstruction two-dimensional image coordinate system and a two-dimensional imaging equipment coordinate system according to imaging parameters of the digital reconstruction two-dimensional image obtained by the digital image reconstruction and imaging parameters corresponding to the first two-dimensional medical imaging and the second two-dimensional medical imaging. And the transformation of the initial pose of the target object to the intraoperative two-dimensional imaging equipment coordinate system is realized through the first transformation matrix to obtain the planning pose of the target object, and the planning pose in the two-dimensional imaging equipment coordinate system is further transformed into the mechanical arm coordinate system through the second transformation matrix.

According to the method provided by the embodiment of the invention, the initial pose of the target object can be converted to the mechanical arm coordinate system through the three-dimensional model constructed for the target object and the first two-dimensional medical imaging and the second two-dimensional medical imaging of the target object, so that the mechanical arm can be guided to operate in an operation area in real time, and the guiding precision of the mechanical arm can be ensured by correcting the images in the operation. Moreover, the two-dimensional imaging equipment and the mechanical arm are integrated equipment, so that the real-time initial pose can be converted into a mechanical arm coordinate system, the real-time pose of the target object in the mechanical arm coordinate system is obtained, and the guide precision is improved.

As shown in fig. 3 and 4, in one embodiment, acquiring a three-dimensional model constructed for a target object based on a three-dimensional medical image taken before an operation includes:

The interpolation processing refers to the interpolation processing of the three-dimensional medical image according to parameters such as the visual field, the reconstruction matrix and the layer thickness, so that the three-dimensional medical image meets the isotropy.

Specifically, a three-dimensional medical image obtained by preoperative scanning of the target object is sequentially subjected to a series of preprocessing such as interpolation processing, noise reduction processing and contrast enhancement to obtain preprocessed image data, three-dimensional reconstruction is performed according to the preprocessed image data to obtain a three-dimensional model of the target object, and subsequent preoperative planning is performed based on the three-dimensional model, for example, a surgical region range is determined according to the three-dimensional model.

According to the method provided by the embodiment of the invention, the influence of noise on a three-dimensional reconstruction result can be reduced by carrying out noise reduction processing on the three-dimensional medical image after interpolation; by performing contrast enhancement processing on the three-dimensional medical image after noise reduction, the difference between the target object and other parts in the three-dimensional medical image can be increased.

With reference to the foregoing embodiments, in one embodiment, acquiring a first transformation matrix between a coordinate system of a digitally reconstructed two-dimensional image and a coordinate system of a two-dimensional imaging device according to an imaging parameter of the digitally reconstructed two-dimensional image obtained by reconstructing a digital image of a three-dimensional model and an imaging parameter of each of a first two-dimensional medical imaging and a second two-dimensional medical imaging includes:

The imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively comprise imaging distance and imaging angle; before registering the digital reconstructed two-dimensional image with the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively, image normalization processing needs to be performed on the digital reconstructed two-dimensional image, the first two-dimensional medical imaging and the second two-dimensional medical imaging. Registration refers to comparing similarity of images. If the similarity of the two images is greater than a preset threshold value, the two images are considered to be successfully registered; and if the similarity of the two images is not greater than the preset threshold, the registration of the two images is considered to be failed.

In addition, the similarity between the two images can be determined by comparing the gray information or contour information of the images. For example, the two images may be subjected to gray level histogram matching, and if the difference value between the gray level histograms of the first two-dimensional medical imaging or the second two-dimensional medical imaging and the digitally reconstructed two-dimensional image in the operation is smaller than a preset difference threshold, it may be considered that the similarity between the two images is larger than the preset threshold, and the two images are successfully registered.

In one example, using an osteotomy procedure as an example, the location of the osteotomy is determined by preoperative planning, as indicated by the line marked region in fig. 5; in the operation, the target pose of the position to be cut is converted into a mechanical arm coordinate system of the mechanical arm through image registration and pose conversion to obtain an expected pose of the position to be cut in the mechanical arm coordinate system, and the mechanical arm of the surgical robot independently or assists a doctor to finish the bone cutting operation according to the expected pose in the mechanical arm coordinate system.

Fig. 6 is a schematic registration diagram, in which the left image in fig. 6 is a pose image when the target object is subjected to CT scanning, and the right image is a pose image when two-dimensional medical imaging is acquired by a two-dimensional imaging device in an operation.

