Positioning Method, System and Computer Device for Pelvic Fixation Puncture

Abstract

The present application relates to a positioning method, system and computer device for pelvic fixation puncture. The positioning method includes: obtaining CT image data of the pelvic region of a target object; obtaining bone parameters based on the CT image data and establishing a three-dimensional bone model based on the bone parameters; determining the puncture point position on the bone based on the three-dimensional bone model; obtaining the outer contour image data of the pelvic region; establishing a three-dimensional outer contour model based on the outer contour image data; selecting a reference point, and matching and splicing the three-dimensional outer contour model and the three-dimensional bone model based on the reference point to form a three-dimensional pelvic model; calculating the fixed position of the outer contour of the target object according to the three-dimensional pelvic model and the puncture point position. The present application can obtain accurate puncture points and fixation points, form an overall navigation system, improve the accuracy and safety of surgery, and adapt to the specific anatomical needs of different patients.

Description

Technical Field

[0001] This application relates to the field of positioning technology, and particularly to a positioning method, system, and computer device for pelvic fixation puncture. Background Art

[0002] The anatomical relationship of the pelvis is very complex, with many muscle tissues attached around it, protecting the internal organs in the pelvic cavity. If the pelvis is fractured, it is easy to cause pelvic organ injury and bleeding. Whether timely and correct diagnosis and treatment can be carried out is the key to affecting the prognosis and quality of life of patients. In pelvic positioning puncture treatment, the application of image recognition technology is crucial for improving the accuracy and safety of surgery. Since the birth of CT, it has developed from single-layer CT to multi-layer CT, and now to the birth of high-tech products such as dual-source spiral CT, and the spatial resolution and temporal resolution have been greatly improved.

[0003] However, in the relevant actual application process, there are some challenges and problems, mainly including: (1) Variability of image quality: Due to differences in the patient's body shape, tissue density, and the parameter settings of the imaging device, the acquired image quality may vary, which will affect the accuracy of image recognition; (2) Difficulty in recognizing complex pelvic structures: The human pelvic structure is complex and highly variable, which poses challenges to image recognition. Especially for soft tissues such as the uterus, the densities are similar on the image and it is difficult to clearly distinguish; (3) Precision problem of image segmentation: When performing image segmentation, especially when dealing with pelvic soft tissue structures, the automatic segmentation algorithm may not be able to achieve the same precision as manual segmentation, and the algorithm needs to be further optimized to improve the recognition accuracy; (4) Requirement for multi-modal image fusion: In some cases, the image information of a single modality may not be sufficient to provide comprehensive diagnostic information, and different modalities of images such as CT and MRI need to be fused to obtain more accurate diagnostic information, but this process poses challenges in technology; (5) Synchronization problem of real-time navigation and image matching: During the operation, it is necessary to update the patient's position and pose information in real time and match it with the pre-acquired image to achieve precise navigation, but this process may be affected by factors such as patient movement. Summary of the Invention

[0004] Based on this, it is necessary to provide a positioning method, system, and computer device for pelvic fixation puncture based on image recognition with high positioning accuracy and strong practicability for the above technical problems.

[0005] On the one hand, a positioning method for pelvic fixation puncture is provided, and the positioning method includes:

[0006] Obtain CT image data of the pelvic region of the target object;

[0007] Obtain bone parameters based on the CT image data, and establish a three-dimensional bone model based on the bone parameters;

[0008] Determine the puncture point position on the bone based on the three-dimensional bone model;

[0009] Obtain the outer contour image data of the pelvic region;

[0010] Establish an outer contour three-dimensional model based on the outer contour image data;

[0011] Select a reference point, and match and splice the outer contour three-dimensional model and the three-dimensional bone model based on the reference point to form a three-dimensional pelvic model;

[0012] Calculate the fixed position of the outer contour of the target object according to the three-dimensional pelvic model and the puncture point position.

[0013] In one embodiment, the step of obtaining the CT image data of the pelvic region of the target object includes: scanning the pelvic region with a q-slice spiral CT, with a scan slice thickness less than 1 mm, to obtain CT image data in Dicom format with a number of slices greater than or equal to 200.

[0014] In one embodiment, the step of obtaining bone parameters based on the CT image data and establishing a three-dimensional bone model based on the bone parameters includes:

[0015] Input the CT image data into MIMICS software or 3DSlicer;

[0016] Binarize the CT image data with a preset threshold gray value and remove redundant pixels to obtain the bone parameters;

[0017] Perform three-dimensional modeling with the bone parameters to obtain a three-dimensional bone model.

