X-ray image registration method and device

Abstract

The present application provides a registration method and device for X-ray images, including: acquiring an X-ray image, the X-ray image being obtained by an image acquisition device photographing a lesion; using the X-ray image to obtain a first positional relationship, the first positional relationship being the positional relationship between the image acquisition device and a locator, the locator being fixed around the lesion; fitting the X-ray image with a plurality of pre-generated digitally reconstructed radiographic images; using the first positional relationship to obtain a second positional relationship, the second positional relationship being the positional relationship between the image acquisition device and the lesion in the fitted digitally reconstructed radiographic image. By fitting the positional relationship between the lesion and the image acquisition device reflected in the X-ray image to the digitally reconstructed radiographic image, it is no longer necessary to manually pair the points on the wound surface and the digitally reconstructed radiographic image one by one to establish a positional relationship, thereby achieving the effect of reducing the duration of the operation and the size of the wound surface.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method and device for registering X-ray images. Background Art

[0002] Augmented Reality (AR) is a new technology that integrates computer-generated virtual graphics into the real-world scene seen by the user. The user can obtain additional information from the simulated model drawn by the computer, thereby enhancing the real environment. Augmented reality has three major characteristics: virtual combination, real-time interaction, and three-dimensional matching. Surgical navigation is to accurately match the patient's preoperative or intraoperative image data with the patient's anatomical structure on the operating table, track the surgical instruments during surgery, and update the position of the surgical instruments in real time on the patient's image in the form of a virtual probe, so that the doctor can see the position of the surgical instruments relative to the patient's anatomical structure at a glance, making surgical operations faster, more accurate, and safer. Augmented Reality Surgery Navigation (AR navigation surgery, Augmented Reality Surgery Navigation) integrates virtual information into the real surgical environment, allowing doctors to directly see the scene after registration and superposition, providing doctors with real-time surgical guidance, making timely and accurate decisions, and reducing surgical risks.

[0003] However, in AR navigation surgery, the registration accuracy of the surgical navigation system will directly affect the operation time and the results of the operation. The registration method in the prior art requires obtaining a CT image of the lesion, manually taking points on the CT image, and then manually matching the points taken with the points on the real lesion one by one. This registration method takes a long time, which may affect the progress of the operation and prolong the operation time. In addition, this method requires dissection of the lesion, which causes great trauma to the patient.

[0004] Therefore, how to reduce the duration of surgery and the size of the patient's wounds during AR navigation surgery is a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0005] In view of this, an embodiment of the present application provides an X-ray image registration method and device, aiming to reduce the operation time and patient wound surface in AR surgery.

[0006] In a first aspect, an embodiment of the present application provides a registration method for an X-ray image, comprising:

[0007] Acquire an X-ray image, where the X-ray image is obtained by photographing the lesion with an image acquisition device;

[0008] Using the X-ray image, a first positional relationship is obtained, where the first positional relationship is a positional relationship between the image acquisition device and a locator, and the locator is fixed around the lesion;

[0009] fitting the X-ray image to a plurality of pre-generated digitally reconstructed radiographic images;

[0010] The second positional relationship is obtained by using the first positional relationship, where the second positional relationship is the positional relationship between the image acquisition device and the lesion in the digitally reconstructed radiological image after fitting.

[0011] Preferably, the obtaining of X-ray images comprises:

[0012] Acquire a first X-ray image, where the first X-ray image is obtained by photographing the lesion in an upright position using an image acquisition device;

[0013] Acquire a second X-ray image, where the second X-ray image is obtained by photographing the lesion from a lateral position using an image acquisition device;

[0014] The step of obtaining a first positional relationship by using the X-ray image includes:

[0015] The first positional relationship is obtained using the first X-ray image and the second X-ray image.

[0016] Preferably, the imaging plate of the image acquisition device is installed with a target block, the target block has at least one steel ball point and at least one tracking ball, the positioner has at least one tracking ball, and the first position relationship is obtained by using the X-ray image, including:

[0017] Using the first X-ray image, obtaining first position information, where the first position information is position information of the steel ball point and the tracking ball in the first X-ray image;

[0018] Using the second X-ray image, obtaining second position information, where the second position information is position information of the steel ball point and the tracking ball in the second X-ray image;

[0019] The first position relationship is obtained by using the first position information and the second position information.