Specifically, the number of digital reconstructed two-dimensional images obtained by reconstructing the digital image of the three-dimensional model can be multiple, the similarity between the first two-dimensional medical imaging and each digital reconstructed two-dimensional image is determined, and the digital reconstructed two-dimensional image with the similarity larger than the preset similarity and the maximum similarity is used as a registration image of the first two-dimensional medical imaging; and determining the similarity between the second two-dimensional medical imaging and each digital reconstruction two-dimensional image, and taking the digital reconstruction two-dimensional image with the similarity larger than the preset similarity and the maximum similarity as a registration image of the second two-dimensional medical imaging. And determining a first conversion matrix between a digital reconstruction two-dimensional image coordinate system of the digital reconstruction two-dimensional image and a coordinate system of two-dimensional imaging equipment (namely a two-dimensional imaging equipment coordinate system) according to the imaging distance and the imaging angle between the first two-dimensional medical imaging and the second two-dimensional medical imaging and the imaging distance and the projection angle between the registration image of the first two-dimensional medical imaging and the registration image of the second two-dimensional medical imaging.

According to the method provided by the embodiment of the invention, the real-time pose of the target object in the coordinate system of the mechanical arm can be obtained by the first two-dimensional medical imaging and the second two-dimensional medical imaging which are acquired in the operation and are registered with the digital reconstruction two-dimensional image, and the first conversion matrix is determined according to the registration result, so that the accuracy of the mechanical arm in the operation process can be improved.

In combination with the above embodiments, in one embodiment, a two-dimensional imaging device includes a C-arm and an X-ray tube; when a first two-dimensional medical imaging is obtained through X-ray tube imaging, the C-shaped arm is in a first posture; the C-arm assumes a second pose when a second two-dimensional medical image is obtained by X-ray tube imaging.

The first posture is orthogonal to the second posture, and the first posture is orthogonal to the second posture, namely that an included angle between a placing angle of the C-shaped arm corresponding to the first posture and a placing angle of the C-shaped arm corresponding to the second posture is 90 degrees. For example, the placing angle of the C-arm corresponding to the first posture is parallel to the horizontal plane, the placing angle of the C-arm corresponding to the second posture is perpendicular to the horizontal plane, and the first posture is orthogonal to the second posture.

In one example, acquiring a scene image of the first two-dimensional medical imaging is shown in fig. 7, fig. 7 is a schematic diagram of image acquisition of the front side of the target object, and fig. 7 is composed of four parts, namely a C-arm X-ray machine 1, a C-arm X-ray tube 2, a C-arm imaging flat plate 3 and a target object 4, wherein the C-arm X-ray tube 2 is placed at a 0 ° position, the target object 4 is placed at a proper position and fixed, and an X-ray image of the target object is acquired as the first two-dimensional medical imaging; fig. 8 shows a scene diagram for acquiring a second two-dimensional medical image, fig. 7 is a schematic diagram of image acquisition of a side surface of a target object, and fig. 8 is composed of four parts, namely, a C-arm X-ray machine 1, a target object 2, a C-arm imaging flat plate 3, and a C-arm X-ray tube 4, wherein the C-arm X-ray tube is placed at a 90 ° position, the target object is placed at a proper position and fixed, and an X-ray image of the target object at this time is acquired as the second two-dimensional medical image.

In one example, taking a knee joint as an example, an X-ray imaging schematic diagram for acquiring a target object by respectively positioning an X-ray tube of a C-arm in a two-dimensional imaging device at 0 ° and 90 ° is shown in fig. 9; the X-ray images acquired at these two angles are used for registration with the digitally reconstructed two-dimensional image.

According to the method provided by the embodiment of the invention, through the first two-dimensional medical imaging and the second two-dimensional medical imaging, the digitally reconstructed two-dimensional image which is registered with the first two-dimensional medical imaging and the second two-dimensional medical imaging can be determined from the plurality of digitally reconstructed two-dimensional images, so that a first conversion matrix between a coordinate system of the digitally reconstructed two-dimensional image and a coordinate system of the two-dimensional imaging equipment can be determined.

With reference to the above description of the embodiments, in one embodiment, the registering the digitally reconstructed two-dimensional image with the first two-dimensional medical image and the second two-dimensional medical image respectively to obtain the digitally reconstructed two-dimensional image with the first two-dimensional medical image and the second two-dimensional medical image respectively registered correspondingly includes:

carrying out digital image reconstruction on the three-dimensional model to obtain at least one digital reconstructed two-dimensional image;

Fig. 10 is a schematic flow chart of registration of a digitally reconstructed two-dimensional image obtained by reconstructing a digital image of a three-dimensional model with a first two-dimensional medical image and a second two-dimensional medical image, respectively. The DRR parameters refer to imaging parameters of a digital reconstruction two-dimensional image, and comprise a projection distance and a projection angle; the DRR image refers to a digitally reconstructed two-dimensional image, and the X-ray image refers to a first two-dimensional medical imaging and a second two-dimensional medical imaging obtained when the two-dimensional imaging apparatus includes X-ray imaging.

