Medical image and imaging device registration method, apparatus, device, and medium

Abstract

The application provides a medical image and a developing device registration method, device, equipment and medium, the method comprises the following steps: extracting an estimated area in a medical image to obtain a mask image; obtaining a connected domain of a developing device; calculating the center coordinate information and the first point cloud data of the developing device in the image coordinate system according to the connected domain, and extracting the pixel point coordinate; converting the pixel point coordinate into the image coordinate to form the image point cloud data; obtaining the center coordinate information and the second point cloud data of the developing device in the mechanical arm coordinate system to generate the simulation point cloud data; selecting the center coordinates of the developing device in the image coordinate system and the mechanical arm coordinate system to obtain an initial transformation matrix; performing initial transformation on the image point cloud data and the simulation point cloud data; using a registration algorithm to perform fitting registration to obtain a registration transformation matrix; and registering the medical image and the developing device according to the registration transformation matrix. The method is used for improving the registration accuracy and the registration speed of the medical image and the developing device.

Description

Technical Field

[0001] This invention relates to the field of medical image processing, and more particularly to a method, apparatus, device, and medium for registering medical images with imaging equipment. Background Technology

[0002] Percutaneous lung biopsy is a minimally invasive, safe, and effective diagnostic and differential diagnostic method that has been widely used in clinical practice in recent years. However, percutaneous puncture requires physicians to have extensive experience and skill, as accurate positioning and manipulation are necessary during the puncture of the pleural cavity to access the lung tissue, while avoiding blood vessels and vital organs as much as possible. This can present challenges for the operator, such as difficulty in positioning and needle insertion.

[0003] In recent years, surgical robots have begun to appear in many clinical surgeries and play an important role in puncture procedures. One of the key requirements of robotic puncture surgery is to ensure the registration effect between medical images and robotic arms. Current technologies suffer from low registration accuracy and slow registration speed, which can easily lead to registration failure and delays in treatment. Therefore, there is an urgent need for a new registration method, device, equipment, and medium for medical images and imaging equipment to improve these problems. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, device, and medium for registering medical images with imaging equipment, which improves the registration accuracy and speed of medical images with imaging equipment.

[0005] In a first aspect, the present invention provides a registration method for medical images and imaging devices, comprising: S1, acquiring a medical image containing N imaging devices, where N is greater than 2; S2, initializing a grayscale threshold, extracting a predicted region containing the imaging devices from the medical image to obtain a mask image; S3, performing connected component analysis based on the mask image to obtain the connected components of the imaging devices; S4, calculating the center coordinate information of the imaging devices in the image coordinate system and first point cloud data based on the connected components, and extracting the pixel coordinates of each imaging device in the pixel coordinate system; S5, converting the pixel coordinates to the spatial information and center coordinates of the medical image. S6. Convert the image coordinates to form image point cloud data; S7. Obtain the center coordinate information of the developing equipment in the robotic arm coordinate system and the second point cloud data, and generate simulated point cloud data according to the shape and size of the developing equipment; S8. Select the center coordinates of N developing devices in the image coordinate system and the robotic arm coordinate system to obtain the initial transformation matrix; S9. Perform initial transformation on the image point cloud data and simulated point cloud data according to the initial transformation matrix; S10. Use a registration algorithm to fit and register the initially transformed image point cloud data and simulated point cloud data to obtain the registration transformation matrix; Register the medical image and the developing equipment according to the registration transformation matrix.

[0006] The beneficial effects of the method of this invention are as follows: This invention calculates the center coordinate information of the developing device in the image coordinate system and the first point cloud data based on the connected components, and extracts the pixel coordinates of each developing device in the pixel coordinate system, which facilitates the location of the developing device in the medical image at its angle and position. By converting the pixel coordinates into image coordinates based on the spatial information and center coordinates of the medical image, image point cloud data is formed, providing accurate data support for subsequent registration. By obtaining the center coordinate information of the developing device in the robotic arm coordinate system and the second point cloud data, simulated point cloud data is generated according to the shape and size of the developing device, which makes the simulated point cloud data fit the image point cloud data better and improves the registration accuracy. Performing an initial transformation before executing the registration algorithm helps to speed up the registration process and avoid delaying the diagnosis.

[0007] Optionally, S4 includes: segmenting the medical image to obtain the pixel coordinate information of the imaging device in the medical image; calculating the image coordinate value of each pixel based on the image spacing and origin information; obtaining and saving the image coordinate value; and calculating the center coordinates of each imaging device in the pixel coordinate system.

