Data processing method and device for hip joint, storage medium and electronic equipment

Abstract

The application discloses a data processing method and device for a hip joint, a storage medium and an electronic device. It relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring medical image data of a target object hip joint; identifying the fusion type of the hip joint in the medical image data by using a fusion recognition model, to obtain a target fusion type corresponding to the medical image data; performing three-dimensional reconstruction based on the medical image data according to the target fusion type, to obtain a first bone model; and obtaining a target registration point set according to the first bone model, wherein the target registration point set is used to provide guidance for registration in a hip joint surgery. The application solves the problem of low accuracy of registration point selection caused by hip joint fusion in the prior art.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and more specifically, to a data processing method and apparatus for a hip joint, a storage medium, and an electronic device. Background Technology

[0002] In the fields of medical robotics and navigation technology, particularly in total hip arthroplasty, precise surgical registration for patients with anatomical abnormalities has become a significant challenge due to the diversification of patient populations. This is especially true for patients with ankylosing spondylitis (AS), whose hip joints may fuse, making traditional hip replacement techniques unsuitable for direct application. Accurate and reliable registration point selection is crucial in surgical scenarios involving fused hip joints. Good registration ensures precise prosthesis placement. Hip fusion alters the natural shape of the hip joint, rendering traditional registration methods relying on fixed anatomical landmarks unreliable and potentially leading to improper prosthesis placement.

[0003] There is currently no effective solution to the problem of low accuracy in registration point selection due to hip fusion in related technologies. Summary of the Invention

[0004] The main objective of this application is to provide a data processing method and apparatus, storage medium and electronic device for hip joints, in order to solve the problem of low accuracy in registration point selection due to hip joint fusion in related technologies.

[0005] To achieve the above objectives, according to one aspect of this application, a data processing method for a hip joint is provided. The method includes: acquiring medical imaging data of a target hip joint; identifying the hip joint fusion type in the medical imaging data using a fusion recognition model to obtain a target fusion type corresponding to the medical imaging data; performing three-dimensional reconstruction based on the medical imaging data according to the target fusion type to obtain a first skeletal model; and obtaining a set of target registration points based on the first skeletal model, wherein the set of target registration points is used to provide guidance for registration in hip joint surgery.

[0006] Further, based on the target fusion type, the three-dimensional reconstruction of the medical image data to obtain the first skeletal model includes: if the target fusion type is a bony fusion type, then the three-dimensional modeling method is confirmed to be a holistic modeling mode, and the medical image data is reconstructed in three dimensions according to the holistic modeling mode to obtain a first skeletal model about the pelvis and femur; if the target fusion type is a fibrous fusion type, then the three-dimensional modeling method is determined to be a local modeling mode, and the medical image data is reconstructed in three dimensions according to the local modeling mode to obtain a first skeletal model about the pelvis.

[0007] Furthermore, the process of performing three-dimensional reconstruction of the medical image data based on the local modeling mode to obtain a first skeletal model of the pelvis includes: performing image segmentation on the medical image data to obtain target image data corresponding to the pelvis; and performing three-dimensional reconstruction on the target image data to obtain the first skeletal model.

[0008] Furthermore, before obtaining the target registration point set based on the first skeletal model, the method further includes: establishing a first coordinate system for the first skeletal model relating to the pelvis and femur; obtaining the acetabular prosthesis implantation parameters based on the first coordinate system and the skeletal state in the first skeletal model; and performing a prosthesis simulation implantation on the first skeletal model based on the acetabular prosthesis implantation parameters to obtain the target skeletal model.

[0009] Further, obtaining the target registration point set based on the first skeletal model includes: when the first skeletal model is a first skeletal model about the pelvis and femur, obtaining registration point constraints; performing bone identification on the target skeletal model based on the registration point constraints using a registration point identification model to obtain identification results; and selecting registration points for the target skeletal model based on the identification results to obtain the target registration point set.

[0010] Further, obtaining the target registration point set based on the first skeletal model includes: when the first skeletal model is a first skeletal model about the pelvis, identifying the occluded areas in the target skeletal model through a registration point recognition model; marking the occluded areas in the target skeletal model to obtain a marked target skeletal model; and obtaining the target registration point set based on the marked target skeletal model.

[0011] Furthermore, after obtaining the target registration point set based on the first skeletal model, the method further includes: obtaining the real coordinate information of each registration point in the target registration point set corresponding to the target object, and registering based on the real coordinate information and the target skeletal model; after registration, collecting the simulated coordinate information of each registration point in the target registration point set in the target skeletal model; performing error verification based on the simulated coordinate information and the real coordinate information; if the verification fails, repeating the step of obtaining the target registration point set based on the first skeletal model until the verification passes.

[0012] To achieve the above objectives, according to another aspect of this application, a data processing apparatus for a hip joint is provided. The apparatus includes: a first acquisition unit for acquiring medical image data of a target object's hip joint; an identification unit for identifying the hip joint fusion type in the medical image data using a fusion identification model to obtain a target fusion type corresponding to the medical image data; a reconstruction unit for performing three-dimensional reconstruction based on the medical image data according to the target fusion type to obtain a first bone model; and a first determination unit for obtaining a target registration point set based on the first bone model, wherein the target registration point set is used to provide guidance for registration in hip joint surgery.

[0013] Furthermore, the reconstruction unit includes: a first determining subunit, configured to, if the target fusion type is a bony fusion type, confirm that the three-dimensional modeling method is a holistic modeling mode, and perform three-dimensional reconstruction of the medical image data according to the holistic modeling mode to obtain a first skeletal model of the pelvis and femur; and a second determining subunit, configured to, if the target fusion type is a fibrous fusion type, determine that the three-dimensional modeling method is a local modeling mode, and perform three-dimensional reconstruction of the medical image data according to the local modeling mode to obtain a first skeletal model of the pelvis.

[0014] Furthermore, the second determining subunit includes: a segmentation module, used to perform image segmentation on the medical image data to obtain target image data corresponding to the pelvis; and a reconstruction module, used to perform three-dimensional reconstruction on the target image data to obtain the first bone model.