[0020] Preferably, the method further comprises:

[0021] The spatial position information of the image acquisition device is fitted with the spatial position information of the optical tracking device using the first position information and the second position information.

[0022] Preferably, before fitting the X-ray image with a plurality of pre-generated digitally reconstructed radiological images, the method further comprises:

[0023] Acquiring a CT image of the lesion;

[0024] Performing three-dimensional modeling according to the CT image of the lesion;

[0025] A plurality of digitally reconstructed radiographic images of the three-dimensional model are acquired.

[0026] In a second aspect, an embodiment of the present application provides an X-ray image registration device, comprising:

[0027] An acquisition module, used to acquire an X-ray image, wherein the X-ray image is obtained by photographing the lesion with an image acquisition device;

[0028] A first position module, used to obtain a first position relationship using the X-ray image, wherein the first position relationship is a position relationship between the image acquisition device and a locator, and the locator is fixed around the lesion;

[0029] A fitting module, used for fitting the X-ray image with a plurality of pre-generated digitally reconstructed radiological images;

[0030] The second position module is used to obtain a second position relationship by using the first position relationship, wherein the second position relationship is the position relationship between the image acquisition device and the lesion in the digitally reconstructed radiological image after fitting.

[0031] Preferably, the acquisition module includes:

[0032] A first acquisition unit is used to acquire a first X-ray image, where the first X-ray image is obtained by an image acquisition device photographing the lesion in an upright position;

[0033] A second acquisition unit is used to acquire a second X-ray image, where the second X-ray image is obtained by photographing the lateral position of the lesion by an image acquisition device;

[0034] The first position module is specifically used to obtain the first position relationship by using the first X-ray image and the second X-ray image.

[0035] Preferably, the imaging board of the image acquisition device is installed with a target block, the target block has at least one steel ball point and at least one tracking ball, the positioner has at least one tracking ball, and the first position module includes:

[0036] A first information unit is used to obtain first position information using the first X-ray image, where the first position information is position information of the steel ball point and the tracking ball in the first X-ray image;

[0037] A second information unit is used to obtain second position information using the second X-ray image, where the second position information is position information of the steel ball point and the tracking ball in the second X-ray image;

[0038] The first relationship unit is used to obtain the first position relationship by using the first position information and the second position information.

[0039] In a third aspect, an embodiment of the present application provides a device, comprising a memory and a processor, wherein the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device performs the X-ray image registration method described in any one of the first aspects above.

[0040] In a fourth aspect, an embodiment of the present application provides a computer storage medium, in which a code is stored. When the code is executed, a device executing the code implements the X-ray image registration method described in any one of the first aspects above.

[0041] The embodiment of the present application provides a registration method for X-ray images. When executing the method, an X-ray image is first acquired, and then the X-ray image is used to obtain a first positional relationship, and then the X-ray image is fitted with a plurality of pre-generated digitally reconstructed radiographic images, and finally the first positional relationship is used to obtain a second positional relationship, so as to reduce the operation time and the patient's wound surface in AR surgery. In this way, because the X-ray image can intuitively reflect the positional relationship between the lesion and the image acquisition device, the positional relationship of multiple different angles can be integrated to obtain a three-dimensional positional relationship between the lesion and the image acquisition device, and then this positional relationship is fitted to the three-dimensional digitally reconstructed radiographic image. The positional relationship between the lesion and the image acquisition device is automatically obtained through the X-ray image, and there is no need to manually establish a positional relationship by matching the points of the lesion and the digitally reconstructed radiographic image one by one, so there is no need to perform point pairing multiple times, which reduces the operation time; at the same time, this method does not require cutting the lesion to expose the bones required to determine the point, which has the effect of reducing the size of the wound surface and the degree of pain of the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A method flow chart of the X-ray image registration method provided in an embodiment of the present application;

[0044] Figure 2Another method flow chart of the X-ray image registration method provided in the embodiment of the present application;

[0045] Figure 3 A schematic diagram of the structure of an apparatus for registration of X-ray images provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In AR navigation surgery, the registration accuracy of the surgical navigation system will directly affect the operation time and the results of the operation. The registration method in the prior art needs to obtain a CT image of the lesion, take points from the CT image, and manually match the taken points with the points on the real lesion one by one. Specifically, the registration method is divided into point matching and surface matching. The point matching method is to manually select points on the CT graphics, and the registration accuracy is low; the surface matching requires manual selection of a large number of points, which will affect the progress of the operation and require a longer operation time. At the same time, both need to match the points of the model in the virtual space with the points in the real space one by one, so both need to dissect the surgical site to leak the bones, which causes a large trauma to the patient.

