Intelligent diagnosis method for ankle joint impact syndrome based on multi-modal data fusion

Abstract

The invention provides an intelligent diagnosis method, device and equipment for an ankle joint impact syndrome based on multi-modal data fusion and a computer readable storage medium. The intelligent diagnosis method for the ankle joint impact syndrome based on multi-modal data fusion comprises the following steps: acquiring at least one ankle orthopedic image and diagnosis prompt information of a patient; wherein the diagnosis prompt information comprises medical history information, symptom information and physical examination information of the patient; inputting the ankle orthopedic image and the diagnosis prompt information into a pre-trained ankle joint impingement syndrome diagnosis model to obtain an ankle joint impingement syndrome diagnosis result output by the ankle joint impingement syndrome diagnosis model; wherein the ankle joint impingement syndrome diagnosis model is used for extracting ankle orthopedic image features and text features and performing ankle joint impingement syndrome diagnosis according to the fused features, and the ankle joint impingement syndrome diagnosis result comprises diagnosis results under a plurality of diagnosis dimensions.

Description

Technical Field

[0001] This application belongs to the field of foot and ankle joint impingement syndrome, and particularly relates to an intelligent diagnostic method, device, equipment and computer-readable storage medium for foot and ankle joint impingement syndrome based on multimodal data fusion. Background Technology

[0002] With the rapid development of orthopedic surgical robot technology, more and more orthopedic surgical robots are being used in orthopedic surgeries, greatly improving the efficiency and effectiveness of these procedures. Before performing orthopedic surgery, doctors need to diagnose the patient to determine the type of lesion and the appropriate surgical approach.

[0003] Foot-ankle impingement syndrome is a common condition in foot and ankle surgery. There are many factors that can lead to foot-ankle impingement syndrome. When diagnosing foot-ankle impingement syndrome, doctors often need to combine orthopedic imaging equipment such as X-ray equipment, computed tomography (CT) equipment, and magnetic resonance imaging (MRI) equipment for evaluation, which is less efficient and more subjective.

[0004] Therefore, how to accurately and efficiently diagnose foot and ankle impingement syndrome is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This application provides an intelligent diagnostic method, apparatus, device, and computer-readable storage medium for foot and ankle joint impingement syndrome based on multimodal data fusion, which can accurately and efficiently diagnose foot and ankle joint impingement syndrome.

[0006] In a first aspect, embodiments of this application provide an intelligent diagnostic method for foot-ankle joint impingement syndrome based on multimodal data fusion, comprising:

[0007] Obtain at least one foot and ankle orthopedic imaging and diagnostic information from the patient; the diagnostic information includes: the patient's medical history, symptoms, and physical examination information;

[0008] Foot and ankle orthopedic imaging and diagnostic information are input into a pre-trained diagnostic model for foot and ankle impingement syndrome, yielding the diagnostic results for foot and ankle impingement syndrome output by the model.

[0009] The foot and ankle joint impingement syndrome diagnostic model is used to extract foot and ankle orthopedic imaging features and text features, and to diagnose foot and ankle joint impingement syndrome based on the fused features. The diagnostic results of foot and ankle joint impingement syndrome include diagnostic results under multiple diagnostic dimensions.

[0010] Optionally, the diagnostic dimension includes the location type of foot-ankle impingement syndrome; the diagnostic results under the location type include:

[0011] Anterior lateral impingement syndrome of the foot and ankle, anterior impingement syndrome of the foot and ankle, posteromedial impingement syndrome of the foot and ankle, posterolateral impingement syndrome of the foot and ankle.

[0012] Optionally, the diagnostic dimension includes the type of impingement in foot-ankle impingement syndrome; the diagnostic results under the impingement type include:

[0013] Anterior malleolar impingement caused by anterior tibial lip osteophytes, anterior malleolar impingement caused by talar neck osteophytes, and anterior malleolar impingement caused by malunion of anterior malleolar fractures; and posterior malleolar impingement caused by triangular bone syndrome, posterior malleolar impingement caused by excessive posterior talar process, posterior malleolar impingement caused by posterior tibial lip osteophytes, and posterior malleolar impingement caused by malunion of posterior talar tubercle fractures; and

[0014] anterolateral impingement caused by Bassett ligament hypertrophy or scarring, anterolateral impingement caused by anterolateral synovitis or synovial hyperplasia, anterolateral impingement caused by scarring after injury to the anterior tibiofibular ligament; and anteromedial impingement caused by anteromedial synovitis or synovial hyperplasia, and anteromedial impingement caused by soft tissue embedding in the anteroinferior aspect of the medial malleolus.