[0018] In one embodiment, the step of determining the puncture point position on the bone based on the three-dimensional bone model includes: measuring and calculating pelvic parameters based on the three-dimensional bone model, combining with a clinical database, calculating the puncture points required for the bone, and marking them in the three-dimensional bone model.

[0019] In one embodiment, the step of obtaining the outer contour image data of the pelvic region includes: extracting the outer contour image data from the CT image data, or scanning the outer contour of the target object with a camera.

[0020] In one embodiment, the step of selecting a reference point, matching and splicing the outer contour three-dimensional model and the three-dimensional bone model based on the reference point to form a three-dimensional pelvic model includes:

[0021] Select a marker as a reference point, where the marker is the same object located within both the three-dimensional outer contour model and the three-dimensional bone model;

[0022] Obtain a first point cloud of the marker in the three-dimensional outer contour model and obtain a second point cloud of the marker in the three-dimensional bone model;

[0023] Calculate the distance relationship between the first point cloud in the three-dimensional bone model and the second point cloud to obtain a matching matrix of the first point cloud and the second point cloud;

[0024] Stitch together the three-dimensional outer contour model and the three-dimensional bone model according to the matching matrix to form a three-dimensional pelvis model.

[0025] In one embodiment, the step of calculating the fixed position of the outer contour of the target object based on the three-dimensional pelvis model and the puncture point position includes:

[0026] Based on the three-dimensional pelvis model, starting from the puncture point, calculate the coordinate information of the puncture path;

[0027] Calculate the puncture point on the outer contour of the target object according to the coordinate information of the puncture path;

[0028] Simulate the fixed position of the fixture in the three-dimensional pelvis model according to the puncture point.

[0029] In one embodiment, the positioning method further includes:

[0030] Record the process data of the three-dimensional outer contour model and the three-dimensional bone model that have been successfully matched and stitched;

[0031] Perform machine learning by combining the process data and the CT image data to obtain a network model for matching three-dimensional models;

[0032] Based on the network model, guide the next matching and stitching of the three-dimensional outer contour model and the three-dimensional bone model.

[0033] On the one hand, provide a positioning system for pelvic fixation puncture, the positioning system includes:

[0034] An image acquisition module, configured to acquire CT image data of the pelvic region of the target object and configured to acquire outer contour image data of the pelvic region;

[0035] A modeling module, connected to the image acquisition module, configured to obtain bone parameters according to the CT image data and establish a three-dimensional bone model based on the bone parameters, and the modeling module is configured to establish a three-dimensional outer contour model according to the outer contour image data;

[0036] A model processing module, connected to the modeling module, capable of selecting a reference point and matching and splicing the three-dimensional outer contour model and the three-dimensional bone model based on the reference point to form a three-dimensional pelvis model;

[0037] A calculation module, connected to the model processing module, for determining the position of the puncture point on the bone based on the three-dimensional bone model, and for calculating the fixed position of the outer contour of the target object according to the three-dimensional pelvis model and the puncture point position.

[0038] On the one hand, a computer device is provided, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned positioning method for pelvic fixation puncture are realized.

[0039] CT image recognition can generate a detailed three-dimensional pelvis model, enabling doctors to observe the detailed structure of the patient's pelvis from different angles and levels in a virtual environment, including bone quality, joints, and surrounding soft tissues, facilitating simulated surgery, risk assessment, optimization of the surgical plan, etc., including determining the best puncture path, depth, and angle, as well as predicting possible anatomical variations and potential risks; registering the three-dimensional model of the outer contour with the three-dimensional bone model, mapping the internal path of the human body to the body surface, obtaining accurate puncture points and fixed points, forming an overall navigation system, improving the accuracy and safety of the surgery, adapting to the specific anatomical needs of different patients, through precise preoperative planning and automated tools, the surgery time can be reduced, the burden on patients and medical staff can be reduced, helping doctors make quick decisions based on the three-dimensional model, coping with unexpected situations that may occur during the surgery, and reducing the time for intraoperative decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic flow chart of the positioning method in an embodiment of the present application.

[0041] Figure 2 It is a schematic diagram of the positioning system in an embodiment of the present application.

