Medical Perspective View-based Target Localization Method and Device

Abstract

The present invention provides a target localization method and device based on medical perspective images, which are applied to the field of medical image processing. The method includes: selecting two-dimensional medical perspective images under any two viewpoints, and obtaining the two-dimensional pixel coordinates and image parameters of target points on the perspective images; calculating a target coordinate transformation matrix according to the image parameters, where the target coordinate transformation matrix is used to convert the two-dimensional pixel coordinates of the target points into three-dimensional world coordinates, and the target coordinate transformation matrix is composed of transformation parameters of a two-dimensional pixel coordinate system, a two-dimensional image coordinate system, a three-dimensional camera coordinate system, and a three-dimensional world coordinate system; substituting the two-dimensional pixel coordinates of the target points from the two viewpoints into the target coordinate transformation matrix to calculate the three-dimensional world coordinates of the initial target points from the two viewpoints; and performing processing and calculation based on the initial target points from the two viewpoints and the three-dimensional world coordinates to obtain the three-dimensional world coordinates of the target points. The present invention realizes fast and accurate localization of target points.

Description

Technical Field

[0001] The present invention relates to the field of medical image processing, and particularly to a target positioning method and device based on medical perspective images. Background Art

[0002] Surgical robots are widely used in minimally invasive surgery, puncture, ablation and other scenarios due to their advantages of high precision, few needle insertion times, and small complications. They do not rely on the experience and techniques of doctors and effectively solve clinical pain points. Fluoroscopic images are black-and-white images generated by X-ray fluoroscopy technology. By means of the difference in X-ray absorption of different human tissues, image data with different brightness levels are formed. Common applications include CBCT images and DSA images. In surgical robot technology, the fluoroscopic images generated from CBCT images can be recombined into high-resolution three-dimensional slice data through a special algorithm, and the target lesion center or other target positions can be accurately located. After obtaining the target image coordinates, combined with the optical navigation module, it guides the robotic arm to perform subsequent operations, improves the success rate of one-time needle insertion, reduces the operation time, and reduces the pain of patients. The whole process requires precise image guidance and is an important link in the surgical process.

[0003] However, fluoroscopic images have limitations in target positioning tasks because they ignore the distance information from the target to the light source, or depth information. In target positioning tasks, if the position of the target deviates from the rotation center plane, the distance from the light source to the target plane and the pixel pitch become unknown, and directly using the DICOM tag value will result in significant errors. Moreover, obtaining the three-dimensional coordinates of the target in the CBCT tomographic image requires the device to complete shooting and reconstruction algorithm processing of more than 200 degrees, as well as subsequent segmentation or modeling. The whole process is complex and time-consuming. Therefore, in the case where the tag values of two-dimensional fluoroscopic images are inaccurate, the three-dimensional coordinates cannot be quickly and accurately determined, and a large amount of calculation is involved, and the process is cumbersome. Summary of the Invention

[0004] In view of this, on the one hand, the present invention provides a target positioning method based on medical perspective images, including:

[0005] Select two-dimensional medical perspective images under any two viewpoints, and obtain the two-dimensional pixel coordinates and image parameters of the target points on the perspective images, where the image parameters are the basic attributes of the medical perspective images and the geometric parameters of the imaging system;

[0006] Calculate the target coordinate transformation matrix according to the image parameters, where the target coordinate transformation matrix is used to convert the two-dimensional pixel coordinates of the target points into three-dimensional world coordinates, and the target coordinate transformation matrix is composed of the transformation parameters of the two-dimensional pixel coordinate system, the two-dimensional image coordinate system, the three-dimensional camera coordinate system and the three-dimensional world coordinate system;

[0007] Substitute the two-dimensional pixel coordinates of the target point with dual perspectives into the target coordinate transformation matrix to calculate the three-dimensional world coordinates of the initial target point with dual perspectives;

[0008] Process and calculate based on the initial target point with dual perspectives and the three-dimensional world coordinates to obtain the three-dimensional world coordinates of the target point.

