Ankle joint replacement preoperative planning method, device and equipment

Abstract

The invention provides a preoperative planning method, device and equipment for ankle joint replacement and a computer readable storage medium. The preoperative planning method for ankle joint replacement is applied to an orthopedic surgery robot system, and the preoperative planning method for ankle joint replacement comprises the following steps: acquiring an ankle joint CT image of a patient; carrying out segmentation and three-dimensional reconstruction on the CT image of the ankle joint to obtain an ankle joint three-dimensional model; on the basis of the three-dimensional model of the ankle joint, key parameters of the ankle joint are determined, and an ankle joint prosthesis model is determined on the basis of the key parameters of the ankle joint; determining a preoperative planning method for ankle joint replacement based on the ankle joint key parameters and the ankle joint prosthesis model; wherein the preoperative planning scheme comprises a placement position and a placement angle of the ankle joint prosthesis model.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of preoperative planning of foot and ankle replacement, and particularly relates to a preoperative planning method, device and equipment of foot and ankle replacement and a computer readable storage medium. BACKGROUND

[0002] With the rapid development of orthopedic surgery robot related technology, more and more orthopedic surgery robots are involved in orthopedic surgery, which greatly improves the surgical efficiency and surgical effect of orthopedic surgery. At present, orthopedic surgery robots are mainly applied in hip and knee joint related operations, while foot and ankle joint related operations often need to be completed by orthopedic surgeons alone, so that the surgical efficiency and surgical effect of foot and ankle joint surgery still need to be improved, especially in complex operations such as foot and ankle replacement. Without using an orthopedic surgery robot system, in order to achieve satisfactory surgical results, the surgeon often needs to spend a lot of time and effort.

[0003] Therefore, how to more accurately use the orthopedic surgery robot system and carry out the corresponding preoperative planning scheme so that the surgeon can accurately and efficiently complete the foot and ankle replacement surgery with the assistance of the orthopedic surgery robot system is a technical problem that those skilled in the art need to solve. SUMMARY

[0004] The embodiments of the present application provide a preoperative planning method, device, equipment and computer readable storage medium for foot and ankle replacement, which can more accurately determine the preoperative planning scheme and help the surgeon accurately and efficiently complete the foot and ankle replacement surgery with the assistance of the orthopedic surgery robot system.

[0005] In a first aspect, the embodiments of the present application provide a preoperative planning method for foot and ankle replacement, which is applied to an orthopedic surgery robot system, and the preoperative planning method comprises:

[0006] Obtaining a CT image of the foot and ankle joint of a patient;

[0007] Segmenting and three-dimensionally reconstructing the CT image of the foot and ankle joint to obtain a three-dimensional model of the foot and ankle joint;

[0008] Determining key parameters of the foot and ankle joint based on the three-dimensional model of the foot and ankle joint, and determining a foot and ankle joint prosthesis model based on the key parameters of the foot and ankle joint;

[0009] Generating a preoperative planning scheme for foot and ankle replacement based on the key parameters of the foot and ankle joint and the foot and ankle joint prosthesis model; wherein the preoperative planning scheme comprises a target placement position and a target placement angle of the foot and ankle joint prosthesis model.

[0010] Optionally, the preoperative planning method comprises segmenting the CT image of the ankle joint according to the following steps:

[0011] The reference skeletal structure CT image and the background label image are extracted from the CT image of the ankle joint by multiple threshold segmentation.

[0012] The seed image containing the skeletal structure and the corresponding label value is generated from the reference skeletal structure CT image and the background label image by threshold segmentation, connected component analysis, background cropping operation and image addition operation in sequence.

[0013] Optionally, the preoperative planning method comprises three-dimensional reconstruction of the ankle joint according to the following steps:

[0014] The noise-containing label image with the same parameters as the CT image of the ankle joint is obtained from the reference skeletal structure image and the seed image, and the noise-containing label image is denoised and filled respectively to obtain the label image containing the corresponding label value of different skeletal structures and the model of each skeletal structure.