[0042] Figure 3 It is a schematic diagram of the clamping device in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] To make the above objects, features, and advantages of the present application more obvious and understandable, the following detailed description of the specific embodiments of the present application is made with reference to the accompanying drawings. Many specific details are set forth in the following description to fully understand the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present application. Therefore, the present application is not limited by the specific embodiments disclosed below.

[0044] In the description of the present application, it should be understood that if there are terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., the orientation or positional relationship indicated by these terms is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application 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 to the present application.

[0045] In addition, if there are terms such as "first" and "second", these terms are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present application, if there is a term "plurality", the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0046] In the present application, unless otherwise clearly defined and limited, if there are terms such as "installation", "connection", "connection", "fixation", etc., these terms should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; 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 be the communication inside two elements or the interaction relationship between two elements, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0047] In the present application, unless otherwise clearly defined and limited, if there is a description such as a first feature being "on" or "under" a second feature, the meaning can be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature being "above", "over" and "on top of" the second feature can be that the first feature is directly above or obliquely above the second feature, or merely indicates that the first feature has a higher horizontal height than the second feature. The first feature being "under", "beneath" and "underneath" the second feature can be that the first feature is directly below or obliquely below the second feature, or merely indicates that the first feature has a lower horizontal height than the second feature.

[0048] It should be noted that if an element is referred to as "fixed to" or "disposed on" another element, it can be directly on the other element or there may also be an intermediate element. If an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. If any, the terms "vertical", "horizontal", "upper", "lower", "left", "right" and similar expressions used in this application are only for the purpose of illustration and do not represent the only implementation.

[0049] Referring to Figure 1 , Figure 1 FIG. shows a schematic flow chart of a positioning method in an embodiment of the present application. The pelvic fixation puncture positioning method provided by an embodiment of the present application includes the steps:

[0050] S100. Obtain CT image data of the pelvic region of the target object;

[0051] S200. Obtain bone parameters according to the CT image data, and establish a three-dimensional bone model based on the bone parameters;

[0052] S300. Determine the puncture point position on the bone based on the three-dimensional bone model;

[0053] S400. Obtain the outer contour image data of the pelvic region;

[0054] S500. Establish an outer contour three-dimensional model according to the outer contour image data;

[0055] S600. Select a reference point, and match and splice the outer contour three-dimensional model and the three-dimensional bone model based on the reference point to form a three-dimensional pelvic model;

[0056] S700. Calculate the fixed position of the outer contour of the target object according to the three-dimensional pelvic model and the puncture point position.

[0057] CT image recognition can generate a detailed three-dimensional pelvic model, enabling doctors to observe the detailed structure of the patient's pelvis, including bone quality, joints and surrounding soft tissues, from different angles and levels in a virtual environment, facilitating simulated surgery, risk assessment, optimization of surgical plans, etc., including determining the best puncture path, depth and angle, and predicting possible anatomical variations and potential risks; by registering the three-dimensional model of the outer contour with the three-dimensional bone model, the internal path of the human body is mapped to the body surface, accurate puncture points and fixation points are obtained, forming an overall navigation system, improving the accuracy and safety of the surgery, adapting to the specific anatomical needs of different patients. Through precise preoperative planning and automated tools, the surgery time can be reduced, the burden on patients and medical staff can be reduced, helping doctors make quick decisions based on the three-dimensional model, coping with unexpected situations that may occur during the surgery, and reducing the decision-making time during the surgery.

[0058] In one embodiment, the step of S100, obtaining CT image data of the pelvic region of the target object, includes: scanning the pelvic region using q-row spiral CT with a scanning layer spacing of less than 1 mm, and obtaining greater than or equal to 200 layers of CT image data in Dicom format.

[0059] DICOM images can clearly and completely display the pelvic structure, and the radiation dose received by the patient is also decreasing. The powerful post-processing workstation provides reliable imaging basis for clinical practice. The specific area of interest and volume rendering (VR) are similar to the gross specimen and can be rotated at any angle to select the best viewing angle for fracture observation. VR can also be rotated at any angle to fully display the anatomical relationship between the lesion and the surrounding tissues, such as changes in the fracture position, dislocation, and the number of bone fragments. Spiral CT can observe whether there is damage to the pelvic viscera, and can compare the continuity and integrity of the pelvic ring before and after surgery, providing orthopedic surgeons with the three-dimensional structure and spatial relationship of the pelvis.