[0047] The method provided in the embodiment of the present application is executed by a computer device and is used to align X-ray images.

[0048] Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0049] See also Figure 1 , Figure 1 A method flow chart of the X-ray image registration method provided in an embodiment of the present application includes:

[0050] Step S101: Acquire an X-ray image.

[0051] During surgery, an image acquisition device can be used to take X-rays of the lesion. When X-rays pass through the human body, the density of each tissue in the human body is different, the absorption of X-rays is different, and the sensitivity obtained on the film is different, so X-rays can well reflect the condition of the lesion and the location of the bone block. Preferably, multiple X-ray images can be obtained by moving the image acquisition device at different angles and distances.

[0052] Step S102: using the X-ray image to obtain a first positional relationship.

[0053] Because the relationship between the tracking ball on the target block and the locator is known by the optical tracking device, the positional relationship between the image acquisition device and the lesion can be calculated through this positional relationship and X-ray images at different angles. Because the locator can be recognized by the optical tracking device, the locator is fixed around the lesion, the position information of the locator can be obtained by the optical tracking device, and the relationship between the locator and the image acquisition device is obtained by calculation, thereby obtaining the positional relationship between the image acquisition device and the lesion. Preferably, the method for calculating the positional relationship can be the Zhang Zhengyou calibration method.

[0054] Step S103: Fitting the X-ray image with a plurality of pre-generated digitally reconstructed radiological images.

[0055] Before fitting, it is necessary to generate multiple digitally reconstructed radiographs (DRR images). Preferably, the method for generating DRR images is to perform three-dimensional modeling based on the CT images taken of the patient before surgery, and then project the three-dimensional model. At this time, there must be an image in the multiple DRR images that has the same angle as the X-ray image obtained in S101. By fitting the two, the corresponding DRR image, i.e., the digitally reconstructed radiograph, can be found.

[0056] Step S104: Using the first positional relationship, a second positional relationship is obtained, wherein the second positional relationship is obtained by fitting the first positional relationship with the DRR image to obtain relative position information between the image acquisition device and the lesion, and the relative position information between the image acquisition device and the lesion is combined with the first positional relationship again to obtain the second positional relationship.

[0057] Because the positional relationship between the image acquisition device and the lesion has been obtained in step S102, after finding the fitted digitally reconstructed radiographic image, this relationship can be established in the digitally reconstructed radiographic image. Therefore, the three-dimensional model seen by the doctor can well reflect the relationship between the lesion and the image acquisition device. When performing surgery using the three-dimensional model, there is no need to dissect the patient or find corresponding points one by one, which saves operation time and reduces the patient's trauma surface.

[0058] In the embodiment of the present application, the above Figure 1 There are many possible implementations of the steps, which are introduced below. It should be noted that the implementations given in the following introduction are only for illustrative purposes and do not represent all implementations of the embodiments of the present application.

[0059] See also Figure 2 , this figure is another method flow chart of the X-ray image registration method provided in an embodiment of the present application.

[0060] Step S201: Acquire an X-ray image of the target block.

[0061] Because the imaging plate of the image acquisition device is installed with a target block, and there is at least one steel ball point and at least one tracking ball on the target block, when the image acquisition device does not shoot other objects, an X-ray image of the target block can be obtained. When X-rays pass through the target block, due to the different densities of the target block and the steel ball points, the absorption of X-rays is different, and the sensitivity obtained on the film is different, so that an X-ray image including the position information of the steel ball points and the tracking ball can be obtained. When shooting, it is necessary to confirm that all steel balls and tracking balls can be photographed, and switch the shooting angle and distance to obtain multiple X-ray images.

