A method, system and storage medium for assisting design of prosthetic socket

By obtaining user information and using machine learning algorithms to construct a prosthetic receiving cavity model, the problems of low adaptability and low efficiency of the prosthetic receiving cavity design in the prior art are solved, and the high matching and personalized design of the prosthetic receiving cavity with the user are achieved. Improves design efficiency and adaptability.

CN118267195BActive Publication Date: 2024-11-26NAT REHABILITATION ASSISTIVE DEVICES RES CENT
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410267203.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-08
Publication Date
2024-11-26
Estimated Expiration
2044-03-08

AI Technical Summary

Technical Problem

The existing prosthetic receptive cavity design has problems such as low adaptability and low design efficiency, which makes it difficult to popularize in clinical practice and cannot fully utilize the advantages of additive manufacturing technology.

Method used

By obtaining user information, extracting user key information, and using the trained prosthetic receiving cavity generation model and feature extraction model, a prosthetic receiving cavity matching with the user is constructed based on machine learning algorithms to improve design efficiency and adaptability.

Benefits of technology

The prosthetic receptive cavity is highly matched with the user's residual limbs, meet personalized needs, improve design efficiency and adaptability, and reduce the time and energy consumption of artificial design.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118267195B_ABST
    Figure CN118267195B_ABST
Patent Text Reader

Abstract

The present invention provides a method, system and storage medium for assisting the design of a prosthetic socket, the method comprising: obtaining user information, the user information comprising basic information, physical condition examination and evaluation results, prosthetic use environment, residual limb examination and evaluation results and patient needs; extracting user key information based on the user information, the user key information comprising physical condition key information, residual limb state key information and prosthetic application key information; constructing a prosthetic socket matching the user through a trained prosthetic socket generation model based on the extracted user key information. The present invention can improve the design efficiency of the prosthetic socket, and improve the compatibility of the prosthetic socket with the user's residual limb.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of prosthetic sockets, and in particular to a prosthetic socket auxiliary design method, system and storage medium. Background Art

[0002] Prostheses are aids for amputees to compensate for missing limbs and compensate for functions. The socket is the human-machine interface that connects the prosthetic joint components to the human body. This human-machine interface mainly plays the role of accommodating residual limbs, supporting body weight, transmitting movement and suspension. Traditionally, the prosthetic socket is made by hand, and the process includes seven steps: inspection and measurement, plaster bandage shaping, negative mold trimming, positive mold pouring, plaster shaping, inner sleeve making, and resin vacuum molding. It is generally designed and made simultaneously by professional prosthetists with certain experience. In the traditional prosthetic socket production process, professional prosthetists often make personalized neutralization and improvements according to the patient's condition when designing and making. Although this can meet personalized needs, it takes a lot of time and effort in the production process. Even if it is the same type, the sockets designed and made by different prosthetists are very different, making it difficult for prosthetists and other professionals to accurately describe and discuss the design of the prosthetic socket.

[0003] At present, some people use additive manufacturing (3D printing) technology to improve the design efficiency of prosthetic sockets. Additive manufacturing (3D printing) technology is a rapid prototyping technology that uses computer-aided design data to obtain a solid model by stacking materials layer by layer through molding equipment. Because it meets the personalized characteristics of the socket, some studies have applied this technology to the design and production of prosthetic sockets; however, studies have found that the prosthetic sockets designed by additive manufacturing (3D printing) technology have the disadvantages of low adaptability and poor user experience. Therefore, it is difficult to popularize in clinical practice, and the advantages of advanced technologies such as additive manufacturing have not been brought into play. The reason is that the digital model of the socket cannot completely replicate the design of the manual production, resulting in defects in the design of the printed socket.

[0004] Therefore, how to improve the design efficiency of the prosthetic socket and improve the compatibility between the prosthetic socket and the user's residual limb are technical problems that need to be solved urgently. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a prosthetic socket auxiliary design method, system and storage medium to eliminate or improve one or more defects existing in the prior art.