[0060] For example, the patient takes a normal supine position for a 256-row spiral CT scan, with the scanning range from the lower edge of the third lumbar vertebra to the ankle joint, the tube voltage of the scan is 120 kV, the tube current is 300 mA, the layer thickness is 0.9 mm, the layer spacing is 1 mm, the pixel is 0.65~0.75 mm, and the matrix is 512×512. The patient lies flat on the center of the bed, holds his head with both hands, and stretches his lower limbs together. The pelvic plain scan is first performed, and then the contrast agent is injected through the median cubital vein with a double-cylinder high-pressure injector at a flow rate of 4.0 m / s. Then, the other syringe injects normal saline for 2 m, and the region of interest (ROI) 2 cm above the bifurcation of the abdominal aorta is used. The contrast agent tracing method is used for CT dynamic monitoring. It is considered that the scan is automatically triggered when the CT value of the ROI reaches 100 Hu. In this way, the original CT scan data of the complete pelvis is obtained, including 400 layers of Dicom format data, which are recorded as CT image data.

[0061] For the original CT scan data, the reconstruction process can be included: the data of the spiral CT scan is transmitted to the GE (Vitea4.2) post-processing workstation, and the three-dimensional VR software and the two-dimensional multi-planar reconstruction (MPR) software are used for imaging, and the six standard positions of front, back, left, right, head and foot are observed to observe the spatial relationship between the fracture and the surrounding structures. The direction of the fracture line, the degree of bone fragmentation and the free position are displayed. At the same time, the observation can be rotated at any angle as needed to generate multi-planar reconstruction images at different angles, and curved surface reconstruction (CPR) can be performed for bone trauma.

[0062] In one embodiment, the step of obtaining bone parameters according to the CT image data and establishing a three-dimensional bone model based on the bone parameters in S200 includes:

[0063] S210. Input the CT image data into MIMICS software or 3DSlicer;

[0064] S220. Binarize the CT image data with the gray value of a preset threshold, and remove redundant pixels to obtain the bone parameters;

[0065] S230. Perform three-dimensional modeling with the bone parameters to obtain a three-dimensional bone model.

[0066] For example, import the above 400-layer Dicom format data into the software in the way of "lossless compression" for automatic image positioning, tissue imaging, and interpolation processing. Set the bone tissue reconstruction threshold to 168 - 1539 Hu; after the MIMICS software automatically generates the surface contour lines of bone tissue on each layer, edit the image to remove irrelevant edge noise and redundant data, and finally reconstruct a three-dimensional pelvic model including part of the lumbar vertebrae and femur through region growing and 3D calculation. Based on the reconstructed complete three-dimensional pelvic model, further use the EditMaski3D function to select a region from the midsagittal plane of the pelvis and reconstruct a three-dimensional model of the left half of the pelvis.

[0067] In one embodiment, the step of determining the puncture point position on the bone based on the three-dimensional bone model includes: measuring and calculating pelvic parameters based on the three-dimensional bone model, combining with a clinical database, calculating the puncture points required for the bone, and marking them in the three-dimensional bone model.

[0068] Specifically, for example, based on the three-dimensional bone model, the anteversion angle, valgus angle, neck-shaft angle, femoral head diameter of the hip prosthesis can be measured, and the relationship between the center of femoral head rotation and the apex of the greater trochanter can be measured; the position of sacral screw insertion, the anteroposterior diameter and transverse diameter of the sacrum can be measured. Combining with medical clinical data, the spatial coordinates of the puncture points can be calculated.

[0069] In one embodiment, the step S400 of obtaining the outer contour image data of the pelvic region includes: extracting the outer contour image data from the CT image data, or scanning the outer contour of the target object with a camera.

[0070] If in step S400 the outer contour image data is extracted from the CT image data, then step S500 includes: Extracting the outer contour image data from the CT image data. The image data of each layer can depict the outer contour of the object in the xy plane. The CT image data of N layers constitutes the coordinate values of the object in the z-axis direction. By superimposing the contour data in multiple xy planes and combining with the Hu threshold selection, in MIMICS software or 3DSlicer software, a three-dimensional model of the outer contour can be established. If the three-dimensional model of the bone and the three-dimensional model of the outer contour are established based on the same CT image data, the registration process in step S600 can be omitted.