[0009] Optionally, the image parameters include the image resolution of the medical fluoroscopic image, pixel pitch, distance from the light source point to the patient in the imaging system, distance from the light source point to the detector panel in the imaging system, first angle, second angle, first angle increment, and second angle increment.

[0010] Optionally, calculate the target coordinate transformation matrix in the following manner:

[0011]

[0012] where, (X W , Y W , Z W ) represents the three-dimensional world coordinates, (u, v) represents the two-dimensional pixel coordinates, row represents the number of pixels in the vertical direction of the fluoroscopic image, cols represents the number of pixels in the horizontal direction of the fluoroscopic image, spacing represents the pixel pitch, SOD represents the distance from the light source point to the patient, SID represents the distance from the light source point to the detector panel, R is the rotation matrix, and T is the offset vector.

[0013] Optionally, calculate the target coordinate transformation matrix in the following manner:

[0014]

[0015] where, (u, v) represents the two-dimensional pixel coordinates, (X W , Y W , Z W ) represents the three-dimensional world coordinates, row represents the number of pixels in the vertical direction of the fluoroscopic image, cols represents the number of pixels in the horizontal direction of the fluoroscopic image, spacing represents the pixel pitch, SOD represents the distance from the light source point to the patient, SID represents the distance from the light source point to the detector panel, R is the rotation matrix, and T is the offset vector.

[0016] Optionally, process based on the initial target point with dual perspectives and the three-dimensional world coordinates to obtain the three-dimensional world coordinates of the target point, including:

[0017] Use the target coordinate transformation matrix to calculate the three-dimensional world coordinates of the light source point with dual perspectives;

[0018] Connect the light source point of the first perspective with the corresponding initial target point to obtain a first connection line, and connect the light source point of the second perspective with the corresponding initial target point to obtain a second connection line;

[0019] Select a point on each of the first connection line and the second connection line respectively, such that the midpoint of the line connecting the two selected points is at the shortest distance from the first connection line and the second connection line;

[0020] Take the midpoint as the target point, and obtain the three-dimensional world coordinates of the target point.

[0021] Optionally, select a point on each of the first connection line and the second connection line respectively in the following manner:

[0022]

[0023] where l 1 represents the connection line equation of the first connection line, l 2 represents the connection line equation of the second connection line, A represents the three-dimensional world coordinates of the light source point on the first connection line, B represents the three-dimensional world coordinates of the initial target point on the first connection line, C represents the three-dimensional world coordinates of the light source point on the second connection line, D represents the three-dimensional world coordinates of the initial target point on the second connection line, i represents the parameter on the first connection line, and j represents the parameter on the second connection line.

[0024] Optionally,

[0025]

[0026] where,

[0027]

[0028] where, (A x , A y , A z ) are the three-dimensional world coordinates of the light source point on the first connection line, (B x , B y , B z ) are the three-dimensional world coordinates of the initial target point on the first connection line, (C x , C y , C z ) are the three-dimensional world coordinates of the light source point on the second connection line, (D x , D y , D z ) are the three-dimensional world coordinates of the initial target point on the second connection line.

[0029] Optionally, the included angle between the first perspective and the second perspective is between 30° and 150°.

[0030] In a second aspect of the present invention, a target positioning device based on medical perspective images is provided. The device includes: a processor and a memory connected to the processor; wherein, the memory stores instructions executable by the processor, and when the instructions are executed by the processor, the processor is caused to execute the above-mentioned target positioning method based on medical perspective images.

[0031] The present invention selects two-dimensional medical perspective images under any two viewpoints, obtains the two-dimensional pixel coordinates of the target points on the perspective images, establishes a target coordinate transformation matrix according to the known perspective geometric parameters, and transforms the two-dimensional pixel coordinates into three-dimensional world coordinates. Compared with traditional multi-viewpoint shooting and reconstruction algorithms, this method only needs to select perspective images under any two viewpoints, greatly reducing the shooting time and the computational amount of the reconstruction algorithm. Moreover, this method has relatively low requirements for the acquisition of perspective data, is applicable to medical perspective image processing in various environments, does not require additional external markers or prior calibration, and reduces the operation complexity and preparation work. Specifically, by selecting two viewpoints to obtain perspective images, the lack of single-viewpoint information is avoided, and at the same time, the processing amount and computational cost are reduced. Due to the possible inaccuracy of the image parameters, this method also performs reprocessing to improve the accuracy of coordinate transformation. This method can quickly and accurately locate the positions such as the center of tumor lesions, body surface markers, the tips of in-vivo puncture needles or ablation needles, and is applicable to a variety of clinical application scenarios, such as registration and navigation systems, lesion confirmation, and ablation treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 It is a flowchart of the target positioning method based on medical perspective images in the embodiments of the present invention;