[0062] Step S202: Acquire imaging parameters of the image acquisition device through the X-ray image of the target block.

[0063] By analyzing the positions of the tracking ball and the steel ball point corresponding to the switching of the shooting angle and distance through multiple X-ray images of the target block, the imaging parameters of the image acquisition device can be obtained. Preferably, the Zhang Zhengyou calibration method can be used to calculate the imaging parameters of the image acquisition device.

[0064] Step S203: Acquire a first X-ray image and a second X-ray image.

[0065] During surgery, an image acquisition device can be used to take X-rays of the lesion. When X-rays pass through the human body, the density of each tissue in the human body is different, and the absorption of X-rays is different. The sensitivity obtained on the film is different, thus obtaining an X-ray image. Therefore, X-rays can well reflect the condition of the lesion and the location of the bone block. At this time, multiple X-ray images can be obtained by moving the angle and distance of the image acquisition device.

[0066] Specifically, the first X-ray image is obtained by the image acquisition device taking a frontal view of the lesion, and the second X-ray image is obtained by the image acquisition device taking a lateral view of the lesion.

[0067] Because the density of the target block and the steel ball point is different due to the human skeleton, the position of the steel ball point in the image can be used as the sampling point, so it can replace manual point selection, and each point can be clearly corresponded, which is convenient for calculation. Because the relationship between the tracking ball and the locator on the target block is known by the optical tracking device, the relationship between the locator and the lesion can be obtained through this condition, thereby achieving the purpose of alignment. The tracking ball can be used in an optical positioning tracking device to identify the tracking ball and record the position of the tracking ball. Preferably, the locator and the target block can be provided with at least 3 tracking balls respectively, and the target block can be provided with at least 7 steel ball points with a diameter of 2 mm.

[0068] Step S204: Acquire the first location information and the second location information.

[0069] The first position information is the position information of the steel ball point in the first X-ray image, and the second position information is the position information of the steel ball point in the second X-ray image.

[0070] By analyzing the changes in the position of the steel ball points in the anteroposterior and lateral views, the positional relationship between the image acquisition device and the lesion can be obtained.

[0071] Step S205: Obtain the first position relationship using the first position information and the second position information.

[0072] Because by analyzing the position information of the steel ball points in the first X-ray image and the position information of the steel ball points in the second X-ray image, the positional relationship between the image acquisition device and the lesion can be obtained; and the locator can be identified by the image acquisition device, and the locator is fixed around the lesion, and the positional relationship between the image acquisition device and the lesion can be obtained through the relationship between the locator and the image acquisition device. Preferably, the method for calculating the positional relationship can be the Zhang Zhengyou calibration method.

[0073] As a possible implementation method, the position information between the steel ball point and the image acquisition device is calculated using the "Zhang Zhengyou calibration method" through at least one steel ball point captured by the first X-ray image and the second X-ray image. Since the target block is a fixed structure, the position information between the steel ball point on the target block and the tracking ball on the target block is known. The first position relationship can be obtained by combining the position information between the steel ball point and the image acquisition device with the position information between the steel ball point on the target block and the tracking ball on the target block.

[0074] As a possible implementation, the spatial position information of the image acquisition device and the spatial position information of the optical tracking device can be fitted using the first position information and the second position information. Since the relationship between the tracking ball and the locator on the target block is known by the optical tracking device, the tracking ball can be used by the optical positioning tracking device to identify the tracking ball and record the position of the tracking ball. Therefore, the position relationship between the lesion reflected by the X-ray and the tracking ball can be displayed in the optical tracking system using this position relationship. Therefore, the spatial position information of the image acquisition device and the spatial position information of the optical tracking device can be fitted with each other.

[0075] Step S206: Perform three-dimensional modeling based on the CT image of the lesion.

[0076] According to the CT image of the lesion, 3D modeling can be performed using CT 3D reconstruction technology. Specifically, CT scanning 3D reconstruction is a post-processing technology commonly used by high-end machines. It refers to the use of computer software on a special workstation to post-process the volume data obtained by scanning, and then reconstruct a more intuitive 3D image for observation.

[0077] Step S207: Acquire multiple digitally reconstructed radiological images of the three-dimensional model.