[0006] One aspect of the present invention provides a method for assisting the design of a prosthetic socket, the method comprising the following steps:

[0007] Obtaining user information, including basic information, physical examination and assessment results, prosthesis use environment, residual limb examination and assessment results, and patient needs;

[0008] Extracting user key information based on the user information, wherein the user key information includes key information on physical condition, key information on residual limb status, and key information on prosthetic application;

[0009] Based on the extracted key information of the user, a prosthetic socket matching the user is constructed through a trained prosthetic socket generation model.

[0010] In some embodiments of the present invention, constructing a prosthetic socket matching the user through a trained prosthetic socket generation model based on the extracted user key information includes:

[0011] Generate a socket feature based on the extracted user key information through a trained socket feature extraction model;

[0012] Based on the socket features, a prosthetic socket matching the user is constructed through a trained prosthetic socket generation model.

[0013] In some embodiments of the present invention, the algorithm used in the receiving cavity feature extraction model is a decision tree algorithm based on information gain, and the calculation formula of the information gain is: Where D represents the set of prosthesis configuration samples, a represents user information, and V represents the possibility that user information has V values; D v Indicates that when the prosthesis configuration sample set D is divided based on user information a, the value of a is a v Ent(D) represents the corresponding purity of the prosthetic configuration sample set D; or,

[0014] The algorithms adopted by the receiving cavity feature extraction model are linear regression algorithm and clustering algorithm.

[0015] In some embodiments of the present invention, before constructing a prosthetic socket matching the user through a trained prosthetic socket generation model based on the socket characteristics, the method further includes: obtaining a user satisfaction result through a trained satisfaction prediction model based on the user information and the socket characteristics; and / or,

[0016] The characteristics of the receiving cavity include the volume of the receiving cavity, the depth of the receiving cavity, the type of the receiving cavity mouth ring, the edge height and direction, the contact and load-bearing method of the residual limb end, the bone movement control method, the condition of the inner liner or silicone sleeve, the material and structure, the way of putting on and taking off, the weight estimation, the extrusion position and range, the load-free position and range, the opening position and size, the supplementary suspension method, the alignment of the receiving cavity, and the shape of the receiving cavity.

[0017] In some embodiments of the present invention, the algorithm used by the satisfaction prediction model is a logistic regression algorithm, and the function of the logistic regression algorithm is h θ (x) represents satisfaction, e is the Euler constant, θ is the model parameter, x is the user information and the receiving cavity characteristics, and T represents the transposition operation.

[0018] In some embodiments of the present invention, extracting key user information based on the user information includes:

[0019] Obtain the evaluation criteria corresponding to each user information;

[0020] Based on the evaluation criteria, it is determined whether the corresponding user information is user key information.

[0021] In some embodiments of the present invention, extracting key user information based on the user information includes:

[0022] Based on the user information, user key information is extracted through a trained key information extraction model.

[0023] In some embodiments of the present invention, the algorithm used by the key information extraction model is: support vector machine, random forest algorithm, one-tailed test algorithm, Pearson correlation analysis method or Spearman rank correlation analysis method; and / or

[0024] The basic information includes: the time and reason of amputation, the state of wearing the prosthesis first; the physical condition examination and assessment results include: balance and coordination, muscle strength, vision, psychology, disease, injury and dysfunction; the prosthesis use environment includes: ground environment and temperature and humidity; the residual limb inspection and assessment results include: amputation position, residual limb length, shape and volume, bone protrusions and bone spurs, skin scar injury and disease, subcutaneous tissue volume and hardness, residual limb end contact and load-bearing capacity, residual limb edema, residual soft tissue sagging, residual limb skin color, residual limb skin temperature, residual limb sensation and pain, joint movement deformity and dysfunction; the patient needs include daily self-care, occupation, sports and entertainment activities, main use of prostheses, movement methods, walking speed and special needs.

[0025] According to another aspect of the present application, a prosthetic socket auxiliary design system is also disclosed, including a processor, a memory and a computer program stored in the memory, the processor is used to execute the computer program, and when the computer program is executed, the system implements the steps of the method described in any of the above embodiments.

