Image real-time guiding and positioning method, system and device and storage medium

Abstract

The invention discloses an image real-time guiding and positioning method, system and device and a storage medium, and the method comprises the steps: collecting a group of three-dimensional images before or during an operation of a target region, and carrying out the operation guiding planning on the basis of the three-dimensional images; marking a needle entering point through a developing adhesive tape; collecting at least two limited-angle two-dimensional projection images, wherein the two-dimensional projection images comprise first projection data of the focus tissue in the target area and second projection data of the target instrument; coordinate information of the target instrument is extracted from the two-dimensional projection image; performing crown vector axis segmentation reconstruction on the target instrument; registering the two-dimensional projection image and the three-dimensional image, and projecting the reconstructed three-dimensional model of the target instrument into the three-dimensional image; and measuring the deviation between the three-dimensional model and the surgical planning path, and optimizing a surgical guiding scheme. According to the invention, the guiding efficiency of the puncture needle in the operation can be improved, and radiation exposure is reduced.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and more specifically, to a real-time image-guided positioning method, system, device, and storage medium. Background Technology

[0002] In recent years, with the continuous improvement of medical image processing technology, surgical navigation technology has been widely used. Surgical navigation technology refers to the technology of using the patient's medical image information to provide image guidance for the surgical process. Through this technology, doctors can understand the patient's internal structure and physiological information during the operation, thereby accurately judging the patient's current treatment status.

[0003] Current technologies primarily rely on medical imaging for precise guidance. The core process typically begins with real-time intraoperative acquisition of high-resolution CT or MRI images of the patient, allowing surgeons to observe the precise position of instrument tips relative to the patient's internal structures on a screen. This process involves lengthy scanning times and high radiation exposure, leading not only to prolonged surgical navigation registration but also to serious radiation damage to both surgeons and patients. Summary of the Invention

[0004] To address the aforementioned technical problems, this application discloses a real-time image-guided positioning method, system, device, and storage medium. By optimizing the surgical guidance planning scheme, it improves the efficiency of intraoperative needle guidance and reduces the radiation dose received by patients and medical staff.

[0005] Specifically, the technical solution of this application is as follows: In a first aspect, this application discloses a real-time image-guided positioning method, comprising the following steps: A set of three-dimensional images of the target area are acquired before or during the operation, and surgical guidance planning is carried out based on the three-dimensional images; the needle insertion point is marked using contrast-enhancing tape; Acquire at least two two-dimensional projection images at a limited angle, wherein the two-dimensional projection images include first projection data of the anatomical structure within the target area and second projection data of the target instrument; Register the two-dimensional projection image with the three-dimensional image, and project the target device in the two-dimensional projection image to the same position in the three-dimensional image; The deviation between the target instrument and the surgical planning path is measured to optimize the surgical guidance plan.

[0006] In some embodiments, the two-dimensional projection image is registered with the three-dimensional image, projecting the target instrument in the two-dimensional projection image to the same position in the three-dimensional image; specifically, this includes the following sub-steps: Features of the target instrument are extracted from the two-dimensional projection image, and the target instrument is reconstructed by coronal and sagittal axis segmentation. Bone feature points are extracted, and the two-dimensional projection image and the three-dimensional image are matched using a rigid registration method to obtain a spatial transformation matrix; Based on the spatial transformation matrix, the reconstructed three-dimensional model of the target instrument is projected onto the three-dimensional image.

[0007] In some implementations, features of the target instrument are extracted from the two-dimensional projection image, and the target instrument is reconstructed by coronal axis segmentation; specifically, this includes the following sub-steps: The target instrument in the two-dimensional projection image is segmented using a threshold segmentation method; the three-dimensional model of the target instrument is reconstructed from the coronal, sagittal and axial planes using a coronal-sagittal-axial segmentation and reconstruction algorithm.

[0008] In other embodiments, during image acquisition, the two-dimensional projected image and the three-dimensional image follow the same spatial geometric acquisition trajectory.

