Big data-based artificial organ production system

WO2024122914A3PCT designated stage expired Publication Date: 2024-12-05CHAE HYEOK JU
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2023/018235
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-12-07
Filing Date
2023-11-14
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

Current methods for producing artificial organs through bioprinting face challenges in efficiently creating customized organs that meet various user requirements, such as specific physical properties and patient-specific conditions, due to the complexity and diversity of raw materials, leading to lengthy and costly experimentation and production processes.

Method used

A big data-based artificial organ production system that includes an input unit for user requirements, a database unit storing relevant big data, and a control unit using machine learning algorithms to generate process variables for a 3D bio-printer, enabling the production of user-customized artificial organs with specified properties like hardness, tensile strength, and ductility, and optimizing raw material composition and synthesis conditions.

Benefits of technology

This system allows for the rapid production of user-customized artificial organs with reduced experimentation and verification time, enabling mass production of artificial organs with desired specifications and improving the accuracy and efficiency of bioprinting processes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2023018235_05122024_PF_FP_ABST
    Figure KR2023018235_05122024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to a big data-based artificial organ production system. The artificial organ production system, according to the present invention, comprises: an input unit that receives a user's requirements for an artificial organ to be produced as an input value; a database unit that stores data necessary for producing artificial organs; a control unit that produces the artificial organ by inputting an input value into an artificial organ production algorithm learned on the basis of the database unit; and a bioprinter that produces the artificial organ according to the control of the control unit.
Need to check novelty before this filing date? Find Prior Art

Description

Big data-based artificial organ production system

[0001] This application claims the benefit of priority from Republic of Korea Patent Application No. 10-2022-0169461, dated December 7, 2022, and all contents of that Republic of Korea patent application are incorporated herein by reference.

[0002] The present invention relates to a system for manufacturing artificial organs, and more specifically, to a system for manufacturing artificial organs based on big data.

[0003] Bioprinting is being utilized as a method for creating artificial organs. Bioprinting allows for the spatial structuring of living cells and other biological products, biomaterials, biochemicals, or biocompatible materials by sequentially depositing them layer by layer under computer control, creating living tissues and organs for tissue engineering, regenerative medicine, pharmacodynamics, and more generally, biological research.

[0004] When attempting to manufacture artificial organs using this type of bioprinting, in order to manufacture artificial organs with the desired conditions, experiments are conducted to ensure that the conditions are met before production.

[0005] Artificial organs are used in a variety of applications, including medical practice. For these purposes, artificial organs are needed for a variety of cases. However, there are limitations in research and experimentation to produce artificial organs that meet the needs of each specific case.

[0006] [Prior Art Literature]

[0007] [Patent Document]

[0008] (Patent Document 1) Republic of Korea Patent Publication No. 10-1954953 (registered on February 27, 2019)

[0009] Therefore, the purpose of the present invention is to provide a big data-based artificial organ manufacturing system capable of manufacturing an artificial organ corresponding to conditions requested by a user based on big data related to artificial organs.

[0010] In order to achieve the above object, the present invention provides a big data-based artificial organ manufacturing system including: an input unit for receiving a user's requirements for an artificial organ to be manufactured as input values; a database unit for storing big data necessary for manufacturing an artificial organ; a control unit for inputting the input values ​​into an artificial organ manufacturing algorithm learned based on the database unit to produce process variables capable of manufacturing an artificial organ; and a bio-printer for manufacturing an artificial organ with the process variables under the control of the control unit.

[0011] The above input values ​​may include hardness, tensile strength, toughness and ductility of the artificial organ.

[0012] The above input value may be a numeric value.

[0013] The above database section can store data on multiple raw materials required for manufacturing artificial organs, the weight of each raw material, preprocessing conditions, temperature, catalyst conditions, and reaction time.

[0014] The above database section can store mechanical property data including Young's Modulus, Ultimate Tensile Strength, Toughness, and Fracture Point according to the ratio of raw materials when synthesizing multiple raw materials.