[0078] Before fitting, it is necessary to generate a plurality of digitally reconstructed radiographs (DRR images) in advance. Preferably, the generated DRR images can be images obtained by taking screenshots of the three-dimensional model.

[0079] Step S208: Fitting the X-ray image with a plurality of digitally reconstructed radiological images.

[0080] By taking screenshots of the 3D model at different angles, you can get multiple different DRR images. Since there are a large number of DRR images and they can be acquired at any angle, there must be an image with the same angle as the X-ray image obtained by S101 among the multiple digitally reconstructed radiological images. By fitting the two, you can find the corresponding DRR image and establish the positional relationship between the two.

[0081] Step S209: using the first position relationship, obtain a second position relationship.

[0082] The second positional relationship is to obtain the relative position information between the image acquisition device and the lesion by fitting the first positional relationship with the DRR image, and then combine the relative position information between the image acquisition device and the lesion with the first positional relationship to obtain the second positional relationship.

[0083] By establishing the positional relationship between the lesion and the camera, the three-dimensional model seen by the doctor can be a model that well reflects the relationship between the lesion and the image acquisition device. This method can fit the X-ray image, the image tracking system and the DRR image, and display the condition of the lesion in three different dimensions. When the three-dimensional model is used for surgery, there is no need to dissect the patient or find corresponding points one by one, which saves operation time and reduces the patient's trauma surface.

[0084] The above are some specific implementations of the X-ray image registration method provided in the embodiments of the present application. Based on this, the present application also provides a corresponding device. The device provided in the embodiments of the present application will be introduced from the perspective of functional modularization.

[0085] See also Figure 2The structure diagram of the X-ray image registration device 300 shown in the figure includes an acquisition module 301, a first position module 302, a fitting module 303 and a second position module 304.

[0086] An acquisition module 301 is used to acquire an X-ray image, where the X-ray image is obtained by an image acquisition device photographing the lesion;

[0087] A first position module 302 is used to obtain a first position relationship using the X-ray image, where the first position relationship is a position relationship between the image acquisition device and a locator, where the locator is fixed around the lesion;

[0088] A fitting module 303, for fitting the X-ray image with a plurality of pre-generated digitally reconstructed radiological images;

[0089] The second position module 304 is used to obtain a second position relationship by using the first position relationship, where the second position relationship is the position relationship between the image acquisition device and the lesion in the digitally reconstructed radiological image after fitting.

[0090] The acquisition module comprises:

[0091] A first acquisition unit is used to acquire a first X-ray image, where the first X-ray image is obtained by an image acquisition device photographing the lesion in an upright position;

[0092] A second acquisition unit is used to acquire a second X-ray image, where the second X-ray image is obtained by photographing the lateral position of the lesion by an image acquisition device;

[0093] The first position module is specifically used to obtain the first position relationship by using the first X-ray image and the second X-ray image.

[0094] The imaging board of the image acquisition device is installed with a target block, the target block has at least one steel ball point and at least one tracking ball, the positioner has at least one tracking ball, and the first position module includes:

[0095] A first information unit is used to obtain first position information using the first X-ray image, where the first position information is position information of the steel ball point and the tracking ball in the first X-ray image;

[0096] A second information unit is used to obtain second position information using the second X-ray image, where the second position information is position information of the steel ball point and the tracking ball in the second X-ray image;

[0097] The first relationship unit is used to obtain the first position relationship by using the first position information and the second position information.

[0098] The device also includes:

[0099] A tracking fitting module is used to fit the spatial position information of the image acquisition device with the spatial position information of the optical tracking device by using the first position information and the second position information.

[0100] A CT acquisition module, used for acquiring a CT image of the lesion;

[0101] A modeling module, used for performing three-dimensional modeling according to the CT image of the lesion;

[0102] The digitally reconstructed radiological image acquisition module is used to acquire a plurality of digitally reconstructed radiological images of the three-dimensional model.

[0103] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.

[0104] The device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the X-ray image registration method described in any embodiment of the present application.

[0105] The computer storage medium stores codes, and when the codes are executed, the device executing the codes implements the X-ray image registration method described in any embodiment of the present application.

