A method for constructing a 3D printing digital twin system based on cloud services

Abstract

The present invention discloses a method for constructing a 3D printing digital twin system based on cloud services, and relates to the technical field of digital twins. During operation of the system, medical data is collected from various sources, and stored, post-processed and cleaned through cloud services. Image processing and analysis are performed on medical imaging data to form a first data group, a second data group and a third data group. A digital twin model of a patient is established, and after calculation, the following is obtained: a 3D printing digital twin index Dyls is obtained, the physiological structure and movement characteristics of the patient are simulated, and a grade evaluation scheme is obtained by matching the 3D printing digital twin index Dyls with a preset standard threshold value Z and a preset standard threshold value X, and prosthetic and artificial medical devices are designed. The physiological characteristics and personalized needs of the patient are considered, and the designed medical device model is converted into a 3D printing file by using 3D printing technology. A cloud service platform is established to store and manage medical data and design files, and collaborative tools and platforms are provided.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins, and in particular to a method for constructing a 3D printing digital twin system based on cloud services. Background Art

[0002] In today's medical field, the application of 3D printing technology has gradually attracted widespread attention. With its fast, flexible and personalized characteristics, 3D printing technology has brought new possibilities to the design and manufacture of medical devices. Through 3D printing technology, medical devices can be customized according to the individual characteristics of patients, realizing personalized medicine, improving treatment effects and the quality of life of patients. With the development of cloud computing technology, the application of cloud services in the medical field is becoming increasingly popular. Cloud services can not only provide powerful data storage and management capabilities, but also enable remote collaboration and access between doctors, patients and designers, providing convenience for the design and manufacture of medical devices.

[0003] However, there are still some problems and challenges in the traditional design and manufacturing process of medical devices. First, the design of traditional medical devices often lacks personalization and it is difficult to fully consider the individual differences of patients, resulting in limited adaptability and comfort of the devices. Secondly, the design and manufacturing process of medical devices usually takes a lot of time and manpower costs, and is inefficient. In addition, due to the complexity and diversity of medical data, traditional medical device design often lacks accurate data support, and the design results may be biased. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides a method for constructing a 3D printing digital twin system based on cloud services, which solves the problems mentioned in the background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for constructing a 3D printing digital twin system based on cloud services, comprising the following steps:

[0008] Step 1: Collect medical data from various sources, including body scan data, medical imaging data, and data required for related parameters, to form a medical imaging information group, a data diversification information group, and a physiological information group, and store the collected data through cloud services;

[0009] Step 2: Processing and cleaning the data quality information group, the data diversity information group and the physiological information group in the data acquisition module, performing image processing and analysis on the medical image data, removing noise and artifacts, and reconstructing and calibrating the body scan data to form a first data group, a second data group and a third data group;

[0010] Step 3: Use the processed first data group, second data group and third data group to establish a digital twin model of the patient, and obtain after calculation: 3D printing digital twin index Dyls, simulate the patient's physiological structure and movement characteristics, including bone structure and muscle tissue, perform biomechanical analysis and simulation, and obtain a grade evaluation scheme by matching the 3D printing digital twin index Dyls with the preset standard threshold Z and the preset standard threshold X to evaluate the practicality of the medical device;

[0011] Step 4: Design medical devices such as prostheses and prostheses based on the digital twin model, taking into account the patient’s physiological characteristics and personalized needs;

[0012] Step 5: Use 3D printing technology to convert the designed medical device model into a 3D printing file, select materials and parameters for printing and production;

[0013] Step 6: Establish a cloud service platform to store and manage medical data and design files, provide collaborative tools and platforms, and enable remote collaboration and access between doctors, designers, and patients.

[0014] Preferably, the medical imaging data, including CT scan images and MRI images, are collected by medical imaging equipment and processed and analyzed by professional technicians to form a medical imaging information group;

[0015] By integrating data recorded by different medical institutions and different devices, diverse information of medical data is collected, including different types of medical data, sampling density and data update frequency, to form a data diversity information group;

[0016] Through 3D scanners or other imaging devices, the patient's body scan data, including residual limb morphology and physiological characteristics, is collected to form a physiological information group, and the collected data is stored through cloud services.

[0017] Preferably, the collected medical image data is processed and analyzed to remove noise and artifacts, the collected medical data diversity information is processed and integrated, and the collected patient body scan data is processed and three-dimensionally reconstructed;

[0018] The pre-processed medical imaging information group, the data diversification information group and the physiological information group are sorted to form a first data group, a second data group and a third data group;

[0019] The first data group includes: medical image resolution Yxfb, signal-to-noise ratio Xzb, data integrity Sjwz and calibration accuracy value Jzjd; the second data group includes: number of data types Sjsl, sampling density value Cymd, data update frequency Sjgx and printing modeling speed Dysd; the third data group includes: body scanning accuracy Stsm, residual limb morphology complexity Czxt, physiological feature matching degree Tzpp and material-skin contact degree Cljc.

