Binocular X-ray guide wire three-dimensional positioning method, device and equipment based on epipolar geometry and storage medium

Abstract

The invention discloses a binocular X-ray guide wire three-dimensional positioning method, a binocular X-ray guide wire three-dimensional positioning device and binocular X-ray guide wire three-dimensional positioning equipment based on epipolar geometry and a storage medium. The method comprises the steps that two to-be-processed images collected by two X-ray scanning devices in the biplane digital subtraction angiography system for a target object in a guide wire intervention state are acquired, and the to-be-processed images comprise intervention guide wires; conducting guide wire positioning on the two to-be-processed images based on projection matrixes which are obtained through pre-calibration and respectively correspond to the two X-ray scanning devices, and determining path information of the interventional guide wire, the path information comprising first position information of the interventional guide wire; obtaining an expected path of the interventional guide wire, and determining an offset error of the interventional guide wire based on expected position information of the interventional guide wire in the expected path and the first position information; the expected path of the intervention guide wire is updated based on the offset error, accurate positioning of the intervention guide wire and updating of the expected path are achieved, and accurate data support is provided for subsequent treatment.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and in particular to a method, apparatus, device, and storage medium for three-dimensional positioning of binocular X-ray guidewires based on epipolar geometry. Background Technology

[0002] Precise positioning of the interventional guidewire is of great significance during minimally invasive interventional surgery.

[0003] In existing technologies, the guidewire is positioned during minimally invasive interventional procedures using a dual-plane digital subtraction angiography (DSA) system. However, the dual-plane DSA system cannot accurately obtain the projection direction and geometric center of the guidewire, resulting in low positioning accuracy. Summary of the Invention

[0004] This invention provides a method, device, equipment, and storage medium for three-dimensional positioning of a binocular X-ray guidewire based on epipolar geometry, so as to achieve precise positioning of the interventional guidewire and provide accurate data support for subsequent treatment.

[0005] According to one aspect of the present invention, a three-dimensional positioning method for binocular X-ray guidewires based on epipolar geometry is provided, the method comprising:

[0006] Two images to be processed are acquired by two X-ray scanning devices in a dual-plane digital subtraction angiography system for a target object under guidewire intervention. The images to be processed include the interventional guidewire.

[0007] Based on the projection matrices corresponding to the two pre-calibrated X-ray scanning devices, guidewire positioning is performed on the two images to be processed to determine the path information of the interventional guidewire, which includes the first position information of the interventional guidewire.

[0008] Obtain the desired path of the interventional guidewire, and determine the offset error of the interventional guidewire based on the desired position information and the first position information of the interventional guidewire in the desired path;

[0009] The desired path of the interventional guidewire is updated based on the offset error.

[0010] According to another aspect of the present invention, a binocular X-ray guidewire three-dimensional positioning device based on epipolar geometry is provided, the device comprising:

[0011] The image acquisition module is used to acquire two images to be processed from the target object in the guidewire intervention state by two X-ray scanning devices in the dual-plane digital subtraction angiography system. The images to be processed include the interventional guidewire.

[0012] The path information determination module is used to locate the guidewire in two images to be processed based on the projection matrices corresponding to the two pre-calibrated X-ray scanning devices, and to determine the path information of the interventional guidewire, including the first position information of the interventional guidewire.

[0013] The offset error determination module is used to obtain the expected path of the interventional guidewire and determine the offset error of the interventional guidewire based on the expected position information and the first position information of the interventional guidewire in the expected path.

[0014] The desired path update module is used to update the desired path of the interventional guidewire based on the offset error.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory that is communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry provided in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry provided in any embodiment of the present invention.

[0020] The technical solution of this invention acquires two images of a target object under guidewire intervention using two X-ray scanning devices in a dual-plane digital subtraction angiography system. These images include the interventional guidewire, providing comprehensive data support for subsequent analysis and processing. Based on the pre-calibrated projection matrices corresponding to the two X-ray scanning devices, guidewire positioning is performed on the two images to determine the guidewire's path information, including its first position information. This precise determination of the guidewire's path provides accurate data support for subsequent guidewire positioning. The desired path of the guidewire is acquired, and its offset error is determined based on the desired position information and the first position information within the desired path. This precise determination of the offset error provides an accurate data basis for updating the desired path of the guidewire. Updating the desired path of the guidewire based on the offset error solves the problem of low positioning accuracy in existing technologies, achieving precise updating of the desired path and improving the positioning accuracy. This provides accurate path support for subsequent guidewire control and enhances surgical safety.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is a schematic diagram of a dual-plane digital subtraction angiography system provided in an embodiment of the present invention;

[0025] Figure 3 This is a flowchart of a skeleton image processing method provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of a limit geometry and solid matching provided by an embodiment of the present invention;

[0027] Figure 5This is a flowchart of a binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry provided in Embodiment 2 of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of a binocular X-ray guidewire three-dimensional positioning device based on epipolar geometry provided in Embodiment 3 of the present invention;

[0029] Figure 7 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] During minimally invasive interventional surgery, due to the tortuosity and narrowing of blood vessels and lumens, interventional guidewires can be used to ensure treatment effectiveness. Interventional guidewires serve to open blood vessels and place therapeutic devices. For example, for vascular stenosis and occlusion, the tip of the interventional guidewire can be passed through the narrowed area to open the occluded section. Furthermore, the tip of the interventional guidewire can carry therapeutic devices, which are then placed at the target location using the guidewire carrying the device. These devices include, but are not limited to, balloon catheters, stent catheters, and thrombectomy stents.

[0033] Example 1

[0034] Figure 1This is a flowchart of a binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry provided in Embodiment 1 of the present invention. This embodiment is applicable to the three-dimensional positioning of interventional guidewires. The method can be executed by a binocular X-ray guidewire three-dimensional positioning device based on epipolar geometry. This device can be implemented in hardware and / or software. The device can be configured in the electronic device provided in this embodiment of the invention. The electronic device can be a server, computer, or mobile terminal, such as a mobile phone or tablet computer. Figure 1 As shown, the method includes:

[0035] S110. Acquire two images to be processed from the target object in the guidewire intervention state by two X-ray scanning devices in the dual-plane digital subtraction angiography system. The images to be processed include the interventional guidewire.

[0036] The dual-plane digital subtraction angiography (DSA) system is a medical imaging device that visualizes the dynamic relationship between blood vessels and interventional guidewires. This dual-plane DSA system includes two X-ray scanning devices, which include, but are not limited to, X-ray sensors. For example, see [link to example]. Figure 2 , Figure 2 This is a schematic diagram of a dual-plane digital subtraction angiography (DSA) system provided in an embodiment of the present invention. The DSA system includes two X-ray sensors deployed at a certain angle within the system. The target object includes, but is not limited to, patients requiring interventional treatment. The image to be processed is an image obtained by scanning the target object using an X-ray scanning device. The image to be processed may include an interventional guidewire, and may also include the blood vessels of the target object, or may include both the interventional guidewire and the blood vessels of the target object.

