A method, device and equipment for intelligently recommending prosthesis parameters in hip replacement surgery and a storage medium

Abstract

The application provides a method and device for intelligently recommending prosthesis parameters in hip replacement surgery, equipment and storage medium. The method comprises: establishing a standard template prosthesis, establishing a reversible mapping function for different brands and models of prostheses and the standard template prosthesis respectively, and composing a prosthesis mapping relationship library; using the standard template prosthesis pose parameters corresponding to the prosthesis model in a large number of hip surgery planning schemes formulated by doctors with rich clinical experience as samples, training a neural network to learn; inputting patient CT images, and outputting the pose parameters corresponding to the standard template prosthesis; after a doctor selects a specific brand and model of prosthesis, the system automatically selects the adaptive model and automatically corrects the pose parameters through the pre-established mapping function. The application can adapt to prostheses of different brands and series by introducing the standard template prosthesis and the mapping function, and increase new brands and series without changing the main process.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, specifically to a method, apparatus, device, and storage medium for intelligently recommending prosthesis parameters in hip replacement surgery. Background Technology

[0002] Hip replacement surgery is one of the most effective methods for treating degenerative hip joint diseases and improving patients' quality of life. With the increasing prominence of China's aging population, the practical significance of hip replacement surgery is even more pronounced. Successful hip replacement surgery relies on accurate, comprehensive, and detailed surgical planning, among which choosing a suitable prosthesis brand and model is particularly important.

[0003] Existing solutions primarily determine the prosthesis pose and model by calculating geometric relationships from acquired key points. Patent CN114587583A provides a method for intraoperative prosthesis recommendation in a knee joint surgery navigation system. This method requires the surgeon to use a probe to select bone registration and positioning points. Then, the system calculates data based on the combination of parameters from these positioning points to obtain femoral prosthesis model parameters, femoral prosthesis varus / valgus angle, femoral prosthesis internal / external rotation angle, femoral prosthesis positioning parameters, and tibial prosthesis parameters. Although this method can recommend prosthesis parameters, the process is complex and requires the surgeon to manually select key points. This not only depends on the surgeon's experience and familiarity with the relevant software, but is also time-consuming and prone to introducing human error. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing prosthesis recommendation methods described in the background section above, and to provide a method, apparatus, device and storage medium for intelligent recommendation of prosthesis models in hip replacement surgery. This method, by introducing standard template prostheses and mapping functions, can adapt to the needs of clinicians in selecting different brands and series of prostheses.

[0005] This invention is achieved through the following technical solution: In a first aspect, this invention provides a method for intelligently recommending prosthesis models in hip replacement surgery, comprising the following steps:

[0006] Establish parameterized standard template prostheses, and after parameterizing prostheses of different brands and models, establish reversible mapping functions with the standard template prostheses to form a prosthesis mapping relationship library;

[0007] Using the prosthesis models in a large number of hip surgery planning schemes developed by experienced clinicians, the corresponding mapping functions are found through the prosthesis mapping relationship library. The prosthesis pose parameters are mapped to the pose parameters of the standard template prosthesis as training data, and the neural network is trained end-to-end for learning.

[0008] Input the patient's CT image and output the pose parameters corresponding to the standard template prosthesis;

[0009] After the doctor selects a specific brand and model of prosthesis, the system automatically selects the appropriate model and automatically corrects the pose parameters through a pre-established mapping function.

[0010] Furthermore, the establishment of parameterized standard template prostheses involves parameterizing prostheses of different brands and models and establishing reversible mapping functions between them and the standard template prostheses, forming a prosthesis mapping relationship library, including:

[0011] Based on research into different brands and series of implants, a parameterized standard template implant is defined;

[0012] Establish the relationship between specific prostheses and standard template prostheses to obtain the corresponding invertible mapping function. After parameterizing a specific model of prosthesis, it is then processed by an invertible mapping function. The pose parameters of this model can be mapped to the pose parameters after replacement with a standard template prosthesis. Similarly, the pose parameters of the standard template prosthesis can be mapped using an inverse mapping function. This will yield the pose parameters corresponding to that model of prosthesis;

[0013] After parameterizing prostheses of different brands and models, different reversible mapping functions are established with standard template prostheses to form a prosthesis mapping relationship library.

[0014] Furthermore, the backbone network structure of the neural network is a variant of U-Net. For the prosthetic parameters, it is recommended to use branch sub-networks, which consist of several 3*3*3 convolutional layers followed by 3 fully connected layers, called RegressionLayer. The feature point branches adopt the same structure as sub-networks, and the specific output parameters are determined by the task objective.