[0020] Preferably, a digital twin model of the patient is constructed according to the processed first data group and the third data group, including modeling of the bone structure and the physiological characteristics of the muscle tissue, and a digital anatomical model of the patient is formed by performing three-dimensional reconstruction and model construction by using medical imaging data and body scanning data, and the following are obtained after calculation by a surface algorithm: 3D printing digital twin index Dyls, data quality coefficient Sjzl, data diversity coefficient Sjdy and adaptability coefficient Spxs;

[0021] The 3D printing digital twin index Dyls is calculated by the following formula:

[0022]

[0023] In the formula, Dyls represents the 3D printing digital twin index, Sjzl represents the data quality coefficient, Sjdy represents the data diversity coefficient, Spxs represents the adaptability coefficient, q, w and e represent the proportional coefficients of the data quality coefficient Sjzl, the data diversity coefficient Sjdy and the adaptability coefficient Spxs respectively;

[0024] Among them, 0.12≤q≤0.28, 0.23≤w≤0.35, 0.22≤e≤0.37, and q+w+e≤1.0, and R represents the first correction constant.

[0025] Preferably, the data quality coefficient Sjzl is calculated by the following formula:

[0026] Sjzl=[(Yxfb*t)+(Xzb*y)+(Sjwz*u)+(Jzjd*i)]+O;

[0027] Where, Yxfb represents the medical image resolution, Xzb represents the signal-to-noise ratio, Sjwz represents the data integrity, Jzjd represents the calibration accuracy value, t, y, u and i represent the proportional coefficients of the medical image resolution Yxfb, the signal-to-noise ratio Xzb, the data integrity Sjwz and the calibration accuracy value Jzjd respectively;

[0028] Among them, 0.16≤t≤0.32, 0.13≤y≤0.22, 0.17≤u≤0.26, 0.15≤i≤0.20, and t+y+u≤1.0, O represents the second correction constant.

[0029] Preferably, the data diversity coefficient Sjdy is calculated by the following formula:

[0030] Sjdy=[(Sjsl*p)+(Cymd*a)+(Sjgx*s)+(Dysd*d)]+F;

[0031] Where, Sjsl represents the number of data types, Cymd represents the sampling density value, Sjgx represents the data update frequency, Dysd represents the printing modeling speed, p, a, s and d represent the proportional coefficients of the number of data types Sjsl, the sampling density value Cymd, the data update frequency Sjgx and the printing modeling speed Dysd respectively;

[0032] Among them, 0.17≤p≤0.25, 0.22≤a≤0.35, 0.12≤s≤0.20, 0.15≤d≤0.20, and p+a+s+d≤1.0, and F represents the third correction constant.

[0033] Preferably, the adaptability coefficient Spxs is calculated by the following formula:

[0034] Hzzt=[(Stsm*g)+(Czxt*h)+(Tzpp*j)+(Cljc*c)]+K;

[0035] Wherein, Stsm represents the accuracy of body scanning, Czxt represents the complexity of residual limb morphology, Tzpp represents the matching degree of physiological characteristics, Cljc represents the contact degree between material and skin, g, h, j and c represent the proportional coefficients of body scanning accuracy Stsm, residual limb morphology complexity Czxt, physiological characteristics matching degree Tzpp and material-skin contact degree Cljc respectively;

[0036] Wherein, 0.27≤g≤0.30, 0.22≤h≤0.35, 0.12≤j≤0.20, 0.07≤c≤0.15, and g+h+j+c≤1.0, K represents the fourth correction constant;

[0037] By matching the 3D printing digital twin index Dyls with the preset standard threshold Z and the preset standard threshold X, the grade evaluation scheme is obtained:

[0038] When the 3D printing digital twin index Dyls ≤ the preset standard threshold Z, the first-level evaluation scheme is obtained, indicating that the digital twin model of the medical device is highly matched with the patient's physiological structure, the design and manufacturing process has reached the expected standards, and the medical device has adaptability and comfort;

[0039] When the preset standard threshold Z is less than the 3D printing digital twin index Dyls and less than the preset standard threshold X, the second-level evaluation scheme is obtained, indicating that the digital twin model of the medical device conforms to the patient's physiological structure, the design and manufacturing process meet the standard requirements, and the adaptability and comfort of the medical device do not need to be adjusted;

[0040] When the 3D printing digital twin index Dyls ≥ the preset standard threshold X, the third-level evaluation scheme is obtained, indicating that the matching degree between the digital twin model of the medical device and the patient's physiological structure is 10% lower than the standard threshold, there is a 10% deviation in the design and manufacturing process, and the adaptability and comfort of the medical device are both 10% lower than the standard. Improvement and optimization are needed, and the reconstruction and calibration process of body scan data should be strengthened.

