Medical image device calibration method and apparatus, storage medium, and electronic device

Abstract

The application provides a medical image equipment calibration method and device, a storage medium and an electronic device. The medical image equipment calibration method comprises: acquiring a to-be-processed image, the to-be-processed image being an image of a calibration tool collected by a medical image equipment; processing the to-be-processed image to obtain image coordinates of a mark ball, the mark ball comprising a first mark ball and a second mark ball; obtaining a cross ratio coefficient of each mark ball group according to the image coordinates of the mark ball; determining a matching relationship between the image coordinates of each mark ball and a world coordinate according to the cross ratio coefficient; and obtaining a calibration parameter of the medical image equipment according to the matching relationship. The calibration method can realize calibration of the medical image equipment.

Description

Technical Field

[0001] This application belongs to the field of image system calibration, and relates to a device calibration method, particularly to a medical imaging device calibration method, apparatus, storage medium and electronic equipment. Background Technology

[0002] Medical imaging equipment plays a vital role in modern medical diagnosis. With advancements in medical science and continuous technological development, medical imaging equipment has evolved and improved, providing doctors with more accurate and detailed image information, thereby enhancing the diagnosis and treatment of diseases. Medical imaging equipment is specifically designed to acquire information about the internal structure and function of the human body. Through the use of different physical principles and technologies, it can generate various types of medical images, such as X-ray images, ultrasound images, computed tomography (CT) images, magnetic resonance imaging (MRI) images, and positron emission tomography (PET) images.

[0003] Calibration is a crucial step in the use of medical imaging equipment, aiming to ensure that the images acquired by the equipment contain accurate and reliable information. The calibration process involves comparing the equipment's measurements with true values ​​and making appropriate adjustments and calibrations to eliminate systematic errors and ensure accuracy. Currently, the calibration of medical imaging equipment is typically performed manually, which is inefficient and prone to errors caused by subjective human factors. Summary of the Invention

[0004] This application provides a medical imaging equipment calibration method, apparatus, storage medium, and electronic device to solve the problems of low efficiency and easy error caused by human subjective factors in existing calibration methods.

[0005] In a first aspect, embodiments of this application provide a method for calibrating a medical imaging device. The method includes: acquiring an image to be processed, wherein the image to be processed is an image of a calibration tool acquired by the medical imaging device, the calibration tool comprising multiple groups of marker spheres, each group comprising one first marker sphere and three second marker spheres arranged collinearly, the size of the first marker sphere being different from that of the second marker spheres, and the cross-ratio coefficient of each group of marker spheres being different; processing the image to be processed to obtain image coordinates of the marker spheres, the marker spheres comprising the first and second marker spheres; obtaining the cross-ratio coefficient of each group of marker spheres based on the image coordinates of the marker spheres; determining the matching relationship between the image coordinates of each marker sphere and world coordinates based on the cross-ratio coefficient; and obtaining calibration parameters of the medical imaging device based on the matching relationship.

[0006] In one implementation of the first aspect, processing the image to be processed to obtain the image coordinates of the marker sphere includes: processing the image to be processed using a medical image processing model to obtain a first heatmap model and a second heatmap model, wherein the first heatmap model and the second heatmap model are heatmap models of the first marker sphere and the second marker sphere, respectively; and obtaining the image coordinates of the first marker sphere and the second marker sphere based on the first heatmap model and the second heatmap model.

[0007] In one implementation of the first aspect, obtaining the image coordinates of the first marker sphere based on the first heatmap model includes: segmenting the first heatmap model into binary labels; obtaining the centroid coordinates of the connected components of the first heatmap model; and obtaining the image coordinates of the first marker sphere based on the centroid coordinates.

[0008] In one implementation of the first aspect, the medical image processing model includes an encoder and a decoder. Processing the image to be processed using the medical image processing model to obtain a first heatmap model and a second heatmap model includes: extracting image features from the image to be processed using the encoder to obtain feature maps of different resolutions; transmitting the feature maps to the decoder via skip connections; and processing the feature maps using the decoder to obtain the first heatmap model and the second heatmap model.