[0008] Optionally, S4 includes: defining the outer point cloud interval of the image based on the center coordinate information in the image coordinate system; traversing all points in the first point cloud data, retaining only the first point cloud data within the outer point cloud interval of the image, and updating the first point cloud data; S6 includes: defining the outer point cloud interval of the robotic arm based on the center coordinate information in the robotic arm coordinate system; traversing all points in the second point cloud data, retaining only the second point cloud data within the outer point cloud interval of the robotic arm, and updating the second point cloud data.

[0009] Optionally, S4 includes: forming a spherical point cloud based on each center coordinate in the image coordinate system; setting an image angle interval, retaining only the first point cloud data within the image angle interval, and updating the first point cloud data; S6 includes: forming a spherical point cloud based on each center coordinate in the robotic arm coordinate system; setting a robotic arm angle interval, retaining only the second point cloud data within the robotic arm angle interval, and updating the second point cloud data.

[0010] Optionally, S9 includes: using an iterative nearest-point algorithm to fit and register the initially transformed image point cloud data and the initially transformed simulated point cloud data until the convergence condition is met or the maximum number of iterations is reached, so as to achieve the best match.

[0011] Optionally, the outer layer of the simulated point cloud data has the same shape as the developing equipment; the size of the simulated point cloud data is proportional to the size of the developing equipment.

[0012] Optionally, S1 includes: when N is set to 3, acquiring a medical image containing 3 imaging devices; wherein the distance from the center line connecting any 2 imaging devices to the remaining imaging device is L, and L is greater than 0.

[0013] Optionally, the developing device is configured with metal beads; the metal beads are made of at least one metal or alloy selected from iron, titanium, cobalt, tantalum, niobium, and zirconium.

[0014] In a second aspect, the present invention provides a registration apparatus for medical images and imaging devices, used in the method described in any one of the first aspects, comprising: an acquisition unit for acquiring a medical image containing N imaging devices, where N is greater than 2; a processing unit for initializing a grayscale threshold, extracting a predicted region containing imaging devices from the medical image to obtain a mask image; performing connected component analysis based on the mask image to obtain connected components of the imaging devices; calculating the center coordinate information of the imaging devices in the image coordinate system and first point cloud data based on the connected components, and extracting the pixel coordinates of each imaging device in the pixel coordinate system; and calculating the center coordinate information of the imaging devices in the image coordinate system and first point cloud data based on the connected components; and extracting the pixel coordinates of each imaging device in the pixel coordinate system based on the spatial information of the medical image and the center coordinate information of the imaging devices in the image coordinate system. The pixel coordinates are converted into image coordinates to form image point cloud data; the center coordinate information of the developing equipment in the robotic arm coordinate system and the second point cloud data are obtained, and simulated point cloud data is generated according to the shape and size of the developing equipment; the center coordinates of N developing devices in the image coordinate system and the robotic arm coordinate system are selected to obtain an initial transformation matrix; the image point cloud data and the simulated point cloud data are initially transformed according to the initial transformation matrix; the initially transformed image point cloud data and the simulated point cloud data are fitted and registered using a registration algorithm to obtain a registration transformation matrix; and the medical image and the developing equipment are registered according to the registration transformation matrix.

[0015] Optionally, the processing unit is further configured to perform segmentation processing on the medical image, obtain the pixel coordinate information of the imaging device in the medical image, calculate the image coordinate value of each pixel based on the image spacing and origin information; obtain the image coordinate value, and calculate the center coordinate of each imaging device; the device further includes a storage unit for storing the image coordinate value.

[0016] Thirdly, the present invention provides an electronic device including a memory and a processor, wherein the memory stores a program executable on the processor, and when the program is executed by the processor, the electronic device performs the method described in any one of the first aspects.

[0017] Fourthly, the present invention provides a readable storage medium storing a program, which, when executed, implements the method described in any one of the first aspects. Attached Figure Description

[0018] Figure 1A schematic flowchart illustrating a registration method for medical images and imaging equipment provided by the present invention;

[0019] Figure 2 This is a schematic diagram of the main structure of a developing device mounted on a cantilever beam, as provided by the present invention.