[0106] The "first" and "second" in the names such as "first" and "second" (if any) mentioned in the embodiments of the present application are only used as name identifiers and do not represent the first or second in order.

[0107] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0108] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0109] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A registration method for X-ray images, characterized in that: The method comprises: Acquire an X-ray image, where the X-ray image is obtained by photographing the lesion with an image acquisition device; Using the X-ray image, a first positional relationship is obtained, where the first positional relationship is a positional relationship between the image acquisition device and a locator, and the locator is fixed around the lesion; fitting the X-ray image to a plurality of pre-generated digitally reconstructed radiographic images; Using the first positional relationship, a second positional relationship is obtained, where the second positional relationship is a positional relationship between the image acquisition device and the lesion in the digitally reconstructed radiological image after fitting; The X-ray image includes a first X-ray image and a second X-ray image; The imaging plate of the image acquisition device is installed with a target block, the target block has at least one steel ball point and at least one tracking ball, the positioner has at least one tracking ball, and the first position relationship is obtained by using the X-ray image, including: Using the first X-ray image, first position information is obtained, and the first position information is the position information of the steel ball point and the tracking ball in the first X-ray image; using the second X-ray image, second position information is obtained, and the second position information is the position information of the steel ball point and the tracking ball in the second X-ray image; using the first position information and the second position information, the first position relationship is obtained.

2. The method according to claim 1, characterized in that The obtaining of X-ray images comprises: Acquire a first X-ray image, where the first X-ray image is obtained by photographing the lesion in an upright position using an image acquisition device; Acquire a second X-ray image, where the second X-ray image is obtained by photographing the lesion from a lateral position using an image acquisition device; The step of obtaining a first positional relationship by using the X-ray image includes: The first positional relationship is obtained using the first X-ray image and the second X-ray image.

3. The method according to claim 1, characterized in that The method further comprises: The spatial position information of the image acquisition device is fitted with the spatial position information of the optical tracking device using the first position information and the second position information.

4. The method according to claim 1, characterized in that: Before fitting the X-ray image to a plurality of pre-generated digitally reconstructed radiographic images, the method further comprises: Acquiring a CT image of the lesion; Performing three-dimensional modeling according to the CT image of the lesion; Multiple digitally reconstructed radiographic images of the three-dimensional model are obtained.

5. An X-ray image registration device, characterized in that: The device comprises: An acquisition module, used to acquire an X-ray image, wherein the X-ray image is obtained by photographing the lesion with an image acquisition device; A first position module, used to obtain a first position relationship using the X-ray image, wherein the first position relationship is a position relationship between the image acquisition device and a locator, and the locator is fixed around the lesion; A fitting module, used for fitting the X-ray image with a plurality of pre-generated digitally reconstructed radiological images; A second position module, used to obtain a second position relationship by using the first position relationship, wherein the second position relationship is a position relationship between the image acquisition device and the lesion in the digitally reconstructed radiological image after fitting; The X-ray image includes a first X-ray image and a second X-ray image; The imaging board of the image acquisition device is installed with a target block, the target block has at least one steel ball point and at least one tracking ball, the positioner has at least one tracking ball, and the first position module includes: The first information unit is used to obtain first position information using the first X-ray image, wherein the first position information is the position information of the steel ball point and the tracking ball in the first X-ray image; the second information unit is used to obtain second position information using the second X-ray image, wherein the second position information is the position information of the steel ball point and the tracking ball in the second X-ray image; the first relationship unit is used to obtain the first position relationship using the first position information and the second position information.

6. The device according to claim 5, characterized in that The acquisition module comprises: A first acquisition unit is used to acquire a first X-ray image, where the first X-ray image is obtained by an image acquisition device photographing the lesion in an upright position; A second acquisition unit is used to acquire a second X-ray image, where the second X-ray image is obtained by photographing the lateral position of the lesion by an image acquisition device; The first position module is specifically used to obtain the first position relationship by using the first X-ray image and the second X-ray image.

7. A device, characterized in that: The device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device performs the X-ray image registration method described in any one of claims 1 to 4.

8. A computer storage medium, characterized in that The computer storage medium stores codes, and when the codes are executed, the computer storage device executing the codes implements the X-ray image registration method according to any one of claims 1 to 4.

Images