[0041] Preferably, the design scheme and planning of medical devices are formulated based on the digital twin model and personalized needs, taking into account the patient's anatomical structure and personalized needs, and determining the overall design concept and functional layout of the medical device;

[0042] According to the design plan, the specific design of the medical device is carried out, including the appearance design and structural design. Combined with the information of the digital twin model and personalized needs, a medical device model that meets the patient's anatomical characteristics and personalized requirements is designed.

[0043] Preferably, the designed medical device model is converted into a print file STL or OBJ format suitable for a 3D printer for subsequent printing production, and the designed model is repaired and optimized to ensure that it is compatible with a specific 3D printer and printing materials and can be smoothly printed and produced. The medical device is selected according to the specific use and environmental requirements, and the printing parameters are adjusted according to the characteristics of the selected material and the requirements of the printing equipment. The parameters include: layer height, printing speed and temperature to ensure the stability of the printing process and the controllability of the printing quality.

[0044] A method for constructing a 3D printing digital twin system based on cloud services, establishing a cloud service platform for storing and managing medical data and design files. Medical data includes medical imaging data, body scan data, and related parameters of patients, and design files include design drawings and 3D model files of medical devices. A safe and reliable data storage system is established to ensure the integrity and confidentiality of medical data and design files, and appropriate data backup and recovery measures are taken to cope with unexpected situations and data loss risks.

[0045] Provide collaborative tools and platforms to achieve remote collaboration and access between doctors, designers and patients. Collaborative tools include instant messaging tools, online meeting tools, and document and file sharing functions. Through collaborative tools and platforms, doctors, designers and patients can communicate and discuss medical data and design files in real time, jointly participate in the design and optimization process of medical devices, and put forward opinions and suggestions to ensure that the design of medical devices meets the needs and expectations of patients.

[0046] (III) Beneficial effects

[0047] The present invention provides a method for constructing a 3D printing digital twin system based on cloud services, which has the following beneficial effects:

[0048] (1) When the system is running, it collects medical data from various sources, stores and processes them through cloud services, cleans them, processes and analyzes medical imaging data to form a first data group, a second data group, and a third data group, establishes a digital twin model of the patient, and obtains the following after calculation: 3D printing digital twin index Dyls, simulates the patient's physiological structure and movement characteristics, matches the 3D printing digital twin index Dyls with the preset standard threshold Z and the preset standard threshold X, obtains a grade evaluation plan, designs prosthetic and artificial medical devices, considers the patient's physiological characteristics and personalized needs, uses 3D printing technology to convert the designed medical device model into a 3D printing file, establishes a cloud service platform, stores and manages medical data and design files, and provides collaborative tools and platforms.

[0049] (2) By collecting medical data from various sources and storing it in cloud services, the security and reliability of the data are ensured. This makes medical data accessible anytime and anywhere, and provides sufficient data support for subsequent steps. Processing and cleaning the collected medical data can improve the quality and accuracy of the data. Removing noise and artifacts through image processing and analysis, as well as reconstructing and calibrating body scan data, ensures the reliability of the data and provides a reliable foundation for subsequent modeling and design.

[0050] (3) Using the processed data set to establish a digital twin model of the patient, it is possible to accurately simulate the patient's physiological structure and movement characteristics. Such a model can not only be used for the design and optimization of medical devices, but also for biomechanical analysis and simulation to evaluate the practicality of the device. Based on the digital twin model, medical devices such as prostheses and prostheses are designed, taking into account the patient's physiological characteristics and personalized needs. This personalized design can improve the adaptability and comfort of medical devices and meet the individual needs of patients.

[0051] (4) Using 3D printing technology, the designed medical device model is converted into a 3D printing file, and the appropriate materials and parameters are selected for printing and production. This rapid manufacturing method can shorten the manufacturing cycle and improve production efficiency. A cloud service platform is established to achieve remote collaboration and access between doctors, designers, and patients. This collaborative method not only improves work efficiency, but also promotes communication and exchanges between multiple parties, allowing them to jointly participate in the design and optimization process of medical devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic diagram of the steps of a method for constructing a 3D printing digital twin system based on cloud services of the present invention; DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] In today's medical field, the application of 3D printing technology has gradually attracted widespread attention. With its fast, flexible and personalized characteristics, 3D printing technology has brought new possibilities to the design and manufacture of medical devices. Through 3D printing technology, medical devices can be customized according to the individual characteristics of patients, realizing personalized medicine, improving treatment effects and the quality of life of patients. With the development of cloud computing technology, the application of cloud services in the medical field is becoming increasingly popular. Cloud services can not only provide powerful data storage and management capabilities, but also enable remote collaboration and access between doctors, patients and designers, providing convenience for the design and manufacture of medical devices.