[0026] According to another aspect of the present application, a computer-readable storage medium is also disclosed, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0027] The prosthetic socket auxiliary design method, system and storage medium of the present invention first extract user key information based on user information, and the extracted user key information includes physical condition key information, residual limb state key information and prosthetic application key information, and then constructs a prosthetic socket matching the user through a trained socket generation model according to the extracted user key information; the method determines the prosthetic socket based on the user key information, meets personalized needs, does not require manual design, and thus improves the design efficiency of the prosthetic socket; and the prosthetic socket of the method is generated by a machine learning algorithm, which improves the compatibility of the prosthetic socket with the user's residual limb.

[0028] In addition, when generating the socket model, the present application also generates a socket feature based on the extracted user key information through a trained socket feature extraction model. The socket feature is determined based on the user key information, and thus can accurately represent the user's demand for the prosthetic socket, so that the generated prosthetic socket is highly matched with the user.

[0029] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention may be achieved and obtained by the structures specifically indicated in the specification and the accompanying drawings.

[0030] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention. The components in the drawings are not drawn to scale, but are only for illustrating the principles of the present invention. In order to facilitate the illustration and description of some parts of the present invention, the corresponding parts in the drawings may be enlarged, that is, they may become larger relative to other components in the exemplary device actually manufactured according to the present invention. In the drawings:

[0032] Figure 1 Schematic diagram of the flow of a prosthetic socket auxiliary design method in one embodiment of the present invention.

[0033] Figure 2 Schematic diagram of the structure of a prosthetic socket auxiliary design system in one embodiment of the present invention.

[0034] Figure 3 Schematic diagram of the input interface of the prosthetic socket auxiliary design system in one embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0036] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0037] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0038] It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection involving an intermediate.

[0039] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0040] Figure 1 FIG. 1 is a flow chart of a method for assisting prosthetic socket design in accordance with an embodiment of the present invention. Figure 1 As shown, the prosthetic socket auxiliary design method at least includes steps S10 to S30.

[0041] Step S10: Obtaining user information, which includes basic information, physical condition examination and assessment results, prosthesis use environment, residual limb examination and assessment results, and patient needs.

[0042] In order to make the designed prosthetic socket meet personalized needs, the user's basic information, physical examination and evaluation results, prosthetic use environment, residual limb examination and evaluation results, and patient needs are first obtained. In order to obtain the physical examination and evaluation results, residual limb examination and evaluation results, etc., the user can be clinically examined, and the examination conclusions can be used as part of the user information, so that the prosthetic socket is designed based on the clinical examination results.

[0043] Exemplarily, the basic information may include: the time and reason for amputation, the state of wearing the prosthesis first, the physical condition examination and assessment results may include: balance and coordination, muscle strength, vision, psychology, disease, injury and dysfunction, the prosthesis use environment may include: ground environment and temperature and humidity conditions, the residual limb inspection and assessment results may include: amputation location, residual limb length, shape and volume, bone protrusions and bone spurs, skin scar injury and disease conditions, subcutaneous tissue volume and hardness, residual limb end contact and load-bearing capacity, residual limb edema, residual soft tissue sagging, residual limb skin color, residual limb skin temperature, residual limb sensation and pain, joint movement deformity and dysfunction, the patient's needs may include daily self-care, occupation, sports and entertainment activities, the main purpose of the prosthesis, movement method, walking speed and special needs. It can be understood that the basic information, physical condition examination and evaluation results, prosthetic use environment, residual limb inspection and evaluation results, and information types included in the patient's needs listed in this embodiment are merely some preferred examples. In other embodiments, in addition to the information listed in the above embodiments, more other information may also be included, and the specific information can be set according to actual needs.

[0044] In the above embodiment, the residual limb sensation and pain conditions included in the residual limb inspection and assessment results may specifically include spontaneous pain, movement pain, tenderness, neuralgia, phantom limb sensation, phantom limb pain, or sensitivity, etc., and the special needs included in the patient needs may specifically include showering, swimming, skiing, decoration, wearing high heels, etc. In other embodiments, the basic information may include information such as gender and age in addition to the types listed above; the physical condition inspection and assessment results may include information such as height and weight in addition to the types listed above.