[0015] The above database section can store data on agarose, acrylamide, N,N'-methylenebis(acrylamide) (MBA), tetramethylethylenediamine (TEMED), deionized water, ammonium sulfate (APS), and temperature.

[0016] The above bioprinter may be a 3D bioprinter.

[0017] The above control unit can generate an artificial organ modeling file (STL) including the process variables using an artificial organ production algorithm learned with the input values, and provide the generated artificial organ modeling file (STL) to the bio printer to bioprint the artificial organ.

[0018] The above artificial organ production algorithm may include a data reverse engineering model that generates virtual data required for machine learning using reverse engineering technology; and an artificial organ production model that performs machine learning using the virtual data generated by the data reverse engineering model and then controls the bioprinter to produce a user-customized artificial organ using the user's requirements as input values.

[0019] The above data reverse engineering model may include a surrogate model that extracts features from raw materials through molecular fingerprinting and predicts target properties (mechanical properties, electrical properties, and 3D printability); a reverse engineering deep learning model that performs raw material selection and process variable selection capable of synthesizing target properties; and a virtual data model that generates virtual data by estimating the data distribution of the synthetic variable space.

[0020] And the artificial organ production model may include a machine learning model that derives an optimal design for each organ tissue based on the user's requirements (patient's physiological (BMI, 3D tissue model), genetic, and demographic ((age, gender)) information); an artificial intelligence model that designs an automated synthesis process including process variables through machine learning based on the big data; and a printer control model that applies the process variables to the control of the bioprinter to produce a user-customized artificial organ.

[0021] According to the present invention, artificial organs can be manufactured based on big data related to artificial organs, responding to user-requested conditions. Specifically, based on big data acquired during the manufacturing process of various artificial organs, customized artificial organs can be manufactured using bioprinting, using the user's requested conditions as input values.

[0022] Since the input values ​​are numerical values ​​for the hardness, tensile strength, toughness, and ductility of the artificial organ, the artificial organ can be customized and manufactured by inputting numerical values, and in the case of artificial organs with the same specifications, there is an advantage in that mass production is possible with just one input.

[0023] Since the artificial organ production system according to the present invention is based on big data, the time required for experimentation, manufacturing, and verification can be reduced.

[0024] Figure 1 is a block diagram showing a big data-based artificial organ production system according to an embodiment of the present invention.

[0025] Figure 2 is a block diagram showing the database section of Figure 1.

[0026] Figures 3 to 5 are graphs showing stress-strain characteristics for monomers (Agarose, Acrylamide) and additives (MBA).

[0027] Figure 6 is a graph showing the mechanical properties of the additive, including Young's modulus, ultimate tensile strength, and toughness.

[0028] Figure 7 is a graph showing the fracture point among the mechanical properties of the additive.

[0029] Figure 8 is a table showing the data processing results of raw materials used in the production of artificial organs.

[0030] Figure 9 is a graph showing mechanical properties according to the ratio of monomer (Agarose, Acrylamide) and additive (MBA).

[0031] Figure 10 is a block diagram showing an artificial organ manufacturing algorithm according to an embodiment of the present invention.

[0032] Figure 11 is a detailed block diagram showing a model that constitutes the artificial organ production algorithm of Figure 10.

[0033] It should be noted that in the following description, only the parts necessary for understanding the embodiments of the present invention are described, and the description of other parts will be omitted to the extent that it does not deviate from the gist of the present invention.

[0034] The terms and words used in this specification and claims described below should not be interpreted as limited to their conventional or dictionary meanings, but should be interpreted with meanings and concepts that conform to the technical idea of ​​the present invention based on the principle that the inventor can appropriately define the concept of the term to best describe his or her own invention. Therefore, the embodiments described in this specification and the configurations illustrated in the drawings are merely preferred embodiments of the present invention and do not represent all of the technical idea of ​​the present invention. Therefore, it should be understood that there may be various equivalents and modified examples that can replace them at the time of this application.