[0034] Figure 2 It is a projection schematic diagram in the embodiments of the present invention;

[0035] Figure 3 It is a schematic diagram of calculating target points in the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0037] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0038] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can also be the communication inside two elements. It can be a wireless connection or a wired connection. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0040] As Figure 1 shown, the embodiment of the present invention provides a target positioning method based on a medical perspective view. This method is executed by an electronic device such as a computer or a server, and specifically includes:

[0041] S1, select two-dimensional medical perspective images under any two viewpoints, and obtain the two-dimensional pixel coordinates and image parameters of the target points on the perspective images. The image parameters are the basic attributes of the medical perspective images and the geometric parameters of the imaging system.

[0042] The imaging system is a C-arm X-ray machine, including a light source system, which includes a transmitter and a receiver. The transmitter and the receiver are respectively located on both sides of the medical bed. X-rays are mainly emitted through the transmitter. After these rays penetrate the human body, they are attenuated. The receiver receives these attenuated signals to obtain perspective images. Among them, X-rays are not "light" in the traditional sense. The present invention can be broadly understood as the rays required for imaging. Then the transmitter (i.e., X-ray source) can be regarded as a part of the light source system, and the light source point mentioned below refers to the transmitter. At the same time, the C-arm can rotate around the patient to obtain more comprehensive perspective images from different angles. The C-arm X-ray machine is used to rotate at a predetermined angle to obtain a number of perspective images, and perspective images of any multiple perspectives (the number is much less than the total number of perspective images) are selected, preferably dual perspectives, such as the C-arm X-ray machine rotates half a circle 180° to obtain 180 frames of perspective images, and perspective images of two frames of two perspectives are selected. Selecting perspective images from multiple perspectives can avoid the loss of information from a single perspective and reduce the time for acquiring images and algorithm calculations. Perspective images from too many perspectives will increase the computing cost. Therefore, two or more perspectives can provide complementary information, reduce the amount of processing, and quickly obtain accurate information.

[0043] Perspective images are two-dimensional pixel images, black-and-white images obtained through X-ray perspective technology, which use the different absorption of X-rays by different tissues of the human body to form data of different brightness. Common ones include CBCT images and DSA images. The target point can be the center of a tumor lesion, a body surface positioning marker, or the tip of a puncture needle or ablation needle in the body. The acquisition method is not limited to manual selection or extraction by traditional methods or machine learning methods to obtain the two-dimensional pixel coordinates (u, v) of the target point with the pixel image as the coordinate system. The image parameters are built-in default values, which can be read from the standard format image of the DICOM image, or can be obtained by technicians or doctors based on actual environment self-test.

[0044] S2, calculate the target coordinate transformation matrix according to the image parameters, the target coordinate transformation matrix is ​​used to transform the two-dimensional pixel coordinates of the target point into three-dimensional world coordinates, wherein the target coordinate transformation matrix is ​​composed of transformation parameters of the two-dimensional pixel coordinate system, the two-dimensional image coordinate system, the three-dimensional camera coordinate system and the three-dimensional world coordinate system.

[0045] The transformation matrix among the 2D pixel coordinate system, 2D image coordinate system, 3D camera coordinate system and 3D world coordinate system is calculated according to the image parameters to transform the 2D pixel coordinates of the target point into 3D world coordinates. All coordinate systems satisfy the right-hand coordinate system.