[0015] Optionally, the preoperative planning method comprises segmenting the CT image of the ankle joint according to the following steps:

[0016] Based on the CT image of the ankle joint and the pre-trained target neural network model, an image segmentation result is obtained; the target neural network model comprises an image encoder, a prompt encoder, a task decoder, a visual prompt generation module and a text prompt generation module; wherein,

[0017] The output of the image encoder and the output of the prompt encoder are fused as the input of the task decoder; the visual prompt generation module is used to locate the CT image of the ankle joint to obtain the bounding box coordinates containing the ankle joint in the CT image; the text prompt generation module is used to generate the positioning description information of the ankle joint; and the positioning description information and the bounding box coordinates are fused as the input of the prompt encoder.

[0018] Optionally, the key parameters of the ankle joint include at least one of the following parameters:

[0019] tibial dome angle, ankle hole width, distal tibial torsion angle, talus dome curvature radius, talus neck angle, talus offset rate, talus trochlear coverage rate, calcaneal inclination angle, subtalar joint adaptation angle, calcaneal width index, ankle force line angle, talus inclination angle, tibiotalar joint gap asymmetry, calcaneal axial force line angle, tibial osteotomy safety thickness, talus osteotomy bone reserve, calcaneal osteotomy risk area.

[0020] Optionally, the preoperative planning scheme of the ankle joint replacement is generated based on the ankle joint key parameters and the ankle joint prosthesis model, and the preoperative planning scheme includes:

[0021] The ankle joint prosthesis model is implanted into the ankle joint three-dimensional model according to the initial placement position and the initial placement angle matched with the ankle joint key parameters;

[0022] First motion simulation is performed based on the ankle joint three-dimensional model in which the ankle joint prosthesis model is implanted, and first motion simulation results are obtained;

[0023] The initial placement position and the initial placement angle are adjusted according to the first motion simulation results, and target placement position and target placement angle of the ankle joint prosthesis model are obtained.

[0024] Optionally, the preoperative planning method further includes:

[0025] Based on the matching relationship between the ankle joint three-dimensional model and the ankle joint prosthesis model, simulated osteotomy is performed to obtain a postoperative bone simulation model;

[0026] Second motion simulation is performed on the postoperative bone simulation model, and second motion simulation results are obtained;

[0027] According to the second motion simulation results, the matching of the ankle joint prosthesis model is verified.

[0028] In a second aspect, an embodiment of the present application provides a preoperative planning device for ankle joint replacement, which is applied to an orthopedic surgery robot system, and the preoperative planning device includes:

[0029] An image acquisition module is configured to acquire CT images of the ankle joint of a patient;

[0030] A three-dimensional reconstruction module is configured to segment and reconstruct the CT images of the ankle joint in three dimensions to obtain an ankle joint three-dimensional model;

[0031] A determination module is configured to determine ankle joint key parameters based on the ankle joint three-dimensional model, and determine an ankle joint prosthesis model based on the ankle joint key parameters;

[0032] A generation module is configured to generate a preoperative planning method for ankle joint replacement based on the ankle joint key parameters and the ankle joint prosthesis model, and the preoperative planning scheme includes placement position and placement angle of the ankle joint prosthesis model.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory storing computer program instructions;

[0034] The processor executes the computer program instructions to implement a preoperative planning method for foot and ankle joint replacement.

[0035] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement a preoperative planning method for foot and ankle joint replacement.

[0036] The preoperative planning method, apparatus, device, and computer-readable storage medium for foot and ankle joint replacement according to the embodiments of this application can more accurately determine the preoperative planning scheme and help doctors to accurately and efficiently complete foot and ankle joint replacement surgery with the assistance of orthopedic surgical robot system.

[0037] The preoperative planning methods for this foot and ankle replacement surgery include:

[0038] Obtain CT images of the patient's foot and ankle joints;

[0039] The CT images of the foot and ankle joint are segmented and reconstructed in three dimensions to obtain a three-dimensional model of the foot and ankle joint.

[0040] Based on the three-dimensional model of the foot and ankle joint, key parameters of the foot and ankle joint are determined, and a prosthesis model of the foot and ankle joint is determined based on the key parameters of the foot and ankle joint.