[0020] Figure 3 A top view schematic diagram of a developing device mounted on a cantilever beam, provided by the present invention;

[0021] Figure 4 A schematic diagram of a mask image provided by the present invention;

[0022] Figure 5 This is a schematic diagram illustrating the fitting and registration of initially transformed image point cloud data and simulated point cloud data provided by the present invention.

[0023] Figure 6 A schematic diagram of the structure of a registration device for medical imaging and imaging equipment provided by the present invention;

[0024] Figure 7 This is a schematic diagram of the structure of an electronic device provided by the present invention.

[0025] Numbering on the map:

[0026] 1. Developing equipment; 2. Cantilever beam; 3. Image point cloud; 4. Simulated point cloud;

[0027] 51. Acquisition unit; 511. Radio frequency pulse generator; 512. Magnet; 513. Gradient coil; 514. Receiver; 52. Processing unit; 53. Storage unit; 54. Robotic arm;

[0028] 61. Processor; 62. Memory; 63. Output interface; 64. Communication interface; 65. Antenna. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions in the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention. Unless otherwise defined, the technical or scientific terms used herein should have the ordinary meaning understood by those skilled in the art. The terms "comprising" and similar expressions used herein mean that the element or object preceding the word covers the element or object listed following the word and its equivalents, but do not exclude other elements or objects.

[0030] In response to the problems existing in the current technology, such as Figure 1 As shown, the first embodiment provides a registration method for medical images and imaging devices, including: S1, acquiring a medical image containing N imaging devices, where N is greater than 2; S2, initializing a grayscale threshold, extracting a predicted region containing imaging devices from the medical image to obtain a mask image; S3, performing connected component analysis based on the mask image to obtain the connected components of the imaging devices; S4, calculating the center coordinate information of the imaging devices in the image coordinate system and the first point cloud data based on the connected components, and extracting the pixel coordinates of each imaging device in the pixel coordinate system; S5, converting the pixel coordinates to the spatial information and center coordinates of the medical image. S6. Convert the image coordinates to form image point cloud data; S7. Obtain the center coordinate information of the developing equipment in the robotic arm coordinate system and the second point cloud data, and generate simulated point cloud data according to the shape and size of the developing equipment; S8. Select the center coordinates of N developing devices in the image coordinate system and the robotic arm coordinate system to obtain the initial transformation matrix; S9. Perform initial transformation on the image point cloud data and simulated point cloud data according to the initial transformation matrix; S10. Use a registration algorithm to fit and register the initially transformed image point cloud data and simulated point cloud data to obtain the registration transformation matrix; Register the medical image and the developing equipment according to the registration transformation matrix.

[0031] It is worth noting that this embodiment calculates the center coordinates of the developing device in the image coordinate system and the first point cloud data based on the connected components, extracting the pixel coordinates of each developing device in the pixel coordinate system. This facilitates locating the angle and position of the developing device in the medical image. By converting the pixel coordinates into image coordinates based on the spatial information and center coordinates of the medical image, image point cloud data is formed, providing accurate data support for subsequent registration. By obtaining the center coordinates of the developing device in the robotic arm coordinate system and the second point cloud data, simulated point cloud data is generated based on the shape and size of the developing device. This allows the simulated point cloud data to better match the image point cloud data, improving registration accuracy. Performing an initial transformation before executing the registration algorithm helps to speed up registration and avoid delaying treatment.

[0032] In some embodiments, S1 includes: when N is set to 3, acquiring a medical image containing 3 imaging devices; wherein the distance from the center line connecting any two imaging devices to the remaining imaging device is L, and L is greater than 0.

[0033] In some embodiments, the developing apparatus is configured with metal beads; the metal beads are made of at least one metal or alloy selected from iron, titanium, cobalt, tantalum, niobium, and zirconium. For example... Figure 2 and Figure 3As shown, specifically, the imaging device 1 is configured with 10 steel balls, located around the periphery of the cantilever beam 2. The cantilever beam 2 is connected to a robotic arm, which drives the movement of the puncture needle. In some other specific embodiments, the imaging device is configured with 3 titanium alloy balls. In still other specific embodiments, the medical image is a magnetic resonance imaging (MRI) image. It is worth noting that the imaging device can be configured with any three-dimensional geometric shape that facilitates the determination of its geometric center. The size of the imaging device can be any value, as long as the field of view of the medical image can accommodate at least 3 imaging devices.

[0034] In some embodiments, S2 includes: reading a preset grayscale threshold, extracting pixel regions from the medical image whose grayscale values ​​are within the grayscale threshold, and obtaining a binary mask image.