[0046] S3, bringing the two-dimensional pixel coordinates of the target point of the dual-view into the target coordinate transformation matrix, and calculating the three-dimensional world coordinates of the initial target point of the dual-view.

[0047] S4. Process and calculate based on the initial target points from dual perspectives and the 3D world coordinates to obtain the 3D world coordinates of the target points.

[0048] Since the image parameters may not be accurate, the world coordinates obtained from the target coordinate transformation matrix may not be accurate. Therefore, reprocessing is required to obtain the accurate 3D world coordinates of the target points.

[0049] In this embodiment, by selecting the two-dimensional medical fluoroscopic images under any dual perspectives, and obtaining the two-dimensional pixel coordinates of the target points on the fluoroscopic images, a target coordinate transformation matrix is established based on the known fluoroscopic geometric parameters to convert the two-dimensional pixel coordinates into 3D world coordinates. Compared with the traditional multi-perspective shooting and reconstruction algorithms, this method only needs to select the fluoroscopic images under any dual perspectives, greatly reducing the shooting time and the computational complexity of the reconstruction algorithm. Moreover, this method has lower requirements for obtaining fluoroscopic data, is applicable to the medical fluoroscopic image processing in various environments, does not require additional external markers or prior calibration, reducing the operation complexity and preparation work. Specifically, by selecting dual perspectives to obtain fluoroscopic images, the lack of single-perspective information is avoided, while the processing amount and computational cost are reduced. Since the image parameters may not be accurate, this method also performs reprocessing to improve the accuracy of coordinate transformation. This method can quickly and accurately locate the positions such as the center of tumor lesions, body surface markers, the tips of in-vivo puncture needles or ablation needles, and is applicable to a variety of clinical application scenarios, such as registration and navigation systems, lesion confirmation, and ablation treatment.

[0050] Preferably, when selecting the fluoroscopic images, the included angle between the first perspective and the second perspective should be controlled between 30° and 150°.

[0051] Controlling the included angle between the fluoroscopic images of the two perspectives within a preset angle range can ensure that there is a certain parallax (the depth and distance of an object) between the two frames of fluoroscopic images, thus contributing to subsequent 3D reconstruction or target point positioning. If the included angle is too small, it may lead to insufficient parallax, thus affecting the accuracy of 3D reconstruction. On the contrary, if the included angle is too large, although the parallax will increase, it may also result in a reduction in the overlapping part between the images, increasing the difficulty of subsequent processing.

[0052] The image parameters obtained in step S1 are the basic attributes of the medical fluoroscopic images and the geometric parameters of the imaging system. Among them, the image parameters include the image resolution row, cols of the medical fluoroscopic image, the pixel pitch Spacing, the distance SOD from the light source point to the patient in the imaging system, the distance SID from the light source point to the detector panel in the imaging system, the first angle θ 1 、the second angle θ 2 、the first angle increment Δθ 1 、the second angle increment Δθ 2 .

[0053] Among them, the distance from the light source point to the detection board in the imaging system is the distance from the emitting end to the receiving end of the C-arm X-ray machine; the first angle and the second angle are the initial angles of two selected fluoroscopic images, and the first angle increment and the second angle increment are the angles of rotation of the corresponding frame images. For example, the angle of the 90th frame is the corresponding initial angle plus the angle increment, that is, the angle of the corresponding viewing angle is obtained. The following descriptions are all based on the dual-view angles of 0° and 90° as examples. In one embodiment, the target coordinate transformation matrix is calculated according to the image parameters, and the target coordinate transformation matrix is obtained from the transformation matrix between the two-dimensional pixel coordinate system and the two-dimensional image coordinate system, the transformation matrix between the two-dimensional image coordinate system and the three-dimensional camera coordinate system, and the transformation matrix between the three-dimensional camera coordinate system and the three-dimensional world coordinate system. Among them, the transformation matrix between the two-dimensional pixel coordinate system and the two-dimensional image coordinate system is calculated through the image resolution and the pixel pitch, the transformation matrix between the two-dimensional image coordinate system and the three-dimensional camera coordinate system is obtained through the distance from the light source point to the patient, and the transformation matrix between the three-dimensional camera coordinate system and the three-dimensional world coordinate system is calculated through the first angle, the second angle, the first angle increment, and the second angle increment.