[0041] Based on the key parameters of the foot and ankle joint and the foot and ankle joint prosthesis model, a preoperative planning scheme for foot and ankle joint replacement is generated; wherein, the preoperative planning scheme includes the target placement position and target placement angle of the foot and ankle joint prosthesis model. Attached Figure Description

[0042] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating a preoperative planning method for foot and ankle joint replacement provided in one embodiment of this application;

[0044] Figure 2 This is a schematic diagram of the architecture of a target neural network model provided in one embodiment of this application;

[0045] Figure 3 This is a schematic diagram of the preoperative planning device for foot and ankle joint replacement provided in one embodiment of this application;

[0046] Figure 4FIG. 1 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purposes, technical solutions and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, but not to limit the present application. The present application can be implemented without some of the specific details by those skilled in the art. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0048] It should be noted that, in this document, relational terms such as first and second and the like can only be used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the elements defined by the statement "comprising" do not exclude the presence of additional identical elements in the process, method, article or device including the elements.

[0049] In order to solve the problems in the prior art, the present application provides a preoperative planning method, device and equipment for ankle joint replacement and a computer readable storage medium. First, the preoperative planning method for ankle joint replacement provided by the present application is introduced.

[0050] Figure 1 FIG. 1 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. Figure 1 As shown in FIG. 1, the preoperative planning method includes:

[0051] S101, acquiring a CT image of an ankle joint of a patient.

[0052] S102, segmenting and three-dimensionally reconstructing the CT image of the ankle joint to obtain a three-dimensional model of the ankle joint.

[0053] S103, determining a key parameter of the ankle joint based on the three-dimensional model of the ankle joint, and determining a prosthesis model of the ankle joint based on the key parameter of the ankle joint.

[0054] S104, generating a preoperative planning scheme for ankle joint replacement based on the key parameter of the ankle joint and the prosthesis model of the ankle joint; wherein the preoperative planning scheme includes a target placement position and a target placement angle of the prosthesis model of the ankle joint.

[0055] For S101 and S102, the acquired CT image of the ankle joint of the patient can be thin layer axial scanning data of 0.5-0.625mm, which can be used for multiplanar reconstruction in three-dimensional reconstruction, including standard coronal, sagittal and oblique coronal for subtalar joint, so as to achieve better three-dimensional reconstruction effect of ankle joint.

[0056] In some embodiments, the CT image of the ankle joint can be segmented by the following steps:

[0057] A1: extracting a reference bone structure CT image and a background label image from the CT image of the ankle joint by multiple threshold segmentation.

[0058] A2: sequentially generating a seed image containing bone structure and corresponding label value according to the reference bone structure CT image and the background label image by threshold segmentation, connected component analysis, background cropping operation and image addition operation.

[0059] In this way, by multiple threshold segmentation, connected component analysis, background cropping operation and image addition operation, invalid information in the CT image can be removed to obtain a seed image for subsequent three-dimensional reconstruction; the multiple threshold segmentation can be a custom threshold segmentation set according to actual needs, which is used to ensure that the regions of each bone structure are not cross-stuck; the image addition operation can fill other bones outside the bone of interest as background, which can make the subsequent region growing faster and avoid errors.

[0060] Further, after generating the seed image containing bone structure and corresponding label value, the ankle joint can be three-dimensionally reconstructed according to the following steps:

[0061] A3: obtaining a noisy label image with the same parameters as the CT image of the ankle joint according to the reference bone structure image and the seed image.

[0062] A4: denoising and filling the noisy label image respectively to obtain a label image containing corresponding label values of different bone structures and a model of each bone structure.

[0063] In actual applications, in addition to using the image segmentation algorithm containing threshold segmentation described above to segment and three-dimensionally reconstruct the CT image of the ankle joint, the CT image of the ankle joint can also be segmented through an image segmentation model, and corresponding three-dimensionally reconstructed processing is performed after segmentation.

[0064] In some embodiments, the CT image of the ankle joint can be segmented according to the following steps:

[0065] Based on the CT image of the ankle joint and a pre-trained target neural network model, an image segmentation result is obtained; the target neural network model comprises an image encoder, a prompt encoder, a task decoder, a visual prompt generation module and a text prompt generation module; wherein,

[0066] The output of the image encoder and the output of the prompt encoder are fused and used as the input of the task decoder; the visual prompt generation module is used to locate the CT image of the ankle joint according to the input CT image to obtain the bounding box coordinates containing the ankle joint in the CT image; the text prompt generation module is used to generate the positioning description information of the ankle joint; and the positioning description information and the bounding box coordinates are fused and used as the input of the prompt encoder.