[0045] In addition, the shape and volume included in the residual limb inspection and evaluation results can be obtained by measuring and collecting the residual limb volume data of the user, and the measurement methods include immersion method, scanning imaging method, negative mold canning method, shape approximation method, etc. The immersion method refers to marking the proximal end of the residual limb and immersing it in a container filled with liquid. The volume of the overflowing liquid is the residual limb volume; the scanning imaging method refers to scanning the outer surface of the residual limb with infrared, laser and other equipment or CT scanning, generating a digital residual limb model, and calculating the digital residual limb volume; the negative mold perfusion method refers to calculating the residual limb volume by perfusing the liquid volume with a plaster negative mold; the shape approximation method is based on the residual limb length, girth distribution and its corresponding width, and approximates the residual limb volume. It can be understood that the residual limb volume measurement method used in this embodiment is only some preferred examples, and other methods can also be used to measure the residual limb volume in other embodiments.

[0046] In some other embodiments, the user information obtained may include, in addition to basic information, physical condition examination and assessment results, prosthetic use environment, residual limb inspection and assessment results, and patient needs, maintenance service assessment results, social and economic environment assessment results, functional level assessment results, etc.

[0047] Accordingly, in the prosthetic socket auxiliary design system corresponding to the prosthetic socket auxiliary design method, this step can be implemented based on the user interface module. In addition, the user information can be input by the user or directly obtained from the database. When the user inputs the user information, he or she can select or input it according to the prompts given on the human-computer interaction interface, such as Figure 3 shown.

[0048] In a specific embodiment, the information input by the user is, for example, "basic information: male, 22, right thigh amputation due to bone tumor ten years ago, currently owns a thigh prosthesis and uses it normally; preliminary assessment results of the patient's physical condition examination: 179cm, 85kg, good balance and coordination, normal muscle strength, normal vision, normal psychology, no other diseases, injuries and functional disorders; prosthetic limb use environment: bathroom, slippery and flat; residual limb inspection and assessment results: thigh amputation, long residual limb, protruding femoral end, no skin scar damage, etc., medium subcutaneous tissue volume and hardness, poor contact and load-bearing capacity of residual limb end, no residual limb edema, no residual soft tissue sagging, residual limb skin color normal, residual limb skin temperature normal, residual limb sensation normal, no pain, normal joint movement; patient needs: self-care in daily life, professional student, the main use of the prosthesis is standing, special needs showering".

[0049] Step S20: extracting key user information based on the user information, wherein the key user information includes key information on physical condition, key information on residual limb status, and key information on prosthetic application.

[0050] This step is to extract key user information from the received user information so that the designed prosthetic socket is highly adapted to the user. Key user information can accurately express the user's physical condition, residual limb status, and the purpose of the prosthesis. Specifically, the key information includes key information on physical condition, key information on residual limb status, and key information on prosthetic application. In a specific embodiment, the key user information extracted based on the user information input by the user is "long residual limb on the right side of the thigh, protruding femur end, and prosthetic use is standing while taking a shower."

[0051] Exemplarily, extracting user key information based on the user information may specifically include: obtaining evaluation criteria corresponding to each item of user information; judging whether the corresponding user information is user key information based on the evaluation criteria. The evaluation criteria are used to judge whether the user information is key information; for example, for age information, the corresponding evaluation criteria may be a key information threshold. When evaluating whether the user's age information is user key information, the age value entered by the user may be compared with the key information threshold corresponding to the age information. When the age value entered by the user reaches the key information threshold, it may be extracted from the user information as user key information. It is understandable that in this embodiment, the evaluation criteria are limited to the key information threshold only corresponding to the information content of the specific information entered by the user as a numerical value, and when the specific information entered by the user is content other than a numerical value, the evaluation criteria are also changed accordingly.

[0052] In some other embodiments of the present invention, user key information can also be extracted based on the user information through a trained key information extraction model. At this time, the input of the key information extraction model is user information, and the output is user key information. Exemplarily, the algorithm used by the key information extraction model is: support vector machine, random forest algorithm, one-tail test algorithm, Pearson correlation analysis method or Spearman rank correlation analysis method. When the algorithm used by the key information extraction model is support vector machine and random forest algorithm, support vector machine or random forest algorithm is used to classify and identify user information; when the algorithm used by the key information extraction model is one-tail test algorithm, one-tail test algorithm is used to calculate the correlation; when the algorithm used by the key information extraction model is Pearson correlation analysis method or Spearman rank correlation analysis method, Pearson correlation coefficient, Spearman rank, etc. are used to calculate the correlation.