[0015] Optionally, the foot-ankle joint impingement syndrome diagnostic model includes an image encoder, a text encoder, an adapter, and multiple diagnostic inference heads; wherein:

[0016] The image encoder is used to segment foot and ankle orthopedic images and encode the segmented regions separately to preserve the fine structure of the foot and ankle joint.

[0017] The text encoder is used to extract symptom keywords from the diagnostic prompt information and encode them;

[0018] The adapter is used to dynamically generate modality-specific parameters based on the modality of foot and ankle orthopedic images, so that the image encoder can process foot and ankle orthopedic images of the corresponding modality.

[0019] The diagnostic inference head is used to diagnose foot and ankle joint impingement syndrome based on the fusion features obtained by fusing foot and ankle orthopedic imaging features and text features, and to obtain the diagnostic result of foot and ankle joint impingement syndrome.

[0020] Optionally, the foot and ankle joint impingement syndrome diagnostic model further includes an alignment module;

[0021] The alignment module is used to construct a joint embedding space, so that foot and ankle orthopedic imaging features and text features are aligned at the semantic level.

[0022] Optionally, the foot and ankle joint impingement syndrome diagnostic model further includes a wavelet multi-head self-attention module;

[0023] The wavelet multi-head self-attention module is used to enhance the frequency domain feature analysis capability and capture high-frequency details and low-frequency structures in images.

[0024] Optionally, the diagnostic inference head includes a lightweight classifier;

[0025] The lightweight classifier is used to filter key features including ankle joint angle and synovial hyperplasia based on deep feature engineering, and reduces computational overhead during inference through a lightweight classification layer.

[0026] Secondly, embodiments of this application provide an intelligent diagnostic device for foot-ankle joint impingement syndrome based on multimodal data fusion, comprising:

[0027] The acquisition module is used to acquire at least one foot and ankle orthopedic image and diagnostic information of the patient; wherein, the diagnostic information includes: the patient's medical history, symptoms, and physical examination information;

[0028] The diagnostic module is used to input foot and ankle orthopedic images and diagnostic prompts into a pre-trained foot and ankle impingement syndrome diagnostic model, and obtain the foot and ankle impingement syndrome diagnostic results output by the model; among which,

[0029] The foot and ankle joint impingement syndrome diagnostic model is used to extract foot and ankle orthopedic imaging features and text features, and to diagnose foot and ankle joint impingement syndrome based on the fused features. The diagnostic results of foot and ankle joint impingement syndrome include diagnostic results under multiple diagnostic dimensions.

[0030] Thirdly, embodiments of this application provide an electronic device, which includes: a processor and a memory storing computer program instructions;

[0031] When the processor executes the computer program instructions, it implements an intelligent diagnostic method for ankle-foot impingement syndrome based on multimodal data fusion.

[0032] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement an intelligent diagnostic method for ankle-foot impingement syndrome based on multimodal data fusion.

[0033] The intelligent diagnostic method, apparatus, device, and computer-readable storage medium for foot and ankle joint impingement syndrome based on multimodal data fusion in this application embodiment can accurately and efficiently diagnose foot and ankle joint impingement syndrome.

[0034] This intelligent diagnostic method for foot and ankle impingement syndrome based on multimodal data fusion includes:

[0035] Obtain at least one foot and ankle orthopedic imaging and diagnostic information from the patient; the diagnostic information includes: the patient's medical history, symptoms, and physical examination information;

[0036] Foot and ankle orthopedic imaging and diagnostic information are input into a pre-trained diagnostic model for foot and ankle impingement syndrome, yielding the diagnostic results for foot and ankle impingement syndrome output by the model.

[0037] The foot and ankle joint impingement syndrome diagnostic model is used to extract foot and ankle orthopedic imaging features and text features, and to diagnose foot and ankle joint impingement syndrome based on the fused features. The diagnostic results of foot and ankle joint impingement syndrome include diagnostic results under multiple diagnostic dimensions. Attached Figure Description

[0038] 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.