[0037] Specifically, the target object is scanned using two X-ray scanning devices to obtain two images of the target object under guidewire intervention, providing comprehensive data support for subsequent analysis and processing.

[0038] S120. Based on the projection matrices corresponding to the two pre-calibrated X-ray scanning devices, guidewire positioning is performed on the two images to be processed to determine the path information of the interventional guidewire, including the first position information of the interventional guidewire.

[0039] The projection matrix is ​​a matrix that quantitatively describes the imaging process of the two X-ray scanning devices in a dual-plane DSA system. The projection matrix can be obtained by calibrating the two X-ray scanning devices separately. For example, the Zhang Zhengyou calibration method can be used to calibrate the two X-ray scanning devices separately, obtaining the projection matrices corresponding to each X-ray scanning device. The path information is the trajectory information of the interventional guidewire within the target body. The path information can be determined based on the projection matrices corresponding to the two X-ray scanning devices. For example, the projection matrices corresponding to the two X-ray scanning devices and two images to be processed are input into a trained path information determination model for processing to obtain the path information of the interventional guidewire. The path information determination model includes, but is not limited to, a neural network model. Optionally, the path information includes the first position information of the interventional guidewire. The first position information is information characterizing the position of the interventional guidewire within the target body. Optionally, the first position information includes the three-dimensional coordinate information and angle information of the head of the interventional guidewire. The three-dimensional coordinate information describes the position of the head of the interventional guidewire in three-dimensional space. Optionally, the three-dimensional coordinate information can be three-dimensional coordinate information under a preset world coordinate system. The angle information is a parameter describing the direction of the interventional guidewire in three-dimensional space. Optionally, angle information includes, but is not limited to, pitch angle information and yaw angle information. Angle information can reflect the directional relationship between the head of the interventional guidewire and the blood vessel.

[0040] Specifically, the two X-ray scanning devices were calibrated using the Zhang Zhengyou calibration method to obtain the projection matrices corresponding to the two X-ray scanning devices. The projection matrices corresponding to the two X-ray scanning devices and the two images to be processed were input into the trained path information determination model for processing to obtain the path information of the interventional guidewire. This achieved accurate determination of the path information of the interventional guidewire and provided accurate data support for the subsequent positioning of the interventional guidewire.

[0041] Optionally, the process for determining the projection matrices corresponding to the two X-ray scanning devices is as follows: acquire multiple images of the calibration plate in different orientations based on the two X-ray scanning devices; calibrate the multiple images for each X-ray scanning device to determine the intrinsic parameter matrix and extrinsic parameter matrix of the X-ray scanning device; and determine the projection matrix based on the intrinsic parameter matrix and extrinsic parameter matrix.

[0042] The image to be calibrated is obtained by scanning a calibration plate using an X-ray scanning device. To prevent the calibration plate from undergoing lateral deformation during X-ray scanning, which could affect the accuracy of the projection matrix determination, a calibration plate suitable for X-rays can be selected. Optionally, the calibration plate can be made of a high-contrast, X-ray-impermeable material. For example, the calibration plate can be a planar checkerboard calibration plate. The size of the calibration plate can be set according to actual needs; for example, the side length of the calibration plate can be 25 mm. The orientation of the calibration plate includes, but is not limited to, translation, pitch, and rotation, to avoid a single planar angle of the calibration plate, which helps to improve the accuracy of the projection matrix determination. Optionally, the image to be calibrated includes the two-dimensional coordinate information of the corner points of the planar checkerboard calibration plate. The intrinsic parameter matrix is ​​a matrix describing the fixed imaging characteristics of the X-ray scanning device. The intrinsic parameter matrix is ​​determined by the hardware design of the X-ray scanning device and is independent of the position and orientation of the X-ray scanning device in space. The intrinsic parameter matrix can be obtained from the two-dimensional coordinate information of the corner points of the planar checkerboard calibration plate in the image to be calibrated and the three-dimensional coordinate information of the corner points in the world coordinate system. For example, the two-dimensional coordinates of the corner points of the planar checkerboard calibration board in the image to be calibrated, and the three-dimensional coordinates of the corner points in the world coordinate system, are input into a trained intrinsic parameter matrix determination model to obtain the intrinsic parameter matrix. The extrinsic parameter matrix is ​​a matrix describing the spatial position and orientation of the X-ray scanning equipment relative to a preset world coordinate system. The extrinsic parameter matrix can be determined based on the intrinsic parameter matrix. For example, the intrinsic parameter matrix is ​​input into a trained extrinsic parameter matrix determination model to obtain the extrinsic parameter matrix. The projection matrix can also be determined based on the intrinsic and extrinsic parameter matrices. For example, the product of the intrinsic and extrinsic parameter matrices is calculated, and this product is used as the projection matrix.

[0043] Specifically, two X-ray scanning devices are used to scan calibration boards in different postures to obtain multiple images to be calibrated. The two-dimensional coordinates of the corner points of the planar checkerboard calibration board in the images to be calibrated and the three-dimensional coordinates of the corner points of the planar checkerboard calibration board in the world coordinate system are input into a trained intrinsic parameter matrix determination model to obtain the intrinsic parameter matrix. The intrinsic parameter matrix is ​​then input into a trained extrinsic parameter matrix determination model to obtain the extrinsic parameter matrix. The product of the intrinsic parameter matrix and the extrinsic parameter matrix is ​​calculated and used as the projection matrix, thus achieving accurate determination of the projection matrix.

[0044] For example, the process of determining the projection matrix corresponding to two X-ray scanning devices is as follows:

[0045] (1) The calibration plates in different postures are scanned by X-ray scanning equipment to obtain multiple images to be calibrated.

[0046] (2) Perform preprocessing operations on multiple images to be calibrated. Preprocessing operations include, but are not limited to, median filtering, histogram equalization and binarization to enhance the contrast of the images to be calibrated.

[0047] (3) Determine the two-dimensional and three-dimensional coordinate information of each corner point. Among them, one corner of the calibration plate can be used as the origin of the world coordinate system, and the column direction and row direction of the calibration plate can be used as the X-axis and Y-axis of the world coordinate system, respectively. The Z-axis coordinate in the three-dimensional coordinate information is 0.

[0048] (4) For any image to be calibrated, determine the homography matrix based on the two-dimensional and three-dimensional coordinate information of each corner point. The formula for calculating the homography matrix is ​​as follows:

[0049] ;

[0050] in, Indicates the first The first image to be calibrated Two-dimensional coordinate information of each corner point; Indicates the first The first image to be calibrated Three-dimensional coordinate information of each corner point; Represents the homography matrix; This represents the radioactivity coefficient.

