Image registration method, imaging device, intraoperative guidance intervention system, and storage medium

Abstract

The application relates to an image registration method, an imaging device, an intraoperative guiding intervention system and a storage medium. The method is applied to the imaging device, the imaging device comprises an imaging source and a bearing assembly, the bearing assembly is provided with a first marker, and a detection object carried by the bearing assembly is provided with a second marker. The method comprises the following steps: acquiring a preoperative three-dimensional image and an intraoperative perspective view of the detection object; the intraoperative perspective view comprises an image of the first marker and an image of the second marker; determining a target height according to the first marker and the second marker and the image of the first marker and the image of the second marker, the target height being a distance between the imaging source and the detection object; and determining a target registration image according to the preoperative three-dimensional image, the intraoperative perspective view and the target height. The image registration method provided by the application can be applied to various surgical scenes without acquiring an intraoperative three-dimensional image for registration, and has higher practicability.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of imaging technology, in particular to an image registration method, an imaging device, an intraoperative guiding interventional system and a storage medium. BACKGROUND

[0002] An interventional surgery is a minimally invasive surgical method. In the interventional surgery, a preoperative three-dimensional image is registered with an intraoperative two-dimensional image to provide a navigation as a roadmap for a doctor, which can reduce the number of intraoperative contrast exposure, the amount of contrast agent, the radiation dose, and the surgery time.

[0003] In the traditional technology, the registration is usually based on an intraoperative three-dimensional image and a preoperative three-dimensional image, and the registration of the preoperative three-dimensional image and the intraoperative two-dimensional image is realized by using a known relative position relationship between the intraoperative three-dimensional image and the intraoperative two-dimensional image.

[0004] However, in most surgery scenarios, it is difficult to obtain the intraoperative three-dimensional image. SUMMARY

[0005] Therefore, it is necessary to provide an image registration method, an imaging device, an intraoperative guiding interventional system and a storage medium, which can realize the registration of a preoperative three-dimensional image and an intraoperative two-dimensional image without obtaining the intraoperative three-dimensional image.

[0006] In a first aspect, the present application provides an image registration method, which is applied to an imaging device, the imaging device comprising an imaging source and a bearing assembly, the bearing assembly being provided with a first marker, and a detection object carried by the bearing assembly being provided with a second marker, and the method comprising:

[0007] obtaining a preoperative three-dimensional image of the detection object and an intraoperative perspective view; the intraoperative perspective view comprising an image of the first marker and an image of the second marker;

[0008] determining a target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker; the target height being a distance between the imaging source and the detection object;

[0009] determining an intermediate registration relationship according to a perspective view of the preoperative three-dimensional image and the intraoperative perspective view; the perspective view of the preoperative three-dimensional image being consistent with the intraoperative perspective view in terms of orientation;

[0010] determining a target registration image according to the target height, the intermediate registration relationship and an image of a third marker in the preoperative three-dimensional image.

[0011] In one of the embodiments, the imaging device further comprises a detector, and determining the target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker comprises:

[0012] obtaining a distance between an imaging source and a bearing assembly, a first actual size of the first marker and a second actual size of the second marker;

[0013] determining the target height according to the distance, the first actual size, the second actual size, a first size of the image of the first marker and a second size of the image of the second marker.

[0014] In one embodiment, determining the target height according to the distance, the first actual size, the second actual size, a first size of the image of the first marker and a second size of the image of the second marker comprises:

[0015] determining a first product of the first size and the second actual size, and a second product of the second size and the first actual size;

[0016] determining the target height according to the first product, the second product and the distance.

[0017] In one embodiment, determining the intermediate registration relationship according to the perspective view of the preoperative three-dimensional image and the intraoperative perspective view comprises:

[0018] determining an image of a third marker in the preoperative three-dimensional image according to a position of the second marker;

[0019] registering the perspective view of the preoperative three-dimensional image and the intraoperative perspective view based on the image of the third marker and the image of the second marker in the perspective view of the preoperative three-dimensional image, to obtain the intermediate registration relationship.

[0020] In one embodiment, determining the intermediate registration relationship according to the perspective view of the preoperative three-dimensional image and the intraoperative perspective view comprises:

[0021] obtaining the perspective view of the preoperative three-dimensional image according to an orientation of the intraoperative perspective view based on a digital reconstructed radiograph method;

[0022] inputting the perspective view of the preoperative three-dimensional image and the intraoperative perspective view into a pre-trained registration model to obtain the intermediate registration relationship.

[0023] In a second aspect, the present application provides an image registration device, which comprises:

[0024] an obtaining module, configured to obtain a preoperative three-dimensional image of a detection object and an intraoperative perspective view; the intraoperative perspective view comprises an image of a first marker and an image of a second marker;

[0025] a determining module, configured to determine a target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker; the target height is a distance between an imaging source and the detection object;

[0026] The determining module is further configured to determine an intermediate registration relationship according to registration of the perspective view of the preoperative three-dimensional image and the intraoperative perspective view; the perspective view of the preoperative three-dimensional image and the intraoperative perspective view are in the same orientation; and determine a target registration image according to the target height, the intermediate registration relationship, and the image of the third marker in the preoperative three-dimensional image.