[0015] Furthermore, the device further includes: an establishment unit, configured to establish a first coordinate system for the first bone model relating to the pelvis and femur before obtaining the target registration point set based on the first bone model; a second determination unit, configured to obtain the prosthesis implantation parameters of the acetabular prosthesis based on the first coordinate system and the bone state in the first bone model; and a simulation unit, configured to perform prosthesis simulation implantation on the first bone model based on the prosthesis implantation parameters of the acetabular prosthesis to obtain the target bone model.

[0016] The first determining unit further includes: an acquisition subunit, used to acquire registration point constraints when the first bone model is a first bone model about the pelvis and femur; a first identification subunit, used to perform bone identification on the target bone model based on the registration point constraints using a registration point identification model to obtain an identification result; and a selection subunit, used to select registration points on the target bone model based on the identification result to obtain the target registration point set.

[0017] Further, the first determining unit includes: a second identification subunit, used to identify the occluded region in the target bone model by means of a registration point identification model when the first bone model is a first bone model about the pelvis; a marking subunit, used to mark the occluded region in the target bone model to obtain a marked target bone model; and a third determining subunit, used to obtain the target registration point set based on the marked target bone model.

[0018] Furthermore, the device further includes: a second acquisition unit, configured to acquire the real coordinate information of each registration point in the target registration point set corresponding to the target object after obtaining the target registration point set based on the first skeletal model, and to register based on the real coordinate information and the target skeletal model; a collection unit, configured to collect the simulated coordinate information of each registration point in the target registration point set in the target skeletal model after registration is completed; and a verification unit, configured to perform error verification based on the simulated coordinate information and the real coordinate information, and if the verification fails, to repeat the step of obtaining the target registration point set based on the first skeletal model until the verification passes.

[0019] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the hip joint data processing method described above during runtime.

[0020] According to another aspect of the present invention, a computer-readable storage medium is also provided, the storage medium storing a program, wherein, when the program is running, the device where the storage medium is located executes the hip joint data processing method described above.

[0021] In this embodiment, the following steps are adopted: acquiring medical imaging data of the hip joint of the target object; identifying the hip joint fusion type in the medical imaging data through a fusion recognition model to obtain the target fusion type corresponding to the medical imaging data; performing three-dimensional reconstruction based on the medical imaging data according to the target fusion type to obtain a first bone model; and obtaining a target registration point set based on the first bone model. The target registration point set is used to provide guidance for registration in hip joint surgery, which solves the technical problem in related technologies that the accuracy of registration point selection is relatively low due to hip joint fusion.

[0022] In this approach, firstly, medical imaging data of the hip joint, such as CT scan data in DICOM format, is acquired from the patient. A pre-trained fusion recognition model is then used to analyze the medical imaging data, accurately distinguishing the hip joint fusion type. Based on the identified target fusion type, a matching 3D reconstruction method is employed to generate an accurate first bone model. Finally, by analyzing the first bone model, a set of target registration points is generated. The recommended set of registration points maximizes coverage of different anatomical planes, reducing registration errors. Through intelligent analysis by the fusion recognition model and subsequent adaptive 3D reconstruction, suitable bone surface regions for registration can be identified more accurately, thus recommending a more reliable set of target registration points and ultimately improving registration accuracy. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0024] Figure 1 A hardware block diagram of a computer terminal for implementing a data processing method for the hip joint is shown.

[0025] Figure 2 This is a flowchart of a data processing method for the hip joint provided according to an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of a data processing method for the hip joint provided in an embodiment of this application. Figure 1 ;

[0027] Figure 4 This is a schematic diagram of a data processing method for the hip joint provided in an embodiment of this application. Figure 2 ;

[0028] Figure 5 This is a schematic diagram of a data processing device for a hip joint according to an embodiment of this application;

[0029] Figure 6 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

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

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

[0032] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0033] Example 1

[0034] According to an embodiment of this application, a method embodiment for data processing of the hip joint is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a data processing method for the hip joint is shown. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the hip joint data processing method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the aforementioned hip joint data processing method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0039] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0040] Under the aforementioned operating environment, this application provides the following: Figure 2 The data processing method for the hip joint is shown. Figure 2 This is a flowchart of a data processing method for a hip joint according to Embodiment 1 of this application. The data processing method for the hip joint includes:

[0041] Step S201: Obtain medical imaging data of the target object's hip joint.

[0042] Optionally, medical imaging data of the patient's (i.e., the target subject) hip joint may be acquired. This medical imaging data can be CT (computed tomography) or MRI (magnetic resonance imaging) images. The hip joint imaging data may include the acetabulum, femoral head, femur, and surrounding soft tissue structures. When dealing with patients with hip fusion, the imaging data can cover the entire hip joint region and adjacent pelvic and femoral portions to facilitate a comprehensive assessment of anatomical changes.

[0043] Before entering the subsequent processing flow, the acquired medical image data may need to undergo certain preprocessing, such as image enhancement, noise removal, and standardization, in order to improve image quality and facilitate subsequent algorithm analysis and processing.

[0044] Step S202: The hip joint fusion type in the medical image data is identified by the fusion recognition model to obtain the target fusion type corresponding to the medical image data.

[0045] Optionally, after acquiring medical imaging data of the target object's (i.e., the patient's) hip joint, the medical imaging data, such as CT or MRI, is input into the fusion recognition model. The fusion recognition model extracts features of the hip joint, such as bone density, edge texture, joint space status, and bone bridge formation, from the medical imaging data. These features are analyzed to identify whether there are signs of bony fusion or fibrous fusion. For example, continuous bone density and clear bone bridge formation can indicate bony fusion, while blurred joint space boundaries may indicate fibrous fusion.

[0046] Based on the extracted features, the fusion recognition model automatically determines the fusion type to obtain the target fusion type. The fusion recognition model is trained on medical image data with known hip joint fusion types and can accurately distinguish the fusion type of the hip joint.

[0047] After obtaining the target fusion type output by the fusion recognition model, it can be combined with clinical symptoms and other diagnostic information to confirm whether the target fusion type needs to be adjusted, thereby improving the accuracy of determining the fusion type.