[0051] (5) Construct the intrinsic parameter matrix and solve for the intrinsic parameter matrix based on the homography matrix. The intrinsic parameter matrix can be:

[0052] ;

[0053] in, It represents the focal length in the horizontal direction, which is the scaling factor in the x-axis direction when the three-dimensional coordinate information is projected onto the plane where the calibration plate is located; Vertical focal length, which is the scaling factor in the y-axis direction when the three-dimensional coordinate information is projected onto the plane of the calibration plate; Indicates the coordinates of the principal point; This represents the inter-axis tilt factor, which is usually set to 0. The constraint equations are constructed and solved to obtain the intrinsic parameter matrix. The constraint equations are as follows:

[0054] ;

[0055] ;

[0056] in, Represents a symmetric matrix The parameter vector, symmetric matrix It can be determined from the intrinsic parameter matrix.

[0057] (6) Solving for the extrinsic parameter matrix. The formula for solving the extrinsic parameter matrix is ​​as follows:

[0058] ;

[0059] ;

[0060] ;

[0061] ;

[0062] in, , and They represent the first Rotation matrix of an image to be calibrated The three column vectors; Represents the homography matrix; Represents the intrinsic parameter matrix; Represents the translation matrix; This represents the translation matrix corresponding to the X-ray scanning device on the right. This represents the translation matrix corresponding to the X-ray scanning device on the left. This represents the rotation matrix corresponding to the X-ray scanning device on the right. This represents the rotation matrix corresponding to the X-ray scanning equipment on the left. The left and right sides represent the relative positions of the X-ray scanning equipment; the rotation matrix... Translation matrix This forms the extrinsic parameter matrix.

[0063] (7) Using the coordinate system corresponding to the X-ray scanning device on the left as the world coordinate system, solve for the extrinsic parameter matrix of the X-ray scanning device on the right in the world coordinate system of the X-ray scanning device on the left. The intrinsic parameter matrices corresponding to the two X-ray scanning devices are as follows:

[0064] ;

[0065] ;

[0066] in, This represents the intrinsic parameter matrix corresponding to the X-ray scanning equipment on the left. This indicates the horizontal focal length of the X-ray scanning device on the left. This indicates the vertical focal length of the X-ray scanning device on the left. This indicates the coordinates of the principal point of the X-ray scanning device on the left. This indicates the interaxial tilt factor of the X-ray scanning equipment on the left. This represents the intrinsic parameter matrix corresponding to the X-ray scanning equipment on the right. This indicates the horizontal focal length of the X-ray scanning device on the right. This indicates the vertical focal length of the X-ray scanning device on the right. This indicates the principal coordinates of the X-ray scanning equipment on the right. This represents the inter-axis tilt factor of the X-ray scanning device on the right. At this point, the extrinsic parameter matrices of the two X-ray scanning devices can be:

[0067] ;

[0068] ;

[0069] in, This represents the rotation matrix corresponding to the X-ray scanning device on the left. Represents the identity matrix; This represents the translation matrix corresponding to the X-ray scanning device on the left. This represents the rotation matrix corresponding to the X-ray scanning device on the right. This represents the translation matrix corresponding to the X-ray scanning device on the right.

[0070] (8) Construct the projection matrix. The formula for calculating the projection matrix is ​​as follows:

[0071] ;

[0072] in, Represents the projection matrix; Intrinsic parameter matrix; Let represent the extrinsic parameter matrix. Therefore, the projection matrix corresponding to the X-ray scanning device on the left is:

[0073] ;

[0074] in, This represents the projection matrix corresponding to the X-ray scanning device on the left. This represents the intrinsic parameter matrix corresponding to the X-ray scanning equipment on the left. This represents the extrinsic parameter matrix corresponding to the X-ray scanning equipment on the left. This indicates the horizontal focal length of the X-ray scanning device on the left. This indicates the vertical focal length of the X-ray scanning device on the left. This indicates the coordinates of the principal point of the X-ray scanning device on the left. This represents the inter-axis tilt factor of the X-ray scanning equipment on the left. The projection matrix corresponding to the X-ray scanning equipment on the right is:

[0075] ;

[0076] in, This represents the projection matrix corresponding to the X-ray scanning device on the right. This represents the intrinsic parameter matrix corresponding to the X-ray scanning equipment on the right. This represents the extrinsic parameter matrix corresponding to the X-ray scanning equipment on the right. This indicates the horizontal focal length of the X-ray scanning device on the right. This indicates the vertical focal length of the X-ray scanning device on the right. This indicates the principal coordinates of the X-ray scanning equipment on the right. This indicates the interaxial tilt factor of the X-ray scanning equipment on the right.

[0077] Based on the above embodiments, the intrinsic parameter matrix can also be optimized. Radial distortion parameters are then obtained. and And obtain tangential distortion parameters and The distortion correction model is mapped to the two-dimensional coordinate information of each corner point:

[0078] ;

[0079]

[0080] in, This represents the horizontal coordinate information in the corrected two-dimensional coordinate information; This represents the ordinate information in the corrected 2D coordinate information. The reprojection error between the 2D coordinate information before and after corner point correction is calculated. The intrinsic parameter matrix and distortion coefficients are optimized to minimize this reprojection error. .

[0081] Based on the above embodiments, the projection matrix can be verified to improve its accuracy and the positioning accuracy of the interventional guidewire. Multiple verification points in the world coordinate system are determined. Based on the projection matrices of the two X-ray scanning devices, multiple verification points are calculated. The desired coordinate information is obtained in the coordinate systems corresponding to the two X-ray scanning devices. Multiple verification points are scanned by the two X-ray scanning devices to obtain the actual coordinate information corresponding to the multiple verification points. The reprojection error between the desired coordinate information and the actual coordinate information is calculated. When the reprojection error is less than the preset reprojection error, it indicates that the projection matrix is ​​correct. When the reprojection error is greater than or equal to the preset reprojection error, the projection matrix needs to be re-determined.

[0082] Optionally, based on the projection matrices corresponding to the two pre-calibrated X-ray scanning devices, guidewire positioning is performed on the two images to be processed to determine the path information of the interventional guidewire. Specifically, this includes: performing skeletonization processing on the images to be processed to obtain a skeleton image corresponding to each image, the skeleton image including the pixel coordinate information corresponding to the interventional guidewire; determining a fundamental matrix based on the pixel coordinate information and the two projection matrices, the fundamental matrix representing the epipolar geometric constraint relationship; determining matching point pairs between the two skeleton images based on the two fundamental matrices and the pixel coordinate information; and determining path information based on the two projection matrices and the matching point pairs.