[0035] like Figure 4 As shown, specifically, the white areas in the mask image are the target areas, and the black areas are the non-target areas. The number of connected components in the target area is 5. In some embodiments, the number of connected components is the same as the number of developing devices. The number of connected components can be any integer greater than 2.

[0036] In some embodiments, S3 includes: performing connected component analysis on the mask image using an eight-neighbor labeling algorithm to obtain the connected components of the developing device. In other specific embodiments, depth-first search (DFS) is used to perform connected component analysis on the mask image. In still other specific embodiments, breadth-first search (BFS) is used to perform connected component analysis on the mask image.

[0037] In some embodiments, S4 includes: segmenting the medical image to obtain the pixel coordinate information of the imaging device in the medical image; calculating the image coordinate value of each pixel based on the image spacing and origin information; obtaining and saving the image coordinate value; and calculating the center coordinates of each imaging device in the pixel coordinate system.

[0038] In some embodiments, S5 includes: setting the coordinates corresponding to the image point cloud data in a pixel coordinate system to lie on a sphere centered at a central coordinate. The number of image point cloud data corresponding to each central coordinate is X, where X is any positive integer.

[0039] In some embodiments, S4 includes: defining an outer point cloud region of the image based on the center coordinate information in the image coordinate system; traversing all points in the first point cloud data, retaining only the first point cloud data within the outer point cloud region of the image, and updating the first point cloud data; S6 includes: defining an outer point cloud region of the robotic arm based on the center coordinate information in the robotic arm coordinate system; traversing all points in the second point cloud data, retaining only the second point cloud data within the outer point cloud region of the robotic arm, and updating the second point cloud data.

[0040] Specifically, the outer layer of the simulated point cloud data has the same shape as the developing equipment; the size of the simulated point cloud data is proportional to the size of the developing equipment.

[0041] In some embodiments, S4 includes: forming a spherical point cloud based on each center coordinate in the image coordinate system; setting an image angle interval, retaining only the first point cloud data within the image angle interval, and updating the first point cloud data; S6 includes: forming a spherical point cloud based on each center coordinate in the robotic arm coordinate system; setting a robotic arm angle interval, retaining only the second point cloud data within the robotic arm angle interval, and updating the second point cloud data.

[0042] In some embodiments, S7 includes: when N is 3, selecting the center coordinates of 3 developing devices in the image coordinate system and the robotic arm coordinate system to obtain an initial transformation matrix.

[0043] It is worth noting that the initial transformation matrix includes a variance matrix and a covariance matrix, where the covariance matrix H satisfies:

[0044] H = (A-centroid) A (B-centroid) B ) T

[0045]

[0046]

[0047] Where A is the coordinate matrix of the developing equipment in the image coordinate system, and B is the coordinate matrix of the developing equipment in the robotic arm coordinate system. A Centroid is the center coordinate function of the developing device in the image coordinate system. B Let N be the center coordinate function of the developing equipment in the robotic arm coordinate system, N be the total number of developing equipment, i be the number of the current developing equipment, and T be the rotation matrix, satisfying:

[0048]

[0049] t = A-centroidB -R×centroid A

[0050] R = VU T

[0051] [U,S,V]=SVD(H)

[0052] Where t is the displacement, R is the rotation coefficient, SVD is the singular value decomposition function, and U, S, and V are the three decomposition results of the singular value decomposition function.

[0053] like Figure 5 As shown, in some embodiments, S9 includes: using an iterative nearest-point algorithm to fit and register the initially transformed image point cloud data and the initially transformed simulated point cloud data, repeating the above process until the convergence condition is met or the maximum number of iterations is reached, in order to achieve the best match. During this process, the initially transformed image point cloud 3 and the initially transformed simulated point cloud 4 approach each other until they overlap.

[0054] Specifically, the Iterative Closest Point (ICP) algorithm is used for registration, including:

[0055] S91, Initialization: Select an initial transformation matrix to align the source point cloud and the target point cloud. For example, determine that the image point cloud is the source point cloud to be aligned, and determine that the simulated point cloud is the target point cloud. In another example, determine that the simulated point cloud is the source point cloud to be aligned, and determine that the image point cloud is the target point cloud.