[0067] Exemplarily, Figure 2 is a schematic diagram of the architecture of the target neural network model provided in an embodiment of the present application. Figure 2 In the above method, on the one hand, the CT image of the ankle joint to be segmented can be input into the image encoder for encoding, and the corresponding encoding result is input into the task decoder after encoding is completed; on the other hand, the CT image of the ankle joint to be segmented can also be input into the visual prompt generation module and the text prompt generation module respectively, so as to generate the visual prompt (i.e. the bounding box coordinates containing the ankle joint in the CT image) and the text prompt (i.e. the positioning description information of the ankle joint) respectively, and the visual prompt and the text prompt can be fused and input into the prompt encoder for encoding after fusion, and the corresponding encoding result is input into the task decoder after encoding is completed, and the task decoder executes image segmentation processing according to the input content to obtain the final segmentation result.

[0068] In some embodiments, the image encoder can be an image encoder in a SAM model, which can extract image features based on a Vision Transformer (ViT); the prompt encoder can be a prompt encoder in the SAM model, which can convert the visual prompt and the text prompt into a 256-dimensional vector; and the task decoder can be a mask decoder in the SAM model, which can generate a high-quality segmentation mask and evaluate the confidence according to the output results of the prompt encoder and the image encoder.

[0069] In some embodiments, the visual prompt generation module can include a CLIP model that can process the input CT image of the ankle joint to be segmented and a pre-set text prompt (e.g., ankle joint). When generating a visual prompt, a saliency map containing the ankle region can be generated using ScoreCAM, and then a rough mask can be obtained by post-processing using a conditional random field (CRF), so that the bounding box coordinates of the ankle joint can be extracted.

[0070] In some embodiments, the text prompt generation module can include a VQA model and an LLM model, where the VQA model is used to answer pre-set positioning questions (e.g., where is the ankle joint in the CT?), to obtain positioning description information of the ankle joint; and the LLM model is used to generate general feature descriptions of the ankle joint (e.g., ankle joint in CT image), to enrich the semantic features input to the prompt encoder, thereby helping the task decoder to better perform image segmentation.

[0071] In some embodiments, the training of the target neural network model can be divided into two stages. In the first stage, a small amount of labeled data (10% or 20% of the total amount of sample data) can be used to train the visual prompt generation module and the text prompt generation module, so that the two prompt generation modules can generate high-quality prompt information. The loss function of the first stage can be FocalLoss and Dice Loss. In the second stage, unlabeled data can be used for training. For the same image, multiple candidate segmentation maps (e.g., 4 or 6 candidate segmentation maps) can be generated by threshold segmentation, and the IoU score of the candidate segmentation map and the real mask can be used to simulate human evaluation, so that manual data labeling can be avoided. The loss function of the second stage can be a DPO loss function to reward high-scoring candidates (e.g., increase the weight of high-scoring samples) and punish low-scoring candidates (e.g., reduce the weight of low-scoring samples, such as setting the weight to 40% or 50% of the weight of high-scoring samples), to optimize the model preference and output high-quality image segmentation results.

[0072] When the IoU score of the candidate segmentation map and the real mask is used to simulate human evaluation, the score can be scored according to a pre-set scoring rule. If the IoU is less than 0.35, the score is 1; if the IoU is greater than 0.35 and less than 0.5, the score is 2; if the IoU is greater than 0.5 and less than 0.75, the score is 3; and if the IoU is greater than 0.5 and less than 0.75, the score is 3.

[0073] For S103 and S104, after the three-dimensional model of the foot and ankle joint is constructed, the corresponding foot and ankle joint key parameters can be identified from the three-dimensional model of the foot and ankle joint through a pre-configured foot and ankle joint key parameter identification algorithm. Further, after the foot and ankle joint key parameters are identified, a foot and ankle joint prosthesis model that matches the foot and ankle joint key parameters of the patient can be screened from the prosthesis model library according to a pre-set foot and ankle joint prosthesis model matching rule.