[0039] Figure 1 This is a flowchart illustrating an intelligent diagnostic method for foot and ankle joint impingement syndrome based on multimodal data fusion provided in one embodiment of this application.

[0040] Figure 2 This is a schematic diagram of the architecture of a diagnostic model for foot and ankle impingement syndrome provided in one embodiment of this application;

[0041] Figure 3 This is a schematic diagram of the structure of an intelligent diagnostic device for foot and ankle joint impingement syndrome based on multimodal data fusion provided in one embodiment of this application;

[0042] Figure 4 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0043] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application 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 only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0044] 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.

[0045] To address the problems of existing technologies, embodiments of this application provide an intelligent diagnostic method, apparatus, device, and computer-readable storage medium for foot-ankle joint impingement syndrome based on multimodal data fusion. The intelligent diagnostic method for foot-ankle joint impingement syndrome based on multimodal data fusion provided in this application embodiment will be described below first.

[0046] Figure 1 This illustration shows a flowchart of an intelligent diagnostic method for foot-ankle impingement syndrome based on multimodal data fusion, according to an embodiment of this application. The intelligent diagnostic method for foot-ankle impingement syndrome can be applied to an orthopedic surgical robot system. The orthopedic surgical robot system includes a sub-millimeter-level optical positioning module, a robotic arm execution module, and a preoperative planning module. The preoperative planning module is used to execute the intelligent diagnostic method for foot-ankle impingement syndrome for preoperative planning. The optical positioning module is used for preoperative registration and intraoperative navigation. The robotic arm execution module is used to assist or independently execute intraoperative pre-set operations. Figure 1 As shown, this intelligent diagnostic method for foot and ankle impingement syndrome based on multimodal data fusion includes:

[0047] S101. Obtain at least one foot and ankle orthopedic imaging and diagnostic information from the patient; wherein, the diagnostic information includes: the patient's medical history, symptoms, and physical examination information.

[0048] S102. Input the foot and ankle orthopedic images and diagnostic information into the pre-trained foot and ankle impingement syndrome diagnostic model to obtain the foot and ankle impingement syndrome diagnostic results output by the model; wherein...

[0049] The foot and ankle joint impingement syndrome diagnostic model is used to extract foot and ankle orthopedic imaging features and text features, and to diagnose foot and ankle joint impingement syndrome based on the fused features. The diagnostic results of foot and ankle joint impingement syndrome include diagnostic results under multiple diagnostic dimensions.

[0050] In some embodiments, the diagnostic dimension includes the location type of foot-ankle impingement syndrome; the diagnostic results under the location type include:

[0051] Anterior lateral impingement syndrome of the foot and ankle, anterior impingement syndrome of the foot and ankle, posteromedial impingement syndrome of the foot and ankle, posterolateral impingement syndrome of the foot and ankle.

[0052] In some embodiments, the diagnostic dimension includes the type of impingement in ankle-foot impingement syndrome; the diagnostic results under the impingement type include:

[0053] Anterior malleolar impingement caused by anterior tibial lip osteophytes, anterior malleolar impingement caused by talar neck osteophytes, and anterior malleolar impingement caused by malunion of anterior malleolar fractures; and posterior malleolar impingement caused by triangular bone syndrome, posterior malleolar impingement caused by excessive posterior talar process, posterior malleolar impingement caused by posterior tibial lip osteophytes, and posterior malleolar impingement caused by malunion of posterior talar tubercle fractures; and

[0054] anterolateral impingement caused by Bassett ligament hypertrophy or scarring, anterolateral impingement caused by anterolateral synovitis or synovial hyperplasia, anterolateral impingement caused by scarring after injury to the anterior tibiofibular ligament; and anteromedial impingement caused by anteromedial synovitis or synovial hyperplasia, and anteromedial impingement caused by soft tissue embedding in the anteroinferior aspect of the medial malleolus.

[0055] In some embodiments, the foot-ankle joint impingement syndrome diagnostic model includes an image encoder, a text encoder, an adapter, and multiple diagnostic inference heads; wherein:

[0056] The image encoder is used to segment foot and ankle orthopedic images and encode the segmented regions separately to preserve the fine structure of the foot and ankle joint.