[0054] According to the two-dimensional pixel coordinates (u, v), the canvas center pixel coordinates (row / 2, col / 2), and the two-dimensional image coordinates (x, y), the transformation matrix between the two-dimensional pixel coordinate system and the two-dimensional image coordinate system is as follows:

[0055]

[0056] According to the coordinates (Xc, Yc, Zc) in the three-dimensional camera coordinate system, the transformation matrix between the two-dimensional image coordinate system and the three-dimensional camera coordinate system is as follows:

[0057]

[0058] The current fluoroscopic image rotates around the Z-axis by an angle of (θ 1 + Δθ 1 ), and rotates around the X-axis by an angle of (θ 2 + Δθ 2 ). For the coordinates (Xw, Yw, Zw) in the three-dimensional world coordinate system, the transformation matrix between the three-dimensional camera coordinate system and the three-dimensional world coordinate system is as follows:

[0059]

[0060] Finally, the target coordinate transformation matrix is calculated:

[0061]

[0062] Among them, (X W , Y W , Z W(u, v) represents the two-dimensional pixel coordinates, (u, v) represents the two-dimensional pixel coordinates, row represents the number of pixels of the perspective image in the vertical direction, cols represents the number of pixels of the perspective image in the horizontal direction, spacing represents the pixel pitch, SOD represents the distance from the light source point to the patient, SID represents the distance from the light source point to the detection plate, R is the rotation matrix, and T represents the offset vector.

[0063] In another embodiment, there is also a method for calculating the target coordinate transformation matrix as follows:

[0064] According to the two-dimensional pixel coordinates (u, v), the center pixel coordinates of the canvas (row / 2, col / 2), and the two-dimensional image coordinates (x, y), the transformation matrix between the two-dimensional pixel coordinate system and the two-dimensional image coordinate system is as follows:

[0065]

[0066] According to the coordinates (Xc, Yc, Zc) in the three-dimensional camera coordinate system, the transformation matrix between the two-dimensional image coordinate system and the three-dimensional camera coordinate system is as follows:

[0067]

[0068] The current perspective image rotates around the Z-axis by an angle of (θ 1 +Δθ 1 ), and rotates around the X-axis by an angle of (θ 2 +Δθ 2 ). For the coordinates (Xw, Yw, Zw) in the three-dimensional world coordinate system, the transformation matrix between the three-dimensional camera coordinate system and the three-dimensional world coordinate system is as follows:

[0069]

[0070]

[0071] Among them, (u, v) represents the two-dimensional pixel coordinates, (X W , Y W , Z W ) represents the three-dimensional world coordinates, row represents the number of pixels of the perspective image in the vertical direction, cols represents the number of pixels of the perspective image in the horizontal direction, spacing represents the pixel pitch, SOD represents the distance from the light source point to the patient, SID represents the distance from the light source point to the detection plate, R is the rotation matrix, and T represents the offset vector.

[0072] In one embodiment, step S4 processes the initial target points of the dual perspectives and the three-dimensional world coordinates to obtain the three-dimensional world coordinates of the target points, including:

[0073] S41. Using the target coordinate transformation matrix, calculate the three-dimensional world coordinates of the light source points of the dual perspectives;

[0074] S42. Connect the light source points of the first perspective with the corresponding initial target points to obtain a first connection line, and connect the light source points of the second perspective with the corresponding initial target points to obtain a second connection line;

[0075] S43. Select a point on each of the first connection line and the second connection line such that the midpoint of the line connecting the two selected points is closest to the first connection line and the second connection line;

[0076] S44. Take the midpoint as the target point and obtain the three-dimensional world coordinates of the target point.