[0055] However, there are still some problems and challenges in the traditional design and manufacturing process of medical devices. First, the design of traditional medical devices often lacks personalization and it is difficult to fully consider the individual differences of patients, resulting in limited adaptability and comfort of the devices. Secondly, the design and manufacturing process of medical devices usually takes a lot of time and manpower costs, and is inefficient. In addition, due to the complexity and diversity of medical data, traditional medical device design often lacks accurate data support, and the design results may be biased.

[0056] Example 1

[0057] The present invention provides a method for constructing a 3D printing digital twin system based on cloud services. Figure 1 , including the following steps:

[0058] Step 1: Collect medical data from various sources, including body scan data, medical imaging data, and data required for related parameters, to form a medical imaging information group, a data diversification information group, and a physiological information group, and store the collected data through cloud services;

[0059] Step 2: Processing and cleaning the data quality information group, the data diversity information group and the physiological information group in the data acquisition module, performing image processing and analysis on the medical image data, removing noise and artifacts, and reconstructing and calibrating the body scan data to form a first data group, a second data group and a third data group;

[0060] Step 3: Use the processed first data group, second data group and third data group to establish a digital twin model of the patient, and obtain after calculation: 3D printing digital twin index Dyls, simulate the patient's physiological structure and movement characteristics, including bone structure and muscle tissue, perform biomechanical analysis and simulation, and obtain a grade evaluation scheme by matching the 3D printing digital twin index Dyls with the preset standard threshold Z and the preset standard threshold X to evaluate the practicality of the medical device;

[0061] Step 4: Design medical devices such as prostheses and prostheses based on the digital twin model, taking into account the patient’s physiological characteristics and personalized needs;

[0062] Step 5: Use 3D printing technology to convert the designed medical device model into a 3D printing file, select materials and parameters for printing and production;

[0063] Step 6: Establish a cloud service platform to store and manage medical data and design files, provide collaborative tools and platforms, and enable remote collaboration and access between doctors, designers, and patients.

[0064] In this embodiment, medical data is collected from various sources, stored, post-processed and cleaned through cloud services, image processing and analysis are performed on medical image data, noise and artifacts are removed, body scan data are reconstructed and calibrated to form a first data group, a second data group and a third data group, a digital twin model of the patient is established, and the following is calculated: 3D printing digital twin index Dyls is obtained, the patient's physiological structure and movement characteristics, including bone structure and muscle tissue, are simulated, biomechanical analysis and simulation are performed, the 3D printing digital twin index Dyls is matched with a preset standard threshold Z and a preset standard threshold X, a grade evaluation scheme is obtained, the practicality of the medical device is evaluated, and based on the digital twin model, prosthetic and artificial medical devices are designed, taking into account the patient's physiological characteristics and personalized needs, using 3D printing technology to convert the designed medical device model into a 3D printing file, materials and parameters are selected for printing and production, a cloud service platform is established, medical data and design files are stored and managed, collaboration tools and platforms are provided, and remote collaboration and access between doctors, designers and patients are realized.

[0065] Example 2

[0066] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: Medical imaging data, including CT scan images and MRI images, are collected through medical imaging equipment and processed and analyzed by professional technicians to form a medical imaging information group;

[0067] By integrating data recorded by different medical institutions and different devices, diverse information of medical data is collected, including different types of medical data, sampling density and data update frequency, to form a data diversity information group;

[0068] Through 3D scanners or other imaging devices, the patient's body scan data, including residual limb morphology and physiological characteristics, is collected to form a physiological information group, and the collected data is stored through cloud services.

[0069] Remove noise and artifacts by performing image processing and analysis on the collected medical image data, process and integrate the diverse information of the collected medical data, and process and 3D reconstruct the collected patient body scan data;

[0070] The pre-processed medical imaging information group, the data diversification information group and the physiological information group are sorted to form a first data group, a second data group and a third data group;

[0071] The first data group includes: medical image resolution Yxfb, signal-to-noise ratio Xzb, data integrity Sjwz and calibration accuracy value Jzjd; the second data group includes: number of data types Sjsl, sampling density value Cymd, data update frequency Sjgx and printing modeling speed Dysd; the third data group includes: body scanning accuracy Stsm, residual limb morphology complexity Czxt, physiological feature matching degree Tzpp and material-skin contact degree Cljc.

[0072] In this embodiment, professional technicians process and analyze medical image data to remove noise and artifacts, thereby ensuring the quality and accuracy of the image data. This provides a reliable data basis for the subsequent establishment of a digital twin model, integrating data from different medical institutions and different equipment records, including different types of medical data, sampling density, and data update frequency, to form a diversified information group. Such data diversity helps to improve the comprehensive performance of the digital twin model. The patient's body scan data, including residual limb morphology and physiological characteristics, is collected to form a physiological information group. These data are of great significance for personalized design and customized medical devices.