[0057] The text encoder is used to extract symptom keywords from the diagnostic prompt information and encode them;

[0058] The adapter is used to dynamically generate modality-specific parameters based on the modality of foot and ankle orthopedic images, so that the image encoder can process foot and ankle orthopedic images of the corresponding modality.

[0059] The diagnostic inference head is used to diagnose foot and ankle joint impingement syndrome based on the fusion features obtained by fusing foot and ankle orthopedic imaging features and text features, and to obtain the diagnostic result of foot and ankle joint impingement syndrome.

[0060] In some embodiments, the image encoder can be an image encoder in the SAM model, which can extract image features based on the Vision Transformer (ViT); the cue encoder can be a cue encoder in the SAM model, which can convert visual cues and text cues into 256-dimensional vectors; and the task decoder can be a mask decoder in the SAM model, which can generate a high-quality segmentation mask and evaluate confidence based on the outputs of the cue encoder and the image encoder.

[0061] In some embodiments, the visual cue generation module may include a CLIP model, which can process the input CT image of the foot and ankle joint to be segmented and a pre-set text cue (e.g., foot and ankle joint). When generating the visual cue, a saliency map containing the foot and ankle region can be generated using ScoreCAM, and then a coarse mask can be obtained through Conditional Random Field (CRF) post-processing, thereby extracting the bounding box coordinates of the foot and ankle joint.

[0062] In some embodiments, the text prompt generation module may include a VQA model and an LLM model. The VQA model is used to answer a pre-defined localization question (e.g., where is the ankle joint located in a CT scan?) to obtain localization description information of the ankle joint. The LLM model is used to generate a general feature description of the ankle joint (e.g., the ankle joint in a CT image) to enrich the feature semantics input to the prompt encoder, thereby helping the task decoder to perform image segmentation better.

[0063] In some embodiments, the training of the foot-ankle joint impingement syndrome diagnostic model can be divided into two stages. In the first stage, a small amount of labeled data (accounting for 10% or 20% of the total sample data) can be used to train the visual cue generation module and the text cue generation module, so that the two cue generation modules can generate high-quality cue information. The loss function in 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. The IoU score between the candidate segmentation map and the real mask is used to simulate human evaluation, so that no manual data labeling is required. The loss function in the second stage can be the DPO loss function, which rewards high-scoring candidates (e.g., increases the weight of high-scoring samples) and penalizes low-scoring candidates (reduces the weight of low-scoring samples, e.g., sets the weight to 40% or 50% of the weight of high-scoring samples) to optimize model preferences and output high-quality image segmentation results.

[0064] In the process of simulating human evaluation by scoring the IoU between the candidate segmentation map and the real mask, the scoring can be carried out according to the pre-set scoring rules: IoU less than 0.35 is scored as 1 point, IoU greater than 0.35 and less than 0.5 is scored as 2 points, IoU greater than 0.5 and less than 0.75 is scored as 3 points, and IoU greater than 0.5 and less than 0.75 is scored as 3 points.

[0065] In addition, the diagnostic inference head can also include the probability level of ankle impingement syndrome. During training, the diagnostic candidate ranking of the probability level of ankle impingement syndrome can also be added, and the diagnostic candidates output by the model can be scored using text information such as the patient's physical examination information as evaluation criteria to optimize the model output.

[0066] In some embodiments, the foot and ankle joint impingement syndrome diagnostic model further includes an alignment module;

[0067] The alignment module is used to construct a joint embedding space, so that foot and ankle orthopedic imaging features and text features are aligned at the semantic level.

[0068] In some embodiments, the foot and ankle joint impingement syndrome diagnostic model further includes a wavelet multi-head self-attention module;

[0069] The wavelet multi-head self-attention module is used to enhance the frequency domain feature analysis capability and capture high-frequency details and low-frequency structures in images.

[0070] In some embodiments, the diagnostic inference head includes a lightweight classifier;

[0071] The lightweight classifier is used to filter key features including ankle joint angle and synovial hyperplasia based on deep feature engineering, and reduces computational overhead during inference through a lightweight classification layer.