[0077] As Figure 2 shown, the light source point of the first perspective (0°) is A, the light source point of the second perspective (90°) is C, the cube represents the patient, point B is the two-dimensional pixel target point obtained from the first perspective (corresponding to a point on the receiving end detection board of the C-arm X-ray machine), and point D is the two-dimensional pixel target point obtained from the second perspective. Since the distance from the light source point to the patient in the image parameters is only the distance from the light source point to the patient, rather than the distance to the in-vivo tumor, when the light source (such as X-rays) penetrates the human body, the image formed on the receiving end (such as the detection board of the C-arm X-ray machine) often only reflects the projection position on the skin surface, rather than the true position of the lesion in the body. Therefore, the two-dimensional pixel target points directly obtained from the image (such as point B and point D) are often only the projections of the lesion on the skin surface, rather than the lesion itself. The initial target point obtained from the first perspective is E, and the initial target point obtained from the second perspective is F. That is to say, the initial target points E and F are also only points on the skin surface, and the real target is located on the line segment or extension line between the light source and the initial target point. Therefore, it is necessary to further process the initial target points E and F. It is necessary to connect point A and point E to obtain a first connection line, and connect point C and point F to obtain a second connection line.

[0078] Furthermore, since points B and D are the target points of the pixel map obtained by the light source point emitting X-rays passing through the human body and projecting onto the detection board of the receiving end, point B is on the extension line of the first connection line, and point D is on the extension line of the second connection line. Then, the equations of the first connection line and the second connection line are as follows:

[0079]

[0080] where l 1 represents the connection equation of the first connection line, l 2The connection equation representing the second connection line, A represents the three-dimensional world coordinates of the light source point on the first connection line, B represents the three-dimensional world coordinates of the initial target point on the first connection line, C represents the three-dimensional world coordinates of the light source point on the second connection line, D represents the three-dimensional world coordinates of the initial target point on the second connection line, i represents the parameter on the first connection line, and j represents the parameter on the second connection line.

[0081] Among them,

[0082]

[0083] The equation construction matrix is as follows:

[0084]

[0085] By solving the basic form of PX = Q through the least squares method, we get:

[0086]

[0087] Among them,

[0088]

[0089] Among them, (A x , A y , A z ) are the three-dimensional world coordinates of the light source point on the first connection line, (B x , B y , B z ) are the three-dimensional world coordinates of the initial target point on the first connection line, (C x , C y , C z ) are the three-dimensional world coordinates of the light source point on the second connection line, and (D x , D y , D z ) are the three-dimensional world coordinates of the initial target point on the second connection line.

[0090] After solving for i and j according to the above formula and substituting them into the l 1 , l 2 two equations, the points on the two connection lines can be obtained. As shown in Figure 3 , the midpoint of the two points is the spatial point closest to the two connection lines. Corresponding to Figure 2 , point G is the target point, and its coordinates will be used as the three-dimensional world coordinates of the target point.

[0091] Since the lesion is located inside the body, it must be at some position on these two connecting lines or their extensions. To find a more accurate estimated position closer to the lesion, this embodiment adopts the method of taking the midpoint of the points with the same distance on the two connecting lines as the target point. This method is based on the assumption that the distances from the lesion to the two connecting lines are equal (or at least very close). By constructing the connecting line equations and solving them using the least squares method, a pair of points (located on the two connecting lines respectively) can be found, and the distances from them to the midpoint are equal (or closest to being equal). This midpoint is the target point we seek, which is closer to the true position of the lesion. This method not only considers the distance from the light source point to the patient, but also further improves the accuracy of target point positioning by solving the intersection points of the connecting lines.

[0092] The three-dimensional world coordinates of the target point have important application values in the medical scenario. For example, in tumor treatment, the three-dimensional coordinates of the target point can be used to accurately navigate surgical instruments such as puncture needles and ablation needles to ensure that they can accurately reach the tumor lesion, improving the accuracy and safety of the surgery. In addition, this method can also be used in registration and navigation systems to accurately align the patient's actual anatomical structure with medical images, providing more accurate surgical guidance for doctors.

[0093] Generally speaking, the method of this embodiment provides an accurate and reliable method for calculating the three-dimensional coordinates of the target point, providing strong support for applications such as navigation and treatment in the medical field. Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0094] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0095] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0097] Obviously, the above embodiments are only examples for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or variations can be made based on the above description. It is not necessary and impossible to exhaustively list all the implementation manners here. And the obvious changes or variations derived therefrom are still within the protection scope of the present invention.