[0027] In a third aspect, the present application further provides an intraoperative guiding interventional system, comprising a processor, which executes the steps of the method provided in the first aspect to realize intraoperative three-dimensional real-time guiding.

[0028] In a fourth aspect, the present application further provides an imaging device, which comprises an imaging source, a detector, a bearing assembly, and a control assembly; the imaging source is arranged correspondingly to the detector; the bearing assembly is configured to bear a detection object; the detector is connected to the control assembly; and the control assembly is configured to execute the steps of the method provided in the first aspect.

[0029] In a fifth aspect, the present application further provides a computer readable storage medium, which stores a computer program; when the computer program is executed by a processor, the steps of the method provided in the first aspect are realized.

[0030] In a sixth aspect, the present application further provides a computer program product, which comprises a computer program; when the computer program is executed by a processor, the steps of the method provided in the first aspect are realized.

[0031] The above image registration method, imaging device, intraoperative guiding interventional system, and storage medium; the method is applied to the imaging device, which comprises an imaging source and a bearing assembly; the bearing assembly is provided with a first marker; a detection object borne by the bearing assembly is provided with a second marker; the method comprises the following steps: obtaining a preoperative three-dimensional image and an intraoperative perspective view of the detection object; the intraoperative perspective view comprises an image of the first marker and an image of the second marker; determining a target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker; the target height is a distance between the imaging source and the detection object; and determining a target registration image according to the preoperative three-dimensional image, the intraoperative perspective view, and the target height. In this embodiment, the target registration image obtained by registration of the preoperative three-dimensional image and the intraoperative perspective view can be obtained through the obtained preoperative three-dimensional image, intraoperative perspective view, and determined distance between the imaging source and the detection object, i.e., the target height; thus, the intraoperative three-dimensional image does not have to be obtained through three-dimensional rotational scanning to be registered with the preoperative three-dimensional image, which can be applied to various surgical scenarios; and the registration method is simple, stable, and highly implementable, and has higher practicability. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 FIG. 1 is a structural schematic diagram of an imaging device in an embodiment;

[0033] Figure 2 A schematic diagram of a step flow of an image registration method in one embodiment;

[0034] Figure 3 A schematic diagram of a step flow of an image registration method in another embodiment;

[0035] Figure 4 A schematic diagram of a step flow of an image registration method in another embodiment;

[0036] Figure 5 A schematic diagram of a step flow of an image registration method in another embodiment;

[0037] Figure 6 A schematic diagram of positions of a first marker and a second marker in an imaging device in one embodiment;

[0038] Figure 7 A schematic diagram of a first marker image and a second marker image in one embodiment;

[0039] Figure 8 A schematic diagram of a step flow of an image registration method in another embodiment;

[0040] Figure 9 A schematic diagram of a step flow of an image registration method in another embodiment;

[0041] Figure 10 A schematic diagram of a structure of an image registration device in one embodiment;

[0042] Figure 11 An internal structure diagram of a control component in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0044] The serial numbers of components in the present application, such as "first", "second", etc., are only used to distinguish the described objects, and do not have any sequence or technical meaning.

[0045] First, before specifically introducing the technical solutions of the embodiments disclosed in the present application, the background technology or technical evolution context on which the embodiments of the present application are based is introduced. In the medical field, interventional surgery is a minimally invasive surgical procedure. In interventional surgery, pre-shot medical images are used as road maps to provide navigation for doctors, which can well reduce surgery time, reduce radiation dose, reduce contrast agent dosage, and improve patient prognosis. For some surgical scenarios, three-dimensional images need to be provided as road maps. Usually, three-dimensional images are obtained by selecting and shooting DSA images by a digital subtraction angiography (DSA) device. In some special cases, such as complete occlusion of blood vessels and non-development of contrast images, preoperative three-dimensional images need to be used and synchronized to intraoperative DSA images to provide navigation or guidance for doctors. The commonly used technology is to use a DSA device to scan intraoperative three-dimensional images based on a cone beam CT (CBCT) protocol, so that the intraoperative three-dimensional images are scanned by the DSA device and are in the coordinate system of the DSA device. By registering the preoperative three-dimensional images and the intraoperative three-dimensional images, the preoperative three-dimensional images can also be registered to the coordinate system of the intraoperative DSA device. The registration method of the above preoperative three-dimensional images and intraoperative three-dimensional images needs to rely on intraoperative three-dimensional rotation scanning, but in many surgeries, due to various factors, the necessary three-dimensional rotation scanning cannot be completed, so the registration of the preoperative three-dimensional images and the intraoperative three-dimensional images cannot be completed. For this purpose, registration between preoperative three-dimensional images and intraoperative two-dimensional images is needed. In traditional technology, the registration method between three-dimensional images and two-dimensional images is usually based on artificial intelligence. However, the registration method based on artificial intelligence has limitations in image modalities, accuracy and stability. For this purpose, the present application provides an image registration method.

[0046] The image registration method provided by the present application can be applied to an imaging device. The structure of the imaging device is shown in Figure 1 The imaging device includes an imaging source 10, a detector 11, a bearing assembly 12, and a control assembly 13. The imaging source 10 is used to emit X-rays to a detection object; the detector 11 is used to receive X-rays passing through the detection object and transmit the detected data to the control assembly 13; the bearing assembly 12 is used to bear the detection object. The control assembly 13 includes, but is not limited to, an industrial computer, a notebook computer, a tablet computer, and the like.