[0009] Furthermore, the extraction of bony feature points involves using a rigid registration method to match the two-dimensional projection image with the three-dimensional image to obtain a spatial transformation matrix; specifically, this includes the following sub-steps: The skeletal region is segmented from the three-dimensional image to extract the skeletal model; simultaneously, the skeletal region is segmented from the two-dimensional projection image to extract bony feature points. The bone model is simulated and a projection of bony features is generated using digital ray casting. The pose parameters of the skeletal model in three-dimensional space are adjusted by an iterative algorithm so that the projection of the bony features and the bony feature points are optimally aligned, thereby obtaining the spatial transformation matrix. The spatial transformation matrix is ​​used to describe the rigid transformation relationship between the three-dimensional image coordinate system and the two-dimensional projected image coordinate system.

[0010] In other embodiments, the position of the image acquisition device relative to the target area changes during the procedure; Obtain the motion trajectory parameters of the image acquisition device; update the spatial transformation matrix based on the motion trajectory parameters; Based on the updated spatial transformation matrix, the newly acquired two-dimensional projection image is registered with the three-dimensional image.

[0011] In other embodiments, measuring the deviation between the target instrument and the surgical planning path to optimize the surgical guidance plan specifically includes the following sub-steps: The deviation parameters between the pose of the target instrument and the surgical planning path are calculated in real time. The deviation parameters include position deviation, angle deviation, and depth deviation. A visual correction guidance scheme is provided based on the aforementioned deviation parameters.

[0012] Secondly, this application discloses an image-based real-time guidance and positioning system, the image-based real-time guidance and positioning system comprising: The first image acquisition module is used to acquire a set of three-dimensional images of the target area before or during the operation, so as to perform surgical guidance planning based on the three-dimensional images; and to mark the needle insertion point using contrast tape. The second image acquisition module is used to acquire at least two two-dimensional projection images with a limited angle. The two-dimensional projection images include first projection data of the anatomical structure in the target area and second projection data of the target instrument. An image registration module is used to register the two-dimensional projection image and the three-dimensional image, projecting the target instrument in the two-dimensional projection image to the same position in the three-dimensional image; The image-guided planning module is used to measure the deviation between the target instrument and the surgical planning path, and to optimize the surgical guidance scheme.

[0013] Thirdly, this application also discloses a real-time image guidance and positioning device, which includes a processor, a memory, and a display; The memory stores computer instructions, which are loaded and executed by the processor to implement the steps of the real-time image guidance and positioning method described in any of the above embodiments.

[0014] Fourthly, this application also discloses a readable storage medium storing computer instructions thereon, which, when executed by a processor, implement the steps of the real-time image guidance and positioning method described in any of the above embodiments.

[0015] Compared with the prior art, this application has at least one of the following beneficial effects: 1. This application does not require real-time intraoperative 3D image scanning. Based on surgical planning and image registration, the puncture needle can be registered to the 3D image. Through this application, limited 2D fluoroscopic information is integrated with 3D preoperative planning data, enabling doctors to receive dynamic surgical guidance with depth information without the need for continuous high-intensity radiation scanning. This significantly improves the accuracy and safety of minimally invasive surgeries such as percutaneous puncture and orthopedic internal fixation. Attached Figure Description

[0016] The preferred embodiments will now be described in a clear and easy-to-understand manner, in conjunction with the accompanying drawings, to further explain the above-mentioned characteristics, technical features, advantages, and implementation methods of this application.

[0017] Figure 1 This is a flowchart illustrating the steps of an embodiment of the real-time image-guided positioning method of this application; Figure 2 This is a flowchart illustrating the steps of another embodiment of the image-guided positioning method of this application. Detailed Implementation

[0018] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application can also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0019] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or sets.

[0020] To keep the drawings concise, each figure only schematically shows the parts relevant to the invention, and these do not represent the actual structure of the product. Furthermore, to facilitate understanding, in some figures, only one of components with the same structure or function is schematically depicted, or only one is labeled. In this document, "one" not only means "only one," but can also mean "more than one."

[0021] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the specific implementation methods of this application will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings and other implementation methods can be obtained based on these drawings without creative effort.