[0056] S92, Nearest Neighbor Search: For each point in the source point cloud, find the nearest point in the target point cloud and generate a search result. S93, Determine Correspondence: Based on the search results, establish the correspondence between the source and target point clouds. S94, Calculate Transformation: Based on the correspondence, calculate the transformation matrix between the source and target point clouds. S95, Apply Transformation: Substitute the source point cloud into the transformation matrix to obtain the aligned point cloud.

[0057] Repeat steps S92-S95 until a termination condition is met; for example, the termination condition is reaching the maximum number of iterations. In another example, the termination condition is that the change in the transformation matrix is ​​less than a threshold. It's worth noting that the output of the ICP algorithm is a transformation matrix that describes the translations and rotations required to align the source point cloud to the target point cloud. By applying the transformation matrix to the source point cloud, point cloud data aligned with the target point cloud can be obtained.

[0058] like Figure 6As shown, the second embodiment provides a registration device for medical images and imaging equipment, used in the method described in any one of the first embodiments, comprising: an acquisition unit 51, used to acquire a medical image containing N imaging equipment, where N is greater than 2; a processing unit 52, used to initialize a grayscale threshold, extract a predicted region containing imaging equipment from the medical image to obtain a mask image; perform connected component analysis based on the mask image to obtain the connected components of the imaging equipment; calculate the center coordinate information of the imaging equipment in the image coordinate system and the first point cloud data based on the connected components, and extract the pixel coordinates of each imaging equipment in the pixel coordinate system; and perform spatial information analysis based on the medical image and... The center coordinates are used to convert the pixel coordinates into image coordinates to form image point cloud data; the center coordinate information of the developing equipment in the 54 coordinate system of the robotic arm and the second point cloud data are obtained, and simulated point cloud data is generated according to the shape and size of the developing equipment; the center coordinates of N developing devices in the image coordinate system and the 54 coordinate system of the robotic arm are selected to obtain an initial transformation matrix; the image point cloud data and the simulated point cloud data are initially transformed according to the initial transformation matrix; the initially transformed image point cloud data and the simulated point cloud data are fitted and registered using a registration algorithm to obtain a registration transformation matrix; the medical image and the developing equipment are registered according to the registration transformation matrix.

[0059] Specifically, the acquisition unit includes, but is not limited to, magnetic resonance imaging equipment or X-ray imaging equipment. For example, the acquisition unit 51 includes a magnet 512, a radio frequency pulse generator 511, a receiver 514, and a gradient coil 513, while the processing unit 52 is configured as a processor 61.

[0060] In some embodiments, the processing unit 52 is further configured to perform segmentation processing on the medical image, obtain the pixel coordinate information of the imaging device in the medical image, calculate the image coordinate value of each pixel according to the image spacing and origin information, obtain the image coordinate value, and calculate the center coordinate of each imaging device; the device further includes a storage unit 53 for storing the image coordinate value.

[0061] like Figure 7 As shown, the third embodiment provides an electronic device including a memory 62 and a processor 61. The memory 62 stores a program that can run on the processor 61. When the program is executed by the processor 61, the electronic device performs the method described in any of the above embodiments.

[0062] In one possible embodiment, the electronic device further includes: an output interface 63 for outputting results; a communication interface 64 for transmitting communication signals; and an antenna 65 for transmitting or receiving signals.

[0063] It should be noted that the processor 61 in this embodiment can be an image processing chip or an integrated circuit chip, capable of processing image signals. In implementation, each step of the above method embodiment can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices. It can implement or execute the methods, steps, and logic block diagrams disclosed in this embodiment. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this embodiment can be directly implemented by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0064] It is understood that the memory 62 in this embodiment can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0065] The fourth embodiment provides a readable storage medium storing a program, which, when executed, implements the method described in any one of the above embodiments.

[0066] While embodiments of the present invention have been described in detail above, it will be apparent to those skilled in the art that various modifications and variations can be made to these embodiments. However, it should be understood that such modifications and variations fall within the scope and spirit of the invention as set forth in the claims. Furthermore, the invention described herein may have other embodiments and can be implemented or carried out in various ways.