[0048] Step S203: Based on the target fusion type, perform three-dimensional reconstruction based on medical image data to obtain the first skeletal model.

[0049] Optionally, based on the identified target fusion type, a matching 3D reconstruction method is determined, and then 3D reconstruction is performed based on medical image data to obtain a first bone model. For example, a high-fidelity 3D bone model is formed by extracting the digital representation of bones from CT or MRI images through threshold segmentation, morphological operations, and boundary detection.

[0050] When processing 3D reconstructions of fused hips, special attention must be paid to the treatment of the fusion region to avoid model distortion. For example, techniques such as smoothing algorithms and boundary refinement can be employed to ensure the accurate representation of the fusion region in the 3D model. To further improve the accuracy of the 3D reconstruction, the generated first bone model can be validated to ensure consistency with the medical imaging data, including size, shape, and relative position.

[0051] The three-dimensional reconstruction in step S203 yields a first skeletal model that reflects the true anatomical structure of the hip joint. This model not only includes the basic geometric information of the hip joint but also fully considers the impact of the fusion type on the skeletal structure, providing an extremely important visualization tool and data support for subsequent registration point selection, surgical path planning, and prosthesis implantation.

[0052] Step S204: Based on the first skeletal model, a set of target registration points is obtained, wherein the set of target registration points is used to provide guidance for registration in hip joint surgery.

[0053] Optionally, a set of target registration points can be obtained based on the first skeletal model using a deep learning model. It should be noted that the selection criteria for registration points may include: Based on skeletal stability: selecting areas with hard, stable bone as registration points, such as the anterior superior iliac spine, pubic symphysis, and posterior wall of the acetabulum. Anatomical accessibility: ensuring that registration points are easily accessible during surgery, avoiding obstruction by soft tissue or osteophytes. Accuracy assurance: the distribution of registration points should meet accuracy requirements, such as following the triangular stability principle, ensuring that points are located on different anatomical planes with sufficient spacing to improve registration accuracy.

[0054] For example, by analyzing the first skeletal model using a deep learning model, suitable bone surface regions can be identified as registration points, and a set of target registration points can be automatically generated.

[0055] It's important to note that registration is the process of precisely aligning the patient's anatomical structure with the preoperative plan or image model. This involves matching the patient's hip joint with a three-dimensional skeletal model constructed from medical imaging data such as CT or MRI scans. This allows for accurate understanding of the anatomical location and orientation of the bones, guiding precise prosthesis implantation. After obtaining the target registration point set, marking tools (such as adjustable probes) are used to mark each point in the target registration point set on the actual bones of the patient's hip joint. These points are then captured by an optical tracking system and paired with corresponding points in the first skeletal model, establishing a spatial correspondence between the actual bone and the model. Once registration is complete, the surgical navigation system uses the guidance provided by the target registration point set to detect and adjust the position of surgical instruments in real time, ensuring the accuracy of the prosthesis implantation angle and position.

[0056] In summary, the process begins with acquiring medical imaging data of the hip joint from the patient, such as CT scan data in DICOM format. A pre-trained fusion recognition model is then used to analyze this data, accurately identifying the hip joint fusion type. Based on the identified target fusion type, a matching 3D reconstruction method is employed to generate an accurate first bone model. Finally, by analyzing the first bone model, a set of target registration points is generated. This recommended set maximizes coverage of different anatomical planes, reducing registration errors. Through intelligent analysis by the fusion recognition model and subsequent adaptive 3D reconstruction, suitable bone surface regions for registration can be identified more accurately, leading to the recommendation of a more reliable set of target registration points and ultimately improving registration accuracy.

[0057] Optionally, in the data processing method for the hip joint provided in this application embodiment, the method of performing three-dimensional reconstruction based on medical image data according to the target fusion type to obtain a first bone model includes: if the target fusion type is a bony fusion type, then the three-dimensional modeling method is confirmed to be an overall modeling mode, and the medical image data is reconstructed in three dimensions according to the overall modeling mode to obtain a first bone model about the pelvis and femur; if the target fusion type is a fibrous fusion type, then the three-dimensional modeling method is determined to be a local modeling mode, and the medical image data is reconstructed in three dimensions according to the local modeling mode to obtain a first bone model about the pelvis.

[0058] In an optional embodiment, when the hip joint is identified as having bony fusion, it means that a bony bridge has formed between the femoral head and the acetabulum, resulting in a loss of relative motion. In this case, the 3D modeling approach is confirmed to be a holistic modeling mode, treating the femur and pelvis as a unified structure for 3D reconstruction. This means treating the fused hip joint as a whole to obtain a first skeletal model of the pelvis and femur. This approach avoids errors that may be introduced by traditional segmentation methods, ensuring the integrity and accuracy of the 3D model.

[0059] When a hip joint is diagnosed as fibro-fused, it means that although the joint space between the femoral head and acetabulum has disappeared, a bony connection has not been formed, and a certain degree of mobility is still retained. For this type of hip joint, a local modeling approach is used to perform three-dimensional reconstruction of medical imaging data to obtain a first skeletal model of the pelvis. Because the anatomical features of a fibro-fused hip differ from those of a completely bony fusion, local modeling allows for more precise adjustments to the registration strategy. For example, by segmenting the femoral image to obtain the first skeletal model of the pelvis, the exposed area of ​​the acetabulum is increased, thereby improving the accuracy of the registration points and the reliability of the registration process.

[0060] Selecting an appropriate 3D modeling strategy based on the target fusion type can improve the accuracy of subsequent registration point selection, thereby improving the accuracy of subsequent registration.

[0061] Optionally, in the data processing method for the hip joint provided in this application embodiment, the method of performing three-dimensional reconstruction of medical image data based on a local modeling mode to obtain a first skeletal model of the pelvis includes: performing image segmentation on the medical image data to obtain target image data corresponding to the pelvis; and performing three-dimensional reconstruction on the target image data to obtain a first skeletal model.