[0047] The technical solutions of the present application and how the technical solutions of the present application solve the technical problems are described in detail below with specific embodiments.

[0048] In one embodiment, as Figure 2As shown, an image registration method is provided, and the embodiment takes the method applied to the control component in the imaging device as an example. In the embodiment, the method comprises the following steps:

[0049] In step 200, a preoperative three-dimensional image of a detection object and an intraoperative fluoroscopy image are acquired; the intraoperative fluoroscopy image comprises an image of a first marker and an image of a second marker.

[0050] The preoperative three-dimensional image can be a Computed Tomography (CT) image, a Magnetic Resonance Imaging (MRI) image, a Computed Tomography Angiography (CTA) image, etc. The embodiment does not limit the modality of the preoperative three-dimensional image as long as the function thereof can be realized.

[0051] The intraoperative fluoroscopy image can be a fluoroscopy image of a DSA image obtained by pre-scanning the detection object using the imaging device. Specifically, the first marker is arranged on the bearing component, and the second marker is attached to the detection object. Both the first marker and the second marker are high-attenuation markers, i.e., objects that strongly absorb energy (such as rays, sound waves, electromagnetic waves, etc.) emitted by the imaging source. The shape of the first marker can be a square, a rectangle, an ellipse, a circle, a straight line, etc. of a specific size. The shape of the first marker can be the same as or different from the shape of the second marker, and the embodiment does not limit this. The first marker can be arranged on the surface of the bearing component close to the detector, or the first marker can be arranged on the surface of the bearing component close to the imaging source, or the first marker can be inlaid in the bearing component. The embodiment does not limit the arrangement position of the first marker and the second marker as long as they are within the imaging range of the imaging device. The second marker can be arranged on the side of the imaging object close to the imaging source, or the second marker can be arranged on the side of the imaging object close to the bearing component. After the detection object is carried on the bearing component, the detection object is scanned using the DSA device, and a two-dimensional intraoperative fluoroscopy image can be obtained, which comprises an image of the first marker and an image of the second marker. Preferably, the first marker is arranged on the surface of the bearing component close to the detector, and the second marker is arranged on the side of the imaging object close to the imaging source.

[0052] The preoperative three-dimensional image can be stored in an image device post-processing workstation or a server such as a PACS (Picture Archiving and Communication Systems). The control component can obtain the preoperative three-dimensional image from the image device post-processing workstation or the PACS. The intraoperative fluoroscopy image can be obtained by real-time scanning of the detection object by the imaging device and sent to the control component. The present embodiment does not limit the specific method of obtaining the preoperative three-dimensional image and the intraoperative fluoroscopy image of the detection object, as long as the function can be realized.

[0053] In step 210, the target height is determined according to the first marker and the second marker, and the image of the first marker and the image of the second marker. The target height is the distance between the imaging source and the detection object.

[0054] The control component obtains the size of the first marker and the size of the second marker. Specifically, the size of the first marker and the size of the second marker can be input by the user to the control component.

[0055] The size of the first marker is related to the shape of the first marker. For example, if the shape of the first marker is a square, the size of the first marker can be the length of the side of the square; if the shape of the first marker is a cuboid, the size of the first marker can be the length of the cuboid or the height of the cuboid; if the shape of the first marker is a circle, the size of the first marker can be the radius or diameter of the circle. Similarly, the size of the second marker is also related to the shape of the second marker.

[0056] After obtaining the size of the first marker and the size of the second marker, the control component determines the distance between the imaging source and the detection object in the imaging device, i.e., the target height, according to the size of the first marker, the size of the second marker, the image of the first marker and the image of the second marker. It can be understood that the second marker is arranged on the detection object, and the distance between the imaging source and the detection object refers to the distance between the imaging source and the second marker.

[0057] In step 220, the target registration image is determined according to the preoperative three-dimensional image, the intraoperative fluoroscopy image and the target height.

[0058] After obtaining the target height, the control component can register the preoperative three-dimensional image and the intraoperative fluoroscopy image based on the target height to obtain the registered image, i.e., the target registration image. The present embodiment does not limit the specific method of determining the target registration image according to the preoperative three-dimensional image, the intraoperative fluoroscopy image and the target height, as long as the function can be realized.

[0059] In an optional embodiment, the control component stores a pre-trained first registration model, and inputs the preoperative three-dimensional image, the intraoperative perspective image and the target height into the first registration model to obtain the target registration image.

[0060] The image registration method provided by the embodiments of the present application is applied to an imaging device, the imaging device comprising an imaging source and a bearing assembly, the bearing assembly being provided with a first marker, and the detection object carried by the bearing assembly being provided with a second marker. The method comprises the following steps: obtaining a preoperative three-dimensional image and an intraoperative perspective image of the detection object; the intraoperative perspective image comprising an image of the first marker and an image of the second marker; determining a target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker; the target height being a distance between the imaging source and the detection object; and determining a target registration image according to the preoperative three-dimensional image, the intraoperative perspective image and the target height. In this embodiment, the target registration image obtained by registering the preoperative three-dimensional image and the intraoperative perspective image can be obtained by using the preoperative three-dimensional image, the intraoperative perspective image and the target height, i.e. the distance between the imaging source and the detection object. Therefore, the registration of the preoperative three-dimensional image and the intraoperative perspective image does not depend on the three-dimensional rotation scanning of the DSA device to obtain the three-dimensional image, and can be applied to various surgical scenarios. In addition, the registration method is simple, stable and easy to implement, and has higher practicability.