Claims

1. A method for registering medical images with imaging equipment, characterized in that, include: S1, acquire medical images containing N imaging devices, where N is greater than 2; S2, initialize grayscale threshold, extract the estimated region containing the imaging device in the medical image to obtain the mask image; S3, perform connected component analysis based on the mask image to obtain the connected components of the developing device; S4. Calculate the center coordinate information of the developing device in the image coordinate system and the first point cloud data based on the connected component, and extract the pixel coordinates of each developing device in the pixel coordinate system. S5. Based on the spatial information and center coordinates of the medical image, the pixel coordinates are converted into image coordinates to form image point cloud data. S6, acquire the center coordinate information of the developing device in the robot arm coordinate system and the second point cloud data, and generate simulated point cloud data according to the shape and size of the developing device; the outer layer of the simulated point cloud data is the same as the shape of the developing device; the size of the simulated point cloud data is proportional to the size of the developing device; S7, select the center coordinates of N developing devices in the image coordinate system and the robotic arm coordinate system to obtain the initial transformation matrix; S8, Perform initial transformation on the image point cloud data and the simulated point cloud data according to the initial transformation matrix; S9, use a registration algorithm to fit and register the initially transformed image point cloud data and the simulated point cloud data to obtain a registration transformation matrix; register the medical image and imaging equipment according to the registration transformation matrix.

2. The method according to claim 1, characterized in that, S4 includes: The medical image is segmented to obtain the pixel coordinate information of the imaging device in the medical image. The image coordinate value of each pixel is calculated based on the image spacing and origin information. The image coordinate values ​​are obtained and saved, and the center coordinates of each imaging device in the pixel coordinate system are calculated.

3. The method according to claim 1 or 2, characterized in that, S4 includes: defining the outer point cloud region of the image based on the center coordinate information in the image coordinate system; traversing all points in the first point cloud data, retaining only the first point cloud data within the outer point cloud region of the image, and updating the first point cloud data; S6 includes: defining the outer point cloud interval of the robotic arm based on the center coordinate information in the robotic arm coordinate system; traversing all points in the second point cloud data, retaining only the second point cloud data within the outer point cloud interval of the robotic arm, and updating the second point cloud data.

4. The method according to claim 1 or 2, characterized in that, S4 includes: forming a spherical point cloud based on each center coordinate in the image coordinate system; setting an image angle interval, retaining only the first point cloud data within the image angle interval, and updating the first point cloud data; S6 includes: forming a spherical point cloud based on each center coordinate in the robot arm coordinate system; setting the robot arm angle interval, retaining only the second point cloud data within the robot arm angle interval, and updating the second point cloud data.

5. The method according to claim 1 or 2, characterized in that, S9 includes: The iterative nearest point algorithm is used to fit and register the initially transformed image point cloud data and the initially transformed simulated point cloud data until the convergence condition is met or the maximum number of iterations is reached, so as to achieve the best match.

6. A registration apparatus for medical imaging and imaging equipment, used in the method according to any one of claims 1 to 5, characterized in that, include: The acquisition unit is used to acquire medical images containing N imaging devices, where N is greater than 2. The processing unit is used to initialize the grayscale threshold, extract the estimated region containing the imaging device in the medical image, and obtain the mask image. Connectivity analysis is performed on the masked image to obtain the connected components of the developing equipment. Based on these connected components, the center coordinates of the developing equipment in the image coordinate system and the first point cloud data are calculated. The pixel coordinates of each developing equipment in the pixel coordinate system are extracted. Based on the spatial information and center coordinates of the medical image, the pixel coordinates are converted into image coordinates to form image point cloud data. The center coordinates of the developing equipment in the robotic arm coordinate system and the second point cloud data are obtained. Simulated point cloud data is generated based on the shape and size of the developing equipment. The center coordinates of N developing equipment in the image coordinate system and the robotic arm coordinate system are selected to obtain an initial transformation matrix. An initial transformation is performed on the image point cloud data and the simulated point cloud data based on the initial transformation matrix. A registration algorithm is used to fit and register the initially transformed image point cloud data and the simulated point cloud data to obtain a registration transformation matrix. The medical image and the developing equipment are registered based on the registration transformation matrix.

7. The apparatus according to claim 6, characterized in that, The processing unit is also used to segment medical images, obtain pixel coordinate information of the imaging devices in the medical images, calculate the image coordinate value of each pixel based on the image spacing and origin information, obtain the image coordinate value, and calculate the center coordinates of each imaging device; The device also includes a storage unit for storing the image coordinate values.

8. An electronic device, characterized in that, The device includes a memory and a processor, wherein the memory stores a program that can run on the processor, and when the program is executed by the processor, causes the electronic device to perform the method of any one of claims 1 to 5.

9. A readable storage medium storing a program, characterized in that, When the program is executed, it implements the method of any one of claims 1 to 5.

Images