[0024] Reference manual attached Figure 1 As shown, one embodiment of the image real-time guided positioning method of this application specifically includes the following steps: S100: Acquire a set of three-dimensional images of the target area before or during the operation, and perform surgical guidance planning based on the three-dimensional images. Mark the needle insertion point using contrast-enhancing tape.

[0025] Specifically, in this embodiment, real three-dimensional images of the patient during or before the operation are imported, and the surgical plan is made in the three-dimensional images. The needle insertion point, needle path, angle and depth can be indicated, so that the needle can reach the preset target point without touching blood vessels, nerves and other key structures.

[0026] In some alternative implementations, the 3D image acquisition process utilizes equipment such as computed tomography (CT), magnetic resonance imaging (MRI), or ultrasound to obtain high-resolution 3D volumetric data of the patient's surgical site. This data is then imported into specialized surgical planning software, where the surgeon interactively analyzes the 3D reconstructed model to plan the theoretically optimal surgical path.

[0027] Optionally, this embodiment uses a C-arm-based CT device for three-dimensional image acquisition.

[0028] Once the planning is complete, the path in the virtual space needs to be accurately mapped onto the actual patient's skin. This requires marking the needle insertion points with radiopaque tape. This radiopaque tape is not ordinary tape; its surface contains materials that are clearly visible in imaging scans, and it is also adhesive, allowing it to be directly applied to the skin. In practice, the doctor applies this tape to the corresponding location on the patient's skin based on the coordinates calculated by the planning software.

[0029] S200, acquire at least two two-dimensional projection images with limited angles, wherein the two-dimensional projection images include first projection data of the anatomical structure within the target area and second projection data of the target instrument.

[0030] Specifically, in this embodiment, during the operation, an X-ray detection device is used to rapidly expose the target area containing anatomical structures and surgical instruments from two or more different angles, thereby obtaining two-dimensional fluoroscopic projection images with limited angles. These two-dimensional images contain both projection data of the patient's internal anatomical structures and projection data of the target instruments. Optionally, surgical instruments include puncture needles, bone screws, catheters, etc.

[0031] In this embodiment, two-dimensional projection images need to be acquired intraoperatively, but only one set of three-dimensional images needs to be acquired. After acquiring one set of three-dimensional images, the three-dimensional image acquisition device, i.e., the CT device of the C-arm robotic arm, can be removed. Compared with the prior art, this application does not require real-time scanning of three-dimensional image information during surgery. After the device is removed, the puncture needle can be registered to the three-dimensional image based on surgical planning and image registration.

[0032] S300, register the two-dimensional projection image with the three-dimensional image, and project the target instrument in the two-dimensional projection image to the same position in the three-dimensional image.

[0033] Specifically, in this embodiment, a rigid registration method is used to find the optimal spatial mapping relationship from the two-dimensional image to the three-dimensional image, so that the entire three-dimensional image data is aligned with the anatomical structure in the two-dimensional image in the spatial coordinate system. After registration is completed, the true position and orientation of the target instrument displayed on the two-dimensional image in three-dimensional space can be calculated and fused and mapped into the aligned three-dimensional image scene.

[0034] On the surgical navigation interface, the virtual model of the surgical instruments can be superimposed on the patient's three-dimensional anatomical model in real time with the correct posture and depth relationship, intuitively showing the spatial relationship between the instrument tip and key structures such as lesions and blood vessels.

[0035] S400, Measure the deviation between the target instrument and the surgical planning path, and optimize the surgical guidance plan.

[0036] Specifically, based on step S300, the generated navigation interface displays the instrument's 3D model and the patient's 3D anatomical structure together, enabling real-time visualization of the instrument's pose in 3D space. In some optional implementations, with the instrument's real-time pose data and the pre-planned surgical path, it is possible to determine whether there is a deviation between the actual path and the planned path, and thus correct any existing deviations.

[0037] Based on the above embodiments, this application discloses another embodiment of an image real-time guided positioning method, as detailed in the appendix to the specification. Figure 2 As shown, step S300 specifically includes the following sub-steps: S310, extract the features of the target instrument from the two-dimensional projection image, and perform coronal axis segmentation and reconstruction on the target instrument.