Fig. 11 is a schematic flow chart of acquiring a DRR image, and the processing flow of acquiring the DRR image includes: acquiring a preoperative CT image and inputting the preoperative CT image into a processing system; performing three-dimensional reconstruction by using a preoperative CT image to obtain a three-dimensional model of a target object; performing preoperative planning based on the three-dimensional model of the target object, determining a surgical area range, and recording the pose in the planned surgical area range; and performing DRR processing based on the three-dimensional model of the target object, obtaining a plurality of virtual DRR images by changing parameters such as projection angles or projection distances of the DRRs, and recording imaging parameters of the DRR images.

Specifically, three-dimensional reconstruction is carried out by using at least one preoperative three-dimensional medical image data to obtain a three-dimensional model of a target object; performing DRR processing based on the three-dimensional model of the target object, obtaining a plurality of DRR images by changing the projection distance and the projection angle of the DRR, and recording the corresponding DRR parameters of each DRR image; acquiring a first two-dimensional medical image and a second two-dimensional medical image of a target object by using intraoperative two-dimensional imaging equipment; performing normalization processing on the DRR image, the first two-dimensional medical imaging and the second two-dimensional medical imaging, and performing similarity comparison; if the DRR image and the two-dimensional medical imaging meet the similarity judgment condition, the registration is successful, and corresponding DRR parameters are output for subsequent coordinate conversion; and if the first two-dimensional medical imaging or the second two-dimensional medical imaging does not determine the corresponding registered digital reconstruction radiological image, updating the DRR parameters, acquiring a new DRR image, and respectively registering the DRR image with the first two-dimensional medical imaging and the second two-dimensional medical imaging based on the new DRR image until the first two-dimensional medical imaging and the second two-dimensional medical imaging determine the corresponding registered digital reconstruction radiological image.

According to the method provided by the embodiment of the invention, the image registered with the first two-dimensional medical imaging and the second two-dimensional medical imaging is determined through the image registration algorithm, and the first conversion matrix between the preoperative image coordinate system and the two-dimensional imaging equipment coordinate system can be determined, so that the real-time pose of the target object under the preoperative image coordinate system can be converted into the real-time pose under the mechanical arm coordinate system, the additional target is prevented from being installed at the target object, the safety of the target object is improved, and the recovery time of the target object is shortened.

With reference to the above description of the embodiments, in one embodiment, the performing digital image reconstruction on the three-dimensional model to obtain at least one digitally reconstructed two-dimensional image includes:

In this embodiment, a light projection algorithm is used as a digital image reconstruction algorithm used in reconstructing a digital image of a three-dimensional model, and as shown in fig. 12, a schematic flow chart of reconstructing a digital image of a three-dimensional model includes a set light source, light ray tracing, linear interpolation, gray scale accumulation, and image mapping. Specifically, firstly, selecting the position of an analog light source, wherein the analog light source emits a plurality of rays, and each ray corresponds to one pixel in a digital reconstruction two-dimensional image plane; determining the projection angle and the projection distance of the simulation light source relative to the three-dimensional model; and then, calculating intersection point coordinates of the light rays emitted by the simulation light source when the light rays pass through the three-dimensional model, recording gray values of the intersection point coordinates after trilinear interpolation, accumulating the gray values of each light ray passing through the three-dimensional model and each intersection point thereof, and endowing the intersection point gray accumulation values of each light ray and the three-dimensional model with intersection points of the light rays and the DRR imaging plane to obtain the DRR image.

According to the method provided by the embodiment of the invention, the digital image reconstruction is carried out on the three-dimensional model, so that a plurality of digital reconstruction two-dimensional images can be obtained, and the digital reconstruction two-dimensional images can be registered with the first two-dimensional medical imaging and the second two-dimensional medical imaging in the operation.

Fig. 13 is a schematic structural diagram of a surgical system in an application scenario, which includes a robot arm 1, a robot arm-C arm connecting device 2, a C-arm X-ray machine 3, a C-arm X-ray tube 4, a C-arm imaging plate 5, and a target object 6.