[0035] Hereinafter, embodiments of the present invention will be described in more detail with reference to the attached drawings.

[0036] FIG. 1 is a block diagram showing a big data-based artificial organ production system according to an embodiment of the present invention. FIG. 2 is a block diagram showing the database section of FIG. 1.

[0037] Referring to FIGS. 1 and 2, the artificial organ production system (100) according to the present embodiment is a system that produces a user-customized artificial organ by bioprinting using an artificial organ production algorithm (50) learned based on big data.

[0038] The artificial organ manufacturing system (100) according to this embodiment includes an input unit (10), a database unit (20), a control unit (30), and a bio-printer (40). The input unit (10) receives a user's requirements for an artificial organ to be manufactured as an input value. The database unit (20) stores big data required for manufacturing an artificial organ. The control unit (30) inputs an input value into an artificial organ manufacturing algorithm (50) learned based on the database unit (20) to produce process variables capable of manufacturing an artificial organ. In addition, the bio-printer (40) manufactures an artificial organ using the process variables under the control of the control unit (30).

[0039] Here, the input unit (10) receives input values ​​from the user regarding requirements for the artificial organ to be manufactured. The user's requirements may include the patient's physiological (BMI, 3D tissue model), genetic, and demographic (age, gender) information. The input values ​​may include information on the type and properties of the artificial organ. Information on the properties includes the hardness, tensile strength, toughness, and ductility of the artificial organ, and the corresponding input values ​​are entered as numerical values.

[0040] Alternatively, information about the physical properties may be entered in text form. The control unit (30) may convert the information about the physical properties entered in text form into numerical values ​​based on big data.

[0041] The input unit (10) may be a physical input device that directly receives a request condition from a user, such as a keyboard or mouse. Alternatively, the input unit (10) may be a communication unit that receives a request condition through a user terminal.

[0042] The database unit (20) stores big data used in the production of various artificial organs. This database unit (20) stores data on a plurality of raw materials required for the production of artificial organs, the weight of each raw material, preprocessing conditions, temperature, catalyst conditions, and reaction time. For example, the database unit (20)

[0043] Data required for the production of artificial organs, such as agarose, acrylamide, N, N'-methylenebis(acrylamide) (MBA), tetramethylethylenediamine (TEMED), deionized water, ammonium sulfate (APS), and temperature, can be stored, and this is a material according to one embodiment, but is not limited thereto.

[0044] As big data, as illustrated in Figures 3 to 9, when synthesizing raw materials used in the production of artificial organs, mechanical property data (Young's Modulus, Ultimate Tensile Strength, Toughness, Fracture Point) are collected according to the ratio of monomer (Agarose, Acrylamide) or additive (MBA). In Figure 8, 'Agar' represents Agarose, and 'AM' represents Acrylamide.

[0045] When synthesizing raw materials, it can be confirmed that the toughness and strength increase as the amount of monomer and additive increases.

[0046] Therefore, in order to manufacture artificial organs, when synthesizing raw materials, based on mechanical property data according to the amount of the above-mentioned monomer and additive, the synthesis conditions (process variables) of raw materials suitable for the user's requirements can be derived through machine learning.

[0047] Here, Figures 3 to 5 are graphs showing the stress-strain characteristics for monomers (Agarose, Acrylamide) and additives (MBA). Figure 3 shows the stress-strain characteristics of Agarose. Figure 4 shows the stress-strain characteristics of Acrylamide. And Figure 5 shows the stress-strain characteristics of the additive (MBA).

[0048] The database section (20) can store an artificial organ modeling file (STL) created using an artificial organ production algorithm (50) learned from the user's requirements as input values.