[0038] In some alternative implementations, S311, the target device in the two-dimensional projection image is segmented using a grayscale thresholding method.

[0039] In some alternative implementations, S311, edge detection or deep learning segmentation networks are used to segment the target device in the two-dimensional projection image.

[0040] In this embodiment, feature information of the target instrument is extracted separately from the two-dimensional projection image. Since surgical instruments typically appear as high-contrast linear or specific geometric shapes in X-ray images, the feature segmentation step precisely segments the pixel-level contour of the instrument in each two-dimensional image and identifies key feature points, such as endpoints and inflection points. After acquiring at least two two-dimensional contours of the target instrument from different viewpoints, segmentation and reconstruction are performed.

[0041] S312, using the coronal-sagittal-axial segmentation reconstruction algorithm, the three-dimensional model of the target instrument is reconstructed from three directions: coronal plane, sagittal plane, and axial plane.

[0042] In practical implementation, the coronal axis segmentation and reconstruction algorithm essentially utilizes multi-view 2D information for 3D reconstruction. Its theoretical basis is binocular vision or the principle of recovering structure from motion. Using the known geometric parameters of the 2D projection device, points on the instrument contour in each 2D image are projected backward into 3D space, forming a corresponding projection ray. The intersection of two or more rays from different viewpoints corresponding to the same physical point on the instrument in 3D space represents the 3D coordinates of that point. By solving for the optimal solution of these ray intersections, a 3D point cloud of a series of discrete points on the instrument can be reconstructed, and then a complete and continuous 3D model of the surgical instrument can be obtained through model fitting.

[0043] S320, extract bony feature points, and use rigid registration to match the two-dimensional projection image with the three-dimensional image to obtain a spatial transformation matrix.

[0044] In some optional implementations, to ensure the accuracy of three-dimensional spatial positioning, the two-dimensional projected images and the three-dimensional images follow the same spatial geometric acquisition trajectory during the sampling process. Based on the spatial geometric acquisition trajectory, since the positions of the two-dimensional images in the trajectory are known, this positional information can be used to constrain the registration process, and the estimated positions of each two-dimensional projected image in the three-dimensional coordinate system can be reconstructed through back-projection calculation methods. Further iterative optimization is then performed based on the estimated positions to complete rigid registration.

[0045] In some alternative implementations, step S320 specifically includes the following sub-steps: S321, segment the skeletal region from the three-dimensional image and extract the skeletal model; simultaneously, segment the skeletal region from the two-dimensional projection image and extract bony feature points.

[0046] S322, The skeletal model is simulated and a projection of bony features is generated by digital ray projection.

[0047] S323, the pose parameters of the skeletal model in three-dimensional space are adjusted through an iterative algorithm to achieve optimal alignment between the projection of the bony features and the bony feature points, thus obtaining the spatial transformation matrix. The spatial transformation matrix is ​​used to describe the rigid transformation relationship between the three-dimensional image coordinate system and the two-dimensional projected image coordinate system.

[0048] In practice, the rigid registration method based on feature points compares the actual 2D projected image with 2D slices at locations estimated from the 3D image. During the matching process, the spatial pose of the 3D image is iteratively optimized and adjusted until the parameter set that optimizes the similarity measure is found, so that the simulated 2D features and the feature points in the real 2D image achieve the best match, or when the error function converges to below the threshold, the 3D image and the 2D projection are spatially aligned, thus completing the rigid registration.

[0049] In some alternative implementations, the position of the image acquisition device relative to the target area is changed during the procedure.

[0050] Step S320 further includes: S324, obtaining the motion trajectory parameters of the image acquisition device, and updating the spatial transformation matrix based on the motion trajectory parameters.

[0051] S325, Based on the updated spatial transformation matrix, the newly acquired two-dimensional projection image is registered with the three-dimensional image.