[0009] In one implementation of the first aspect, obtaining the cross ratio coefficient of the marker ball group based on the image coordinates of the marker ball includes: taking the first marker ball as a reference point, obtaining a plurality of straight lines passing through the reference point; obtaining a second marker ball that is collinear with the first marker ball based on the positional relationship between the second marker ball and the straight lines; and obtaining the cross ratio coefficient of the marker ball group including the first marker ball based on the image coordinates of the first marker ball and the second marker ball that is collinear with it.

[0010] In one implementation of the first aspect, obtaining a second marker ball collinear with the first marker ball based on the positional relationship between the second marker ball and the straight line includes: obtaining the distance between each second marker ball and each straight line; obtaining the neighboring marker balls of each straight line based on the distance, wherein the neighboring marker balls of the straight line are the three second marker balls closest to the straight line; obtaining a target straight line based on the distance between each straight line and its neighboring marker balls, wherein the neighboring marker balls of the target straight line are the second marker balls collinear with the first marker ball.

[0011] In one implementation of the first aspect, the image to be processed is a two-dimensional image or a three-dimensional image.

[0012] Secondly, embodiments of this application provide a medical imaging equipment calibration device, comprising: an image acquisition module for acquiring an image to be processed, wherein the image to be processed is an image of a calibration tool acquired by a medical imaging equipment, the calibration tool comprising multiple groups of marker spheres, each group of marker spheres comprising one first marker sphere and three second marker spheres arranged collinearly, the size of the first marker sphere being different from that of the second marker spheres, and the cross ratio coefficient of each group of marker spheres being different; an image coordinate acquisition module for processing the image to be processed to obtain image coordinates of the marker spheres, wherein the marker spheres include the first marker sphere and the second marker sphere; a cross ratio coefficient acquisition module for obtaining the cross ratio coefficient of each group of marker spheres based on the image coordinates of the marker spheres; a matching relationship acquisition module for determining the matching relationship between the image coordinates and world coordinates of each marker sphere based on the cross ratio coefficient; and a calibration parameter acquisition module for obtaining calibration parameters of the medical imaging equipment based on the matching relationship.

[0013] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the medical imaging equipment calibration method described in any one of the first aspects of this application.

[0014] Fourthly, embodiments of this application provide an electronic device, the electronic device comprising: a memory storing a computer program; and a processor communicatively connected to the memory, which executes the medical imaging equipment calibration method described in any one of the first aspects of this application when the computer program is invoked.

[0015] In summary, this application provides a method for calibrating medical imaging equipment. This method utilizes a specially designed calibration tool and, based on the principle of cross-ratio invariance, can achieve fully automated detection of the coordinates of a marker sphere and automatically acquire the calibration parameters of the medical imaging equipment. Compared to existing technologies, this method is more efficient and avoids errors caused by human subjective factors. Attached Figure Description

[0016] Figure 1 The diagram shows an application scenario of the medical imaging equipment calibration method in this application.

[0017] Figure 2 The flowchart shown is a medical imaging equipment calibration method provided in an embodiment of this application.

[0018] Figure 3A The flowchart shown is a process for obtaining image coordinates in an embodiment of this application.

[0019] Figure 3B The diagram shown is a structural schematic of the medical image processing model in an embodiment of this application.

[0020] Figure 3C The flowchart shown is a process for obtaining a heat map model in an embodiment of this application.

[0021] Figure 3D The flowchart shown is a process for obtaining image coordinates in an embodiment of this application.

[0022] Figure 4A The flowchart shown is a process for obtaining the cross ratio coefficient of the marker ball group in an embodiment of this application.

[0023] Figure 4B The flowchart shown is a process for obtaining the target straight line in an embodiment of this application.

[0024] Figure 5 The diagram shown is a structural schematic of the medical imaging equipment calibration device in an embodiment of this application.

[0025] Figure 6 The diagram shown is a structural schematic of an electronic device in an embodiment of this application.