[0061] In one embodiment, as shown in FIG. 10, an implementation of determining a target registration image according to a preoperative three-dimensional image, an intraoperative perspective image and a target height is provided. The implementation comprises the following steps: Figure 3

[0062] Step 300: registering the perspective view of the preoperative three-dimensional image and the intraoperative perspective image to determine an intermediate registration relationship; the perspective view of the preoperative three-dimensional image and the intraoperative perspective image have the same orientation.

[0063] After obtaining the preoperative three-dimensional image, the control component determines the perspective view of the preoperative three-dimensional image according to the preoperative three-dimensional image. Specifically, the control component projects the preoperative three-dimensional image according to the orientation of the obtained intraoperative perspective image, i.e. the orientation of the imaging source when scanning the detection object, to obtain the perspective view of the preoperative three-dimensional image which has the same orientation as the intraoperative perspective image. Specifically, the intraoperative perspective image is an en face perspective image, i.e. the imaging source faces the detection object to scan the detection object, and the determined perspective view of the preoperative three-dimensional image is also an en face perspective image.

[0064] In an optional embodiment, the control component can obtain the perspective view of the preoperative three-dimensional image based on a digital reconstructed radiography (DRR) method. Specifically, the preoperative three-dimensional image is projected according to the orientation of the intraoperative perspective image to obtain the perspective view of the preoperative three-dimensional image.​Figure 1 The perspective view of the preoperative three-dimensional image is a two-dimensional image. After obtaining the preoperative three-dimensional image, the control component determines the perspective view of the preoperative three-dimensional image, registers the perspective view of the preoperative three-dimensional image and the intraoperative perspective view, and determines the intermediate registration relationship, i.e., the registration relationship between the preoperative three-dimensional image and the intraoperative perspective view in the X direction and the Y direction. The embodiment does not limit the specific method of registering the perspective view of the preoperative three-dimensional image and the intraoperative perspective view, as long as the function can be realized.

[0065] The perspective view of the preoperative three-dimensional image is a two-dimensional image. After obtaining the preoperative three-dimensional image, the control component determines the perspective view of the preoperative three-dimensional image, registers the perspective view of the preoperative three-dimensional image and the intraoperative perspective view, and determines the intermediate registration relationship, i.e., the registration relationship between the preoperative three-dimensional image and the intraoperative perspective view in the X direction and the Y direction. The embodiment does not limit the specific method of registering the perspective view of the preoperative three-dimensional image and the intraoperative perspective view, as long as the function can be realized.

[0066] In an optional embodiment, the control component inputs the perspective view of the preoperative three-dimensional image and the intraoperative perspective view into a pre-trained second registration model to obtain the intermediate registration relationship.

[0067] In another optional embodiment, the control component can obtain a first feature by performing feature analysis on the perspective view of the preoperative three-dimensional image, obtain a second feature by performing feature analysis on the intraoperative perspective view, and register the perspective view of the preoperative three-dimensional image and the intraoperative perspective view based on the first feature and the second feature to obtain the intermediate registration relationship.

[0068] Step 310: determining a target registration image according to the target height, the intermediate registration relationship, and the image of the third marker in the preoperative three-dimensional image.

[0069] The image of the third marker in the preoperative three-dimensional image can be obtained by setting the third marker on the detection object during the process of obtaining the preoperative three-dimensional image and scanning by the imaging device, or can be the image of the third marker marked in the preoperative three-dimensional image after obtaining the preoperative three-dimensional image. The position of the third marker set on the detection object is the same as the position of the second marker set on the detection object. The position of the third marker in the preoperative three-dimensional image, i.e., the position of the third marker on the image of the detection object, is the same as the position of the second marker on the image of the detection object. The image of the third marker can be a marker point on the preoperative three-dimensional image corresponding to the position of the second marker, or an image with the same shape and size as the second marker. For example, the shape of the second marker is a circle, the center position of the circle is determined, and a marker point is set at a position on the preoperative three-dimensional image corresponding to the center position of the circle; or a circle with the same shape and size as the second marker is directly set at a position on the preoperative three-dimensional image corresponding to the circle.

[0070] It is understandable that the target height is the registration relationship between the intraoperative perspective view and the preoperative 3D image in the Z direction. After obtaining the intermediate registration relationship and the target height, the control component can use the intermediate registration relationship to complete the registration of the preoperative 3D image and the intraoperative perspective view in the X and Y directions. Using the target height and the image of the third marker in the preoperative 3D image, the registration of the preoperative 3D image and the intraoperative perspective view in the Z direction can be completed, thereby obtaining the preoperative 3D image registered with the intraoperative perspective view, i.e., the target registration image.