[0071] If in step S400 a camera is used to scan the outer contour of the object, the camera can be optical, especially a laser camera, or acoustic, especially an ultrasonic camera, then step S500 includes: Generating a scanning matrix according to the scanning method and scanning trajectory, controlling the camera to move horizontally parallel to the object in a rotational scanning, linear scanning or fan-shaped scanning manner, move up and down vertically perpendicular to the object to be scanned, or rotate by a preset angle around the central axis perpendicular to the object to be scanned for scanning, obtaining image data, and establishing a three-dimensional model of the outer contour according to the image data and the scanning matrix.

[0072] Furthermore, for example, when the camera is an RGB-D camera, step S500 further includes:

[0073] Calibrating the movement trajectory of the camera. Through this step, a parameter matrix (such as focal length, principal point, skew and distortion) is obtained. After all the movement trajectories of the camera are calibrated, the pose information of the camera shooting pose in the world coordinate system is obtained; constructing a first relationship between the coordinates in the RGB-D camera coordinate system and the coordinates in the world coordinate system, and based on the internal parameter matrix of the RGB-D camera, constructing a second relationship between the image pixel coordinates and the coordinates in the camera coordinate system; combining the first relationship and the second relationship to determine the spatial transformation matrix corresponding to the RGB-D camera in the current shooting pose, and taking it as the pose information of the current shooting pose of the RGB-D camera in the world coordinate system;

[0074] The outer contour image data obtained in S400 can be two-dimensional RGB image data and depth information. In S500, each pixel coordinate (u, v, Z C ) with depth in the object image captured by the RGB-D camera in the current shooting pose is converted into the corresponding camera coordinates (X C , Y C , Z C ), and then according to the first relationship and the pose information of the current shooting pose of the RGB-D camera in the world coordinate system, (X C , YC , Z C ) is converted to (X W , Y W , Z W ) in the world coordinate system, so as to obtain the coordinates of each pixel in the world coordinate system; finally, according to the coordinates of each pixel in the world coordinate system, the pixels at different positions are stitched together, and the three-dimensional surface can be reconstructed. In addition, the pixel features at the same position in different images can be fused. For example, the pixel features are weighted and averaged, and the fused feature value is used as the feature value of the pixel at this position after reconstruction.

[0075] It can be understood that step S400 and step S100 can be executed simultaneously or separately, without a sequential limit.

[0076] In one embodiment, the step S600 of selecting a reference point and matching and splicing the outer contour three-dimensional model and the bone three-dimensional model based on the reference point to form a pelvic three-dimensional model includes:

[0077] S610. Select a marker as the reference point, and the marker is the same object located within both the outer contour three-dimensional model and the bone three-dimensional model;

[0078] S620. Obtain the first point cloud set of the marker in the outer contour three-dimensional model, and obtain the second point cloud set of the marker in the bone three-dimensional model;

[0079] S630. Calculate the distance relationship between the first point cloud set in the bone three-dimensional model and the second point cloud set, and obtain the matching matrix of the first point cloud set and the second point cloud set;

[0080] S640. Splice the outer contour three-dimensional model and the bone three-dimensional model according to the matching matrix to form a pelvic three-dimensional model.

[0081] In S610, the marker can be selected as a unique physiological structure inside or outside the target object's body as the marker. Steps S620 - S640 further include: respectively calculating the centroids of the outer contour three-dimensional model and the bone three-dimensional model; respectively translating the centroids of the two models to coincide with the origin to obtain a new reference modality and a floating modality; respectively calculating the first eigenaxis vector and the second eigenaxis vector of the reference modality and the floating modality; constructing a rotation operator according to the obtained eigenaxis vectors, and completing the rotation of the floating image; completing registration after translation and rotation.

[0082] In one embodiment, the step S700 of calculating the fixed position of the outer contour of the target object according to the pelvic three-dimensional model and the puncture point position includes:

[0083] S710. Based on the three-dimensional pelvic model, starting from the puncture point, calculate the coordinate information of the puncture path;

[0084] S720. Calculate the puncture point on the outer contour of the target object according to the coordinate information of the puncture path;

[0085] S730. Simulate the fixed position of the fixture in the three-dimensional pelvic model according to the puncture point.