[0015] Furthermore, after the doctor selects a specific brand and model of prosthesis, the system automatically selects the appropriate model and automatically corrects the pose parameters through a pre-established mapping function, including:

[0016] After the neural network outputs the pose parameters corresponding to the standard template prosthesis, the doctor selects a specific brand and model of prosthesis. After the pose parameters are inversely mapped, the pose of the specific model of prosthesis is automatically corrected to obtain the extended and newly added model of prosthesis.

[0017] For the newly added prosthesis model, its parameterization yields a mapping function with the standard template.

[0018] In a second aspect, the present invention provides a device for intelligently recommending prosthesis models during hip replacement surgery, the device comprising:

[0019] A database module is established to create parameterized standard template prostheses. After parameterizing prostheses of different brands and models, reversible mapping functions are established between them and the standard template prostheses to form a prosthesis mapping relationship library.

[0020] The neural network training module is used to utilize the prosthesis models in a large number of hip surgery planning schemes developed by experienced clinicians. By looking up the corresponding mapping functions through the prosthesis mapping relationship library, the prosthesis pose parameters are mapped to the pose parameters of the standard template prosthesis as training data, and the neural network is trained end-to-end for learning.

[0021] The input / output module is used to input patient CT images and output the pose parameters corresponding to the standard template prosthesis.

[0022] The calibration module is used so that after the doctor selects a specific brand and model of prosthesis, the system automatically selects the appropriate model and automatically corrects the pose parameters through a pre-established mapping function.

[0023] Thirdly, the present invention provides a device for intelligently recommending prosthesis models in hip replacement surgery. The device includes: a processor, a memory, and computer program instructions stored in the memory and executable on the processor. The processor is used to execute the computer program instructions stored in the memory to implement the method for intelligently recommending prosthesis models in hip replacement surgery described above.

[0024] Fourthly, the present invention also provides a storage medium for intelligently recommending prosthesis models in hip replacement surgery, wherein the computer storage medium stores computer program instructions, and the computer program instructions, when executed by a processor, implement the above-described method for intelligently recommending prosthesis models in hip replacement surgery.

[0025] Compared with existing technologies, the method for intelligently recommending prosthesis models in hip replacement surgery provided by this invention has the following technical advantages:

[0026] 1. By using neural networks to learn from the prosthesis planning schemes created by experienced doctors, the system can output recommended prosthesis models and pose parameters end-to-end.

[0027] 2. Since doctors use different brands of prostheses in clinical practice, and the parameters of different prostheses vary, the method provided by this invention can adapt to the needs of doctors to choose different brands and series of prostheses by introducing a standard template prosthesis and a mapping function, and can add new brands and series without changing the main process;

[0028] 3. It resolves the relationship between individuality and commonality, enabling prostheses from different brands and series to be used to train neural networks, ensuring the simplicity of neural network training, and solving the problem of parameter errors caused by prostheses from different brands and series. Attached Figure Description

[0029] The features, advantages and technical effects of exemplary embodiments of the present invention will now be described with reference to the accompanying drawings.

[0030] Figure 1 This is a flowchart of a method for intelligently recommending prosthesis models in hip replacement surgery provided in an embodiment of the present invention;

[0031] Figure 2 This is a schematic diagram of the branch subnetwork structure in the neural network provided in the embodiment of the present invention;

[0032] Figure 3 This is a schematic diagram of a device for intelligently recommending prosthesis models in hip replacement surgery provided in an embodiment of the present invention;

[0033] Figure 4 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present invention. Detailed Implementation

[0034] The features and exemplary embodiments of various aspects of this disclosure will now be described in detail. To make the objectives, technical solutions, and advantages of this disclosure clearer, the disclosure will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to explain this disclosure only and not to limit it. For those skilled in the art, this disclosure can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this disclosure by illustrating examples.

[0035] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0036] To better understand the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0037] Figure 1 This is a flowchart of a method for intelligently recommending prosthesis models in hip replacement surgery provided in an embodiment of the present invention.

[0038] like Figure 1 As shown, this invention provides a method for intelligently recommending prosthesis models in hip replacement surgery, comprising the following steps:

[0039] S101, establish parameterized standard template prostheses, and after parameterizing prostheses of different brands and models, establish reversible mapping functions with the standard template prostheses to form a prosthesis mapping relationship library;

[0040] S102 utilizes the prosthesis models in a large number of hip surgery planning schemes formulated by experienced doctors, and searches for the corresponding mapping functions through the prosthesis mapping relationship library. The prosthesis pose parameters are mapped to the pose parameters corresponding to the standard template prosthesis as training data, and the end-to-end training neural network is used for learning.