[0071] In one optional embodiment, the control component may first complete the registration of the preoperative 3D image and the intraoperative perspective view in the X and Y directions based on the intermediate registration relationship, and then complete the registration in the Z direction based on the target height and the image of the third marker in the preoperative 3D image; alternatively, it may first complete the registration in the Z direction based on the target height and the image of the third marker in the preoperative 3D image, and then complete the registration of the preoperative 3D image and the preoperative perspective view in the X and Y directions based on the intermediate registration relationship.

[0072] In an optional embodiment, the control component includes a display screen. After registering the preoperative 3D image and the intraoperative perspective view in the X and Y directions according to the intermediate registration relationship, the display screen shows the intraoperative perspective view and the image registered with the preoperative 3D image and the intraoperative perspective view in the X and Y directions, i.e., the initial registration image. The size of the initial registration image is larger or smaller than that of the intraoperative perspective view. The control component performs registration in the Z direction based on the target height and the image of the third marker in the preoperative 3D image, i.e., scaling the size of the initial registration image displayed on the display screen so that the size of the initial registration image coincides with that of the intraoperative perspective view, thereby obtaining the target registration image.

[0073] In this embodiment, the intermediate registration relationship is first obtained by registering the preoperative 3D perspective view and the intraoperative perspective view. The orientation of the preoperative 3D perspective view and the intraoperative perspective view are consistent. Then, the target registration image is determined based on the target height, the intermediate registration relationship, and the image of the third marker in the preoperative 3D image. This transforms the registration between 3D and 2D images into the registration between 2D images, which improves the efficiency and accuracy of registration. Furthermore, compared with artificial intelligence registration methods, it has higher practicality and stability.

[0074] In one embodiment, such as Figure 4 As shown, an implementation method for determining the height of a target based on a first marker and a second marker, and an image of the first marker and an image of the second marker, includes the following steps:

[0075] Step 400: Obtain the distance between the imaging source and the carrier component, the first actual size of the first marker and the second actual size of the second marker.

[0076] The distance between the imaging source and the bearing assembly can be measured by the user between the imaging source and the detector and input to the control assembly. The first actual size of the first marker and the second actual size of the second marker can refer to the specific description of the above embodiments, which will not be described here.

[0077] The control assembly obtains the distance, the first actual size and the second actual size.

[0078] Step 410, according to the distance, the first actual size, the second actual size, and the first size of the image of the first marker and the second size of the image of the second marker, determine the target height.

[0079] The distance, the first actual size, the second actual size, the first size and the second size, and the target height have a corresponding relationship. The control assembly can determine the target height according to the obtained distance, the first actual size, the second actual size, and the first size of the image of the first marker and the second size of the image of the second marker.

[0080] In one embodiment, the relationship between the distance between the imaging source and the detector, i.e. the distance between the focal point of the imaging source and the detector, also known as (focal spot to image receptor distance, SID), and the distance between the imaging source and the bearing assembly, the first actual size, the second actual size, the first size of the image of the first marker, the second size of the image of the second marker and the target height can be represented as: , wherein R1 is the first size of the image of the first marker, R2 is the second size of the image of the second marker, is the ratio between the first size and the second size, i.e. the size ratio, r1 is the first actual size, r2 is the second actual size, L1 is the distance, and L2 is the target height. The above corresponding relationship can be converted to SID can be obtained directly from the parameter setting interface or the operation interface of the imaging device, or can be measured by the user between the imaging source and the detector and input to the control assembly. The present embodiment does not limit the method of obtaining the first distance, as long as it can achieve its function.

[0081] In this case, as shown in Figure 5 , one implementation of determining the target height according to the distance, the first actual size, the second actual size, and the first size of the image of the first marker and the second size of the image of the second marker, the steps of the implementation include:

[0082] Step 500, determining a first product of the first size and the second actual size, and a second product of the second size and the first actual size.

[0083] The control component calculates the first product of the first size and the second actual size, i.e., ; and calculates the second product of the second size and the first actual size, i.e. .

[0084] Step 510, determining the target height according to the first product, the second product and the distance.

[0085] The control component can obtain the target height by calculating the ratio of the first product and the second product, and calculating the product of the ratio and the distance, i.e. .

[0086] In the embodiment, the accurate target height can be determined by simple calculation according to the distance, the first actual size, the second actual size, the first size of the image of the first marker and the second size of the image of the second marker, and the efficiency and accuracy of the image registration method can be improved.

[0087] In an alternative embodiment, as shown in Figure 6 , the shapes of the first marker and the second marker are both circular. The first marker and the second marker are located between the imaging source 10 and the detector 11 of the imaging device, the first marker is arranged on the bearing component 12 close to the imaging source 10, and the second marker is attached to the detection object close to the detector 11. The schematic diagram of the image of the first marker and the image of the second marker is shown in Figure 7 .

[0088] In an embodiment, as shown in Figure 8 , an implementation of determining the intermediate registration relationship is related to the registration of the preoperative three-dimensional image perspective and the intraoperative perspective, and the implementation includes:

[0089] Step 800, determining the image of the third marker in the preoperative three-dimensional image according to the position of the second marker.

[0090] The position of the second marker refers to the position of the second marker on the detection object. The position of the second marker can be input by the user, or can be determined by the control component by analyzing the intraoperative perspective. The embodiment does not limit the specific method of determining the position of the second marker.