[0052] Optionally, in this embodiment, the image acquisition device is an image C-arm device. During the surgery, it provides dynamic tracking of the positional changes of the C-arm machine or the patient. When the C-arm machine rotates or translates, its built-in angle sensor or encoder can accurately obtain the motion parameters of the gantry itself; at the same time, by continuously analyzing the skeletal feature points in the two-dimensional image, it is possible to detect possible movements of the patient.

[0053] By combining the relative positional changes between the C-arm machine and the patient, an updated spatial transformation matrix can be calculated in real time. Based on the updated spatial transformation matrix, the newly captured two-dimensional image can be immediately re-aligned with the original three-dimensional image.

[0054] Therefore, whether the C-arm is moved due to adjusting the shooting angle or the patient's slight displacement, the system can automatically compensate for these positional changes, ensuring that the instrument position reconstructed or projected from the two-dimensional image remains registered in three-dimensional space without the need for a rigid registration process again.

[0055] S330, based on the spatial transformation matrix, the reconstructed three-dimensional model of the target instrument is projected onto the three-dimensional image.

[0056] Based on the spatial transformation matrix obtained from registration in step S320, the reconstructed 3D instrument model is projected onto the registered 3D preoperative image using visual fusion. On the navigation interface, this reconstructed instrument model can then be rendered along with the patient's bones, blood vessels, lesions, and other 3D anatomical structures with correct depth, occlusion, and perspective relationships. This method results in higher image quality and reduced intraoperative radiation exposure, providing a more comprehensive and realistic real-time 3D scene perception for complex interventional surgeries.

[0057] Based on the above embodiments, this application discloses another embodiment of an image-guided positioning method, wherein the target instrument is equipped with a marker. Surgical operations are performed using a tool with a built-in marker.

[0058] Specifically, markers are typically small spheres, coils, or specific patterns made of platinum, gold, or stainless steel, rigidly attached to the handle or a specific section of the target instrument. They act as beacons for the instrument in the imaging space. In X-ray projection, these markers appear as clear, bright dots or characteristic patterns. Computer vision algorithms can detect and locate these bright spots with extremely reliable and sub-pixel precision, bypassing the difficulties of segmentation and identification directly from blurry instrument images. This is especially true for instruments that are not easily imaged clearly by X-rays. Many surgical instruments are made of non-metallic or low atomic number materials, such as some plastics, carbon fibers, ceramics, or certain alloys. These instruments have extremely low contrast with the surrounding soft tissue in X-ray images, almost transparent, making them indistinguishable from complex anatomical background noise by both surgeons and computer algorithms. The core function of markers is to actively and explicitly define the position and orientation of the instrument in space by artificially attaching a physical feature with extremely high and stable contrast under X-rays and a known geometric shape and arrangement.

[0059] Based on this, step S300 in this embodiment specifically includes the following sub-steps: S310, feature segmentation is performed on the markers on the target device in the two-dimensional projection image. Based on the fixed positions of the markers on the target device, the pixel positions of the entire target device in the two-dimensional projection image are calculated.

[0060] S320, Reconstruct the three-dimensional model of the target instrument.

[0061] The specific technical details of the implementation are the same as those in the above embodiments, and will not be repeated in this embodiment.

[0062] This application provides another embodiment of an image real-time guided positioning method. Based on any of the above embodiments, step S400 specifically includes the following sub-steps: S410, calculate in real time the deviation parameters between the pose of the target instrument and the surgical planning path, the deviation parameters including position deviation, angle deviation and depth deviation.

[0063] S420, based on the deviation parameters, provides a visual correction guidance scheme.

[0064] Specifically, in this embodiment, deviation parameters are calculated to visually guide the operator on how to correct the deviation. These deviation parameters include positional deviation, angular deviation, and depth deviation.

[0065] Positional deviation is the vertical distance between the instrument tip and the planned path line, i.e., the shortest vertical distance, used to quantify whether the instrument deviates from the flight path in space. Angular deviation is the angle between the instrument's current actual pointing vector and the ideal direction vector of the planned path, used to reflect whether the instrument's attitude is consistent with the predetermined direction. Depth deviation is the remaining straight-line distance from the instrument tip to the preset target point.