[0072] Figure 2 This is a schematic diagram of the architecture of a diagnostic model for foot and ankle impingement syndrome provided in one embodiment of this application. Figure 2 The diagnostic model for foot and ankle joint impingement syndrome includes an adapter, an image encoder, a text encoder, an alignment module, a diagnostic inference head, and a lightweight classifier. It can process the input foot and ankle orthopedic images and diagnostic prompts to obtain diagnostic results in multiple diagnostic dimensions, thereby helping doctors make preoperative decisions more quickly.

[0073] Figure 3 This is a schematic diagram of the structure of an intelligent diagnostic device for foot-ankle impingement syndrome based on multimodal data fusion, according to an embodiment of this application. The intelligent diagnostic device for foot-ankle impingement syndrome based on multimodal data fusion includes:

[0074] The acquisition module 301 is used to acquire at least one foot and ankle orthopedic image and diagnostic information of the patient; wherein, the diagnostic information includes: the patient's medical history, symptoms, and physical examination information;

[0075] The diagnostic module 302 is used to input foot and ankle orthopedic images and diagnostic prompts into a pre-trained foot and ankle impingement syndrome diagnostic model to obtain the foot and ankle impingement syndrome diagnostic results output by the model; wherein,

[0076] The foot and ankle joint impingement syndrome diagnostic model is used to extract foot and ankle orthopedic imaging features and text features, and to diagnose foot and ankle joint impingement syndrome based on the fused features. The diagnostic results of foot and ankle joint impingement syndrome include diagnostic results under multiple diagnostic dimensions.

[0077] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0078] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0079] 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 embodiments of this application.

[0080] Memory 402 may include mass storage for data or instructions. For example, and not limitingly, memory 402 may include a 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. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be internal or external to an electronic device. In a particular embodiment, memory 402 may be a non-volatile solid-state memory.

[0081] In one embodiment, memory 402 may be read-only memory (ROM). In one embodiment, 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.

[0082] The processor 401 reads and executes computer program instructions stored in the memory 402 to implement any of the intelligent diagnostic methods for ankle-foot impingement syndrome based on multimodal data fusion in the above embodiments.

[0083] In one example, the electronic device may also include a communication interface 403 and a bus 410. For example, Figure 4 As shown, the processor 401, memory 402, and communication interface 403 are connected through bus 410 and complete communication with each other.

[0084] The communication interface 403 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0085] Bus 410 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (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, bus 410 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0086] Furthermore, in conjunction with the intelligent diagnostic method for foot-ankle joint impingement syndrome based on multimodal data fusion in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement any of the intelligent diagnostic methods for foot-ankle joint impingement syndrome based on multimodal data fusion in the above embodiments.

[0087] It should be clarified that this application 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 application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0088] The functional modules shown in the above-described block 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 application are programs or code segments used to perform the required tasks. The programs or code segments 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. "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. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0089] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0090] The aspects of this application 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 application. 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 dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0091] The above description is merely a specific implementation of this application. 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 application 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 application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. An intelligent diagnostic method for foot-ankle joint impingement syndrome based on multimodal data fusion, characterized in that, The intelligent diagnostic method includes: Obtain at least one foot and ankle orthopedic imaging and diagnostic information from the patient; the diagnostic information includes: the patient's medical history, symptoms, and physical examination information; Foot and ankle orthopedic imaging and diagnostic information are input into a pre-trained diagnostic model for foot and ankle impingement syndrome, yielding the diagnostic results for foot and ankle impingement syndrome output by the model. The foot and ankle joint impingement syndrome diagnostic model is used to extract foot and ankle orthopedic imaging features and text features, and to diagnose foot and ankle joint impingement syndrome based on the fused features. The diagnostic results of foot and ankle joint impingement syndrome include diagnostic results under multiple diagnostic dimensions.

2. The intelligent diagnostic method for foot and ankle impingement syndrome based on multimodal data fusion according to claim 1, characterized in that, Diagnostic dimensions include the location type of foot-ankle impingement syndrome; diagnostic results under location type include: Anterior lateral impingement syndrome of the foot and ankle, anterior impingement syndrome of the foot and ankle, posteromedial impingement syndrome of the foot and ankle, posterolateral impingement syndrome of the foot and ankle.