[0091] The control component labels the same position as the position of the second marker in the preoperative three-dimensional image after determining the position of the second marker, and obtains the preoperative three-dimensional image including the image of the third marker. The image of the third marker can be the same as or different from the image of the second marker. The present embodiment does not limit the method for determining the image of the third marker in the preoperative three-dimensional image, as long as the function can be realized. The description of the image of the third marker in the preoperative three-dimensional image can refer to the specific description of the above-mentioned embodiments, which will not be repeated here.

[0092] Step 810, registering the perspective view of the preoperative three-dimensional image and the intraoperative perspective view based on the image of the third marker and the image of the second marker in the perspective view of the preoperative three-dimensional image, to obtain an intermediate registration relationship.

[0093] After the control component determines the image of the third marker in the preoperative three-dimensional image, the perspective view of the preoperative three-dimensional image also includes the image of the third marker. The control component can register the perspective view of the preoperative three-dimensional image and the intraoperative perspective view based on the image of the third marker and the image of the second marker, to obtain the conversion relationship between the perspective view of the preoperative three-dimensional image and the intraoperative perspective view, i.e. the intermediate registration relationship.

[0094] In the present embodiment, by determining the image of the third marker in the preoperative three-dimensional image according to the position of the second marker on the detection object, and directly registering the image of the third marker in the perspective view of the preoperative three-dimensional image and the second marker in the intraoperative perspective view when registering the perspective view of the preoperative three-dimensional image and the preoperative perspective view, such registration method does not depend on the structure of each tissue and organ in the perspective view, and can improve the accuracy and stability of the obtained intermediate registration relationship, thereby improving the accuracy and stability of the target registration image obtained by registration.

[0095] Please refer to Figure 9 An embodiment of the present application provides an image registration method applied to an imaging device, the imaging device comprising an imaging source and a bearing component, the bearing component being provided with a first marker, and a detection object carried by the bearing component being provided with a second marker, and the steps of the image registration method comprising:

[0096] Step 900, obtaining a preoperative three-dimensional image of the detection object and an intraoperative perspective view, and determining an image of a third marker in the preoperative three-dimensional image according to the position of the second marker on the detection object; the intraoperative perspective view including an image of the first marker and an image of the second marker.

[0097] Step 910, determining a perspective view of the preoperative three-dimensional image according to the preoperative three-dimensional image; the perspective view of the preoperative three-dimensional image being consistent with the orientation of the intraoperative perspective view;

[0098] Step 920, registering the perspective view of the preoperative three-dimensional image and the intraoperative perspective view based on the image of the third marker in the perspective view of the preoperative three-dimensional image and the image of the second marker in the intraoperative perspective view, to obtain an intermediate registration relationship;

[0099] Step 930, determining a target height between the imaging source and the detection object according to the distance between the imaging source and the bearing assembly, the first actual size of the first marker, the second actual size of the second marker, and the first size of the image of the first marker and the second size of the image of the second marker.

[0100] Step 940, determining a target registration image according to the target height, the intermediate registration relationship, and the image of the third marker in the preoperative three-dimensional image.

[0101] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0102] Based on the same inventive concept, the embodiments of the present application also provide an image registration device for implementing the above-mentioned image registration method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more image registration device embodiments provided below can refer to the limitations of the image registration method in the above text, which will not be repeated here.

[0103] In one embodiment, as shown in Figure 10 An image registration device 20 is provided, comprising: an acquisition module 21 and a determination module 22, wherein:

[0104] The acquisition module 21 is configured to acquire a preoperative three-dimensional image of a detection object and an intraoperative perspective view; the intraoperative perspective view includes an image of a first marker and an image of a second marker.

[0105] The determination module 22 is configured to determine a target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker; the target height is a distance between an imaging source and the detection object.

[0106] The determining module 22 is also configured to determine the target registration image according to the preoperative three-dimensional image, the intraoperative fluoroscopy, and the target height.

[0107] In one embodiment, the determining module 22 includes a registration unit and a first determining unit. The registration unit is configured to determine an intermediate registration relationship according to registration of a perspective view of the preoperative three-dimensional image and the intraoperative fluoroscopy. The perspective view of the preoperative three-dimensional image is consistent with the intraoperative fluoroscopy in orientation. The determining unit is configured to determine the target registration image according to the target height, the intermediate registration relationship, and the image of the third marker in the preoperative three-dimensional image.

[0108] In one embodiment, the determining module 22 further includes an obtaining unit and a second determining unit. The obtaining unit is configured to obtain a distance between the imaging source and the bearing assembly, a first actual size of the first marker, and a second actual size of the second marker. The second determining unit is configured to determine the target height according to the distance, the first actual size, the second actual size, a first size of the image of the first marker, and a second size of the image of the second marker.

[0109] In one embodiment, the second determining unit is specifically configured to determine the target height according to a first product of the first size and the second actual size, and a second product of the second size and the first actual size; and determine the target height according to the first product, the second product, and the distance.

[0110] In one embodiment, the registration unit is specifically configured to determine the image of the third marker in the preoperative three-dimensional image according to the position of the second marker; and register the perspective view of the preoperative three-dimensional image and the intraoperative fluoroscopy based on the image of the third marker and the image of the second marker in the perspective view of the preoperative three-dimensional image, to obtain the intermediate registration relationship.