[0066] In some optional implementations, these deviation values ​​are displayed in real-time and visually on the navigation interface, providing the operator with intuitive feedback. Based on this real-time deviation data, decision support and action guidance are provided through an intelligent human-computer interaction interface to correct the current deviation and achieve dynamic optimization of the plan. Specifically, the navigation page not only displays the 3D fused image but also generates a virtual "guided view." For example, when there is an angular deviation, the system instructs the operator in which direction to rotate the instrument so that the marker representing the instrument's axis coincides with the marker representing the planned path. When there is a positional deviation, arrows or color changes are used to prompt the operator to adjust the entry point to the side, etc.

[0067] In some alternative implementations, the insertion direction is adjusted using a surgical staple universal visualization device.

[0068] Surgical staple omnidirectional visualization devices are a type of device that, within a near-field electromagnetic positioning or mixed reality framework, acquires the three-dimensional pose of instruments in real time and integrates it into the patient's anatomical model. Through a head-mounted optical fluoroscopic display or a fixed screen, virtual staple holes, virtual axes, and planned trajectories are projected from any angle and in any rotation mode. This allows doctors to obtain multi-degree-of-freedom, three-dimensional guidance information while directly viewing the operating area during surgery, without having to repeatedly adjust the image acquisition equipment or look down at the monitor.

[0069] In other alternative implementations, the visual correction guidance scheme also includes predictive guidance and collision avoidance warnings. By calculating the current trajectory and speed of the instrument, the system can predict its path within the next few seconds and determine in advance whether it will collide with critical sensitive structures outside the planned path, thereby issuing a warning to reduce surgical risks and further improve safety.

[0070] Based on the same concept, this application also discloses a real-time image-guided positioning system. The system is used to implement the steps described in any of the above method embodiments. Specifically, one embodiment of the real-time image-guided positioning system of this application includes: The first image acquisition module is used to acquire a set of three-dimensional images of the target area before or during surgery, so as to guide surgical planning based on the three-dimensional images. Insertion points are marked using contrast-enhancing tape.

[0071] The second image acquisition module is used to acquire at least two two-dimensional projection images at a limited angle. The two-dimensional projection images include first projection data of the anatomical structure within the target area and second projection data of the target instrument.

[0072] An image registration module is used to register the two-dimensional projection image with the three-dimensional image, projecting the target instrument in the two-dimensional projection image to the same position in the three-dimensional image.

[0073] The image-guided planning module is used to measure the deviation between the target instrument and the surgical planning path, and to optimize the surgical guidance scheme.

[0074] Based on the same concept, this application also discloses a real-time image guidance and positioning device, which includes a processor, a memory, and a display.

[0075] The memory stores computer instructions, which are loaded and executed by the processor to implement the steps of the real-time image guidance and positioning method described in any of the above embodiments.

[0076] Based on the same concept, this application also discloses a readable storage medium storing computer instructions that, when executed by a processor, implement the steps of the real-time image guidance and positioning method described in any of the above embodiments.

[0077] The image real-time guided positioning method, system, device and storage medium of this application have the same technical concept, and the technical details of the embodiments of the four are applicable to each other. In order to reduce repetition, they will not be described again here.

[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of program modules is merely an example. In practical applications, the above functions can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program units or modules to complete all or part of the functions described above. The program modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software program unit. Furthermore, the specific names of the program modules are only for easy differentiation and are not intended to limit the scope of protection of this application.

[0079] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A real-time image-guided positioning method, characterized in that, Includes the following steps: A set of three-dimensional images of the target area are acquired before or during the operation, and surgical guidance planning is performed based on the three-dimensional images; the needle insertion point is marked using contrast-enhancing tape; Acquire at least two two-dimensional projection images at a limited angle, wherein the two-dimensional projection images include first projection data of the anatomical structure within the target area and second projection data of the target instrument; Register the two-dimensional projection image with the three-dimensional image, and project the target instrument in the two-dimensional projection image to the same position in the three-dimensional image; The deviation between the target instrument and the surgical planning path is measured to optimize the surgical guidance scheme.