[0041] S103, Input the patient's CT image, and output the pose parameters corresponding to the standard template prosthesis;

[0042] S104: After the doctor selects a specific brand and model of prosthesis, the system automatically selects the appropriate model and automatically corrects the pose parameters through a pre-established mapping function.

[0043] The prosthesis parameterization is divided into the model of acetabular-related prostheses (acetabular cup and liner) and femoral-related prostheses (ball head and femoral stem). Generally, the liner model needs to be referenced to the acetabular cup model, and the ball head model needs to be referenced to the femoral stem model. The acetabular cup model is mainly defined by the diameter of the acetabular cup, and the femoral stem model is mainly defined by the neck-shaft angle and the horizontal width of the neck. The neck-shaft angle is generally fixed within a certain range, and the horizontal width of the neck determines whether the femoral stem prosthesis is suitable for implantation in the patient. We define the problem of recommending prosthesis models as recommending the acetabular cup model and the femoral stem model, and output the recommended diameter of the acetabular cup and the horizontal width of the femoral stem neck. Since doctors use different brands of prostheses in clinical practice, and the parameters of prosthesis models of different brands are different, in order to ensure the simplicity of neural network training, solve the parameter errors caused by different brands and series of prostheses, and make the recommendation results applicable to different prosthesis brands and series, we need to consider these factors.

[0044] Optionally, the parameterized standard template prosthesis described in S101, after parameterizing prostheses of different brands and models, establishes reversible mapping functions with the standard template prosthesis to form a prosthesis mapping relationship library, including:

[0045] Based on research into different brands and series of implants, a parameterized standard template implant is defined;

[0046] Establish the relationship between specific prostheses and standard template prostheses to obtain the corresponding invertible mapping function. After parameterizing a specific model of prosthesis, it is then processed by an invertible mapping function. The pose parameters of this model can be mapped to the pose parameters after replacement with a standard template prosthesis. Similarly, the pose parameters of the standard template prosthesis can be mapped using an inverse mapping function. This will yield the pose parameters corresponding to that model of prosthesis;

[0047] After parameterizing prostheses of different brands and models, different reversible mapping functions are established with standard template prostheses to form a prosthesis mapping relationship library.

[0048] Optionally, the backbone network structure of the neural network described in S102 is a variant of U-Net, and branch subnetworks are recommended for the prosthetic parameters, with the structure as follows: Figure 2 As shown, it consists of several 3*3*3 convolutional layers followed by 3 fully connected layers, called the RegressionLayer. The feature point branch adopts the same structure as a sub-network, and the specific output parameters are determined by the task objective.

[0049] Alternatively, the prosthesis parameter recommendation and feature point branching can also use other network structures that can achieve the same or similar effects.

[0050] Optionally, after the doctor selects a specific brand and model of prosthesis as described in S104, the system automatically selects the appropriate model and automatically corrects the pose parameters through a pre-established mapping function, including:

[0051] After the neural network outputs the pose parameters corresponding to the standard template prosthesis, the doctor selects a specific brand and model of prosthesis. After the pose parameters are inversely mapped, the pose of the specific model of prosthesis is automatically corrected to obtain the extended and newly added model of prosthesis.

[0052] For the newly added prosthesis model, its parameterization yields a mapping function with the standard template.

[0053] Figure 3 This is a schematic diagram of a device for intelligently recommending prosthesis models in hip replacement surgery provided in an embodiment of the present invention.

[0054] like Figure 3 As shown, the present invention provides a device for intelligently recommending prosthesis models during hip replacement surgery, the device comprising:

[0055] Establish database module 301 to create parameterized standard template prostheses. After parameterizing prostheses of different brands and models, establish reversible mapping functions with the standard template prostheses to form a prosthesis mapping relationship library.

[0056] The neural network training module 302 is used to utilize the prosthesis models in a large number of hip surgery planning schemes formulated by experienced doctors, and to find the corresponding mapping functions through the prosthesis mapping relationship library to map the prosthesis pose parameters to the pose parameters corresponding to the standard template prosthesis as training data, and to train the neural network end-to-end for learning.

[0057] Input / output module 303 is used to input patient CT images and output the pose parameters corresponding to the standard template prosthesis.