Claims

1. A target positioning method based on medical perspective images, characterized in that: include: Select a two-dimensional medical perspective image under any dual viewing angles, and obtain the two-dimensional pixel coordinates and image parameters of the target point on the perspective image, wherein the image parameters are basic attributes of the medical perspective image and geometric parameters of the imaging system, and the image parameters include image resolution of the medical perspective image, pixel spacing, a distance from a light source point to a patient in the imaging system, a distance from a light source point to a detection plate in the imaging system, a first angle, a second angle, a first angle increment, and a second angle increment, wherein the angle between the first viewing angle and the second viewing angle is between 30° and 150°; Calculating a target coordinate conversion matrix according to the image parameters, the target coordinate conversion matrix is ​​used to convert the two-dimensional pixel coordinates of the target point into three-dimensional world coordinates, wherein the target coordinate conversion matrix is ​​composed of conversion parameters of a two-dimensional pixel coordinate system, a two-dimensional image coordinate system, a three-dimensional camera coordinate system, and a three-dimensional world coordinate system; Substituting the two-dimensional pixel coordinates of the target point of the dual-view into the target coordinate conversion matrix, and calculating the three-dimensional world coordinates of the initial target point of the dual-view; Using the target coordinate transformation matrix, the three-dimensional world coordinates of the light source point of dual viewing angles are calculated; Connecting the light source point of the first viewing angle with the corresponding initial target point to obtain a first connecting line, and connecting the light source point of the second viewing angle with the corresponding initial target point to obtain a second connecting line; Selecting a point on the first connecting line and the second connecting line respectively, so that the midpoint of the connecting line between the two selected points is closest to the first connecting line and the second connecting line; The midpoint is used as a target point, and the three-dimensional world coordinates of the target point are obtained.

2. The method according to claim 1, characterized in that: The target coordinate transformation matrix is ​​calculated as follows: Among them, (X W ,Y W ,Z W ) represents the three-dimensional world coordinates, (u, v) represents the two-dimensional pixel coordinates, row represents the number of pixels of the perspective image in the vertical direction, cols represents the number of pixels of the perspective image in the horizontal direction, spacing represents the pixel spacing, SOD represents the distance from the light source to the patient, SID represents the distance from the light source to the detection board, R is the rotation matrix, and T represents the offset vector.

3. The method according to claim 1, characterized in that The target coordinate transformation matrix is ​​calculated as follows: Wherein, (u, v) represents the two-dimensional pixel coordinates, (X W ,Y W ,Z W ) represents the three-dimensional world coordinates, row represents the number of pixels of the perspective image in the vertical direction, cols represents the number of pixels of the perspective image in the horizontal direction, spacing represents the pixel spacing, SOD represents the distance from the light source to the patient, SID represents the distance from the light source to the detection board, R is the rotation matrix, and T represents the offset vector.

4. The method according to claim 1, characterized in that Select a point on the first connecting line and the second connecting line respectively in the following manner: Among them, l1 represents the line equation of the first line, l2 represents the line equation of the second line, A represents the three-dimensional world coordinates of the light source point on the first line, B represents the three-dimensional world coordinates of the initial target point on the first line, C represents the three-dimensional world coordinates of the light source point on the second line, D represents the three-dimensional world coordinates of the initial target point on the second line, i represents the parameter on the first line, and j represents the parameter on the second line.

5. The method according to claim 4, characterized in that in, Among them, (A x ,A y ,A z ) is the 3D world coordinate of the light source point on the first line, (B x ,B y ,B z ) is the 3D world coordinate of the initial target point on the first line, (C x ,C y ,C z ) is the 3D world coordinate of the light source point on the second line, (D x ,D y ,D z ) is the 3D world coordinate of the initial target point on the second line.

6. A target positioning device based on medical perspective images, characterized in that: include: A processor and a memory connected to the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor so that the processor executes the target positioning method based on medical fluoroscopic images as described in any one of claims 1-5.

Images