2. The image real-time guided positioning method as described in claim 1, characterized in that, The registration of the two-dimensional projection image and the three-dimensional image, projecting the target instrument in the two-dimensional projection image to the same position in the three-dimensional image, specifically includes the following sub-steps: Features of the target instrument are extracted from the two-dimensional projection image, and the target instrument is reconstructed by coronal and sagittal axis segmentation. Bone feature points are extracted, and the two-dimensional projection image and the three-dimensional image are matched using a rigid registration method to obtain a spatial transformation matrix; Based on the spatial transformation matrix, the reconstructed three-dimensional model of the target instrument is projected onto the three-dimensional image.

3. The image real-time guided positioning method as described in claim 2, characterized in that... The step of extracting features of the target instrument from the two-dimensional projection image and performing coronal and sagittal axis segmentation and reconstruction on the target instrument specifically includes the following sub-steps: The target instrument in the two-dimensional projection image is segmented using a threshold segmentation method; the three-dimensional model of the target instrument is reconstructed from the coronal, sagittal and axial planes using a coronal-sagittal-axial segmentation and reconstruction algorithm.

4. The image real-time guided positioning method as described in claim 2, characterized in that, During image acquisition, the two-dimensional projected image and the three-dimensional image follow the same spatial geometric acquisition trajectory.

5. The image real-time guided positioning method as described in claim 4, characterized in that, The extraction of bony feature points involves using a rigid registration method to match the two-dimensional projection image with the three-dimensional image to obtain a spatial transformation matrix. Specifically, it includes the following sub-steps: The skeletal region is segmented from the three-dimensional image to extract the skeletal model; simultaneously, the skeletal region is segmented from the two-dimensional projection image to extract bony feature points. The bone model is simulated and a projection of bony features is generated using digital ray casting. The pose parameters of the skeletal model in three-dimensional space are adjusted by an iterative algorithm so that the projection of the bony features and the bony feature points are optimally aligned, thereby obtaining the spatial transformation matrix. The spatial transformation matrix is ​​used to describe the rigid transformation relationship between the three-dimensional image coordinate system and the two-dimensional projected image coordinate system.

6. The image real-time guided positioning method as described in claim 5, characterized in that, During the procedure, the position of the image acquisition device relative to the target area changes; Obtain the motion trajectory parameters of the image acquisition device; update the spatial transformation matrix based on the motion trajectory parameters; Based on the updated spatial transformation matrix, the newly acquired two-dimensional projection image is registered with the three-dimensional image.

7. The image real-time guided positioning method as described in claim 1, characterized in that, The process of measuring the deviation between the target instrument and the surgical planning path to optimize the surgical guidance plan includes the following sub-steps: The deviation parameters between the pose of the target instrument and the surgical planning path are calculated in real time. The deviation parameters include position deviation, angle deviation, and depth deviation. A visual correction guidance scheme is provided based on the aforementioned deviation parameters.

8. A real-time image-guided positioning system, characterized in that, The real-time image-guided positioning system includes: The first image acquisition module is used to acquire a set of three-dimensional images of the target area before or during the operation, so as to perform surgical guidance planning based on the three-dimensional images; and to mark the needle insertion point using contrast tape. The second image acquisition module is used to acquire at least two two-dimensional projection images with a limited angle. The two-dimensional projection images include first projection data of the anatomical structure in the target area and second projection data of the target instrument. An image registration module is used to register the two-dimensional projection image and the three-dimensional image, projecting the target instrument in the two-dimensional projection image to the same position in the three-dimensional image; The image-guided planning module is used to measure the deviation between the target instrument and the surgical planning path, and to optimize the surgical guidance scheme.

9. A real-time image-guided positioning device, characterized in that, The real-time image guidance and positioning device includes a processor, a memory, and a display; The memory stores computer instructions, which are loaded and executed by the processor to implement the steps of the real-time image guidance and positioning method according to any one of claims 1-7.

10. A readable storage medium having computer instructions stored thereon, characterized in that, When executed by a processor, the computer instructions implement the steps of the method according to any one of claims 1-7.

Images