[0026] Component designation explanation

[0027] 500 Medical Imaging Equipment Calibration Device

[0028] 510 Image Acquisition Module

[0029] 520 Image Coordinate Acquisition Module

[0030] 530 Cross-ratio Coefficient Acquisition Module

[0031] 540 Matching Relationship Acquisition Module

[0032] 550 Calibration Parameter Acquisition Module

[0033] 600 electronic devices

[0034] 610 Memory

[0035] 620 processor

[0036] 630 monitor

[0037] Steps S21 to S25

[0038] Steps S31 to S32

[0039] Steps S311~S313

[0040] Steps S321~S323

[0041] Steps S41 to S43

[0042] Steps S421~S423 Detailed Implementation

[0043] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0044] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the illustrations only show the components related to this application and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0045] In the field of medical imaging and surgical navigation, establishing transformation relationships between different coordinate systems is a crucial issue, with three-dimensional rigid transformations and projective transformations being the most common. For example, in tasks such as calibration of a flat C-arm, 2D-3D registration, and 3D-3D registration, it is necessary to solve for the corresponding spatial transformation relationships to achieve system calibration or information fusion. Before solving for the spatial transformation, two tasks are required: first, detecting the position of the marker sphere in the image and obtaining the spatial coordinates (2D or 3D) of its center point; second, constructing the correspondence between the marker spheres and matching the image coordinates and world coordinates of the marker sphere's center point. In some technical solutions, the user manually selects image coordinate points and matches their corresponding world coordinates, or adjusts parameters to achieve relatively accurate detection and matching results in the calibration algorithm. These manual or semi-automatic methods, in actual clinical use, often require users to be very familiar with the spatial distribution and shape characteristics of the marker spheres, and also require strong spatial perception abilities, often consuming a significant amount of operation time. Therefore, these technical solutions generally suffer from low efficiency and may be subject to errors due to human subjective factors.

[0046] To address at least the aforementioned problems, this application provides a method for calibrating medical imaging equipment. This method utilizes a specially designed calibration tool and, based on the principle of cross-ratio invariance, can achieve fully automated detection of the coordinates of a marker sphere and automatically acquire the calibration parameters of the medical imaging equipment. Compared to existing technologies, this method is more efficient and avoids errors caused by human subjective factors.

[0047] Figure 1 This diagram illustrates an application scenario of the medical imaging equipment calibration method provided in this application. The medical imaging equipment refers to a device capable of acquiring information about the internal structure and function of the human body and generating medical images. In this application embodiment, the medical imaging equipment can be a flat-panel C-arm for two-dimensional imaging or a CT scanner for three-dimensional imaging; both use X-rays and computer technology to acquire detailed images of the internal structure of the human body. The flat-panel C-arm transmits X-rays through the body at a certain angle, then uses sensors to receive the X-rays passing through the body and transmits the received data to a computer for processing. CT scans the human body using X-ray tomography and reconstruct a three-dimensional image of the human body from the data. It should be noted that the medical imaging equipment described in this application is not limited to a flat-panel C-arm or a CT scanner.

[0048] In this embodiment, the medical imaging device and the electronic device can communicate via a data transmission interface. In some possible implementations, the medical imaging device is equipped with a data transmission interface, such as an Ethernet interface, a Universal Serial Bus (USB) interface, or a serial interface. These interfaces allow the medical imaging device to transmit image data and device control information to the electronic device for processing and storage.

[0049] Electronic devices include one or more data storage units and a processor connected thereto. The data storage unit may include a storage medium and a memory unit. The storage medium may be read-only, such as read-only memory (ROM), or read-write, such as a hard disk or flash memory. The memory unit may be random access memory (RAM). The memory unit may be integrated with the processor or may be a separate component.

[0050] A processor is the control center of an electronic device, used to execute program code to perform functions corresponding to the program instructions. Optionally, a processor includes one or more Central Processing Units (CPUs). Optionally, an electronic device includes more than one processor, which may be a single-core processor or a multi-core processor. As used herein, the term "processor" refers to one or more devices, circuits, and / or processing cores used to process data such as computer program instructions.

[0051] The CPU of a processor stores the program code it executes in memory or a storage medium. Optionally, the program code stored in the storage medium can be copied to memory for the processor to execute. The processor can control the operation of electronic devices by controlling the execution of other programs, controlling communication with peripheral devices, and controlling the use of electronic device resources.