[0073] Example 3

[0074] This embodiment is explained in Example 1, please refer to Figure 1 Specifically: construct a digital twin model of the patient according to the processed first data group and the third data group, including modeling of the bone structure and muscle tissue physiological characteristics, and perform three-dimensional reconstruction and model construction by using medical imaging data and body scan data to form a digital anatomical model of the patient, and obtain the following after calculation by the surface algorithm: 3D printing digital twin index Dyls, data quality coefficient Sjzl, data diversity coefficient Sjdy and adaptability coefficient Spxs;

[0075] The 3D printing digital twin index Dyls is calculated by the following formula:

[0076]

[0077] In the formula, Dyls represents the 3D printing digital twin index, Sjzl represents the data quality coefficient, Sjdy represents the data diversity coefficient, Spxs represents the adaptability coefficient, q, w and e represent the proportional coefficients of the data quality coefficient Sjzl, the data diversity coefficient Sjdy and the adaptability coefficient Spxs respectively;

[0078] Among them, 0.12≤q≤0.28, 0.23≤w≤0.35, 0.22≤e≤0.37, and q+w+e≤1.0, and R represents the first correction constant.

[0079] The data quality coefficient Sjzl is calculated by the following formula:

[0080] Sjzl=[(Yxfb*t)+(Xzb*y)+(Sjwz*u)+(Jzjd*i)]+O;

[0081] Where, Yxfb represents the medical image resolution, Xzb represents the signal-to-noise ratio, Sjwz represents the data integrity, Jzjd represents the calibration accuracy value, t, y, u and i represent the proportional coefficients of the medical image resolution Yxfb, the signal-to-noise ratio Xzb, the data integrity Sjwz and the calibration accuracy value Jzjd respectively;

[0082] Among them, 0.16≤t≤0.32, 0.13≤y≤0.22, 0.17≤u≤0.26, 0.15≤i≤0.20, and t+y+u≤1.0, O represents the second correction constant.

[0083] The data diversity coefficient Sjdy is calculated by the following formula:

[0084] Sjdy=[(Sjsl*p)+(Cymd*a)+(Sjgx*s)+(Dysd*d)]+F;

[0085] Where, Sjsl represents the number of data types, Cymd represents the sampling density value, Sjgx represents the data update frequency, Dysd represents the printing modeling speed, p, a, s and d represent the proportional coefficients of the number of data types Sjsl, the sampling density value Cymd, the data update frequency Sjgx and the printing modeling speed Dysd respectively;

[0086] Among them, 0.17≤p≤0.25, 0.22≤a≤0.35, 0.12≤s≤0.20, 0.15≤d≤0.20, and p+a+s+d≤1.0, and F represents the third correction constant.

[0087] The adaptability coefficient Spxs is calculated by the following formula:

[0088] Hzzt=[(Stsm*g)+(Czxt*h)+(Tzpp*j)+(Cljc*c)]+K;

[0089] Wherein, Stsm represents the accuracy of body scanning, Czxt represents the complexity of residual limb morphology, Tzpp represents the matching degree of physiological characteristics, Cljc represents the contact degree between material and skin, g, h, j and c represent the proportional coefficients of body scanning accuracy Stsm, residual limb morphology complexity Czxt, physiological characteristics matching degree Tzpp and material-skin contact degree Cljc respectively;

[0090] Wherein, 0.27≤g≤0.30, 0.22≤h≤0.35, 0.12≤j≤0.20, 0.07≤c≤0.15, and g+h+j+c≤1.0, K represents the fourth correction constant;

[0091] By matching the 3D printing digital twin index Dyls with the preset standard threshold Z and the preset standard threshold X, the grade evaluation scheme is obtained:

[0092] When the 3D printing digital twin index Dyls ≤ the preset standard threshold Z, the first-level evaluation scheme is obtained, indicating that the digital twin model of the medical device is highly matched with the patient's physiological structure, the design and manufacturing process has reached the expected standards, and the medical device has adaptability and comfort;

[0093] When the preset standard threshold Z is less than the 3D printing digital twin index Dyls and less than the preset standard threshold X, the second-level evaluation scheme is obtained, indicating that the digital twin model of the medical device conforms to the patient's physiological structure, the design and manufacturing process meet the standard requirements, and the adaptability and comfort of the medical device do not need to be adjusted;

[0094] When the 3D printing digital twin index Dyls ≥ the preset standard threshold X, the third-level evaluation scheme is obtained, indicating that the matching degree between the digital twin model of the medical device and the patient's physiological structure is 10% lower than the standard threshold, there is a 10% deviation in the design and manufacturing process, and the adaptability and comfort of the medical device are both 10% lower than the standard. Improvement and optimization are needed, and the reconstruction and calibration process of body scan data should be strengthened.