[0086] In one embodiment, the positioning method further includes step S800 of machine learning optimization:

[0087] S810. Record the process data of the outer contour three-dimensional model and the bone three-dimensional model that have completed matching and splicing;

[0088] S820. Perform machine learning by combining the process data and the CT image data to obtain a network model for matching the three-dimensional models;

[0089] S830. Guide the next matching and splicing of the outer contour three-dimensional model and the bone three-dimensional model based on the network model.

[0090] Specifically, step S820 further includes:

[0091] Perform local region optimization and segmentation on the bone three-dimensional model and the outer contour three-dimensional model to extract local features; use a siamese network to extract the global features of the three-dimensional pelvic model and make full use of the label information; fuse the local features and the global features, establish a neural network model after fusion, and use this to optimize the next matching and splicing of the outer contour three-dimensional model and the bone three-dimensional model, the calculation of the fixed position, etc.

[0092] Refer to Figure 2 、 3 , Figure 2 、 3 shows a schematic diagram of the positioning system in an embodiment of the present application. The positioning system for pelvic fixation and puncture provided in an embodiment of the present application includes:

[0093] An image acquisition module 10, configured to acquire CT image data of the pelvic region of the target object and configured to acquire outer contour image data of the pelvic region;

[0094] A modeling module 20, connected to the image acquisition module 10, configured to obtain bone parameters according to the CT image data and establish a bone three-dimensional model based on the bone parameters, and the modeling module 20 is configured to establish an outer contour three-dimensional model according to the outer contour image data;

[0095] The model processing module 30, connected to the modeling module 20, is capable of selecting a reference point and matching and splicing the three-dimensional outer contour model and the three-dimensional bone model based on the reference point to form a three-dimensional pelvic model;

[0096] The calculation module 40, connected to the model processing module 30, is used to determine the puncture point positions on the bone based on the three-dimensional bone model, and is used to calculate the fixed positions of the outer contour of the target object according to the three-dimensional pelvic model and the puncture point positions.

[0097] As Figure 3 shown, the positioning system further includes a clamping device 50. The clamping device 50 includes a positioning arm 51 and an adjustment module 52. There are two positioning arms 51. The two positioning arms 51 are arranged at intervals from each other. Each positioning arm 51 corresponds to a fixed position on one side of the target object. The two positioning arms 51 are arranged at the fixed positions on both sides of the target object to complete the clamping. The adjustment module 52 is used to adjust the distance between the positioning arms.

[0098] The calculation module 40 calculates the fixed positions, and further calculates the distance between the two positioning arms 51. After the clamping device 50 is pre-positioned, the adjustment module 52 is controlled to adjust the positioning arms 51 to the corresponding distance.

[0099] Further, a camera and an indicator are provided on the positioning arm. The camera and the indicator are electrically connected to the calculation module 40. The image acquisition module 10 includes the camera and can be used to scan the outer contour of the target object to obtain the outer contour image data in real time. The calculation module 40 emits a signal to the indicator according to the fixed position information in combination with the three-dimensional pelvic model. The indicator projects the fixed position area that needs to be fixed at the corresponding position on the body surface of the target object, and can also project the puncture points.

[0100] In one embodiment, the positioning system further includes a machine learning module, connected to the calculation module 40 and the model processing module 30, for implementing the above step S800.

[0101] On the one hand, a computer device is provided, including a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of the above positioning method for pelvic fixation and puncture are implemented.

[0102] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a positioning method for pelvic fixation puncture. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or may be a button, a trackball, or a touchpad provided on the housing of the computer device, or may also be an external keyboard, a touchpad, or a mouse, etc.

[0103] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0104] The above-described embodiments only represent several implementation manners of the present application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A positioning system for pelvic fixation puncture, characterized in that, The positioning system includes: An image acquisition module, configured to acquire CT image data of the pelvic region of the target object and to acquire outer contour image data of the pelvic region; the image acquisition module scans the pelvic region using a q-slice spiral CT with a slice thickness less than 1 mm to obtain at least 200 layers of Dicom format CT image data, with the scanning range from the lower edge of the third lumbar vertebra to the ankle joint, taking the area 2 cm above the bifurcation of the abdominal aorta as the region of interest, and performing CT dynamic monitoring using the contrast agent tracking method, and setting to automatically trigger the scan when the CT value of the region of interest reaches 100 Hu; A modeling module, connected to the image acquisition module, configured to obtain bone parameters based on the CT image data and to establish a three-dimensional bone model based on the bone parameters, and the modeling module is configured to establish an outer contour three-dimensional model based on the outer contour image data; A model processing module, connected to the modeling module, capable of selecting a reference point and matching and splicing the outer contour three-dimensional model and the bone three-dimensional model based on the reference point to form a pelvic three-dimensional model; the model processing module selects a marker as the reference point, and the marker is the same object located within both the outer contour three-dimensional model and the bone three-dimensional model; obtaining a first point cloud set of the marker in the outer contour three-dimensional model and obtaining a second point cloud set of the marker in the bone three-dimensional model; calculating the distance relationship between the first point cloud set and the second point cloud set in the bone three-dimensional model to obtain a matching matrix of the first point cloud set and the second point cloud set; A calculation module, connected to the model processing module, configured to determine the puncture point position on the bone based on the three-dimensional bone model and to calculate the fixed position of the outer contour of the target object according to the pelvic three-dimensional model and the puncture point position.

2. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of a positioning method for pelvic fixation puncture, and the positioning method includes: Acquiring CT image data of the pelvic region of the target object; Obtaining bone parameters based on the CT image data and establishing a three-dimensional bone model based on the bone parameters; Determining the puncture point position on the bone based on the three-dimensional bone model; Acquiring outer contour image data of the pelvic region; Establishing an outer contour three-dimensional model based on the outer contour image data; Selecting a reference point and matching and splicing the outer contour three-dimensional model and the bone three-dimensional model based on the reference point to form a pelvic three-dimensional model, including: selecting a marker as the reference point, and the marker is the same object located within both the outer contour three-dimensional model and the bone three-dimensional model; obtaining a first point cloud set of the marker in the outer contour three-dimensional model and obtaining a second point cloud set of the marker in the bone three-dimensional model; calculating the distance relationship between the first point cloud set and the second point cloud set in the bone three-dimensional model to obtain a matching matrix of the first point cloud set and the second point cloud set; Splicing the outer contour three-dimensional model and the bone three-dimensional model according to the matching matrix to form a pelvic three-dimensional model; Calculating the fixed position of the outer contour of the target object according to the pelvic three-dimensional model and the puncture point position; The steps of obtaining CT image data of the pelvic region of the target object include: scanning the pelvic region with a q-slice spiral CT, with a slice thickness of less than 1 mm, to obtain CT image data in DICOM format with 200 or more slices. The scanning range is from the lower edge of the third lumbar vertebra to the ankle joint. Taking 2 cm above the bifurcation of the abdominal aorta as the region of interest, the contrast agent tracking method is adopted for CT dynamic monitoring, and it is set that when the CT value of the region of interest reaches 100 Hu, the scan is automatically triggered.

3. The computer device according to claim 2, characterized in that, The steps of the computer device obtaining bone parameters according to the CT image data and establishing a three-dimensional bone model based on the bone parameters include: Inputting the CT image data into MIMICS software or 3D Slicer; Binarizing the CT image data with a preset threshold gray value and removing redundant pixels to obtain the bone parameters; Performing three-dimensional modeling with the bone parameters to obtain a three-dimensional bone model.

4. The computer device according to claim 2, characterized in that, The steps of the computer device determining the puncture point position on the bone based on the three-dimensional bone model include: measuring and calculating pelvic parameters based on the three-dimensional bone model, combining with a clinical database, calculating the puncture points required for the bone, and marking them in the three-dimensional bone model.

5. The computer device according to claim 2, characterized in that, The steps of the computer device obtaining the outer contour image data of the pelvic region include: extracting the outer contour image data from the CT image data, or scanning the outer contour of the target object with a camera.

6. The computer device according to claim 2, wherein, The steps of the computer device calculating the fixed position of the outer contour of the target object according to the three-dimensional pelvic model and the puncture point position include: Based on the three-dimensional pelvic model, taking the puncture point as the starting point, calculating the coordinate information of the puncture path; Calculating the insertion point on the outer contour of the target object according to the coordinate information of the puncture path; Simulating the fixed position of the fixture in the three-dimensional pelvic model according to the insertion point.

7. The computer device according to claim 2, wherein The positioning method executed by the computer device further includes: Recording the process data of the three-dimensional outer contour model and the three-dimensional bone model that have been completed in matching and splicing; Performing machine learning by combining the process data and the CT image data to obtain a network model for matching three-dimensional models; Guiding the next matching and splicing of the three-dimensional outer contour model and the three-dimensional bone model based on the network model.

Images