[0052] Electronic devices may also include a communication interface through which they can communicate directly with another device or system or via an external network.

[0053] Optionally, the electronic device also includes output devices and input devices. Output devices are connected to the processor and are capable of displaying output information in one or more ways. An example of an output device is a visual display device, such as a liquid crystal display (LCD), a light-emitting diode (LED) display, a cathode ray tube (CRT), or a projector. Input devices are connected to the processor and are capable of receiving user input in one or more ways. Examples of input devices include a mouse, keyboard, touchscreen device, sensing device, and so on.

[0054] The aforementioned components of the electronic device can be interconnected through any one or more combinations of buses such as data bus, address bus, control bus, expansion bus, and local bus.

[0055] The calibration tool contains multiple sets of marker balls. Figure 1 The diagram shows the structure of one of the marker sphere groups. Each marker sphere group consists of one first marker sphere and three second marker spheres arranged collinearly. The dimensions of the first marker spheres differ from those of the second marker spheres, and the cross ratio coefficient of each marker sphere group is different. The first and second marker spheres have specific radius designs, positional layouts, and spatial relationships, and their world coordinates in the world coordinate system are known.

[0056] In some possible implementations, the size of the first marker ball is larger than the size of the second marker ball.

[0057] In some possible implementations, both the first and second marker spheres are metal spheres that can be clearly visualized in flat panel X-ray imaging and CT scan imaging.

[0058] Figure 2 The flowchart shown is a medical imaging equipment calibration method provided in an embodiment of this application. This medical imaging equipment calibration method can be used, for example, in [the following context is missing from the original text]. Figure 1 The electronic device shown is for... Figure 1 The medical imaging equipment shown is calibrated. For example... Figure 2 As shown, the medical imaging equipment calibration method provided in this application includes the following steps S21 to S25.

[0059] S21, acquire the image to be processed. The image to be processed is an image of the calibration tool acquired by the medical imaging equipment. In this embodiment, the calibration tool includes M groups of marker spheres, each with a different cross-ratio coefficient, where M is a positive integer. The cross-ratio coefficient of the marker sphere group refers to the cross-ratio coefficient calculated based on the coordinates of each marker sphere in the group. The image to be processed can be obtained by imaging the M groups of marker spheres using the medical imaging equipment.

[0060] S22 processes the image to be processed to obtain the image coordinates of the marker spheres. The marker spheres include a first marker sphere and a second marker sphere. The image coordinates of the marker spheres refer to their coordinates in an image coordinate system, which is a coordinate system established with the points in the image to be processed as the origin.

[0061] S23, obtain the cross ratio coefficient of each group of marker balls based on the image coordinates of the marker balls.

[0062] S24. Determine the matching relationship between the image coordinates and world coordinates of each marker sphere based on the cross-ratio coefficient. Specifically, the cross-ratio coefficient is invariant under rigid transformation and projective transformation; therefore, the cross-ratio coefficient calculated based on the world coordinates of the marker sphere is equal to the cross-ratio coefficient calculated based on the image coordinates of the marker sphere. Specifically, for M marker sphere groups G_1, G_2, ..., G_M in the world coordinate system, the world coordinates of the first and second marker spheres contained therein are known, and the cross-ratio coefficients of marker sphere groups G_1, G_2, ..., G_M can be obtained based on these world coordinates. For M marker sphere groups P_1, P_2, ..., P_M in the image coordinate system, the image coordinates of the first and second marker spheres contained therein can be obtained according to step S22, and the cross-ratio coefficients of marker sphere groups P_1, P_2, ..., P_M can be obtained based on these image coordinates. According to the invariance of cross ratio, if the cross ratios of the marker ball group G_a and the marker ball group P_b are the same or similar, then the marker ball group G_a and the marker ball group P_b have a matching relationship, and thus the matching relationship between the marker balls contained in the marker ball groups G_a and P_b can be established.

[0063] S25, Obtain the calibration parameters of the medical imaging equipment based on the matching relationship. These calibration parameters may be, for example, the intrinsic and / or extrinsic parameter matrices of the medical imaging equipment.