[0083] The skeleton image is obtained by skeletonizing the central axis of the interventional guidewire in the image to be processed. Skeletonization algorithms can be used to skeletonize the image, including but not limited to binarization algorithms, such as the Zhang-Suen thinning algorithm. The skeleton image includes the pixel coordinate information corresponding to the interventional guidewire. The pixel coordinate information is the coordinate of the pixel corresponding to the central axis of the interventional guidewire. Optionally, the pixel coordinate information can be two-dimensional coordinate information. The fundamental matrix is ​​a matrix describing the epipolar geometric constraint relationship between the skeleton images corresponding to the two X-ray scanning devices. The fundamental matrix can be determined based on the pixel coordinate information and two projection matrices. For example, the pixel coordinate information and two projection matrices can be input into a trained fundamental matrix determination model for processing to obtain the fundamental matrix. The fundamental matrix determination model includes, but is not limited to, a transformer model. Matching point pairs are pixel pairs formed by pixels corresponding to the same position of the interventional guidewire in the two skeleton images. Optionally, the matching point pairs include the three-dimensional coordinate information of the pixels corresponding to the interventional guidewire in the skeleton image. Matching point pairs can be determined based on the two fundamental matrices and the pixel coordinate information. For example, in any skeleton image, multiple pixels that need to be matched are identified, and the epipolar lines corresponding to these pixels are determined based on two fundamental matrices. Matching is then performed in another skeleton image based on these epipolar lines. For example, matching can be performed using a normalized cross-correlation algorithm and a deep feature matching algorithm to obtain the pixels corresponding to the multiple pixels. The corresponding pixels in the two skeleton images form a matching point pair.

[0084] Specifically, the Zhang–Suen thinning algorithm is used to skeletonize the images to be processed, resulting in a skeleton image for each image. Pixel coordinates and two projection matrices are input into a trained fundamental matrix determination model for processing, yielding the fundamental matrix. In any skeleton image, multiple pixels requiring matching are identified. Based on the two fundamental matrices, the epipolar lines corresponding to these pixels are determined. Matching is then performed in another skeleton image based on these epipolar lines, resulting in pixels corresponding to the multiple pixels. The corresponding pixels in the two skeleton images form matching point pairs, achieving precise determination of these pairs and providing accurate data support for the positioning of the interventional guidewire.

[0085] For example, the projection matrix corresponding to the X-ray scanning device on the left is The projection matrix corresponding to the X-ray scanning device on the right is The formula for calculating the fundamental matrix is ​​as follows:

[0086] ;

[0087] ;

[0088] ;

[0089] ;

[0090] ;

[0091] ;

[0092] ;

[0093] in, This represents the intrinsic parameter matrix corresponding to the X-ray scanning equipment on the left. This represents the extrinsic parameter matrix corresponding to the X-ray scanning equipment on the left. This represents the intrinsic parameter matrix corresponding to the X-ray scanning equipment on the right. This represents the extrinsic parameter matrix corresponding to the X-ray scanning equipment on the right. Represents the fundamental matrix; Represents the essential matrix; Represents the translation matrix; , and These represent the translation vectors of the translation matrix along the X, Y, and Z axes, respectively. The antisymmetric matrix representing the translation matrix; This represents the three-dimensional coordinate information of the pixels on the skeleton image to the left of the matching point pair; This represents the 3D coordinate information of pixels on the skeleton image on the right side of the matching point pair. It is based on multiple pixels on the skeleton image on the left side. The epipolar lines corresponding to multiple pixels are determined, and the formula for calculating the epipolar lines is as follows:

[0094] ;

[0095] in, The skeleton image on the right is the first Epipolar lines corresponding to each pixel; Represents the fundamental matrix; This indicates the first skeleton image on the left. The three-dimensional coordinate information of each pixel.

[0096] Before skeletonizing the image to be processed, preprocessing operations can be performed. Preprocessing operations include, but are not limited to, image segmentation, denoising, and image filling. Image segmentation can be performed using deep learning models, including but not limited to U-Net and Transformer models. By segmenting the image to be processed, a mask image is obtained. In the mask image, the portion corresponding to the intervention guidewire can be set to 1, and the rest can be set to 0. Denoising can be achieved through erosion and dilation operations, which can be implemented using pre-defined structuring elements. For example, the structuring element can be a cross-shaped matrix or a square matrix. The structuring element structure is as follows:

[0097] ;

[0098] ;

[0099] in, This represents a structural element. The calculation formula for the erosion operation is as follows:

[0100] ;

[0101] in, This represents the image to be processed after the erosion operation; This represents the image to be processed. The formula for dilation is as follows:

[0102] ;

[0103] in, This represents the image to be processed after the dilation operation. This represents the image to be processed. Image filling can be achieved through morphological closing operations. For example, after performing erosion and dilation operations sequentially on the image to be processed following dilation, the formula for calculating the filled image is as follows:

[0104] ;

[0105] ;

[0106] in, This represents the image to be processed after the erosion and dilation operations; This represents the image to be processed after filling.

[0107] Connectivity analysis is performed on the skeleton image to remove fragmented skeleton branches with lengths less than a preset threshold, reducing interference from these branches. Subpixel-level coordinate optimization is then performed on the pixels in the skeleton image using a curve fitting algorithm to obtain the point set. and Connectivity tracing is performed on the masked image, and the pixels on the connected components are sorted in order to obtain an ordered list of pixels. Calculate the cumulative Euclidean distance between adjacent pixels. The formula for calculating the cumulative Euclidean distance is as follows:

[0108] ;

[0109] ;

[0110] in, This represents the cumulative sum of Euclidean distances. The maximum value in the cumulative sum of Euclidean distances is determined, and the path corresponding to this maximum value is used as the path information for the interventional guidewire. The cumulative sum of Euclidean distances corresponding to the maximum value is normalized. The formula for calculating the normalized cumulative sum of Euclidean distances corresponding to the maximum value is as follows:

[0111] ;

[0112] in, This represents the cumulative Euclidean distance corresponding to the maximum value after normalization. The normalized cumulative Euclidean distance is then subjected to cubic B-spline interpolation. The formula for cubic B-spline interpolation is as follows:

[0113] ;

[0114] ;

[0115] in, Represents the B-spline basis functions; and Indicates the control point coefficient; Indicates the number of control points. and Construct a linear least squares problem:

[0116] ;

[0117] ;

[0118] The two formulas above can be converted into matrix form as follows:

[0119] ;

[0120] ;

[0121] ;

[0122] ;

[0123] ;

[0124] in, This represents the basis function matrix. By solving the above linear least squares problem, the path information of the interventional guidewire is smoothly processed. For an example, see... Figure 3 , Figure 3 This is a flowchart illustrating the processing of a skeleton image according to an embodiment of the present invention. The images from left to right are, in order, the image to be processed, the mask image, and the skeleton image.