[0095] In this embodiment, a digital twin model of the patient is constructed by processing the first data group and the third data group, including modeling of the physiological characteristics of the bone structure and muscle tissue. This model can more accurately simulate the patient's physiological structure and movement characteristics, and provide a reliable basis for the design of personalized medical devices. The 3D printing digital twin index Dyls and related data quality coefficients, data diversity coefficients, and adaptability coefficients are calculated by the surface algorithm. These indicators can comprehensively evaluate the quality and matching degree of the digital twin model, and provide a reference for the practicality of the medical device design. According to the comparison between the 3D printing digital twin index Dyls and the preset standard threshold, the grade evaluation scheme of the medical device is obtained, which helps to evaluate the matching degree between the medical device model and the patient's physiological structure, as well as the degree of compliance of the design and manufacturing process, and provides guidance for further improvement and optimization. According to the digital twin model and the evaluation results, personalized medical devices can be designed and optimized. By considering the patient's physiological characteristics and personalized needs, a medical device model that meets the patient's anatomical characteristics and personalized requirements is designed, thereby improving the adaptability and comfort of the medical device.

[0096] Example 4

[0097] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: Develop the design plan and plan of medical devices based on the digital twin model and personalized needs, ,consider the patient's anatomical structure and personalized needs, and determine the ,overall design concept and functional layout of medical devices;

[0098] According to the design plan, the specific design of the medical device is carried out, including the appearance design and structural design. Combined with the information of the digital twin model and personalized needs, a medical device model that meets the patient's anatomical characteristics and personalized requirements is designed.

[0099] Convert the designed medical device model into a print file STL or OBJ format suitable for 3D printers for subsequent printing production. Repair and optimize the designed model to ensure its compatibility with specific 3D printers and printing materials, and to enable smooth printing production. Select the medical device according to its specific use and environmental requirements, and adjust the printing parameters according to the characteristics of the selected material and the requirements of the printing equipment. The parameters include: layer height, printing speed and temperature to ensure the stability of the printing process and the controllability of the printing quality.

[0100] Example 5

[0101] A method for building a 3D printing digital twin system based on cloud services, please refer to Figure 1 Specifically: Establish a cloud service platform to store and manage medical data and design files. Medical data includes patients' medical imaging data, body scan data and related parameters. Design files include design drawings and 3D model files of medical devices. Establish a safe and reliable data storage system to ensure the integrity and confidentiality of medical data and design files, and take corresponding data backup and recovery measures to deal with unexpected situations and data loss risks;

[0102] Provide collaborative tools and platforms to achieve remote collaboration and access between doctors, designers and patients. Collaborative tools include instant messaging tools, online meeting tools, and document and file sharing functions. Through collaborative tools and platforms, doctors, designers and patients can communicate and discuss medical data and design files in real time, jointly participate in the design and optimization process of medical devices, and put forward opinions and suggestions to ensure that the design of medical devices meets the needs and expectations of patients.

[0103] In this embodiment, by establishing a safe and reliable data storage system, medical data and design files are effectively protected to ensure their integrity and confidentiality. Data backup and recovery measures are taken to effectively combat unexpected situations and data loss risks, ensure the security and reliability of medical information, provide instant messaging tools, online conference tools, and the function of sharing documents and files, and realize remote collaboration and access between doctors, designers, and patients. It helps to improve communication efficiency and collaboration effects. Doctors, designers, and patients can jointly participate in the design and optimization process of medical devices, put forward opinions and suggestions, and improve the quality and applicability of medical devices. The remote collaboration and access platform can effectively improve the work efficiency of the design team. Real-time communication and discussion between doctors, designers, and patients helps to discover and solve problems in a timely manner, accelerates the process of medical device design, and improves design quality. The remote collaboration platform provides opportunities for communication and cooperation for professionals in different fields.

[0104] Specific example:

[0105] Assume that a patient needs to use a cloud-based 3D printing digital twin system construction method to collect the following parameters:

[0106] First data set:

[0107] Medical image resolution Yxfb: 1, signal-to-noise ratio Xzb: 25, data integrity Sjwz: 95%, calibration accuracy value Jzjd: 0.1;

[0108] Second data set:

[0109] Number of data types Sjsl: 5, sampling density value Cymd: 200, data update frequency Sjgx: 1, printing modeling speed Dysd: 30;

[0110] The third data set:

[0111] Body scanning accuracy Stsm: 25, residual limb morphology complexity Czxt: 80%, physiological characteristics matching degree Tzpp: 80%

[0112] Material contact with skin Cljc: 99%;