[0053] Exemplarily, in order to obtain a trained key information extraction model, it is first necessary to construct an initial key information extraction model; then construct a sample data set, the sample data in the sample data set includes user information sample data and user key information corresponding to the user information sample data; further, the initial key information extraction model is pre-trained through the sample data set to obtain a trained key information extraction model.

[0054] In the prosthetic socket auxiliary design system corresponding to the prosthetic socket auxiliary design method, step S20 can be implemented based on the data processing module, that is, the data processing module performs data preprocessing on the user information received by the user interface module to obtain key user information.

[0055] Step S30: constructing a prosthetic socket matching the user through a trained prosthetic socket generation model based on the extracted user key information.

[0056] In this step, the input information of the prosthetic socket generation model is the user's key information, and the output information is the constructed prosthetic socket.

[0057] Similarly, in order to obtain a trained prosthetic socket generation model, it is necessary to first construct an initial prosthetic socket generation model, then determine a sample data set, and pre-train the initial prosthetic socket generation model based on the sample data set, and then obtain a trained prosthetic socket generation model. The sample data in the sample data set includes user key information sample data and prosthetic socket sample data.

[0058] In some embodiments, a prosthetic socket matching the user is constructed through a trained prosthetic socket generation model based on the extracted user key information, which may specifically include the following steps: generating a socket feature through a trained socket feature extraction model based on the extracted user key information; and constructing a prosthetic socket matching the user through a trained prosthetic socket generation model based on the socket feature. In this embodiment, the prosthetic socket feature is first generated based on the user key information, and then a specific prosthetic socket is generated based on the prosthetic socket feature; wherein the socket feature covers all aspects of load-bearing, suspension, and inclusion of residual limbs, and incorporates ergonomic considerations, sports biomechanical factors, materials, physiology, comfort and aesthetic requirements, personalized preferences and needs, cost and accessibility, patient feedback, etc.; such as biomechanical factors include but are not limited to pressure distribution, joint torque, muscle activity, motor function, etc., and patient feedback includes comfort, stability, controllability, breathability, adjustability and adaptability, etc. In a specific embodiment, the characteristics of the receiving cavity include the volume of the receiving cavity, the depth of the receiving cavity, the type of the receiving cavity mouth ring, the edge height and trend, the contact and load-bearing method of the residual limb end, the bone movement control method, the condition of the inner sleeve or silicone sleeve, the material and structure, the wearing and removing method, the weight estimation, the extrusion position and range, the load-free position and range, the opening position and size, the supplementary suspension method, the alignment of the receiving cavity, and the shape of the receiving cavity. For example, in a specific embodiment, the characteristics of the receiving cavity are "the compression ratio of the receiving cavity volume is 2%, the depth of the receiving cavity is 28.5cm, the type of the receiving cavity mouth ring is a quadrilateral, the edge height and trend are normal, the residual limb end can be contacted but not load-bearing, the ischium is load-bearing, the femur is in the adduction position, there is no inner sleeve and silicone sleeve, the material is a polyethylene sheet, the wearing and removing method of the easy-pull cloth, the weight estimation is 300 grams, the extrusion position and range are the outer side of the thigh + the femoral triangle + the inner side + the biceps femoris, the femoral end is free of load, there is no opening, there is no supplementary suspension, the alignment of the receiving cavity is at the level of the ischium plateau + the femur is appropriately adducted".

[0059] Furthermore, the algorithm used in the socket feature extraction model is a decision tree algorithm based on information gain, and the calculation formula of information gain is: Where D represents the set of prosthesis configuration samples, a represents user information, and V represents the possibility that user information has V values; D v Indicates that when the prosthesis configuration sample set D is divided based on user information a, the value of a is a v Ent(D) represents the corresponding purity of the prosthetic configuration sample set D.