[0074] In some embodiments, the foot and ankle joint key parameters can include at least one of the following parameters:

[0075] tibial dome angle, ankle hole width, distal tibial torsion angle, talus dome curvature radius, talus neck stem angle, talus offset rate, talus trochlear coverage rate, calcaneal inclination angle, subtalar joint adaptation angle, calcaneal width index, ankle joint force line angle, talus inclination angle, tibiotalar joint gap asymmetry, calcaneal axis force line angle, tibial osteotomy safety thickness, talus osteotomy bone reserve, calcaneal osteotomy risk area.

[0076] In some embodiments, generating a preoperative planning scheme for foot and ankle joint replacement based on the foot and ankle joint key parameters and the foot and ankle joint prosthesis model can be performed by the following steps:

[0077] B1: implant the foot and ankle joint prosthesis model into the three-dimensional model of the foot and ankle joint according to the initial placement position and the initial placement angle matched with the foot and ankle joint key parameters.

[0078] B2: perform first motion simulation based on the three-dimensional model of the foot and ankle joint with the implanted foot and ankle joint prosthesis model to obtain first motion simulation results.

[0079] The first simulation motion can be a pre-configured motion for evaluating the placement effect of the foot and ankle joint prosthesis model, which can include dorsiflexion, plantar flexion, inversion, and eversion.

[0080] B3: adjust the initial placement position and the initial placement angle according to the first motion simulation results to obtain a target placement position and a target placement angle of the foot and ankle joint prosthesis model.

[0081] Here, in the case where the simulation motion results do not meet the pre-set motion result requirements, adaptive adjustment can be performed according to pre-configured placement position and angle adjustment rules, and the first motion simulation is continued using the adaptively adjusted foot and ankle joint prosthesis model until the first motion simulation results meet the motion result requirements.

[0082] In some embodiments, the foot and ankle joint prosthesis model can also be verified for matching by the following steps:

[0083] C1: performing simulated osteotomy based on the matching relationship between the ankle joint three-dimensional model and the ankle joint prosthesis model to obtain a postoperative simulated model of the bone.

[0084] C2: performing second motion simulation on the postoperative simulated model of the bone to obtain a second motion simulation result.

[0085] C3: performing matching verification on the ankle joint prosthesis model according to the second motion simulation result.

[0086] Here, the second simulation motion is used to evaluate the expected postoperative effect after using the corresponding prosthesis, so that it can be judged from the second motion simulation result whether the currently used ankle joint prosthesis model is the most matched.

[0087] Among them, the second simulation motion can be a motion for evaluating the postoperative effect, which can include at least one of dorsiflexion, plantar flexion, inversion, eversion, walking gait, heel raising motion, squatting, single foot standing balance test, heel walking, toe walking, rotation motion (internal rotation or external rotation).

[0088] In some embodiments, the first motion simulation and the second motion simulation can be used jointly, such as first using the first motion simulation to find a plurality of ankle joint prosthesis models and their most suitable placement positions and angles from the prosthesis model library, and then determining the ankle joint prosthesis model with the best postoperative expected effect from the plurality of ankle joint prosthesis models through the second motion simulation, so that the best ankle joint prosthesis can be matched for the patient before the operation, so that the most matched ankle joint prosthesis can be used for the patient in the subsequent actual operation process. Or, the ankle joint prosthesis model with the best postoperative expected effect can be found from the prosthesis model library through the second motion simulation first, and then the most matched placement position and angle of the ankle joint prosthesis model can be found through the first motion simulation.

[0089] Figure 3 is a structural schematic diagram of a preoperative planning device for ankle joint replacement provided by an embodiment of the present application. The preoperative planning device is applied to an orthopedic surgery robot system, and the preoperative planning device comprises:

[0090] An image acquisition module 301 is configured to acquire an ankle joint CT image of a patient.

[0091] A three-dimensional reconstruction module 302 is configured to segment and three-dimensionally reconstruct the CT image of the ankle joint to obtain an ankle joint three-dimensional model.

[0092] A determination module 303 is configured to determine ankle joint key parameters based on the ankle joint three-dimensional model, and determine an ankle joint prosthesis model based on the ankle joint key parameters.