[0125] Optionally, path information is determined based on two projection matrices and matching point pairs, including: determining multiple homogeneous coordinate information of the interventional guidewire based on two projection matrices and multiple matching point pairs; performing non-homogeneous processing on the multiple homogeneous coordinate information to determine multiple non-homogeneous coordinate information of the interventional guidewire; and fitting the multiple non-homogeneous coordinate information to obtain path information.

[0126] Homogeneous coordinate information refers to the homogeneous representation of the three-dimensional coordinates of pixels in the interventional guidewire. Homogeneous coordinate information can be determined based on a projection matrix and multiple matching point pairs. For example, triangulation can be used to process two projection matrices and multiple matching point pairs to obtain multiple homogeneous coordinate information of the interventional guidewire. Non-homogeneous coordinate information is obtained by performing non-homogeneous processing on the homogeneous coordinate information. Non-homogeneous processing on the homogeneous coordinate information includes, but is not limited to, normalization processing, such as scale normalization. Path information can be obtained by fitting multiple non-homogeneous coordinate information. For example, curve smoothing can be performed on multiple non-homogeneous coordinate information to obtain path information. Another example is performing three-dimensional spline fitting on multiple non-homogeneous coordinate information to obtain path information.

[0127] Specifically, the two projection matrices and multiple matching point pairs are processed by triangulation to obtain multiple homogeneous coordinate information of the interventional guidewire. The multiple homogeneous coordinate information is then normalized to obtain the corresponding non-homogeneous coordinate information. The multiple non-homogeneous coordinate information is then smoothed to obtain the path information. This achieves accurate determination of the path information of the interventional guidewire, so that the path information of the interventional guidewire can accurately reflect the true path of the interventional guidewire.

[0128] For example, the three-dimensional coordinate information corresponding to the matching point pairs in the skeleton image on the left is as follows: The 3D coordinate information corresponding to the matching point pairs in the skeleton image on the right is as follows: , and The calculation formula is as follows:

[0129] ;

[0130] ;

[0131] The formula for calculating homogeneous coordinate information is as follows:

[0132] ;

[0133] ;

[0134] ;

[0135] ;

[0136] ;

[0137] ;

[0138] ;

[0139] in, and Represents homogeneous factors; This represents the projection matrix corresponding to the X-ray scanning device on the left. This represents the projection matrix corresponding to the X-ray scanning device on the right. Represents homogeneous coordinate information; This represents the coefficient matrix, used to solve for homogeneous coordinate information. Singular Value Decomposition (SVD) is then performed on the coefficient matrix. ,in, Represents the left singular value matrix; Represents a singular value matrix; Represents the right singular value matrix. Take the right singular vector corresponding to the smallest singular value in the right singular value matrix. Obtain homogeneous coordinate information , This represents the homogeneous coordinate information corresponding to the matching point pair. The calculation formula for normalizing the homogeneous coordinate information corresponding to the matching point pair is as follows:

[0140] ;

[0141] in, Indicates non-homogeneous coordinate information; This represents the first component of the homogeneous coordinate information; This represents the second component of the homogeneous coordinate information; This represents the third component of the homogeneous coordinate information. This represents the fourth component of the homogeneous coordinate information. For each pair of matching points in the skeleton image... Repeat the above process to obtain multiple non-homogeneous coordinate information, which together form a three-dimensional point set. For a three-dimensional point set Perform curve smoothing or 3D spline fitting to obtain path information.

[0142] S130. Obtain the desired path of the interventional guidewire, and determine the offset error of the interventional guidewire based on the desired position information and the first position information of the interventional guidewire in the desired path.

[0143] The desired path is the pre-set trajectory information of the interventional guidewire. The desired path can be planned based on the medical imaging data of the target object. For example, medical imaging data of the target object is collected and input into a trained desired path determination model to obtain the desired path. The desired path determination model includes, but is not limited to, a neural network model. Another example is collecting medical imaging data of the target object and determining the desired path of the interventional guidewire based on experience through analysis of the medical imaging data. Optionally, the desired path includes the desired position information of the interventional guidewire. The desired position information characterizes the ideal position of the interventional guidewire within the target object's body. The offset error is data describing the degree of offset between the desired position information and the first position information of the interventional guidewire. The offset error can be determined by calculating the difference between the desired position information and the first position information.

[0144] Specifically, medical image data of the target object is collected and input into a trained desired path determination model to obtain the desired path. The offset error is determined by calculating the difference between the desired position information and the first position information, thus achieving accurate determination of the offset error and providing an accurate data basis for updating the desired path of the subsequent interventional guidewire.

[0145] S140. Update the desired path of the interventional guidewire based on the offset error.

[0146] Specifically, the three-dimensional coordinate error, angle error, and desired path in the offset error are input into the trained desired path update model for processing to obtain the updated desired path of the interventional guidewire. The desired path update model includes, but is not limited to, a neural network model.

[0147] Specifically, the three-dimensional coordinate error, angle error, and desired path in the offset error are input into the trained desired path update model for processing to obtain the updated desired path of the interventional guidewire. This achieves accurate updating of the desired path of the interventional guidewire, providing accurate path support for subsequent control of the interventional guidewire and improving the safety of the operation.

[0148] For example, see Figure 4 , Figure 4 This is a schematic diagram illustrating a limit geometry and solid matching method provided in an embodiment of the present invention. Wherein, This indicates the head of the interventional guidewire; This indicates the projection point of the guidewire tip onto image plane 1; image plane 1 represents the plane of the target object scanned by X-ray scanning device 1. This indicates the projection point of the guidewire tip onto image plane 2; image plane 2 represents the plane of the target object scanned by X-ray scanning device 2. This indicates the X-ray source of X-ray scanning device 1; Indicates the X-ray source of X-ray scanning device 2; baseline A spatial baseline representing polar geometry.

[0149] The technical solution of this embodiment acquires two images of the target object under guidewire intervention state using two X-ray scanning devices in a dual-plane digital subtraction angiography system. These images include the interventional guidewire, providing comprehensive data support for subsequent analysis and processing. Based on the pre-calibrated projection matrices corresponding to the two X-ray scanning devices, guidewire positioning is performed on the two images to determine the path information of the interventional guidewire. This path information includes the first position information of the interventional guidewire, achieving precise determination of the guidewire path and providing accurate data support for subsequent guidewire positioning. The desired path of the interventional guidewire is acquired, and the offset error is determined based on the desired position information and the first position information within the desired path, achieving precise determination of the offset error and providing an accurate data basis for updating the desired path of the interventional guidewire. The desired path of the interventional guidewire is updated based on the offset error, achieving precise updating of the desired path and providing accurate path support for subsequent guidewire control, which is beneficial for improving the safety of the procedure.