Fig. 14 is a block diagram of a system structure in an embodiment, specifically, a target pose in a coordinate system (i.e., a coordinate system of a digitally reconstructed two-dimensional image) of a CT image is first converted into a coordinate system (i.e., a coordinate system of a two-dimensional imaging device) of an X-ray system by image registration to obtain a planning pose, and then the planning pose is converted into a coordinate system of a mechanical arm where the mechanical arm is located.

FIG. 15 is a schematic flow chart of coordinate transformation according to an embodiment, including: acquiring a preoperative CT image and inputting the preoperative CT image into a system, and then performing three-dimensional reconstruction, wherein the coordinate (or pose) of the CT image can be acquired; converting preoperative CT image coordinates (or pose) into intraoperative X-ray image coordinates (or pose) within a two-dimensional imaging device coordinate system as a result of intraoperative image to preoperative image registration; the coordinate system of the two-dimensional imaging equipment and the coordinate system of the C-shaped arm belong to the coordinate system of the same system, and the coordinate (or the pose) of the X-ray system can be directly converted into the coordinate in the coordinate system of the mechanical arm because the C-shaped arm is directly connected with the mechanical arm and the second conversion matrix between the coordinate system of the C-shaped arm where the C-shaped arm is located and the coordinate system of the mechanical arm where the mechanical arm is located is known. And finally, converting the CT image coordinate (or pose) into a mechanical arm coordinate system in which the mechanical arm is located.

In one embodiment, as shown in fig. 16, an image-based registration method includes:

1601. inputting a CT image which is acquired preoperatively and contains a target object;

1602. performing three-dimensional reconstruction by using the input CT image to obtain a three-dimensional model of the target object;

1603. performing preoperative planning based on the three-dimensional reconstruction result, determining an operative region range, and storing a preoperative planning result;

1604. performing multi-parameter DRR reconstruction on the three-dimensional reconstruction result to obtain a plurality of DRR images and recording corresponding DRR parameters;

1605. in the operation, a target is not required to be implanted into a target object, and a C-shaped arm X-ray imaging device is used for acquiring 0-degree and 90-degree X-ray images of the target object;

1606. registering an X-ray image acquired in an operation with a DRR image before the operation, and storing projection parameters of the DRR image after registration;

1607. and converting the initial coordinates (or the pose) of the target object in the preoperative image coordinate system into an intraoperative X-ray image coordinate system by using the registration result to obtain the planning coordinates (or the pose) of the target object, and further converting the planning coordinates (or the pose) into a mechanical arm coordinate system by using a C-shaped arm coordinate system to obtain the expected coordinates (or the pose) of the target object.

1608. The robot arm is guided to operate by the desired coordinates (or pose).

According to the method provided by the embodiment of the invention, the pose conversion in the operation area range can be realized through the image registration method, and an additional target does not need to be installed at the target object, so that the safety of the target object is improved, the burden of a doctor is reduced, and the recovery time of the target object is shortened; in addition, the robot can be guided in real time according to the actual information of the target object by using the real-time X-ray image in the operation, so that the accuracy of guiding the operation is improved; in addition, the registration of the intraoperative two-dimensional X-ray image with the preoperative three-dimensional image may reduce the radiation dose received by the intraoperative target object. Finally, image acquisition, registration, coordinate or pose conversion and operation guidance in the operation are completed in the registration system, so that the time error of the registration system is reduced, and the operation precision of the mechanical arm is improved.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application further provides an image-based registration apparatus for implementing the image-based registration method mentioned above. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the image-based registration apparatus provided below can be referred to as limitations on the image-based registration method in the foregoing, and details are not repeated here.

In one embodiment, as shown in fig. 17, an image-based registration apparatus is provided for use in a registration system comprising a two-dimensional imaging device and a robotic arm, the two-dimensional imaging device being fixedly connected to the robotic arm; the device comprises: a first obtaining module 1701, a second obtaining module 1702, a reconstructing module 1703, a third obtaining module 1704, and a configuring module 1705, wherein:

a first obtaining module 1701, configured to obtain a three-dimensional model constructed for a target object based on a three-dimensional medical image shot before an operation;

a second obtaining module 1702, configured to obtain a first two-dimensional medical imaging and a second two-dimensional medical imaging of the target object, where a posture of the two-dimensional imaging device when the first two-dimensional medical imaging is obtained through imaging is orthogonal to a posture of the two-dimensional imaging device when the second two-dimensional medical imaging is obtained through imaging;