[0062] In an optional embodiment, for fibro-fused hips, since the joint space between the femoral head and acetabulum may be lost without bony fusion, the pelvis needs to be processed separately to ensure the integrity of its structural features. Using deep learning algorithms, such as convolutional neural networks, or traditional image processing techniques, such as thresholding and edge detection, the pelvic portion is accurately segmented from complete CT or MRI image data to obtain target image data corresponding to the pelvis. Three-dimensional reconstruction is then performed on the target image data of the pelvis to recover the three-dimensional structure of the pelvis from the two-dimensional image data, resulting in a first skeletal model.

[0063] For example, image analysis can be performed by standardizing raw medical image data (such as CT or MRI images) to a uniform range of pixel intensity. Techniques such as filtering and contrast adjustment are used to enhance structural features in the image. A trained deep learning model is then used to identify and label skeletal regions in the enhanced image. To reduce noise or discontinuous boundaries, neighboring pixel filling can be used to optimize the segmentation results, ensuring the integrity and accuracy of the contours.

[0064] For example, the following steps are used to achieve 3D reconstruction: The target image data corresponding to the pelvis is converted into 3D voxel data, where each voxel represents a tiny volumetric unit in the image, and the voxel value reflects the density of that region. A surface reconstruction algorithm is used to extract a 3D mesh representing the pelvic surface from the voxel data. This step transforms the pelvic surface into a 3D model composed of polygons. The generated 3D model is further optimized, such as by applying smoothing algorithms to reduce surface irregularities and refining the model structure using quadrilateral or triangular meshes to ensure the model's accuracy and visual quality.

[0065] 3D reconstruction using local modeling mode focuses on the pelvic structure, avoiding registration errors that may arise from overall modeling. This provides more accurate registration reference points, especially when dealing with complex cases such as fibro-fused hips.

[0066] Optionally, in the data processing method for the hip joint provided in the embodiments of this application, before obtaining the target registration point set based on the first bone model, the method further includes: establishing a first coordinate system for the first bone model about the pelvis and femur; obtaining the prosthesis implantation parameters of the acetabular prosthesis based on the first coordinate system and the bone state in the first bone model; and performing prosthesis simulation implantation on the first bone model based on the prosthesis implantation parameters of the acetabular prosthesis to obtain the target bone model.

[0067] In an optional embodiment, for a first skeletal model of the pelvis and femur, stable reference points are selected within the first skeletal model as the origin and axial reference of the coordinate system. For the pelvis, reference points may include, for example, the anterior superior iliac spine, the pubic symphysis, the obturator foramen margin, etc. Based on the selected reference points, a local coordinate system is established on the model using a three-dimensional coordinate transformation method. This coordinate system will be used to describe the position and orientation of the acetabulum and other skeletal structures. The axis and origin of the coordinate system are adjusted to ensure they match the physiological axis and anatomical features of the hip joint, improving the accuracy of subsequent surgical planning.

[0068] Based on the established first coordinate system and anatomical information (such as the size, shape, and depth of the acetabulum) in the first skeletal model, deep learning algorithms are used to analyze and recommend key parameters of the acetabular prosthesis, including its size, anteversion angle, and abduction angle. The AI-recommended parameters are then personalized according to the patient's specific anatomical conditions and clinical needs to ensure optimal matching between the prosthesis and the patient's skeleton. After determining the prosthesis implantation parameters, collision detection analysis is performed to check for potential conflicts between the prosthesis and surrounding bone structures, ensuring safety.

[0069] The selected acetabular prosthesis model is imported into the surgical planning system. This model includes the prosthesis's geometry and material properties. The prosthesis model is positioned within a first bone model using parameters such as anteversion and abduction angles to simulate its implantation. During the simulated implantation, the system dynamically adjusts the prosthesis's position and angle based on collision analysis results, bone structure, and user feedback until the optimal implantation state is achieved, thus obtaining the target bone model.

[0070] Simulated implantation of prostheses can provide precise surgical planning for hip replacement surgery, improving the accuracy of preoperative planning.

[0071] Optionally, in the data processing method for the hip joint provided in this application embodiment, obtaining the target registration point set based on the first bone model includes: when the first bone model is a first bone model about the pelvis and femur, obtaining registration point constraints; performing bone identification on the target bone model based on the registration point constraints using a registration point identification model to obtain identification results; and selecting registration points for the target bone model based on the identification results to obtain the target registration point set.

[0072] In an alternative embodiment, firstly, constraints for registration point selection are obtained based on surgical requirements and bone characteristics. For example, constraints may include: bone stability (bone density), anatomical accessibility (surface palpability), the operating range of surgical instruments, and the geometric relationship between registration points (such as the triangular stability principle). Constraints may also consider the specificities of fused hips; for example, in bony fused hips, registration points should avoid the fusion area, while in fibrofused hips, the degree of acetabular exposure must be considered.

[0073] Then, the registration point identification model performs bone quality identification on the target bone model based on registration point constraints. According to the results of bone quality identification and registration point constraints, the registration point identification model selects bone surfaces that meet the requirements as potential registration points. For example, bone surface locations with high bone density and easy access by instruments are selected.

[0074] In an optional embodiment, a deep neural network (i.e., the registration point recognition model described above) is used to extract potential high-stability regions on the bone surface. Based on the triangular stability principle (large spacing between points, uniform distribution, and location on different anatomical planes), three initial registration points are initially recommended. It should be noted that at least one of these three registration points is located on the thigh; for example, the three initial registration points could be located on the lateral side of the posterior wall of the acetabulum, the lateral side of the superior acetabulum, or posterior to the greater trochanter of the femur. The bone model is identified using the deep neural network, and locations with intact bone quality are selected for random distribution of fine-calibration points. Following the principle of being as dispersed as possible within the intraoperative field of view and at locations with good bone quality, fine-calibration points are randomly generated. The number of fine-calibration points can be adjusted according to the patient's actual assessment.

[0075] In an optional embodiment, each point in the target registration point set can be highlighted with color coding or specific symbols in the 3D visualization interface to facilitate users' intuitive understanding and confirmation of the registration point location.