[0150] Example 2

[0151] Figure 5 This is a flowchart of a binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry, provided in Embodiment 2 of the present invention. This embodiment is a refinement of the above embodiments. Based on the aforementioned embodiments, it provides a detailed explanation of determining the offset error of the interventional guidewire based on the expected position information and first position information of the interventional guidewire in the expected path. For specific implementation details, please refer to the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here. Figure 2 As shown, the method includes:

[0152] S210. Acquire two images to be processed from the target object in the guidewire intervention state by two X-ray scanning devices in the dual-plane digital subtraction angiography system. The images to be processed include the interventional guidewire.

[0153] S220. Based on the projection matrices corresponding to the two pre-calibrated X-ray scanning devices, guidewire positioning is performed on the two images to be processed to determine the path information of the interventional guidewire. The path information includes the first position information of the interventional guidewire, which includes the three-dimensional coordinate information and angle information of the head of the interventional guidewire.

[0154] S230. Obtain the desired path of the interventional guidewire. The desired position information in the desired path includes the desired three-dimensional coordinate information and desired angle information of the head of the interventional guidewire. Determine the three-dimensional coordinate error based on the three-dimensional coordinate information and the desired angle information. Determine the angle error based on the angle information and the desired angle information.

[0155] The desired three-dimensional coordinate information refers to the ideal coordinates of the guidewire tip within the target body. The desired angle information refers to the ideal angle of the guidewire tip within the target body. The offset error represents the deviation between the first position information and the desired position information of the guidewire. The offset error can be determined by calculating the position information difference between the first position information and the desired position information. The three-dimensional coordinate error represents the error between the three-dimensional coordinate information of the guidewire tip and the desired three-dimensional coordinate information. The three-dimensional coordinate error can be determined based on the three-dimensional coordinate information of the guidewire tip and the desired three-dimensional coordinate information. For example, the distance difference between the three-dimensional coordinate information of the guidewire tip and the desired three-dimensional coordinate information can be calculated, and this distance difference can be used as the three-dimensional coordinate error. The angle error represents the deviation between the angle information of the guidewire tip and the desired angle information. The angle error can be determined by calculating the angle information of the guidewire tip and the desired angle information. For example, the difference between the angle information of the guidewire tip and the desired angle information can be calculated, and this difference can be used as the angle error.

[0156] Specifically, the distance difference between the three-dimensional coordinate information of the guidewire tip and the expected three-dimensional coordinate information is calculated, and the above distance difference is used as the three-dimensional coordinate error; the difference between the angle information of the guidewire tip and the expected angle information is calculated, and the above difference is used as the angle error. This achieves accurate determination of the three-dimensional coordinate error and the angle error, providing an accurate data basis for subsequent updates of the expected path of the guidewire.

[0157] For example, the formula for calculating the three-dimensional coordinate error of the interventional guidewire is as follows:

[0158] ;

[0159] in, This indicates the three-dimensional coordinate error of the interventional guidewire; This represents the desired three-dimensional coordinate information of the interventional guidewire; This represents the three-dimensional coordinate information of the interventional guidewire. The formula for calculating the angle error of the interventional guidewire is as follows:

[0160] ;

[0161] in, This indicates the angle error of the interventional guidewire; This indicates the angle information of the interventional guidewire; This indicates the desired angle information for the interventional guidewire. This indicates the angle between the head of the interventional guidewire and the tangential direction of the blood vessel. It can be determined based on the Frenet–Serret frame. The calculation formula is as follows:

[0162] ;

[0163] ;

[0164] in, Represents the tangential vector of the blood vessel; A parameterized curve representing a blood vessel; The parameter representing the arc length of the curve; and This represents the component of the tangential vector of the blood vessel.

[0165] S240, Update the desired path of the interventional guidewire based on the offset error.

[0166] Optionally, the desired path of the interventional guidewire is updated based on the offset error, specifically including: determining the corrected coordinate information, corrected angle information, and corrected normal information of the interventional guidewire based on the three-dimensional coordinate error and the angle error, respectively; and updating the desired path based on the corrected coordinate information, corrected angle information, and corrected normal information.

[0167] The corrected coordinate information refers to the corrected three-dimensional coordinates of the guidewire tip, used to characterize the guidewire's advancement direction. The corrected coordinate information can be determined based on the three-dimensional coordinate error and the three-dimensional coordinates of the guidewire tip. For example, the three-dimensional coordinate error and the three-dimensional coordinates of the guidewire tip are input into a trained corrected coordinate information determination model for processing to obtain the corrected coordinate information. The corrected angle information is the corrected angle information, used to characterize the guidewire's rotation angle. The corrected angle information can be determined based on the angle error and the angle information. For example, the angle error and the angle information are input into a trained corrected angle information determination model for processing to obtain the corrected angle information. The corrected normal information is the corrected normal information. The corrected normal information is perpendicular to the guidewire's advancement direction. The corrected normal information can be determined based on the three-dimensional coordinate error and the three-dimensional coordinates of the guidewire tip. For example, the three-dimensional coordinate error and the three-dimensional coordinates of the guidewire tip are input into a trained corrected normal information determination model for processing to obtain the corrected normal information.

[0168] Specifically, the three-dimensional coordinate error and the three-dimensional coordinate information of the guidewire tip are input into a trained model for determining corrected coordinate information to obtain corrected coordinate information; the angle error and angle information are input into a trained model for determining corrected angle information to obtain corrected angle information; the three-dimensional coordinate error and the three-dimensional coordinate information of the guidewire tip are input into a trained model for determining corrected normal information to obtain corrected normal information; the corrected coordinate information, corrected angle information, corrected normal information, and desired path are input into a trained model for updating desired path to obtain the updated desired path of the guidewire. This achieves precise updating of the desired path of the guidewire, providing accurate path support for subsequent control of the guidewire and improving the safety of the procedure.

[0169] For example, the desired path of the interventional guidewire can be updated based on a feedback control model, which includes, but is not limited to, a proportional-derivative (PD) control model. The update formula for the desired path of the interventional guidewire using the PD control model is as follows:

[0170] ;

[0171] ;

[0172] ;

[0173] in, This indicates the corrected coordinate information of the interventional guidewire, i.e., the direction of guidewire advancement;

[0174] The proportional gain representing the axial position error; Indicates axial position error; The differential gain represents the derivative of the axial position error; The derivative representing the axial position error; This indicates the correction angle information for the interventional guidewire; The proportional gain represents the angle error; Indicates angular error; The differential gain represents the angular error; The derivative representing the angular error; This indicates the corrected normal information of the interventional guidewire, which is perpendicular to the direction of guidewire advancement. The proportional gain represents the lateral position error; Indicates lateral position error; The differential gain represents the derivative of the lateral position error; The derivative represents the lateral position error.

[0175] Optionally, the method further includes: acquiring second location information of the interference item based on two X-ray scanning devices, the interference item including at least one of the blood vessel wall and thrombus, the second location information including the three-dimensional coordinate information of the interference item; determining target distance information based on the first location information and the second location information, the target distance information representing the minimum distance between the head of the interventional guidewire and the interference item; and redetermining the desired path if the target distance information meets preset conditions.