[0093] The generating module 304 is configured to generate a preoperative planning method for the ankle joint replacement based on the ankle joint key parameters and the ankle joint prosthesis model, wherein the preoperative planning method includes a placement position and a placement angle of the ankle joint prosthesis model.

[0094] Figure 4 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown.

[0095] The electronic device can include a processor 401 and a memory 402 storing computer program instructions.

[0096] Specifically, the processor 401 can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0097] The memory 402 can include a mass storage for data or instructions. By way of example and not limitation, the memory 402 can include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 402 can include removable or non-removable (or fixed) media. Where appropriate, the memory 402 can be internal or external to the electronic device. In a particular embodiment, the memory 302 can be a non-volatile solid-state memory.

[0098] In one embodiment, the memory 402 can be a read-only memory (ROM). In one embodiment, the ROM can be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0099] The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the preoperative planning methods for the ankle joint replacement in the above embodiments.

[0100] In one example, the electronic device can further include a communication interface 403 and a bus 410. As shown, the processor 401, the memory 402, and the communication interface 403 are connected through the bus 410 and complete communication among each other. Figure 4

[0101] ​The communication interface 403 is mainly configured to implement the communication between the modules, devices, units and / or equipment in the embodiments of the present application.

[0102] Bus 410 includes hardware, software, or both, to couple electronic devices to each other in a manner that allows information to be passed between or among them. The bus can include, for example, an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand (IB) interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel 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 another suitable bus or a combination of two or more of these. Where appropriate, bus 310 can include one or more buses. Although the present application is described and illustrated with a particular bus, it is not intended to be limited to this arrangement.

[0103] In addition, in combination with the preoperative planning method for ankle joint replacement in the above embodiments, the present application can provide a computer readable storage medium to implement. The computer readable storage medium has computer program instructions stored thereon; the computer program instructions are executed by the processor to implement any one of the preoperative planning methods for ankle joint replacement in the above embodiments.

[0104] It should be understood that the present application is not limited to the particular configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of known methods are omitted. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application 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 between steps, after understanding the spirit of the present application.

[0105] The functions of the modules shown in the structural block diagram described above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. The "machine-readable medium" can include any medium that can store or transfer information. Examples of the machine-readable medium include an electronic circuit, a semiconductor memory device, a ROM, a flash memory, an erasable ROM (EROM), a floppy diskette, a CD-ROM, an optical disk, a hard disk, a fiber optic medium, a radio frequency (RF) link, and the like. The code segments can be downloaded via a computer network, such as the Internet, an intranet, and the like.

[0106] It is also noted that the examples mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the steps mentioned above, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0107] The above-described aspects and implementations of the present application can be embodied in a specific way shown in the following examples. It will be appreciated that those skilled in the art will be able to imagine many modifications and changes without departing from the scope of the present application. Therefore, the embodiments described herein are intended to be illustrative only and the scope of the present application is to be given by claims.

[0108] The above merely describes a specific implementation of the present application. Those skilled in the art can clearly understand the specific working processes of the system, modules and units described above for the convenience and brevity of description, and can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited to this, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A preoperative planning method for ankle arthroplasty, characterized in that, The preoperative planning method is applied to an orthopedic surgery robot system, and the preoperative planning method comprises: Obtaining a CT image of an ankle joint of a patient; Segmenting and three-dimensionally reconstructing the CT image of the ankle joint to obtain a three-dimensional model of the ankle joint; Based on the three-dimensional model of the ankle joint, determining key parameters of the ankle joint, and based on the key parameters of the ankle joint, determining a prosthesis model of the ankle joint; Based on the key parameters of the ankle joint and the prosthesis model of the ankle joint, generating a preoperative planning scheme for ankle joint replacement; wherein the preoperative planning scheme comprises a target placement position and a target placement angle of the prosthesis model of the ankle joint.

2. The preoperative planning method of ankle joint replacement according to claim 1, characterized in that, The preoperative planning method comprises segmenting the CT image of the ankle joint according to the following steps: Based on the CT image of the ankle joint and a pre-trained target neural network model, an image segmentation result is obtained; the target neural network model comprises an image encoder, a prompt encoder, a task decoder, a visual prompt generation module, and a text prompt generation module; wherein The output of the image encoder and the output of the prompt encoder are fused as the input of the task decoder; the visual prompt generation module is used to locate the CT image of the ankle joint according to the input to obtain a bounding box coordinate containing the ankle joint in the CT image; the text prompt generation module is used to generate positioning description information of the ankle joint; and the positioning description information and the bounding box coordinate are fused as the input of the prompt encoder.