[0076] By following the steps above, the bone identification can be made more accurate based on the characteristics of the first skeletal model, thereby improving the accuracy of obtaining the target registration point set.

[0077] Optionally, in the data processing method for the hip joint provided in this application embodiment, obtaining the target registration point set based on the first bone model includes: when the first bone model is a first bone model about the pelvis, identifying the occluded area in the target bone model through a registration point recognition model; marking the occluded area in the target bone model to obtain a marked target bone model; and obtaining the target registration point set based on the marked target bone model.

[0078] In an optional embodiment, since the first pelvic bone model may contain osteophytes and joint capsule occlusion areas, an occlusion area in the target bone model can be identified using a registration point recognition model. This involves analyzing which areas of the bone surface might be obscured by osteophytes, soft tissue, or other bone structures, affecting the selection and marking of registration points. The identified occlusion areas are then marked on the first bone model, for example, using different colors or transparency settings to distinguish these areas, facilitating visual identification in subsequent operations.

[0079] In the labeled target skeleton model, candidate regions for registration points are selected based on factors such as bone surface texture, stability, and accessibility. These regions should avoid occluded areas to ensure clear visibility and easy accessibility of the registration points. A registration point identification model is then used to select the most suitable points from the candidate regions. This model needs to consider multiple factors, including the distance between points, uniformity of distribution, and the relationship between points and key anatomical structures, to improve the accuracy and stability of registration.

[0080] By following the steps above, occluded areas in the first skeletal model can be effectively identified and labeled, avoiding the need to select registration points in these areas and selecting the optimal set of target registration points.

[0081] Optionally, in the data processing method for the hip joint provided in this application embodiment, after obtaining the target registration point set based on the first bone model, the method further includes: obtaining the real coordinate information of each registration point in the target registration point set corresponding to the target object, and registering it based on the real coordinate information and the target bone model; after registration, collecting the simulated coordinate information of each registration point in the target registration point set in the target bone model; performing error verification based on the simulated coordinate information and the real coordinate information; if the verification fails, repeating the step of obtaining the target registration point set based on the first bone model until the verification passes.

[0082] In an optional embodiment, a traceable positioning tool is used to obtain the real coordinate information of each registration point in the target registration point set corresponding to the target object. The real coordinate information of the target registration point is matched with the corresponding point in the first skeleton model. Algorithms such as point-to-point registration, rigid body transformation, and non-rigid body deformation are used to adjust the orientation and position of the first skeleton model based on the collected real coordinate information to ensure the consistency between the model and the actual skeleton structure.

[0083] After registration, the surgical planning system places virtual markers in the target skeleton model at positions corresponding to the target registration points. Software tools are then used to read the position information of these virtual markers in the target skeleton model's coordinate system—the simulated coordinate information. The actual coordinate information obtained from the target registration points is compared with the simulated coordinate information of the corresponding virtual markers in the model, and the distance difference between the two (registration error) is calculated. An error threshold is set, such as 0.5mm; if the registration error of any registration point exceeds this threshold, the registration is considered unsuccessful.

[0084] If the verification fails, repeat the step of obtaining the target registration point set based on the first skeleton model until the verification passes.

[0085] In an alternative embodiment, it can be as follows: Figure 3The diagram illustrates the data processing of the hip joint, including CT data import and fusion recognition. After importing CT DICOM data of both hip joints, the fusion recognition module is automatically invoked to analyze features such as bone density continuity, edge texture, bone bridge formation, cortical continuity, and joint space structure between the femoral head and acetabulum. This analysis then determines the fusion type. If it is a fibrous fusion, a local 3D reconstruction is used to obtain a pelvic model; if it is a bony fusion, a holistic modeling mode is enabled, treating the pelvis and femur as a single 3D structure for reconstruction. This avoids the need for forcibly separating the hip joint space, effectively preventing model distortion caused by misprocessing of the fusion area.

[0086] In an optional embodiment, step 1: CT data import and fusion identification. After importing the CT DICOM data of the patient's bilateral hip joints, the system automatically calls the fusion identification module to analyze AI features such as bone density continuity, edge texture, and bone bridge formation between the femoral head and acetabulum, and determines it to be a bony fusion type. At this time, the system automatically activates the overall modeling mode, reconstructing the pelvis and femur as a whole structure in three dimensions, without forcibly separating the hip joint space, effectively avoiding model distortion caused by misprocessing of the fusion area.

[0087] Step 2: Preoperative planning. A pelvic coordinate system is established based on stable bony landmarks such as the pubic symphysis, anterior superior iliac spine, and teardrop mark. The system recommends an initial acetabular prosthesis placement angle of 20° anteversion and 40° abduction, which can be adaptively adjusted according to the patient's individual anatomical parameters. The surgeon can also manually input the target prosthesis parameters, and the system will automatically simulate and generate a feasible path and perform collision warning analysis.

[0088] Step 3: Registration point recommendation and dynamic adjustment. Using a deep neural network, potential high-stability regions are automatically extracted from the bone surface. Based on the principle of triangular stability (large spacing between selected points, uniform distribution, and location on different anatomical planes), three initial registration points are initially recommended, such as: the lateral side of the posterior wall of the acetabulum, the lateral side of the superior acetabulum, and the posterior side of the greater trochanter of the femur.

[0089] The system uses a deep neural network to identify bone models and randomly distributes fine-tuning points in locations with good bone quality. Following the principle of being as dispersed as possible within the intraoperative field of view and in good bone condition, fine-tuning indicator points are randomly generated. The number of fine-tuning points can be adjusted based on the patient's actual assessment. After registration begins, the system uses optical tracking to collect registration point matching errors. If the error exceeds a threshold (e.g., 0.5mm), the system automatically invokes a registration point optimization algorithm to reselect candidate points on the visible bone surface, such as auxiliary points near the posterior femoral neck or anterior superior iliac spine. Recommended points are displayed in a color-coded visualization to show the registration stability level, allowing the surgeon to select and confirm. This AI registration point generation module has self-learning capabilities; postoperative accuracy data is used to optimize the point recommendation model for subsequent cases, thereby continuously improving algorithm performance.