[0176] The second location information refers to the position of the interfering item in three-dimensional space. This second location information can be obtained using two X-ray scanning devices. For example, by scanning the target location using two X-ray scanning devices, including the location of the interfering item, a scanned image of the target location is obtained. This scanned image includes the second location information of the interfering item, which includes multiple three-dimensional coordinates of the interfering item. The target distance information is the minimum distance between the head of the interventional guidewire and the interfering item. The target distance information can be determined based on the first and second location information. For example, the distances between the three-dimensional coordinates in the first location information and the multiple three-dimensional coordinates in the second location information are calculated, and the minimum distance among these distances is determined. This minimum distance is used as the target distance information. When the target distance information is less than a preset safety distance, it indicates that the target distance information meets the preset conditions, but the head of the interventional guidewire is too close to the interfering item, requiring a re-determination of the desired path.

[0177] Specifically, the target location, including the location of the interference item, is scanned using two X-ray scanning devices to obtain a scanned image of the target location. The scanned image includes the second location information of the interference item. The distances between the three-dimensional coordinates in the first location information and the multiple three-dimensional coordinates in the second location information are calculated respectively. The minimum distance among the above distances is determined and used as the target distance information. When the target distance information is less than the preset safety distance, it indicates that the target distance information meets the preset conditions. The desired path is then redefined, which prevents the interventional guidewire from getting too close to the interference item and improves the safety of the operation.

[0178] For example, the update formula for the expected path is as follows:

[0179] ;

[0180] in, Indicates the expected path after the update; This represents the three-dimensional coordinate information in the first position information; Three-dimensional coordinate information representing the second position; Indicates the weighting coefficient; This represents the smoothness constraint of the desired path.

[0181] The technical solution of this embodiment acquires two images of the target object under guidewire intervention state using two X-ray scanning devices in a dual-plane digital subtraction angiography system. These images include the interventional guidewire, providing comprehensive data support for subsequent analysis and processing. Based on the pre-calibrated projection matrices corresponding to the two X-ray scanning devices, guidewire positioning is performed on the two images to determine the path information of the interventional guidewire. This path information includes the first position information of the interventional guidewire, achieving precise determination of the guidewire path and providing accurate data support for subsequent guidewire positioning. The desired path of the interventional guidewire is acquired, including the desired three-dimensional coordinates and desired angle information of the guidewire head. Three-dimensional coordinate errors are determined based on the three-dimensional coordinates and the desired angle information, and angle errors are determined based on the angle information and the desired angle information, achieving precise determination of the three-dimensional coordinate errors and angle errors, providing an accurate data foundation for updating the desired path of the interventional guidewire. The desired path of the interventional guidewire is updated based on the offset error, achieving precise updating of the desired path and providing accurate path support for subsequent guidewire control, which is beneficial to improving the safety of the procedure.

[0182] Example 3

[0183] Figure 6This is a schematic diagram of a binocular X-ray guidewire three-dimensional positioning device based on epipolar geometry provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes an image acquisition module 310, a path information determination module 320, an offset error determination module 330, and a desired path update module 340.

[0184] The system includes: an image acquisition module 310, which acquires two images of the target object in a guidewire-interventional state using two X-ray scanning devices in a dual-plane digital subtraction angiography system; the images include the interventional guidewire; a path information determination module 320, which locates the guidewire in the two images based on the pre-calibrated projection matrices of the two X-ray scanning devices and determines the path information of the interventional guidewire, including the first position information of the interventional guidewire; an offset error determination module 330, which acquires the desired path of the interventional guidewire and determines the offset error of the interventional guidewire based on the desired position information and the first position information of the interventional guidewire in the desired path; and a desired path update module 340, which updates the desired path of the interventional guidewire based on the offset error.

[0185] The technical solution of this embodiment acquires two images of the target object in a guidewire-interventional state using two X-ray scanning devices in a dual-plane digital subtraction angiography system via the image acquisition module 310. These images include the interventional guidewire, providing comprehensive data support for subsequent analysis and processing. The path information determination module 320, based on the pre-calibrated projection matrices corresponding to the two X-ray scanning devices, locates the guidewire in the two images and determines the path information of the interventional guidewire. This path information includes the first position information of the interventional guidewire, achieving precise path information for the interventional guidewire. The system provides accurate data support for the subsequent positioning of the interventional guidewire. The offset error determination module 330 obtains the expected path of the interventional guidewire and determines the offset error based on the expected position information and the first position information of the interventional guidewire within the expected path. This accurate determination of the offset error provides an accurate data basis for updating the expected path of the interventional guidewire. The expected path update module 340 updates the expected path of the interventional guidewire based on the offset error, achieving accurate updating of the expected path and providing accurate path support for the subsequent control of the interventional guidewire, thus improving the safety of the procedure.

[0186] Based on the above embodiments, optionally, the path information determination module 320 is further configured to: acquire multiple images of the calibration plate in different orientations based on two X-ray scanning devices; calibrate the multiple images of the calibration plate for any X-ray scanning device to determine the intrinsic parameter matrix and extrinsic parameter matrix of the X-ray scanning device; and determine the projection matrix based on the intrinsic parameter matrix and extrinsic parameter matrix.

[0187] Optionally, the path information determination module 320 is further configured to: perform skeletonization processing on the image to be processed to obtain a skeleton image corresponding to each image to be processed, the skeleton image including the pixel coordinate information corresponding to the intervention guide wire; determine the basis matrix based on the pixel coordinate information and two projection matrices, the basis matrix representing the epipolar geometric constraint relationship; determine the matching point pair of the two skeleton images based on the two basis matrices and pixel coordinate information; and determine the path information based on the two projection matrices and the matching point pair.

[0188] Optionally, the path information determination module 320 is also used to: determine multiple homogeneous coordinate information of the interventional guidewire based on two projection matrices and multiple matching point pairs; perform non-homogeneous processing on the multiple homogeneous coordinate information to determine multiple non-homogeneous coordinate information of the interventional guidewire; and fit the multiple non-homogeneous coordinate information to obtain path information.

[0189] Optionally, the first position information includes the three-dimensional coordinates and angle information of the head of the interventional guidewire.

[0190] Optionally, the desired location information includes the desired three-dimensional coordinates and desired angle information of the tip of the interventional guidewire.

[0191] Optionally, offset error includes three-dimensional coordinate error and angle error.

[0192] Optionally, the offset error determination module 330 is also used to: determine the three-dimensional coordinate error based on the three-dimensional coordinate information and the three-dimensional coordinate information; and determine the angle error based on the angle information and the desired angle information.

[0193] Optionally, the desired path update module 340 is also used to: determine the corrected coordinate information, corrected angle information, and corrected normal information of the interventional guidewire based on the three-dimensional coordinate error and angle error, respectively; and update the desired path based on the corrected coordinate information, corrected angle information, and corrected normal information.