[0111] The modules in the image registration apparatus described above can be implemented in whole or in part by software, hardware, or a combination thereof. The modules described above can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to the modules.

[0112] In one embodiment, an intraoperative guidance interventional system is provided, which includes a processor configured to perform the image registration method provided in the embodiments described above to realize three-dimensional real-time guidance in surgery.

[0113] The processor in the intraoperative guidance interventional system can obtain a three-dimensional target registration image through the image registration method described above, and use the target registration image as a road map to provide navigation for a doctor, so as to realize three-dimensional real-time guidance in surgery.

[0114] The intraoperative guidance intervention system in the embodiment is used for executing the steps of the image registration method in the above embodiment, and therefore has all the beneficial effects of the image registration method, which will not be described herein again.

[0115] In one embodiment, as shown in Figure 1 An imaging device is provided, which includes an imaging source 10, a detector 11, a bearing assembly 12 and a control assembly 13. The imaging device can be described with reference to the specific description of the above embodiment, which will not be described herein again.

[0116] The internal structure of the control assembly can be as shown in Figure 11 The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, mobile cellular network, NFC (Near Field Communication) or other technologies. The computer program is executed by the processor to implement an image registration method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0117] Those skilled in the art can understand that Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0118] In one embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the following steps:

[0119] Obtain a preoperative three-dimensional image of a detection object and an intraoperative perspective view; the intraoperative perspective view includes an image of a first marker and an image of a second marker;

[0120] Determine a target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker; the target height is a distance between the imaging source and the detection object.

[0121] determining the target registration image according to the preoperative three-dimensional image, the intraoperative fluoroscopy and the target height.

[0122] In one embodiment, the processor, when executing the computer program, further implements the following steps: determining an intermediate registration relationship according to registration of the perspective of the preoperative three-dimensional image and the intraoperative fluoroscopy; the perspective of the preoperative three-dimensional image is consistent with the intraoperative fluoroscopy; determining the target registration image according to the target height, the intermediate registration relationship and the image of the third marker in the preoperative three-dimensional image.

[0123] In one embodiment, the processor, when executing the computer program, further implements the following steps: obtaining a distance between the imaging source and the bearing assembly, a first actual size of the first marker and a second actual size of the second marker; determining the target height according to the distance, the first actual size, the second actual size, a first size of the image of the first marker and a second size of the image of the second marker.

[0124] In one embodiment, the processor, when executing the computer program, further implements the following steps: determining a first product of the first size and the second actual size, and a second product of the second size and the first actual size; determining the target height according to the first product, the second product and the distance.

[0125] In one embodiment, the processor, when executing the computer program, further implements the following steps: determining the image of the third marker in the preoperative three-dimensional image according to the position of the second marker; registering the perspective of the preoperative three-dimensional image and the intraoperative fluoroscopy based on the image of the third marker and the image of the second marker in the perspective of the preoperative three-dimensional image, to obtain an intermediate registration relationship.

[0126] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:

[0127] obtaining a preoperative three-dimensional image of a detection object and an intraoperative fluoroscopy; the intraoperative fluoroscopy includes an image of a first marker and an image of a second marker;

[0128] determining a target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker; the target height is a distance between an imaging source and the detection object;

[0129] determining the target registration image according to the preoperative three-dimensional image, the intraoperative fluoroscopy and the target height.

[0130] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: determining an intermediate registration relationship according to registration of the perspective view of the preoperative three-dimensional image and the intraoperative perspective view; the perspective view of the preoperative three-dimensional image is consistent with the orientation of the intraoperative perspective view; and determining the target registration image according to the target height, the intermediate registration relationship and the image of the third marker in the preoperative three-dimensional image.

[0131] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: obtaining the distance between the imaging source and the bearing assembly, the first actual size of the first marker and the second actual size of the second marker; and determining the target height according to the distance, the first actual size, the second actual size, the first size of the image of the first marker and the second size of the image of the second marker.

[0132] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: determining a first product of the first size and the second actual size, and a second product of the second size and the first actual size; and determining the target height according to the first product, the second product and the distance.

[0133] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: determining the image of the third marker in the preoperative three-dimensional image according to the position of the second marker; and obtaining an intermediate registration relationship by registering the perspective view of the preoperative three-dimensional image and the intraoperative perspective view based on the image of the third marker and the image of the second marker in the perspective view of the preoperative three-dimensional image.

[0134] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0135] obtaining a preoperative three-dimensional image of a detection object and an intraoperative perspective view; the intraoperative perspective view comprises an image of a first marker and an image of a second marker;

[0136] determining a target height according to the first marker and the second marker, and the image of the first marker and the image of the second marker; the target height is the distance between the imaging source and the detection object;

[0137] determining a target registration image according to the preoperative three-dimensional image, the intraoperative perspective view and the target height.

[0138] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: determining an intermediate registration relationship according to registration of the perspective view of the preoperative three-dimensional image and the intraoperative perspective view; the perspective view of the preoperative three-dimensional image is consistent with the orientation of the intraoperative perspective view; and determining the target registration image according to the target height, the intermediate registration relationship and the image of the third marker in the preoperative three-dimensional image.