[0113] Corresponding proportional coefficients: q = 0.25, w = 0.25, e = 0.32, t = 0.22, y = 0.20, u = 0.28, i = 0.16, p = 0.18, a = 0.20, s = 0.18, d = 0.16, g = 0.28, h = 0.26, j = 0.18, c = 0.12;

[0114] The first correction constant: R = 0.98, the second correction constant: O = 0.52, the third correction constant: F = 0.42, the fourth correction constant: K = 0.92;

[0115] Sjzl=(1×0.22)+(25×0.20)+(0.95×0.28)+(0.1×0.16)+0.52=6;

[0116] Sjdy=(5×0.18)+(200×0.20)+(1×0.18)+(30×0.16)+0.42=46;

[0117] Hzzt=(25×0.28)+(80×0.26)+(80×0.18)+(99×0.12)+0.92=55;

[0118] [(0.25×5.484)+(0.25×45.88) / 0.25+0.25]+(0.32×54.08)+0.98=44;

[0119] When the preset standard threshold X is set to 50, the preset standard threshold Z is set to 30, and the preset standard threshold Z is less than the 3D printing digital twin index Dyls less than the preset standard threshold X, the second-level evaluation scheme is obtained, indicating that the digital twin model of the medical device conforms to the patient's physiological structure, the design and manufacturing process meet the standard requirements, and the adaptability and comfort of the medical device do not need to be adjusted.

[0120] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for constructing a 3D printing digital twin system based on cloud services, characterized in that: The following steps are involved: Step 1: Collect medical data from various sources, including body scan data, medical imaging data, and data required for related parameters, to form a medical imaging information group, a data diversification information group, and a physiological information group, and store the collected medical data through cloud services; Collect medical imaging data, including CT scan images and MRI images, to form a medical imaging information group; By integrating data recorded by different medical institutions and different devices, diverse information of medical data is collected, including different types of medical data, sampling density and data update frequency, to form a data diversity information group; Collect patient body scan data, including residual limb morphology and physiological characteristics, to form a physiological information group; Step 2: Remove noise and artifacts by performing image processing and analysis on the collected medical image data, process and integrate the diverse information of the collected medical data, and process and three-dimensionally reconstruct the collected patient body scan data; The pre-processed medical imaging information group, the data diversification information group and the physiological information group are sorted to form a first data group, a second data group and a third data group; The first data group includes: medical image resolution Yxfb, signal-to-noise ratio Xzb, data integrity Sjwz and calibration accuracy value Jzjd, the second data group includes: data type number Sjsl, sampling density value Cymd, data update frequency Sjgx and printing modeling speed Dysd, the third data group includes: body scanning accuracy Stsm, residual limb morphology complexity Czxt, physiological feature matching degree Tzpp and material-skin contact degree Cljc; Step 3: Based on the processed first data group, second data group and third data group, a digital twin model of the patient is constructed, including the modeling of the bone structure and the physiological characteristics of the muscle tissue. By using the medical imaging information group and the physiological information group, three-dimensional reconstruction and model construction are performed to form a digital anatomical model of the patient. After calculation by the surface algorithm, the following are obtained: 3D printing digital twin index Dyls, data quality coefficient Sjzl, data diversity coefficient Sjdy and adaptability coefficient Spxs; Simulate the patient's physiological structure and movement characteristics, including bone structure and muscle tissue, to perform biomechanical analysis and simulation; The 3D printing digital twin index Dyls is calculated by the following formula: In the formula, Dyls represents the 3D printing digital twin index, Sjzl represents the data quality coefficient, Sjdy represents the data diversity coefficient, Spxs represents the adaptability coefficient, q, w and e represent the proportional coefficients of the data quality coefficient Sjzl, the data diversity coefficient Sjdy and the adaptability coefficient Spxs respectively; Wherein, 0.12≤q≤0.28, 0.23≤w≤0.35, 0.22≤e≤0.37, and q+w+e≤1.0, R represents the first correction constant; The data quality coefficient Sjzl is calculated by the following formula: Sjzl=[(Yxfb*t)+(Xzb*y)+(Sjwz*u)+(Jzjd*i)]+O; Where, Yxfb represents the medical image resolution, Xzb represents the signal-to-noise ratio, Sjwz represents the data integrity, Jzjd represents the calibration accuracy value, t, y, u and i represent the proportional coefficients of the medical image resolution Yxfb, the signal-to-noise ratio Xzb, the data integrity Sjwz and the calibration accuracy value Jzjd respectively; Wherein, 0.16≤t≤0.32, 0.13≤y≤0.22, 0.17≤u≤0.26, 0.15≤i≤0.20, and t+y+u≤1.0, O represents the second correction constant; The data diversity coefficient Sjdy is calculated by the following formula: Sjdy=[(Sjsl*p)+(Cymd*a)+(Sjgx*s)+(Dysd*d)]+F; Where, Sjsl represents the number of data types, Cymd represents the sampling density value, Sjgx represents the data update frequency, Dysd represents the printing modeling speed, p, a, s and d represent the proportional coefficients of the number of data types Sjsl, the sampling density value Cymd, the data update frequency Sjgx and the printing modeling speed Dysd respectively; Wherein, 0.17≤p≤0.25, 0.22≤a≤0.35, 0.12≤s≤0.20, 0.15≤d≤0.20, and p+a+s+d≤1.0, F represents the third correction constant; The adaptability coefficient Spxs is calculated by the following formula: Spxs=[(Stsm*g)+(Czxt*h)+(Tzpp*j)+(Cljc*c)]+K; Wherein, Stsm represents the accuracy of body scanning, Czxt represents the complexity of residual limb morphology, Tzpp represents the matching degree of physiological characteristics, Cljc represents the contact degree between material and skin, g, h, j and c represent the proportional coefficients of body scanning accuracy Stsm, residual limb morphology complexity Czxt, physiological characteristics matching degree Tzpp and material-skin contact degree Cljc respectively; Wherein, 0.27≤g≤0.30, 0.22≤h≤0.35, 0.12≤j≤0.20, 0.07≤c≤0.15, and g+h+j+c≤1.0, K represents the fourth correction constant; By matching the 3D printing digital twin index Dyls with the preset standard threshold Z and the preset standard threshold X, the grade evaluation scheme is obtained: When the 3D printing digital twin index Dyls ≤ the preset standard threshold Z, the first-level evaluation scheme is obtained, indicating that the digital twin model of the medical device is highly matched with the patient's physiological structure, the design and manufacturing process has reached the expected standards, and the medical device has adaptability and comfort; When the preset standard threshold Z is less than the 3D printing digital twin index Dyls and less than the preset standard threshold X, the second-level evaluation scheme is obtained, indicating that the digital twin model of the medical device conforms to the patient's physiological structure, the design and manufacturing process meet the standard requirements, and the adaptability and comfort of the medical device do not need to be adjusted; When the 3D printing digital twin index Dyls ≥ the preset standard threshold X, the third-level evaluation scheme is obtained, indicating that the matching degree between the digital twin model of the medical device and the patient's physiological structure is 10% lower than the standard threshold, there is a 10% deviation in the design and manufacturing process, and the adaptability and comfort of the medical device are both 10% lower than the standard. Improvement and optimization are needed to strengthen the reconstruction and calibration process of body scan data; Step 4: Design medical devices such as prostheses and prostheses based on the digital twin model, taking into account the patient’s physiological characteristics and personalized needs; Step 5: Use 3D printing technology to convert the designed medical device model into a 3D printing file, select materials and parameters for printing and production; Step 6: Establish a cloud service platform to store and manage medical data and design files, provide collaborative tools and platforms, and enable remote collaboration and access between doctors, designers, and patients.