[0064] In one embodiment of this application, each group of marker balls contains four marker balls, one of which is a first marker ball and the other three are second marker balls. The coordinates of a marker ball can be, for example, the coordinates of its center point, but this application is not limited to this. The coordinates of the marker balls in the world coordinate system are known. For the j-th marker ball in the i-th group of marker balls, its world coordinates in the world coordinate system are p. ij ={x ij ,y ij ,z ij}, where i∈[1,M], j∈[1,4]. For the i-th group of marker balls, the cross ratio c can be calculated using the following formula 1 based on the world coordinates of the marker balls. i .

[0065]

[0066] Figure 3A This is a flowchart illustrating the process of processing the image to be processed to obtain the image coordinates of the marker sphere, as shown in an embodiment of this application. Figure 3A As shown, processing the image to be processed to obtain the image coordinates of the marker sphere includes the following steps S31 and S32.

[0067] S31, the medical image processing model is used to process the image to be processed to obtain a first heatmap model and a second heatmap model. The first heatmap model is a heatmap model of the first marker sphere, and the second heatmap model is a heatmap model of the second marker sphere. The medical image processing model is a trained artificial intelligence model.

[0068] S32, obtain the image coordinates of the first and second marker spheres based on the first and second heat map models.

[0069] Figure 3B The diagram shown is a structural schematic of the medical image processing model in an embodiment of this application. Figure 3B As shown in the embodiments of this application, the medical image processing model is a U-shaped convolutional neural network model, including an encoder and a decoder. Figure 3C The flowchart shows how the medical image processing model is used to process the image to be processed to obtain a first heatmap model and a second heatmap model. For example... Figure 3B As shown, the process of obtaining the first heat map model and the second heat map model in this embodiment of the application includes the following steps S311 to S313.

[0070] S311, the encoder is used to extract image features from the image to be processed to obtain feature maps f1 to f5 at different resolutions.

[0071] S312 transmits the feature map to the decoder via a skip connection.

[0072] S313, The decoder is used to process the feature map to obtain the first heatmap model H. l Second thermographic model H s H l and H s The range of values ​​is, for example, (0, 1).

[0073] In some possible implementations, medical image processing models can be trained using deep supervision strategies, outputting results at different resolutions at different levels of the decoder. and Where d = 1, 2, 3. During training, gold-standard heatmaps at different resolutions are used. and As a form of supervision, the network prediction error is calculated using the L1 loss function, thereby iteratively updating the network parameters to optimize the network.

[0074] In some possible implementations, the image to be processed, I, is a two-dimensional image. The loss function of the medical image processing model in these implementations is shown in Equation 2 below.

[0075]

[0076] Among them, W d and H d These represent the width and height of the output heatmap for level d, respectively.

[0077] Figure 3D This is a flowchart illustrating the process of obtaining the image coordinates of the first marker sphere based on the first heatmap model, as shown in this embodiment of the application. Figure 3D As shown, the above process includes the following steps S321 to S323.

[0078] S321, the first heatmap model is segmented into binary labels. For example, a threshold ε can be used. h The first heatmap model is segmented, and the threshold ε is used. h Configurations can be made based on experience or actual needs.

[0079] S322, Obtain the centroid coordinates of the connected components of the first heatmap model. These coordinates represent the detection result of the first marker sphere predicted by the network.

[0080] S323, Obtain the image coordinates of the first marker sphere based on its centroid coordinates. Specifically, for any centroid coordinate of the first marker sphere, extract a local image patch centered on that first marker sphere. The image coordinates of the first marker sphere can then be obtained by optimizing the centroid coordinates using a post-processing algorithm.

[0081] It should be understood that the above description uses the first marker sphere as an example to illustrate the method for obtaining its image coordinates. Similarly, the centroid coordinates of the second marker sphere can be obtained using a method similar to steps S321 to S323 described above. and image coordinates

[0082] Figure 4A This is a flowchart illustrating how the cross-ratio coefficients of a group of marker balls are obtained based on the image coordinates of the marker balls in an embodiment of this application. For example... Figure 4A As shown, the above process includes the following steps S41 to S43.