a reconstruction module 1703, configured to obtain a first transformation matrix between a coordinate system of the digitally reconstructed two-dimensional image and a coordinate system of the two-dimensional imaging device according to an imaging parameter of the digitally reconstructed two-dimensional image obtained by reconstructing the digital image of the three-dimensional model and an imaging parameter of each of the first two-dimensional medical imaging and the second two-dimensional medical imaging;

a third obtaining module 1704, configured to obtain a planning pose of the target object in a coordinate system of the two-dimensional imaging device based on the initial pose of the target object in the three-dimensional model and the first transformation matrix;

and a configuration module 1705, configured to convert the planned pose into a coordinate system of the robot arm, and obtain an expected pose of the target object in the coordinate system of the robot arm.

In one embodiment, the first obtaining module 1701 includes:

the first acquisition sub-module is used for acquiring a CT image which is acquired before an operation and contains a target object;

and the processing submodule is used for sequentially carrying out interpolation processing, noise reduction processing and contrast enhancement processing on the three-dimensional medical image, carrying out three-dimensional reconstruction on the basis of the processed three-dimensional medical image and obtaining a three-dimensional model constructed aiming at the target object.

In one embodiment, the reconstruction module 1703 includes:

the registration sub-module is used for registering the digital reconstruction two-dimensional image with the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively to obtain the digital reconstruction two-dimensional images which are respectively and correspondingly registered by the first two-dimensional medical imaging and the second two-dimensional medical imaging;

and the determining submodule is used for determining a first conversion matrix according to the imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively and the digital reconstruction imaging parameters of the digital reconstruction two-dimensional image corresponding to the registration of the first two-dimensional medical imaging and the digital reconstruction imaging parameters of the digital reconstruction two-dimensional image corresponding to the registration of the second two-dimensional medical imaging.

In one embodiment, a registration sub-module, comprising:

the reconstruction unit is used for reconstructing digital images of the three-dimensional model to obtain at least one digitally reconstructed two-dimensional image;

and the registration unit is used for registering the first two-dimensional medical imaging and the second two-dimensional medical imaging with the digital reconstruction two-dimensional images respectively, updating the digital image reconstruction parameters and performing digital image reconstruction on the three-dimensional model under the condition that the corresponding registered digital reconstruction two-dimensional images are not determined by the first two-dimensional medical imaging or the second two-dimensional medical imaging, obtaining a plurality of digital reconstruction two-dimensional images again and performing re-registration, and repeating the updating, reconstructing and registering processes until the corresponding registered digital reconstruction two-dimensional images are determined by the first two-dimensional medical imaging and the second two-dimensional medical imaging, so as to obtain the digital reconstruction two-dimensional images which are respectively and correspondingly registered by the first two-dimensional medical imaging and the second two-dimensional medical imaging.

In one embodiment, a reconstruction unit comprises:

the first acquisition subunit is used for acquiring digital reconstruction imaging parameters, wherein the digital reconstruction imaging parameters comprise the position of the analog light source and the projection angle of the analog light source to the three-dimensional model;

the calculating subunit is used for emitting light rays to the three-dimensional model through the simulation light source according to the projection angle and the position, and calculating intersection point coordinates between the light rays emitted by the simulation light source and the three-dimensional model when the light rays pass through the three-dimensional model;

the second acquisition subunit is used for acquiring a gray value obtained after the intersection point coordinates corresponding to each ray are subjected to trilinear interpolation and accumulating the gray value of the intersection point coordinates corresponding to each ray;

and the third acquisition subunit is used for endowing the gray value accumulation result corresponding to each ray to the intersection point between each ray and the digital imaging plane so as to obtain a digital reconstruction two-dimensional image corresponding to the digital reconstruction imaging parameters.

The various modules in the image-based registration apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 18. The computer device comprises a processor, a memory, a communication interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement an image based registration method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the configuration shown in fig. 18 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, databases, or other media used in the embodiments provided herein can include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An image-based registration method is characterized by being applied to a registration system comprising two-dimensional imaging equipment and a mechanical arm, wherein the two-dimensional imaging equipment is fixedly connected with the mechanical arm; the method comprises the following steps:

acquiring a first two-dimensional medical imaging and a second two-dimensional medical imaging of the target object, wherein the posture of the two-dimensional imaging equipment during the imaging to obtain the first two-dimensional medical imaging is orthogonal to the posture of the two-dimensional imaging equipment during the imaging to obtain the second two-dimensional medical imaging;

acquiring a first conversion matrix between a coordinate system of the digital reconstruction two-dimensional image and a coordinate system of the two-dimensional imaging equipment according to imaging parameters of the digital reconstruction two-dimensional image obtained by reconstructing the digital image of the three-dimensional model and respective imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging;

acquiring a planning pose of the target object in a coordinate system of the two-dimensional imaging device based on the initial pose of the target object in the three-dimensional model and the first transformation matrix;

and converting the planning pose into a mechanical arm coordinate system to obtain an expected pose of the target object in the mechanical arm coordinate system.