2. The method for constructing a 3D printing digital twin system based on cloud services according to claim 1, characterized in that: Based on the digital twin model and personalized needs, formulate the design plan and planning of medical devices, consider the patient's anatomical structure and personalized needs, and determine the overall design concept and functional layout of medical devices; According to the design plan, the specific design of the medical device is carried out, including the appearance design and structural design. Combined with the information of the digital twin model and personalized needs, a medical device model that meets the patient's anatomical characteristics and personalized requirements is designed.

3. The method for constructing a 3D printing digital twin system based on cloud services according to claim 1, characterized in that: Convert the designed medical device model into a print file STL or OBJ format suitable for 3D printers for subsequent printing production. Repair and optimize the designed model to ensure its compatibility with specific 3D printers and printing materials, and to enable smooth printing production. Select the medical device according to its specific use and environmental requirements, and adjust the printing parameters according to the characteristics of the selected material and the requirements of the printing equipment. The parameters include: layer height, printing speed and temperature to ensure the stability of the printing process and the controllability of the printing quality.

4. The method for constructing a 3D printing digital twin system based on cloud services according to claim 1, characterized in that: Establish a cloud service platform to store and manage medical data and design files. Medical data includes patients' medical imaging data, body scan data and related parameters. Design files include design drawings and 3D model files of medical devices. Establish a safe and reliable data storage system to ensure the integrity and confidentiality of medical data and design files, and take appropriate data backup and recovery measures to deal with unexpected situations and data loss risks; Provide collaborative tools and platforms to achieve remote collaboration and access between doctors, designers and patients. Collaborative tools include instant messaging tools, online meeting tools, and document and file sharing functions. Through collaborative tools and platforms, doctors, designers and patients can communicate and discuss medical data and design files in real time, jointly participate in the design and optimization process of medical devices, and put forward opinions and suggestions to ensure that the design of medical devices meets the needs and expectations of patients.

Images