[0083] S41, with any first marker ball Using the benchmark as a reference point, obtain several lines passing through the benchmark point. A straight line.

[0084] In some possible implementations, several lines passing through the benchmark point can be obtained. It also traverses the straight lines in the image space.

[0085] In some possible implementations, the image to be processed is a two-dimensional image. These implementations can construct... And its direction is parallel to the line of unit vector v1 = (cosθ, sinθ), where θ ∈ (0, π).

[0086] In some possible implementations, the image to be processed is a 3D image. These implementations can construct images after q... k (l) And the direction is a straight line parallel to the unit vector v2, where v2 can be traversed in the manner of Equation 3 or Equation 4.

[0087] v2=(sinβcosα,sinβsinα,cosβ),α∈(0,π),β∈(0,π), Equation 3.

[0088]

[0089] Where N is a positive integer.

[0090] S42, based on the positional relationship between each second marker ball and the straight line, obtain the second marker ball that is collinear with the first marker ball.

[0091] Please see Figure 4B In some possible implementations, obtaining the second marker ball that is collinear with the first marker ball based on the positional relationship between the second marker ball and the straight line includes the following steps S421 to S423.

[0092] S421, obtain the distance between each second marker ball and each straight line.

[0093] S422, based on the above distance, obtain the nearest marker balls of each straight line. The nearest marker balls of a straight line are the three second marker balls closest to the straight line.

[0094] In some possible implementations, for those that have undergone The nth straight line Acquisition and The three closest second marker balls are used as The nearest marker sphere. The image coordinates of this nearest coordinate sphere are... The three and average distance in, It can be obtained through the following equation 5.

[0095]

[0096] in, It is a straight line The direction vector.

[0097] S423, obtain the target line based on the distance between each line and its neighboring marker ball, and the neighboring marker ball of the target line is the second marker ball that is collinear with the first marker ball.

[0098] In some possible implementations, after Select from all the lines The smallest straight line is taken as the target line. The nearest marker balls to this target line are... They form a group A of the same marker balls.

[0099] S43, based on the first marker ball And the image coordinates of the second marker sphere that is collinear with it, to obtain the image containing the first marker sphere. The cross ratio coefficient of the marker ball group A. Specifically, with and The direction vector of the line formed As the positive direction, calculate and Directed distance between And achieve the desired result based on the directed distance. and The sorting. Among them, The formula for calculating the directed distance is shown in Equation 6 below.

[0100]

[0101] After sorting, obtain and The cross ratio coefficient formed by the image coordinates in It can be obtained in a similar manner to Equation 1. Based on the invariance of the cross ratio coefficients under rigid and projective transformations, by... By comparing and matching the cross ratio coefficients with those in the world coordinate system, a cross ratio can be constructed. and The matching relationship between image coordinates and world coordinates.

[0102] The above This paper introduces a method for obtaining the cross-ratio coefficient of marker ball group A using the image coordinates of the marker balls, and a method for obtaining the matching relationship between the image coordinates and world coordinates of the marker balls in group A. By using a similar method, the cross-ratio coefficients of all marker ball groups can be obtained based on the image coordinates of the marker balls, thereby determining the matching relationship between the image coordinates and world coordinates of all marker balls. k~q k}

[0103] In one embodiment of this application, a medical imaging equipment calibration method can be used to calibrate a flat C-arm. The image to be processed in this embodiment is, for example, a two-dimensional X-ray image. The method for calibrating a flat C-arm in this embodiment includes: constructing a matching relationship between image coordinates and world coordinates using steps S21 to S24; and, if the number of matching points is greater than 6, solving for the intrinsic and extrinsic parameter matrices of the flat C-arm.

[0104] In one embodiment of this application, the medical imaging equipment calibration method can be used for two-dimensional and three-dimensional registration. The image to be processed in this embodiment is, for example, a two-dimensional X-ray image. The method for two-dimensional and three-dimensional registration in this embodiment includes: constructing a matching relationship between image coordinates and world coordinates using steps S21 to S24; and, based on the imaging system intrinsic parameter matrix obtained from previous calibration, solving for the imaging system extrinsic parameter matrix, i.e., the spatial transformation relationship from the world coordinate system to the image coordinate system, when the number of matching points is greater than 3. Based on this, the pose of the imaging target object observed by the imaging system in the world coordinate system can be estimated, thereby achieving two-dimensional and three-dimensional registration.