[0060] In the above embodiment, the prosthetic socket feature values ​​are calculated item by item based on the user key information through the decision tree algorithm. Exemplarily, the socket feature extraction model based on the decision tree algorithm is: credit_model = DecisionTreeClassifier (max_depth = 10, max_features = 3, random_state = 25), wherein credit_model represents the model, DecisionTreeClassifier represents the decision tree classifier, max_depth represents the maximum tree depth, max_features represents the maximum number of features, and random_state = 25 represents a random number.

[0061] In addition, the algorithm used by the socket feature extraction model can be a linear regression algorithm and a clustering algorithm in addition to the decision tree algorithm based on information gain. That is, this embodiment predicts the socket feature value by a linear regression algorithm, and uses a clustering algorithm to perform cluster analysis on the information to identify the needs and preferences of different patient groups for the performance of the prosthetic socket.

[0062] In some embodiments of the present invention, before the step of constructing a prosthetic socket matching the user through a trained prosthetic socket generation model based on the socket characteristics, the prosthetic socket auxiliary design method further includes the following step: obtaining a user satisfaction result through a trained satisfaction prediction model based on the user information and the socket characteristics. In this embodiment, the user satisfaction result can be obtained by inputting the user information and the socket characteristics into the trained satisfaction prediction model. Exemplarily, the algorithm used by the satisfaction prediction model is a logistic regression algorithm, and the hypothesis function of the logistic regression algorithm is h θ (x) represents satisfaction, e is the Euler constant, θ is the model parameter, x is the user information and the receiving cavity characteristics, and T represents the transposition operation.

[0063] In the above embodiment, a satisfaction prediction model based on a logistic regression algorithm is used to predict the user's satisfaction with the socket characteristics. The input of the satisfaction prediction model is user information and the socket characteristic value, and the output result is the user satisfaction value. Exemplarily, in order to obtain a trained satisfaction prediction model, an initial satisfaction prediction model is first constructed based on the following information: clf = LR (C = 4, multi_class = "multinomial", max_iter = 500000, tol = 0.0001, class_weight = "balanced"), where clf is a model, LR represents a logistic regression classifier, C represents a regularization parameter, multi_class represents multi-classification, max_iter iterations, tol represents a stop criterion, and class_weight represents a class weight; further, a sample data set is constructed, and the sample data in the sample data set are user information sample data, socket characteristic sample data, and user satisfaction sample data; the initial satisfaction prediction model is pre-trained by using the constructed sample data set to obtain a trained satisfaction prediction model.

[0064] In the above embodiment, when the satisfaction prediction model predicts that the user is relatively satisfied with the characteristic values ​​of the socket, a prosthetic socket solution can be further generated based on the socket characteristics and the preset solution template. Being satisfied with the characteristic values ​​of the socket means that the user is satisfied with all aspects of the prosthetic socket performance, such as load-bearing, suspension, and accommodating residual limbs.

[0065] In some other embodiments, a deep neural network can also be trained through a deep learning algorithm, so that it can automatically generate a prosthetic socket model that meets personalized needs directly based on the extracted key user information. Deep learning algorithms such as convolutional neural networks (CNN) and generative adversarial networks (GAN) have excellent performance in image generation and model optimization, and can be used to construct and optimize the prosthetic socket model of the present application. In addition, during the design process of the prosthetic socket, the parameters of the algorithm model are optimized in the present application, which can further improve the quality and efficiency of the socket design.

[0066] In order to better reflect the advantages of the present application, a specific embodiment is listed below to specifically illustrate the prosthetic socket auxiliary design method and system of the present application:

[0067] The user information input by the user is: "Basic information: male, 22, right thigh amputation due to bone tumor for ten years, currently using a thigh prosthesis, using it normally; the patient's physical condition examination and pre-assessment are: 179cm, 85kg, good balance and coordination, normal muscle strength, normal vision, normal psychology, no other diseases, injuries and functional disorders; the prosthesis use environment assessment is: bathroom, slippery and flat; residual limb inspection and assessment are: thigh amputation, long residual limb, protruding femoral end, no skin scar damage, etc., subcutaneous tissue volume and hardness are medium, residual limb end contact and bearing capacity are poor, no residual limb edema, no residual soft tissue sagging, residual limb skin color is normal, residual limb skin temperature is normal, residual limb sensation is normal, no pain, normal joint movement; patient needs assessment is: daily life self-care, vocational student, the main use of the prosthesis is standing, special needs shower". The data processing module pre-processes the received user information and extracts the user's key information: "long residual limb on the right side of the thigh, protruding femoral end, prosthesis use is standing when taking a shower". The further design algorithm module inputs the key information of the user into the socket feature extraction model, and obtains the socket features corresponding to the user as "the socket volume compression ratio is 2%, the socket depth is 28.5cm, the socket mouth ring type is a quadrilateral, the edge height and trend are normal, the end of the residual limb can be touched but not load-bearing, the ischium is load-bearing, the femur is in the adducted position, there is no liner sleeve and silicone sleeve, the material is polyethylene sheet, the way of wearing and removing the easy-to-pull cloth, the estimated weight is 300 grams, the compression position and range are the outer side of the thigh + the femoral triangle + the inner side + the biceps femoris, the end of the femur is free of load, there is no opening, there is no supplementary suspension, and the socket alignment is the ischium platform level + the femur is appropriately adducted". Furthermore, the result display module presents the socket feature values ​​to the prosthetist and the user. The prosthetist further adjusts, optimizes and confirms the design effect presented by the result display module. After confirmation, the system fills the socket feature values ​​into the preset scheme template to generate the socket design scheme for the user. In addition, according to this scheme, different prosthetists and advanced manufacturing technologies can produce prosthetic sockets with the same wearing effect.

[0068] The prosthetic socket auxiliary design method and system of the above-mentioned embodiment can also provide optimization suggestions based on the performance of the prosthetic socket predicted by historical data through machine learning algorithms; users can also optimize and adjust the constructed prosthetic socket model through real-time interactive operations, thereby enhancing the user experience. In addition, the system will generate multiple solutions for doctors and patients to choose from; the system can be equipped with a virtual environment to simulate the performance of the prosthetic socket; the system can perform iterative optimization based on user feedback to continuously improve the design quality.

[0069] Accordingly, the present invention also provides a prosthetic socket auxiliary design system, the system includes a processor, a memory and a computer program stored in the memory, the processor is used to execute the computer program, and when the computer program is executed, the system implements the steps of the method described in any of the above embodiments. When the system executes the above method, user information, user key information, socket characteristics, and socket scheme are used as four-stage variables, and the prosthetic socket outcome or satisfaction is used as the label dependent variable.

[0070] Exemplarily, the prosthetic socket auxiliary design system may specifically include a user interface module, a data processing module, a design algorithm module, and a result display module. The user interface module is responsible for collecting user information; the data processing module extracts key user information based on the user information; the design algorithm module performs personalized design of the prosthetic socket based on artificial intelligence technology, including generating a prosthetic socket model, quantifying the socket characteristics, and optimizing the design scheme; the result display module presents the design results to the user in a visual form.

[0071] Specifically, in this system, users input individual information through the user interface module; the data processing module preprocesses the input data and extracts key user information; the design algorithm module generates the prosthetic socket model, quantifies the socket characteristics, and optimizes the design scheme; the result display module presents the design results to the user in the form of a three-dimensional prosthetic socket model, and the user can perform real-time interactive operations to further adjust and optimize the prosthetic socket model. The system iterates and optimizes according to user feedback until a design result that satisfies the user is achieved.

[0072] In summary, in the prior art, the existing prosthetic socket design methods can only select basic information such as the type and material of the socket when designing the prosthetic socket, and cannot achieve a high degree of adaptation with the user. Moreover, the existing prosthetic socket design methods can only know whether the design scheme is feasible after it is completed and actually worn on the patient for adaptation evaluation. It is even difficult to modify the scheme and redesign and manufacture it. The prosthetic socket design system of the present application extracts key information on prosthetic assembly, quantifies the design features of the socket, and uses artificial intelligence algorithms for design and optimization, and quickly generates a prosthetic socket design scheme that meets personalized needs based on the construction model. This method is of great significance for improving the accuracy and efficiency of socket design, meeting personalized needs and digitizing the socket.

[0073] The embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the aforementioned edge computing server deployment method are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0074] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. 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, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0075] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention 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 the steps after understanding the spirit of the present invention.