[0058] The calibration module 304 is used to automatically select the appropriate model and automatically correct the pose parameters through a pre-established mapping function after the doctor selects a specific brand and model of prosthesis.

[0059] Figure 3 Each module / unit in the illustrated device has the ability to implement Figure 1 The functions of each step in the process and their corresponding technical effects are described in detail here for the sake of brevity.

[0060] like Figure 4 As shown, the present invention also provides a device for intelligently recommending prosthesis models in hip replacement surgery. The device includes: a processor 401, a memory 402, and computer program instructions stored in the memory 402 and executable on the processor 401. The processor 401 is used to execute the computer program instructions stored in the memory 402 to implement the method for intelligently recommending prosthesis models in hip replacement surgery described above.

[0061] Specifically, the processor 401 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the present invention.

[0062] Memory 402 may include mass storage for data or instructions. For example, and not as a limitation, memory may include hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these devices.

[0063] In one instance, memory 402 may include removable or non-removable (or fixed) media, or the memory may be non-volatile solid-state memory. The memory may be internal or external to the integrated gateway disaster recovery device.

[0064] In one instance, memory 402 may be read-only memory (ROM). In one instance, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0065] In one example, memory 402 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0066] The processor 401 reads and executes computer program instructions stored in the memory 402 to achieve... Figure 1 The methods / steps in the illustrated embodiments, and the corresponding technical effects they achieve, will not be elaborated upon here for the sake of brevity.

[0067] In one embodiment, the computing device may further include a communication interface 403 and a bus 404. For example... Figure 4 As shown, the processor 401, memory 402, and communication interface 403 are connected through bus 404 and complete communication with each other.

[0068] The communication interface 403 is mainly used to realize communication between various modules, devices, units and / or equipment in this invention.

[0069] Bus 404 includes hardware, software, or both, that couples components of an online data flow metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, the bus may include one or more buses. Although specific buses are described and illustrated in this invention, this disclosure contemplates any suitable bus or interconnect.

[0070] Furthermore, in conjunction with the method for intelligently recommending prosthesis models in hip replacement surgery described in the above embodiments, this invention also provides a computer storage medium for implementation. The computer storage medium stores computer program instructions, which, when executed by a processor, implement the aforementioned method for intelligently recommending prosthesis models in hip replacement surgery.

[0071] The computer storage medium provided in this invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0072] Compared with existing technologies, the method for intelligently recommending prosthesis models in hip replacement surgery provided by this invention has the following technical advantages:

[0073] 1. By using neural networks to learn from the prosthesis planning schemes created by experienced doctors, the system can output recommended prosthesis models and pose parameters end-to-end.

[0074] 2. Since doctors use different brands of prostheses in clinical practice, and the parameters of different prostheses vary, the method provided by this invention can adapt to the needs of doctors to choose different brands and series of prostheses by introducing a standard template prosthesis and a mapping function, and can add new brands and series without changing the main process;

[0075] 3. It resolves the relationship between individuality and commonality, enabling prostheses from different brands and series to be used to train neural networks, ensuring the simplicity of neural network training, and solving the problem of parameter errors caused by prostheses from different brands and series.

[0076] It should be clarified that this disclosure is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this disclosure is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this disclosure.

[0077] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this disclosure are programs or code segments used to perform the required tasks. Those skilled in the art can write computer program code for performing the operations of this invention in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. Furthermore, the program or code segment can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. A machine-readable medium can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc.

[0078] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0079] The above description is merely a specific embodiment of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this disclosure is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this disclosure, and these modifications or substitutions should all be covered within the protection scope of this disclosure.