[0105] In one embodiment of this application, the medical imaging equipment calibration method can be used for three-dimensional registration. The image to be processed in this embodiment is, for example, a three-dimensional CT image. The method for achieving three-dimensional registration in this embodiment includes: constructing a matching relationship between image coordinates and world coordinates using steps S21 to S24; and, when the number of matching points is greater than or equal to 3, solving the spatial transformation relationship from the world coordinate system to the CT image coordinate system, thereby achieving three-dimensional registration.

[0106] This application also provides a medical imaging equipment calibration device. Figure 5 The diagram shown is a structural schematic of the medical imaging equipment calibration device 500 in an embodiment of this application. Figure 5As shown, the medical imaging equipment calibration device 500 includes an image acquisition module 510, an image coordinate acquisition module 520, a cross-ratio coefficient acquisition module 530, a matching relationship acquisition module 540, and a calibration parameter acquisition module 550. The image acquisition module 510 acquires an image to be processed. The image to be processed is an image of a calibration tool acquired by the medical imaging equipment. The calibration tool contains multiple groups of marker spheres, each group containing one first marker sphere and three second marker spheres arranged collinearly. The size of the first marker spheres differs from that of the second marker spheres, and the cross-ratio coefficient of each group of marker spheres is different. The image coordinate acquisition module 520 processes the image to be processed to obtain the image coordinates of the marker spheres, which include first and second marker spheres. The cross-ratio coefficient acquisition module 530 acquires the cross-ratio coefficient of each group of marker spheres based on their image coordinates. The matching relationship acquisition module 540 determines the matching relationship between the image coordinates and world coordinates of each marker sphere based on the cross-ratio coefficients. The calibration parameter acquisition module 550 acquires the calibration parameters of the medical imaging equipment based on the matching relationships.

[0107] It should be noted that the various modules included in the medical imaging equipment calibration device 500 are related to... Figure 2 The steps S21 to S25 of the medical imaging equipment calibration method shown correspond one-to-one, and will not be elaborated here.

[0108] This application also provides a computer-readable storage medium storing a computer program thereon. When executed, the computer program implements the medical imaging equipment calibration method provided in any embodiment of this application. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state hard disk, magnetic tape, floppy disk, optical disk, and any combination thereof. The above storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0109] This application also provides an electronic device. Figure 6 The diagram shown is a structural schematic of an electronic device 600 according to an embodiment of this application. Figure 6As shown, in this embodiment, the electronic device 600 includes a memory 610 and a processor 620.

[0110] The memory 610 is used to store computer programs. In some possible implementations, the memory 610 may include various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0111] In this embodiment, memory 610 may include a computer system readable medium in the form of volatile memory, such as RAM and / or cache memory. Electronic device 600 may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 610 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0112] The processor 620 is connected to the memory 610 and is used to execute the computer program stored in the memory 610 so that the electronic device 600 performs the medical imaging equipment calibration method.

[0113] In this embodiment, the processor 620 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0114] In some possible implementations, the electronic device 600 provided in this application embodiment may further include a display 630. The display 630 is communicatively connected to the memory 610 and the processor 620, and is used to display a graphical user interface (GUI) related to the calibration method of the medical imaging equipment.