2. The method as claimed in claim 1, wherein the obtaining of the three-dimensional model constructed for the target object based on the three-dimensional medical image taken before the operation comprises:

3. The method of claim 1, wherein the obtaining a first transformation matrix between a coordinate system of the digitally reconstructed two-dimensional image and a coordinate system of the two-dimensional imaging device according to the imaging parameters of the digitally reconstructed two-dimensional image obtained by digitally reconstructing the three-dimensional model and the imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging comprises:

registering the digital reconstructed two-dimensional image with the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively to obtain digital reconstructed two-dimensional images which are respectively and correspondingly registered with the first two-dimensional medical imaging and the second two-dimensional medical imaging;

and determining a first conversion matrix according to the imaging parameters of the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively and the digital reconstruction imaging parameters of the digital reconstruction two-dimensional image corresponding to the first two-dimensional medical imaging and the digital reconstruction imaging parameters of the digital reconstruction two-dimensional image corresponding to the second two-dimensional medical imaging.

4. The method of claim 1, wherein the two-dimensional imaging device comprises a C-arm and an X-ray tube; the C-arm is in a first pose when the first two-dimensional medical imaging is obtained by the X-ray tube imaging; the C-arm assumes a second pose when the second two-dimensional medical imaging is obtained by the X-ray tube imaging.

5. The method of claim 3, wherein the registering the digitally reconstructed two-dimensional image with the first and second two-dimensional medical images, respectively, to obtain the digitally reconstructed two-dimensional images with the first and second two-dimensional medical images respectively registered, comprises:

registering the first two-dimensional medical imaging and the second two-dimensional medical imaging with the digital reconstruction two-dimensional image respectively, updating the digital image reconstruction parameters and reconstructing the digital image of the three-dimensional model under the condition that the corresponding registered digital reconstruction two-dimensional image is not determined by the first two-dimensional medical imaging or the second two-dimensional medical imaging, re-obtaining a plurality of digital reconstruction two-dimensional images and re-registering, and repeating the updating, reconstructing and registering processes until the corresponding registered digital reconstruction two-dimensional images are determined by the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively to obtain the corresponding registered digital reconstruction two-dimensional images of the first two-dimensional medical imaging and the second two-dimensional medical imaging respectively.

6. The method of claim 5, wherein said digitally reconstructing the three-dimensional model to obtain at least one digitally reconstructed two-dimensional image comprises:

according to the projection angle and the position, emitting light rays to the three-dimensional model through the simulation light source, and calculating intersection point coordinates between the light rays emitted by the simulation light source and the three-dimensional model when the light rays pass through the three-dimensional model;

and giving the gray value accumulation result corresponding to each light ray to the intersection point between each light ray and the digital imaging plane to obtain a digital reconstruction two-dimensional image corresponding to the digital reconstruction imaging parameter.

7. An image-based registration device is applied to a registration system comprising a two-dimensional imaging device and a mechanical arm, wherein the two-dimensional imaging device is fixedly connected with the mechanical arm; characterized in that the device comprises:

the second acquisition module is used for acquiring a first two-dimensional medical imaging and a second two-dimensional medical imaging of the target object, and the posture of the two-dimensional imaging equipment during imaging to obtain the first two-dimensional medical imaging is orthogonal to the posture of the two-dimensional imaging equipment during imaging to obtain the second two-dimensional medical imaging;

a third obtaining module, configured to obtain a planning pose of the target object within a coordinate system of the two-dimensional imaging device based on the initial pose of the target object in the three-dimensional model and the first transformation matrix;

and the configuration module is used for converting the planning pose into a mechanical arm coordinate system to obtain an expected pose of the target object in the mechanical arm coordinate system.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, on which a computer program is stored, which, when run on a computer, causes the computer to carry out the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, when the computer program is run on a computer, it causes the computer to carry out the method of any one of claims 1 to 6 when executed.