[0090] Step 4: Osteotomy and Prosthesis Implantation. After registration, the system prompts the surgeon to perform in-situ osteotomy. Without dislocation, the acetabulum is precisely reamed along the pre-planned path using a robotic arm or navigation guide. The system monitors deviations from the planned trajectory in real time; if significant differences are found, it can suggest fine-tuning the tool path to ensure the prosthesis implantation direction and depth match the pre-operative goals.

[0091] In an optional embodiment, the fibro-fusion hip registration method is as follows: Step 1: CT modeling and fusion determination. After importing CT DICOM data, the system combines various AI image recognition features such as bone density distribution, cortical continuity, and joint space structure to determine whether the hip joint is of the fibro-fusion type. The system automatically adopts the standard bone segmentation process to reconstruct the pelvis and femur as two independent models in three dimensions, providing a structural basis for subsequent step-by-step registration.

[0092] Step 2: Preoperative parameter planning. Based on key pelvic structures (teardrop line, anterior superior iliac spine, pubic symphysis, obturator foramen margin), a local pelvic coordinate system is automatically established. An AI algorithm recommends the acetabular prosthesis size and installation angle, with default parameters of 20° anteversion and 40° abduction. Personalized fitting can be performed based on the patient's body type and bone condition. The system provides a simulation report on the prosthesis-bone surface fit and predicts potential osteophyte interference areas.

[0093] Step 3: Registration Point Generation and Dynamic Adjustment. The AI ​​registration point recommendation module automatically generates multiple candidate initial registration points in areas such as the lateral posterior wall, superior lateral wall, and lateral anterior wall of the acetabulum, based on the currently exposed bone surface and considering angle, accessibility, and bone texture characteristics. These points are visualized using a heatmap to indicate their stability and registration contribution, and surgeons are advised to prioritize points with high stability. The system performs the initial registration operation based on the selected points. If the registration error exceeds a set threshold (e.g., 0.5mm), an "adaptive point replacement mechanism" is immediately activated. The system analyzes the source of the error (e.g., single-point drift, regional occlusion) and provides a new set of recommended point combinations for the surgeon to choose from or for the system to automatically confirm and re-execute the registration process.

[0094] Step 4: Grinding and Prosthesis Implantation. After registration, the system generates a robotic arm navigation trajectory based on preoperative planning and actual registration results, automatically avoiding osteophyte areas or areas obstructing the field of vision, and recommending a grinding path. For complex acetabular shapes, the system can also suggest the grinding sequence and depth range, and adjust the robotic arm angle based on real-time feedback to ensure the stability of the prosthesis and consistency with the target angle.

[0095] In an alternative embodiment, it can be as follows: Figure 4The diagram illustrates the data processing for the hip joint. After obtaining the skeletal model through 3D reconstruction, AI can be used to optimize the prosthesis implantation parameters. An adjustable probe marks the registration point, determining whether the registration error exceeds a set threshold, i.e., whether the accuracy requirements are met. If they are met, the next step (prosthesis implantation) is executed. If not, the source of the error is analyzed (such as single-point drift or regional occlusion), and a new set of recommended point combinations is provided for the surgeon to choose from, or the system automatically confirms and re-executes the registration process.

[0096] The data processing method for hip joints provided in this application involves acquiring medical imaging data of the target object's hip joint; identifying the hip joint fusion type in the medical imaging data using a fusion recognition model to obtain the target fusion type corresponding to the medical imaging data; performing three-dimensional reconstruction based on the medical imaging data according to the target fusion type to obtain a first bone model; and obtaining a target registration point set based on the first bone model. This target registration point set is used to provide guidance for registration in hip joint surgery, solving the technical problem in related technologies where the accuracy of registration point selection is relatively low due to hip joint fusion.

[0097] In this approach, firstly, medical imaging data of the hip joint, such as CT scan data in DICOM format, is acquired from the patient. A pre-trained fusion recognition model is then used to analyze the medical imaging data, accurately distinguishing the hip joint fusion type. Based on the identified target fusion type, a matching 3D reconstruction method is employed to generate an accurate first bone model. Finally, by analyzing the first bone model, a set of target registration points is generated. The recommended set of registration points maximizes coverage of different anatomical planes, reducing registration errors. Through intelligent analysis by the fusion recognition model and subsequent adaptive 3D reconstruction, suitable bone surface regions for registration can be identified more accurately, thus recommending a more reliable set of target registration points and ultimately improving registration accuracy.

[0098] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0099] Example 2

[0100] This application also provides a data processing device for a hip joint. It should be noted that the data processing device for a hip joint in this application can be used to execute the data processing method for a hip joint provided in this application. The data processing device for a hip joint provided in this application is described below.

[0101] According to an embodiment of this application, an apparatus for implementing the above-described data processing method for the hip joint is also provided, such as... Figure 5 As shown, the device includes: a first acquisition unit 501, an identification unit 502, a reconstruction unit 503, and a first determination unit 504.

[0102] The first acquisition unit 501 is used to acquire medical imaging data of the hip joint of the target object;

[0103] The identification unit 502 is used to identify the hip joint fusion type in medical image data through a fusion identification model, and obtain the target fusion type corresponding to the medical image data.

[0104] Reconstruction unit 503 is used to perform three-dimensional reconstruction based on medical image data according to the target fusion type to obtain the first bone model;

[0105] The first determining unit 504 is used to obtain a set of target registration points based on the first skeletal model, wherein the set of target registration points is used to provide guidance for registration in hip joint surgery.

[0106] The data processing device for the hip joint provided in this application embodiment acquires medical image data of the target object's hip joint through a first acquisition unit 501; an identification unit 502 identifies the hip joint fusion type in the medical image data through a fusion identification model to obtain the target fusion type corresponding to the medical image data; a reconstruction unit 503 performs three-dimensional reconstruction based on the medical image data according to the target fusion type to obtain a first bone model; and a first determination unit 504 obtains a set of target registration points based on the first bone model. The set of target registration points is used to provide guidance for registration in hip joint surgery, solving the technical problem in related technologies where the accuracy of registration point selection is relatively low due to hip joint fusion.