3. The preoperative planning method of ankle joint replacement according to claim 1, characterized in that, The preoperative planning method comprises segmenting the CT image of the ankle joint according to the following steps: By multiple threshold segmentation, a reference bone structure CT image and a background label image are extracted from the CT image of the ankle joint; According to the reference bone structure CT image and the background label image, a seed image containing bone structure and corresponding label value is generated by sequentially performing threshold segmentation, connected component analysis, background cropping operation and image addition operation.

4. The preoperative planning method of ankle joint replacement according to claim 3, characterized in that, The preoperative planning method comprises three-dimensionally reconstructing the ankle joint according to the following steps: According to the reference bone structure image and the seed image, a noisy label image with the same parameters as the CT image of the ankle joint is obtained, and the noisy label image is denoised and filled respectively to obtain a label image containing different bone structure corresponding label values and a model of each bone structure.

5. The preoperative planning method of ankle joint replacement according to any one of claims 1 to 4, characterized in that, The key parameters of the ankle joint include at least one of the following parameters: tibial dome angle, ankle hole width, tibial distal torsion angle, talus dome curvature radius, talus neck stem angle, talus offset rate, talus trochlear coverage rate, calcaneal inclination angle, subtalar joint fitting angle, calcaneal width index, ankle joint force line angle, talus inclination angle, tibiotalar joint gap asymmetry, calcaneal axial force line angle, tibial osteotomy safety thickness, talus osteotomy bone reserve, calcaneal osteotomy risk area.

6. The preoperative planning method of ankle joint replacement according to any one of claims 1 to 4, characterized in that, The preoperative planning method comprises three-dimensionally reconstructing the ankle joint according to the following steps: According to the initial placement position and the initial placement angle matched with the key parameters of the ankle joint, the prosthesis model of the ankle joint is implanted into the three-dimensional model of the ankle joint; The first motion simulation is performed based on the foot and ankle joint three-dimensional model and the foot and ankle joint prosthesis model, and a first motion simulation result is obtained; The initial placement position and the initial placement angle are adjusted according to the first motion simulation result, and a target placement position and a target placement angle of the foot and ankle joint prosthesis model are obtained.

7. The preoperative planning method of ankle joint replacement according to any one of claims 1 to 4, characterized in that, The preoperative planning method further comprises: Based on the matching relationship between the foot and ankle joint three-dimensional model and the foot and ankle joint prosthesis model, a simulated osteotomy is performed to obtain a postoperative bone simulation model; A second motion simulation is performed on the postoperative bone simulation model, and a second motion simulation result is obtained; According to the second motion simulation result, the matching of the foot and ankle joint prosthesis model is verified.

8. A preoperative planning device for ankle arthroplasty, characterized in that The preoperative planning device is applied to an orthopedic surgery robot system, and the preoperative planning device comprises: An image acquisition module is configured to acquire a CT image of a patient's foot and ankle joint; A three-dimensional reconstruction module is configured to segment and three-dimensionally reconstruct the CT image of the foot and ankle joint to obtain a foot and ankle joint three-dimensional model; A determination module is configured to determine foot and ankle joint key parameters based on the foot and ankle joint three-dimensional model, and to determine a foot and ankle joint prosthesis model based on the foot and ankle joint key parameters; A generation module is configured to generate a preoperative planning method for foot and ankle joint replacement based on the foot and ankle joint key parameters and the foot and ankle joint prosthesis model; wherein the preoperative planning method comprises a placement position and a placement angle of the foot and ankle joint prosthesis model.

9. An electronic device, comprising: The electronic device comprises a processor and a memory storing computer program instructions; The processor executes the computer program instructions to implement the preoperative planning method for foot and ankle joint replacement according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer program instructions, and the computer program instructions are executed by the processor to implement the preoperative planning method for foot and ankle joint replacement according to any one of claims 1-7.

Images