[0115] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for calibrating medical imaging equipment, characterized in that, The medical imaging equipment calibration method includes: Acquire an image to be processed, which is an image of a calibration tool acquired by a medical imaging device. The calibration tool includes multiple groups of marker balls. Each group of marker balls includes one first marker ball and three second marker balls arranged collinearly. The size of the first marker ball is different from that of the second marker balls, and the cross ratio coefficient of each group of marker balls is different. The image to be processed is processed to obtain the image coordinates of the marker sphere, which includes the first marker sphere and the second marker sphere; The cross ratio coefficient of each group of marker balls is obtained based on the image coordinates of the marker balls. The matching relationship between the image coordinates and world coordinates of each of the marker spheres is determined based on the cross ratio coefficient; The calibration parameters of the medical imaging equipment are obtained based on the matching relationship; The cross ratio coefficient of the group of marker balls obtained based on the image coordinates of the marker balls includes: Using any one of the first marker balls as a reference point, obtain several straight lines passing through the reference point; Obtain the distance between each of the second marker balls and each of the lines; The nearest marker balls of each straight line are obtained according to the distance, and the nearest marker balls of each straight line are the three second marker balls closest to the straight line; The target line is obtained based on the distance between each of the lines and its neighboring marker balls, and the neighboring marker ball of the target line is the second marker ball that is collinear with the first marker ball; Based on the image coordinates of the first marker ball and the second marker ball that is collinear with it, the cross ratio coefficient of the marker ball group containing the first marker ball is obtained.

2. The medical imaging equipment calibration method according to claim 1, characterized in that, Processing the image to be processed to obtain the image coordinates of the marker sphere includes: The image to be processed is processed using a medical image processing model to obtain a first heatmap model and a second heatmap model, wherein the first heatmap model and the second heatmap model are respectively the heatmap models of the first marker sphere and the second marker sphere; The image coordinates of the first and second marker spheres are obtained based on the first and second heatmap models.

3. The medical imaging equipment calibration method according to claim 2, characterized in that, The image coordinates of the first marker sphere are obtained based on the first heatmap model, including: The first heatmap model is segmented into binary labels; Obtain the centroid coordinates of the connected components of the first heatmap model; The image coordinates of the first marker sphere are obtained based on the centroid coordinates.

4. The medical imaging equipment calibration method according to claim 2, characterized in that, The medical image processing model includes an encoder and a decoder. Processing the image to be processed using the medical image processing model to obtain a first heatmap model and a second heatmap model includes: The encoder is used to extract image features from the image to be processed to obtain feature maps of different resolutions; The feature map is transmitted to the decoder via a skip connection; The feature map is processed using the decoder to obtain the first heatmap model and the second heatmap model.

5. The medical imaging equipment calibration method according to claim 1, characterized in that, The image to be processed is a two-dimensional image or a three-dimensional image.

6. A medical imaging equipment calibration device, characterized in that, The medical imaging equipment calibration device includes: The image acquisition module is used to acquire an image to be processed, which is an image of a calibration tool acquired by a medical imaging device. The calibration tool includes multiple groups of marker balls. Each group of marker balls includes one first marker ball and three second marker balls arranged collinearly. The size of the first marker ball is different from that of the second marker balls, and the cross ratio coefficient of each group of marker balls is different. An image coordinate acquisition module is used to process the image to be processed to obtain the image coordinates of the marker sphere, wherein the marker sphere includes a first marker sphere and a second marker sphere; The cross ratio coefficient acquisition module is used to acquire the cross ratio coefficient of each group of marker balls based on the image coordinates of the marker balls. The matching relationship acquisition module is used to determine the matching relationship between the image coordinates and world coordinates of each of the marker balls based on the cross ratio coefficient; A calibration parameter acquisition module is used to acquire the calibration parameters of the medical imaging equipment according to the matching relationship. The cross ratio coefficient of the group of marker balls obtained based on the image coordinates of the marker balls includes: Using any one of the first marker balls as a reference point, obtain several straight lines passing through the reference point; Obtain the distance between each of the second marker balls and each of the lines; The nearest marker balls of each straight line are obtained according to the distance, and the nearest marker balls of each straight line are the three second marker balls closest to the straight line; The target line is obtained based on the distance between each of the lines and its neighboring marker balls, and the neighboring marker ball of the target line is the second marker ball that is collinear with the first marker ball; Based on the image coordinates of the first marker ball and the second marker ball that is collinear with it, the cross ratio coefficient of the marker ball group containing the first marker ball is obtained.

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

8. An electronic device, characterized in that, The electronic device includes: A memory that stores a computer program; The processor, which is communicatively connected to the memory, executes the medical imaging equipment calibration method according to any one of claims 1 to 5 when calling the computer program.

Images