Claims

1. A method for intelligently recommending prosthesis parameters in hip replacement surgery, characterized in that, Includes the following steps: S101, establish parameterized standard template prostheses, and after parameterizing prostheses of different brands and models, establish reversible mapping functions with the standard template prostheses to form a prosthesis mapping relationship library; S102 utilizes the prosthesis models in a large number of hip surgery planning schemes formulated by experienced doctors, and searches for the corresponding invertible mapping functions through the prosthesis mapping relationship library to map the prosthesis pose parameters to the pose parameters corresponding to the standard template prosthesis. These parameters are then used as training data to train the neural network end-to-end for learning. S103, Input the patient's CT image, and output the pose parameters corresponding to the standard template prosthesis; S104: After the doctor selects a specific brand of implant, the system automatically selects the appropriate model and automatically corrects the pose parameters through a pre-established reversible mapping function. The parameterized standard template prosthesis described in S101 involves establishing reversible mapping functions between parameterized prostheses of different brands and models and the standard template prosthesis, forming a prosthesis mapping relationship library, including: Based on research on different brands and models of implants, a parameterized standard template implant was established; A connection is established between a specific model prosthesis and a standard template prosthesis, yielding the corresponding reversible mapping function f(·). After parameterizing the specific model prosthesis, the pose parameters under that specific model are mapped to the pose parameters after replacement with the standard template prosthesis via the reversible mapping function f(·). Similarly, the pose parameters of the standard template prosthesis are mapped via the inverse mapping function f(·). -1 (·) will yield the pose parameters corresponding to that specific model of prosthesis; After parameterizing prostheses of different brands and models, different reversible mapping functions are established with standard template prostheses to form a prosthesis mapping relationship library; As described in S104, after the doctor selects a specific brand of prosthesis, the system automatically selects the appropriate model and automatically corrects the pose parameters through a pre-established reversible mapping function, including: After the neural network outputs the pose parameters corresponding to the standard template prosthesis, the doctor selects a specific brand of prosthesis, and the pose of the specific model of prosthesis is automatically corrected after the pose parameters are inversely mapped to obtain the extended and newly added model of prosthesis. For the newly added prosthesis model, parameterization yields a reversible mapping function with the standard template prosthesis.

2. The method for intelligently recommending prosthesis parameters in hip replacement surgery according to claim 1, characterized in that, The backbone network structure of the neural network described in S102 is a variant of U-Net. It uses branch subnetworks for prosthetic parameters, consisting of several 3*3*3 convolutional layers followed by 3 fully connected layers. The feature point branch uses several 3*3*3 convolutional layers followed by 3 fully connected layers as subnetworks.

3. A device for intelligently recommending prosthesis parameters in hip replacement surgery, characterized in that, include: Establish database module 301 to create parameterized standard template prostheses. After parameterizing prostheses of different brands and models, establish reversible mapping functions with the standard template prostheses to form a prosthesis mapping relationship library. The neural network training module 302 is used to utilize the prosthesis models in a large number of hip surgery planning schemes formulated by experienced doctors, and to find the corresponding invertible mapping functions through the prosthesis mapping relationship library to map the prosthesis pose parameters to the pose parameters corresponding to the standard template prosthesis as training data for end-to-end training of the neural network. Input / output module 303 is used to input patient CT images and output the pose parameters corresponding to the standard template prosthesis. The calibration module 304 is used to automatically select the appropriate model and automatically correct the pose parameters through a pre-established reversible mapping function after the doctor selects a specific brand of prosthesis. The database module 301 establishes parameterized standard template prostheses. After parameterizing prostheses of different brands and models, reversible mapping functions are established between these parameterized prostheses and the standard template prostheses to form a prosthesis mapping relationship library, including: Based on research on different brands and models of implants, a parameterized standard template implant was established; A connection is established between a specific model prosthesis and a standard template prosthesis, yielding the corresponding reversible mapping function f(·). After parameterizing the specific model prosthesis, the pose parameters under that specific model are mapped to the pose parameters after replacement with the standard template prosthesis via the reversible mapping function f(·). Similarly, the pose parameters of the standard template prosthesis are mapped via the inverse mapping function f(·). -1 (·) will yield the pose parameters corresponding to that specific model of prosthesis; After parameterizing prostheses of different brands and models, different reversible mapping functions are established with standard template prostheses to form a prosthesis mapping relationship library; After the doctor selects a specific brand of prosthesis, the calibration module 304 automatically selects the appropriate model and automatically corrects the pose parameters through a pre-established reversible mapping function, including: After the neural network outputs the pose parameters corresponding to the standard template prosthesis, the doctor selects a specific brand of prosthesis, and the pose of the specific model of prosthesis is automatically corrected after the pose parameters are inversely mapped to obtain the extended and newly added model of prosthesis. For the newly added prosthesis model, parameterization yields a reversible mapping function with the standard template prosthesis.

4. A device, characterized in that, The device includes: a processor, a memory, and computer program instructions stored in the memory and executable on the processor, wherein the processor is configured to execute the computer program instructions stored in the memory to implement the method for intelligently recommending prosthesis parameters in hip replacement surgery according to any one of claims 1 to 2.

5. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed by a processor, implement the method for intelligently recommending prosthesis parameters in any one of claims 1 to 2 hip replacement surgery.

Images