[0107] In this approach, firstly, medical imaging data of the hip joint, such as CT scan data in DICOM format, is acquired from the patient. A pre-trained fusion recognition model is then used to analyze the medical imaging data, accurately distinguishing the hip joint fusion type. Based on the identified target fusion type, a matching 3D reconstruction method is employed to generate an accurate first bone model. Finally, by analyzing the first bone model, a set of target registration points is generated. The recommended set of registration points maximizes coverage of different anatomical planes, reducing registration errors. Through intelligent analysis by the fusion recognition model and subsequent adaptive 3D reconstruction, suitable bone surface regions for registration can be identified more accurately, thus recommending a more reliable set of target registration points and ultimately improving registration accuracy.

[0108] Optionally, in the data processing device for the hip joint provided in this application embodiment, the reconstruction unit includes: a first determining subunit, used to determine that the three-dimensional modeling method is the overall modeling mode if the target fusion type is the bony fusion type, and to perform three-dimensional reconstruction of the medical image data according to the overall modeling mode to obtain a first skeletal model about the pelvis and femur; and a second determining subunit, used to determine that the three-dimensional modeling method is the local modeling mode if the target fusion type is the fibrous fusion type, and to perform three-dimensional reconstruction of the medical image data according to the local modeling mode to obtain a first skeletal model about the pelvis.

[0109] Optionally, in the data processing device for the hip joint provided in the embodiments of this application, the second determining subunit includes: a segmentation module for performing image segmentation on medical image data to obtain target image data corresponding to the pelvis; and a reconstruction module for performing three-dimensional reconstruction on the target image data to obtain a first bone model.

[0110] Optionally, in the data processing apparatus for the hip joint provided in the embodiments of this application, the apparatus further includes: an establishment unit, used to establish a first coordinate system for the first bone model regarding the pelvis and femur before obtaining the target registration point set based on the first bone model; a second determination unit, used to obtain the prosthesis implantation parameters of the acetabular prosthesis based on the first coordinate system and the bone state in the first bone model; and a simulation unit, used to perform prosthesis simulation implantation on the first bone model based on the prosthesis implantation parameters of the acetabular prosthesis to obtain the target bone model.

[0111] Optionally, in the data processing device for the hip joint provided in this application embodiment, the first determining unit includes: an acquisition subunit, used to acquire registration point constraints when the first bone model is a first bone model about the pelvis and femur; a first identification subunit, used to perform bone identification on the target bone model based on the registration point constraints through a registration point identification model to obtain identification results; and a selection subunit, used to select registration points on the target bone model according to the identification results to obtain a set of target registration points.

[0112] Optionally, in the data processing device for the hip joint provided in the embodiments of this application, the first determining unit includes: a second identification subunit, used to identify the occluded area in the target bone model by means of a registration point identification model when the first bone model is a first bone model about the pelvis; a marking subunit, used to mark the occluded area in the target bone model to obtain a marked target bone model; and a third determining subunit, used to obtain a target registration point set based on the marked target bone model.

[0113] Optionally, in the data processing device for the hip joint provided in this application embodiment, the device further includes: a second acquisition unit, configured to acquire the real coordinate information of each registration point in the target registration point set corresponding to the target object after obtaining the target registration point set based on the first bone model, and register based on the real coordinate information and the target bone model; a collection unit, configured to collect the simulated coordinate information of each registration point in the target registration point set in the target bone model after registration is completed; and a verification unit, configured to perform error verification based on the simulated coordinate information and the real coordinate information, and if the verification fails, repeat the step of obtaining the target registration point set based on the first bone model until the verification passes.

[0114] It should be noted that the first acquisition unit 501, identification unit 502, reconstruction unit 503, and first determination unit 504 mentioned above correspond to steps S201 to S204 in Embodiment 1. The four units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0115] Example 3

[0116] Embodiments of this application may provide an electronic device. Figure 6 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 6 As shown, the electronic device may include: one or more ( Figure 6 (Only one is shown) Processor 602, memory 604, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0117] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0118] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: acquiring medical imaging data of the target object's hip joint; identifying the hip joint fusion type in the medical imaging data using a fusion recognition model to obtain the target fusion type corresponding to the medical imaging data; performing three-dimensional reconstruction based on the medical imaging data according to the target fusion type to obtain a first bone model; and obtaining a set of target registration points based on the first bone model, wherein the set of target registration points is used to provide guidance for registration in hip joint surgery.

[0119] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: Based on the target fusion type, perform three-dimensional reconstruction using medical image data to obtain a first skeletal model, including: if the target fusion type is bony fusion, confirm that the three-dimensional modeling method is a holistic modeling mode, and perform three-dimensional reconstruction of the medical image data based on the holistic modeling mode to obtain a first skeletal model of the pelvis and femur; if the target fusion type is fibrous fusion, determine that the three-dimensional modeling method is a local modeling mode, and perform three-dimensional reconstruction of the medical image data based on the local modeling mode to obtain a first skeletal model of the pelvis.

[0120] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: performing three-dimensional reconstruction of medical image data based on the local modeling mode to obtain a first skeletal model of the pelvis, including: performing image segmentation on the medical image data to obtain target image data corresponding to the pelvis; performing three-dimensional reconstruction on the target image data to obtain the first skeletal model.

[0121] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: before obtaining the target registration point set based on the first bone model, the method further includes: establishing a first coordinate system for the first bone model about the pelvis and femur; obtaining the prosthesis implantation parameters of the acetabular prosthesis based on the first coordinate system and the bone state in the first bone model; and performing prosthesis simulation implantation on the first bone model based on the prosthesis implantation parameters of the acetabular prosthesis to obtain the target bone model.

[0122] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtaining the target registration point set based on the first bone model includes: when the first bone model is a first bone model about the pelvis and femur, obtaining registration point constraints; performing bone identification on the target bone model based on the registration point constraints through the registration point identification model to obtain the identification result; selecting registration points on the target bone model based on the identification result to obtain the target registration point set.