[0139] In one embodiment, the computer program, when executed by the processor, further implements the steps of: obtaining a distance between the imaging source and the carrier assembly, a first actual size of the first marker and a second actual size of the second marker; determining the target height according to the distance, the first actual size, the second actual size, and a first size of the image of the first marker and a second size of the image of the second marker.

[0140] In one embodiment, the computer program, when executed by the processor, further implements the steps of: determining a first product of the first size and the second actual size, and a second product of the second size and the first actual size; determining the target height according to the first product, the second product and the distance.

[0141] In one embodiment, the computer program, when executed by the processor, further implements the steps of: determining an image of the third marker in the preoperative three-dimensional image according to the position of the second marker; and registering the intraoperative perspective view and the perspective view of the preoperative three-dimensional image based on the image of the third marker and the image of the second marker in the perspective view of the preoperative three-dimensional image, to obtain an intermediate registration relationship.

[0142] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0143] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0144] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An image registration method, characterized in that, An imaging device, comprising an imaging source and a carrier component, wherein the carrier component is provided with a first marker and a detection object carried by the carrier component is provided with a second marker, the method comprising: Acquire preoperative three-dimensional images and intraoperative perspective images of the object being detected; the intraoperative perspective images include images of the first marker and the second marker; The target height is determined based on the first marker and the second marker, as well as the images of the first marker and the second marker; the target height is the distance between the imaging source and the detected object. The intermediate registration relationship is determined by registering the preoperative 3D perspective view with the intraoperative perspective view; the orientation of the preoperative 3D perspective view and the intraoperative perspective view are consistent. The target registration image is determined based on the target height, the intermediate registration relationship, and the image of the third marker in the preoperative 3D image; the position of the third marker on the image of the detection object is the same as the position of the second marker on the image of the detection object. The step of determining the target height based on the first marker and the second marker, and the images of the first marker and the second marker, includes: The distance between the imaging source and the carrier component, the first actual size of the first marker, and the second actual size of the second marker are obtained. The target height is determined based on the distance, the first actual size, the second actual size, and the first size of the image of the first marker and the second size of the image of the second marker.

2. The method according to claim 1, characterized in that, Determining the target height based on the distance, the first actual size, the second actual size, and the first size of the image of the first marker and the second size of the image of the second marker includes: Determine a first product of the first dimension and the second actual dimension, and a second product of the second dimension and the first actual dimension; The target height is determined based on the first product, the second product, and the distance.

3. The method according to claim 1, characterized in that, The process of registering the preoperative 3D perspective image with the intraoperative perspective image to determine the intermediate registration relationship includes: Based on the location of the second marker, the image of the third marker is determined in the preoperative three-dimensional image; Based on the images of the third marker and the second marker in the perspective view of the preoperative three-dimensional image, the perspective view of the preoperative three-dimensional image and the perspective view of the intraoperative image are registered to obtain the intermediate registration relationship.

4. The method according to claim 3, characterized in that, The step of determining the image of the third marker in the preoperative three-dimensional image based on the position of the second marker includes: The imaging device scans the object to be detected to obtain an image of the third marker in the preoperative three-dimensional image; the object to be detected, supported by the carrier component, is provided with the third marker; or, In response to a user's marking operation on the preoperative 3D image based on the position of the second marker, an image of the third marker is obtained.

5. The method according to claim 1, characterized in that, The process of registering the preoperative 3D perspective image with the intraoperative perspective image to determine the intermediate registration relationship includes: Based on the digital reconstruction radiographic imaging method, the preoperative three-dimensional perspective view is obtained according to the orientation of the intraoperative perspective view; The perspective view of the preoperative 3D image and the perspective view of the intraoperative image are input into a pre-trained registration model to obtain the intermediate registration relationship.

6. An image registration device, characterized in that, An imaging device is used in an imaging apparatus, the imaging apparatus including an imaging source and a carrier component, the carrier component being provided with a first marker, and a detection object carried by the carrier component being provided with a second marker, the device comprising: The acquisition module is used to acquire preoperative three-dimensional images and intraoperative perspective images of the object to be detected; the intraoperative perspective images include images of a first marker and images of a second marker; The determining module is configured to determine the target height based on the first marker and the second marker, as well as the images of the first marker and the second marker; the target height is the distance between the imaging source and the detection object; The determination module is also used to register the perspective view of the preoperative three-dimensional image with the intraoperative perspective view to determine the intermediate registration relationship; the perspective view of the preoperative three-dimensional image and the intraoperative perspective view are aligned; and the target registration image is determined based on the target height, the intermediate registration relationship, and the image of the third marker in the preoperative three-dimensional image. The determining module includes an acquisition unit and a second determining unit. The acquisition unit is used to acquire the distance between the imaging source and the carrier component, the first actual size of the first marker, and the second actual size of the second marker. The second determining unit is used to determine the target height based on the distance, the first actual size, the second actual size, and the first size of the image of the first marker and the second size of the image of the second marker.

7. An intraoperative guidance interventional system, characterized in that, The method includes a processor that performs the steps of any one of claims 1 to 5 to achieve intraoperative three-dimensional real-time guidance.

8. An imaging device, characterized in that, The imaging device includes an imaging source, a detector, a carrier component, and a control component; the imaging source is correspondingly arranged with the detector, the carrier component is used to carry the detection object, the detector is connected to the control component, and the control component is used to execute the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images