[0194] Optionally, the device further includes a desired path redeter module for: acquiring second location information of an interfering item based on two X-ray scanning devices, the interfering item including at least one of a blood vessel wall and a thrombus, the second location information including three-dimensional coordinate information of the interfering item; determining target distance information based on the first location information and the second location information, the target distance information representing the minimum distance between the head of the interventional guidewire and the interfering item; and redetermining the desired path if the target distance information meets preset conditions.

[0195] The binocular X-ray guidewire three-dimensional positioning device based on epipolar geometry provided in this invention can execute the binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry provided in any embodiment of this invention, and has the corresponding functional modules and beneficial effects of the method.

[0196] Example 4

[0197] Figure 7 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0198] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0199] Multiple components in electronic device 10 are connected to input / output (I / O) interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0200] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a binocular X-ray guidewire three-dimensional localization method based on epipolar geometry.

[0201] In some embodiments, a binocular X-ray guidewire three-dimensional localization method based on epipolar geometry can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via read-only memory (ROM) 12 and / or communication unit 19. When the computer program is loaded into random access memory (RAM) 13 and executed by processor 11, one or more steps of the epipolar geometry-based binocular X-ray guidewire three-dimensional localization method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform an epipolar geometry-based binocular X-ray guidewire three-dimensional localization method by any other suitable means (e.g., by means of firmware).

[0202] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0203] A computer program for implementing the present invention, a binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry, can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0204] Example 5

[0205] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry, the method comprising:

[0206] Two images to be processed, including the interventional guidewire, are acquired by two X-ray scanning devices in a dual-plane digital subtraction angiography system targeting a target object under guidewire intervention. Based on the pre-calibrated projection matrices of the two X-ray scanning devices, guidewire positioning is performed on the two images to determine the path information of the interventional guidewire, including its first position information. The desired path of the interventional guidewire is obtained, and its offset error is determined based on the desired position information and the first position information within the desired path. The desired path of the interventional guidewire is then updated based on the offset error.

[0207] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0208] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0209] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0210] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0211] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0212] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A three-dimensional positioning method for binocular X-ray guidewires based on epipolar geometry, characterized in that, The method includes: Two images to be processed are acquired by two X-ray scanning devices in a dual-plane digital subtraction angiography system for a target object under guidewire intervention, wherein the images to be processed include the interventional guidewire; Based on the projection matrices corresponding to the two X-ray scanning devices obtained through pre-calibration, guidewire positioning is performed on the two images to be processed to determine the path information of the interventional guidewire, which includes the first position information of the interventional guidewire. Obtain the desired path of the interventional guidewire, and determine the offset error of the interventional guidewire based on the desired position information of the interventional guidewire in the desired path and the first position information; The desired path of the interventional guidewire is updated based on the offset error.

2. The method according to claim 1, characterized in that, The process for determining the projection matrices corresponding to the two X-ray scanning devices is as follows: Multiple calibration images of calibration plates in different orientations were acquired using the two X-ray scanning devices. For any of the X-ray scanning devices, multiple images to be calibrated are calibrated to determine the intrinsic parameter matrix and extrinsic parameter matrix of the X-ray scanning device; the projection matrix is ​​determined based on the intrinsic parameter matrix and the extrinsic parameter matrix.

3. The method according to claim 1, characterized in that, The step of locating the guidewire in the two images to be processed based on the pre-calibrated projection matrices corresponding to the two X-ray scanning devices, and determining the path information of the interventional guidewire, includes: The images to be processed are skeletonized to obtain a skeleton image corresponding to each image to be processed. The skeleton image includes the pixel coordinate information corresponding to the interventional guidewire. A fundamental matrix is ​​determined based on the pixel coordinate information and the two projection matrices, and the fundamental matrix represents the epipolar geometric constraint relationship. The matching point pairs of the two skeleton images are determined based on the two basic matrices and the pixel coordinate information; The path information is determined based on the two projection matrices and the matching point pairs.

4. The method according to claim 3, characterized in that, Determining the path information based on the two projection matrices and the matching point pairs includes: Based on the two projection matrices and the multiple matching point pairs, determine multiple homogeneous coordinate information of the interventional guidewire; The multiple homogeneous coordinate information is processed in a non-homogeneous manner to determine the multiple non-homogeneous coordinate information of the interventional guidewire; The path information is obtained by fitting multiple non-homogeneous coordinate information.

5. The method according to claim 1, characterized in that, The first position information includes the three-dimensional coordinate information and angle information of the head of the interventional guidewire; the desired position information includes the desired three-dimensional coordinate information and desired angle information of the head of the interventional guidewire; the offset error includes the three-dimensional coordinate error and the angle error; The determination of the deviation error of the interventional guidewire based on the expected position information of the guidewire in the expected path and the first position information includes: The three-dimensional coordinate error is determined based on the three-dimensional coordinate information and the three-dimensional coordinate information. The angle error is determined based on the angle information and the desired angle information.

6. The method according to claim 5, characterized in that, The step of updating the desired path of the interventional guidewire based on the offset error includes: Based on the three-dimensional coordinate error and the angle error, the corrected coordinate information, corrected angle information and corrected normal information of the interventional guidewire are determined respectively; The desired path is updated based on the corrected coordinate information, the corrected angle information, and the corrected normal information.

7. The method according to claim 1, characterized in that, The first location information includes the three-dimensional coordinate information and angle information of the head of the interventional guidewire; The method further includes: The second location information of the interference item is obtained based on the two X-ray scanning devices. The interference item includes at least one of the blood vessel wall and thrombus. The second location information includes the three-dimensional coordinate information of the interference item. Target distance information is determined based on the first location information and the second location information, wherein the target distance information represents the minimum distance between the head of the interventional guidewire and the interference item; If the target distance information meets the preset conditions, the desired path is redefined.

8. A binocular X-ray guidewire three-dimensional positioning device based on epipolar geometry, characterized in that, include: The image acquisition module is used to acquire two images to be processed in a dual-plane digital subtraction angiography system, which are two X-ray scanning devices targeting a target object in a guidewire-intervention state. The images to be processed include the interventional guidewire. The path information determination module is used to locate the guidewire in the two images to be processed based on the projection matrices corresponding to the two X-ray scanning devices obtained by pre-calibration, and to determine the path information of the interventional guidewire, wherein the path information includes the first position information of the interventional guidewire. The offset error determination module is used to obtain the expected path of the interventional guidewire and determine the offset error of the interventional guidewire based on the expected position information of the interventional guidewire in the expected path and the first position information. The desired path update module is used to update the desired path of the interventional guidewire based on the offset error.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the binocular X-ray guidewire three-dimensional positioning method based on epipolar geometry as described in any one of claims 1-7.

Images