3. The intelligent diagnostic method for foot-ankle joint impingement syndrome based on multimodal data fusion according to claim 1 or 2, characterized in that, The diagnostic dimensions include the type of impact in foot and ankle impingement syndrome; the diagnostic results under the type of impact include: Anterior malleolar impingement caused by anterior tibial lip osteophytes, anterior malleolar impingement caused by talar neck osteophytes, and anterior malleolar impingement caused by malunion of anterior malleolar fractures; and posterior malleolar impingement caused by triangular bone syndrome, posterior malleolar impingement caused by excessive posterior talar process, posterior malleolar impingement caused by posterior tibial lip osteophytes, and posterior malleolar impingement caused by malunion of posterior talar tubercle fractures; and anterolateral impingement caused by Bassett ligament hypertrophy or scarring, anterolateral impingement caused by anterolateral synovitis or synovial hyperplasia, anterolateral impingement caused by scarring after injury to the anterior tibiofibular ligament; and anteromedial impingement caused by anteromedial synovitis or synovial hyperplasia, and anteromedial impingement caused by soft tissue embedding in the anteroinferior aspect of the medial malleolus.

4. The intelligent diagnostic method for foot and ankle impingement syndrome based on multimodal data fusion according to claim 1, characterized in that, The diagnostic model for ankle-foot impingement syndrome includes an image encoder, a text encoder, an adapter, and multiple diagnostic inference heads; wherein: The image encoder is used to segment foot and ankle orthopedic images and encode the segmented regions separately to preserve the fine structure of the foot and ankle joint. The text encoder is used to extract symptom keywords from the diagnostic prompt information and encode them; The adapter is used to dynamically generate modality-specific parameters based on the modality of foot and ankle orthopedic images, so that the image encoder can process foot and ankle orthopedic images of the corresponding modality. The diagnostic inference head is used to diagnose foot and ankle joint impingement syndrome based on the fusion features obtained by fusing foot and ankle orthopedic imaging features and text features, and to obtain the diagnostic result of foot and ankle joint impingement syndrome.

5. The intelligent diagnostic method for foot and ankle impingement syndrome based on multimodal data fusion according to claim 4, characterized in that, The diagnostic model for foot and ankle joint impingement syndrome also includes an alignment module; The alignment module is used to construct a joint embedding space, so that foot and ankle orthopedic imaging features and text features are aligned at the semantic level.

6. The intelligent diagnostic method for foot-ankle joint impingement syndrome based on multimodal data fusion according to claim 4 or 5, characterized in that, The diagnostic model for ankle-foot impingement syndrome also includes a wavelet multi-head self-attention module; The wavelet multi-head self-attention module is used to enhance the frequency domain feature analysis capability and capture high-frequency details and low-frequency structures in images.

7. The intelligent diagnostic method for foot and ankle joint impingement syndrome based on multimodal data fusion according to claim 4 or 5, characterized in that, The diagnostic inference head includes a lightweight classifier; The lightweight classifier is used to filter key features including ankle joint angle and synovial hyperplasia based on deep feature engineering, and reduces computational overhead during inference through a lightweight classification layer.

8. An intelligent diagnostic device for foot-ankle joint impingement syndrome based on multimodal data fusion, characterized in that, The intelligent diagnostic device includes: The acquisition module is used to acquire at least one foot and ankle orthopedic image and diagnostic information of the patient; wherein, the diagnostic information includes: the patient's medical history, symptoms, and physical examination information; The diagnostic module is used to input foot and ankle orthopedic images and diagnostic prompts into a pre-trained foot and ankle impingement syndrome diagnostic model, and obtain the foot and ankle impingement syndrome diagnostic results output by the model; among which, The foot and ankle joint impingement syndrome diagnostic model is used to extract foot and ankle orthopedic imaging features and text features, and to diagnose foot and ankle joint impingement syndrome based on the fused features. The diagnostic results of foot and ankle joint impingement syndrome include diagnostic results under multiple diagnostic dimensions.

9. An electronic device, characterized in that, The electronic device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the intelligent diagnostic method for ankle-foot impingement syndrome based on multimodal data fusion as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the intelligent diagnostic method for ankle-foot impingement syndrome based on multimodal data fusion as described in any one of claims 1-7.

Images