[0123] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtaining the target registration point set based on the first skeleton model includes: when the first skeleton model is a first skeleton model about the pelvis, identifying the occluded area in the target skeleton model through the registration point recognition model; marking the occluded area in the target skeleton model to obtain the marked target skeleton model; and obtaining the target registration point set based on the marked target skeleton model.

[0124] The processor can call the information and application stored in the memory through the transmission device to execute the following steps: After obtaining the target registration point set based on the first skeleton model, the method further includes: obtaining the real coordinate information of each registration point in the target registration point set corresponding to the target object, and registering based on the real coordinate information and the target skeleton model; after registration is completed, collecting the simulated coordinate information of each registration point in the target registration point set in the target skeleton model; performing error verification based on the simulated coordinate information and the real coordinate information; if the verification fails, repeating the step of obtaining the target registration point set based on the first skeleton model until the verification passes.

[0125] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 6 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 6 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 6 The different configurations shown.

[0126] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0127] Example 4

[0128] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the hip joint data processing method provided in Embodiment 1.

[0129] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0130] This application also provides a computer program product, which, when executed on a data processing device, is adapted to perform data processing method steps for a hip joint.

[0131] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0132] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0134] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0136] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0137] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A data processing method for the hip joint, characterized in that, include: Acquire medical imaging data of the target object's hip joint; The hip joint fusion type in the medical image data is identified by a fusion recognition model to obtain the target fusion type corresponding to the medical image data. Based on the target fusion type, a three-dimensional reconstruction is performed on the medical image data to obtain a first skeletal model; Based on the first skeletal model, a set of target registration points is obtained, wherein the set of target registration points is used to provide guidance for registration in hip joint surgery; The first skeletal model, obtained by performing three-dimensional reconstruction based on the medical image data according to the target fusion type, includes: If the target fusion type is a bony fusion type, then the three-dimensional modeling method is confirmed to be the overall modeling mode, and the medical image data is reconstructed in three dimensions according to the overall modeling mode to obtain the first skeletal model of the pelvis and femur. If the target fusion type is fiber fusion type, then the three-dimensional modeling method is determined to be local modeling mode, and the medical image data is reconstructed in three dimensions according to the local modeling mode to obtain the first skeletal model of the pelvis. Based on the first skeletal model, the target registration point set is obtained by: when the first skeletal model is a first skeletal model about the pelvis and femur, obtaining registration point constraints; The target bone model is identified by the registration point recognition model based on the registration point constraints to obtain the recognition result. The target bone model is obtained after the first bone model is implanted with a prosthesis. Based on the recognition results, registration points are selected for the target skeletal model to obtain the target registration point set; Based on the first skeletal model, the target registration point set is obtained by: when the first skeletal model is a first skeletal model about the pelvis, identifying the occluded areas in the target skeletal model through the registration point recognition model; The occluded areas in the target skeleton model are marked to obtain the marked target skeleton model; Based on the labeled target skeleton model, the target registration point set is obtained.

2. The method according to claim 1, characterized in that, Based on the local modeling pattern, the medical image data is reconstructed in three dimensions to obtain a first skeletal model of the pelvis, including: The medical image data is segmented to obtain the target image data corresponding to the pelvis; The target image data is reconstructed in three dimensions to obtain the first skeletal model.

3. The method according to claim 1, characterized in that, Before obtaining the target registration point set based on the first skeletal model, the method further includes: A first coordinate system is established for the first skeletal model of the pelvis and femur; Based on the first coordinate system and the skeletal state in the first skeletal model, the implantation parameters of the acetabular prosthesis are obtained; Based on the implantation parameters of the acetabular prosthesis, the prosthesis is simulated and implanted in the first bone model to obtain the target bone model.

4. The method according to claim 3, characterized in that, After obtaining the target registration point set based on the first skeletal model, the method further includes: Obtain the real coordinate information of each registration point in the target registration point set corresponding to the target object, and register the target based on the real coordinate information and the target skeleton model; After registration is completed, the simulated coordinate information of each registration point in the target registration point set in the target skeleton model is collected; Error verification is performed based on the simulated coordinate information and the real coordinate information. If the verification fails, the step of obtaining the target registration point set based on the first skeleton model is repeated until the verification passes.

5. A data processing device for a hip joint, characterized in that, include: The first acquisition unit is used to acquire medical imaging data of the hip joint of the target object; The identification unit is used to identify the hip joint fusion type in the medical image data through a fusion identification model, and obtain the target fusion type corresponding to the medical image data. The reconstruction unit is used to perform three-dimensional reconstruction based on the medical image data according to the target fusion type to obtain a first skeletal model; The first determining unit is used to obtain a set of target registration points based on the first bone model, wherein the set of target registration points is used to provide guidance for registration in hip joint surgery; The reconstruction unit includes: a first determining subunit, used to determine that if the target fusion type is a bony fusion type, the three-dimensional modeling method is a holistic modeling mode, and to perform three-dimensional reconstruction of the medical image data according to the holistic modeling mode to obtain a first skeletal model about the pelvis and femur; and a second determining subunit, used to determine that if the target fusion type is a fibrous fusion type, the three-dimensional modeling method is a local modeling mode, and to perform three-dimensional reconstruction of the medical image data according to the local modeling mode to obtain a first skeletal model about the pelvis. The first determining unit includes: an acquisition subunit, used to acquire registration point constraints when the first bone model is a first bone model about the pelvis and femur; a first identification subunit, used to perform bone identification on the target bone model based on the registration point constraints using a registration point identification model to obtain an identification result; and a selection subunit, used to select registration points on the target bone model according to the identification result to obtain the target registration point set, wherein the target bone model is obtained after the first bone model undergoes prosthesis simulation implantation; The first determining unit includes: a second identification subunit, used to identify occluded regions in the target bone model by means of a registration point identification model when the first bone model is a first bone model about the pelvis; a marking subunit, used to mark the occluded regions in the target bone model to obtain a marked target bone model; and a third determining subunit, used to obtain the target registration point set based on the marked target bone model.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the data processing method for the hip joint according to any one of claims 1 to 4.

7. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the data processing method for the hip joint according to any one of claims 1 to 4.

Images