[0076] In the present invention, the features described and / or illustrated for one embodiment may be used in the same manner or in a similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for assisting the design of a prosthetic socket. It is characterized in that The method comprises the following steps: Obtaining user information, including basic information, physical examination and assessment results, prosthesis use environment, residual limb examination and assessment results, and patient needs; Extracting user key information based on the user information, wherein the user key information includes key information on physical condition, key information on residual limb status, and key information on prosthetic application; Based on the extracted user key information, a prosthetic socket matching the user is constructed through a trained prosthetic socket generation model; Wherein, constructing a prosthetic receiving cavity matching the user through a trained prosthetic receiving cavity generation model based on the extracted user key information includes: Generate a socket feature based on the extracted user key information through a trained socket feature extraction model; Based on the socket features, a prosthetic socket matching the user is constructed by using a trained prosthetic socket generation model; The characteristics of the receiving cavity include the volume of the receiving cavity, the depth of the receiving cavity, the type of the receiving cavity mouth ring, the edge height and direction, the contact and load-bearing method of the residual limb end, the bone movement control method, the condition of the inner liner or silicone sleeve, the material and structure, the way of putting on and taking off, the weight estimation, the extrusion position and range, the load-free position and range, the opening position and size, the supplementary suspension method, the alignment of the receiving cavity, and the shape of the receiving cavity.

2. The prosthetic socket auxiliary design method according to claim 1, It is characterized in that The algorithm used in the receiving cavity feature extraction model is a decision tree algorithm based on information gain, and the calculation formula of information gain is: Where D represents the set of prosthesis configuration samples, a represents user information, and V represents the possibility that user information has V values; D v Indicates that when the prosthesis configuration sample set D is divided based on user information a, the value of a is a v Ent(D) represents the corresponding purity of the prosthetic configuration sample set D; or, The algorithms adopted by the receiving cavity feature extraction model are linear regression algorithm and clustering algorithm.

3. The prosthetic socket auxiliary design method according to claim 1, It is characterized in that Before constructing a prosthetic socket matching the user through a trained prosthetic socket generation model based on the socket characteristics, the method further includes: obtaining a user satisfaction result through a trained satisfaction prediction model based on the user information and the socket characteristics.

4. The prosthetic socket auxiliary design method according to claim 3, It is characterized in that The algorithm used in the satisfaction prediction model is a logistic regression algorithm, and the function of the logistic regression algorithm is: h θ (x) represents satisfaction, e is the Euler constant, θ is the model parameter, x is the user information and the receiving cavity characteristics, and T represents the transposition operation.

5. The prosthetic socket auxiliary design method according to claim 1, It is characterized in that Extracting key user information based on the user information includes: Obtain the evaluation criteria corresponding to each user information; Based on the evaluation criteria, it is determined whether the corresponding user information is user key information.

6. The prosthetic socket auxiliary design method according to claim 1, It is characterized in that Extracting key user information based on the user information includes: Based on the user information, user key information is extracted through a trained key information extraction model.

7. The prosthetic socket auxiliary design method according to claim 6, It is characterized in that The algorithm used by the key information extraction model is: support vector machine, random forest algorithm, one-tail test algorithm, Pearson correlation analysis method or Spearman rank correlation analysis method; and / or The basic information includes: the time and reason of amputation, the state of wearing the prosthesis first; the physical condition examination and assessment results include: balance and coordination, muscle strength, vision, psychology, disease, injury and dysfunction; the prosthesis use environment includes: ground environment and temperature and humidity; the residual limb inspection and assessment results include: amputation position, residual limb length, shape and volume, bone protrusions and bone spurs, skin scar injury and disease, subcutaneous tissue volume and hardness, residual limb end contact and load-bearing capacity, residual limb edema, residual soft tissue sagging, residual limb skin color, residual limb skin temperature, residual limb sensation and pain, joint movement deformity and dysfunction; the patient needs include: daily self-care, occupation, sports and entertainment activities, main use of prostheses, movement methods, walking speed and special needs.

8. A prosthetic socket auxiliary design system, comprising a processor, a memory, and a computer program stored in the memory, It is characterized in that The processor is used to execute the computer program. When the computer program is executed, the system implements the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.