[0049] The bioprinter (40) manufactures artificial organs using a learned artificial organ manufacturing algorithm (50) under the control of the control unit (30). The bioprinter (40) is a 3D bioprinter. That is, the bioprinter (40) receives an artificial organ modeling file (STL) created using the learned artificial organ manufacturing algorithm (50) and manufactures an artificial organ using 3D bioprinting.

[0050] Here, artificial organs are manufactured by 3D bioprinting and may include, but are not limited to, artificial skin, artificial blood vessels (for bleeding and hemostasis), and artificial peritoneum.

[0051] 3D bioprinting involves scanning a target structure in three dimensions to obtain an image, then transforming the scanned image into a three-dimensional structure using cells and bioink. Common 3D printing technologies include extrusion, inkjet, and laser-based processes. Of these, extrusion is the most widely used method for bioprinting, which involves creating three-dimensional structures with cells. Since bioprinting relies on the inclusion of living cells, bioink, the substance that mixes with cells to form three-dimensional structures, is a crucial component of 3D bioprinting.

[0052] Meanwhile, in the case where the artificial organ according to the present embodiment is used for medical education, not all raw materials constituting the bioink need to be biocompatible substances.

[0053] And the control unit (30) is a microprocessor that performs overall control of the artificial organ production system (100). The control unit (30) controls the production of a customized artificial organ by bio-printing using an artificial organ production algorithm (50) learned based on big data. That is, the control unit (30) uses the learned artificial organ production algorithm (50) with the user's requirements for the artificial organ to be produced as input values ​​to generate an artificial organ modeling file (STL). And the control unit (30) provides the artificial organ modeling file (STL) to the bio-printer (40), thereby producing a customized artificial organ by bio-printing.

[0054] The artificial organ manufacturing algorithm (50) according to this embodiment analyzes trends based on big data, then selects an algorithm with a high predictive rate to reverse engineer raw materials. Furthermore, machine learning can be used to provide customized artificial organs to minimize trial and error based on various user requirements, such as gender and age.

[0055] Machine learning encompasses a variety of algorithms, and the appropriate algorithm can be selected based on the data. Machine learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.

[0056] Supervised learning uses labeled data to train a computer. The label represents the correct value for the data, and the computer determines which correct value is similar to a new input. In other words, supervised learning utilizes data with correct answers to train the computer.

[0057] Algorithms for supervised learning include, but are not limited to, k-Nearest Neighbors, Linear Regression, Logistic Regression, Gaussian Process Regression, Support Vector Machine (SVM), Decision Tree, Random Forest, and Neural Network.

[0058] Unsupervised learning is a method where a computer learns from data that does not contain labels. In other words, unsupervised learning is a method where the computer, without the correct answer, clusters (groups) similar data together and predicts results for new data.

[0059] These unsupervised learning algorithms include, but are not limited to, clustering, visualization, dimensionality reduction, and association rule learning. Clustering may include k-means, hierarchical cluster analysis (HCA), and expectation maximization. Visualization and resource reduction may include principal component analysis (PCA), kernel PCA, locally linear embedding (LLE), and t-distributed stochastic neighbor embedding (t-SNE). And association rule learning may include Apriori and Eclat.

[0060] Semi-supervised learning is a hybrid of supervised and unsupervised learning, where some data contains labels. Semi-supervised learning aims to improve the performance of supervised learning, but when labeling resources are limited, it uses labels only for a portion of the data.

[0061] Reinforcement learning learns through trial and error, taking actions in a given environment and receiving feedback from those actions. Reinforcement learning allows machine learning models to make decisions without explicitly providing data, and then receive feedback on whether those decisions are right or wrong. This feedback is called a reward, and the model learns to make decisions that lead to positive rewards in the next decision and, if possible, avoid decisions that lead to negative rewards.

[0062] This artificial organ production algorithm (50) includes a data reverse engineering model (60) and an artificial organ production model (70), as illustrated in FIGS. 10 and 11. FIG. 10 is a block diagram illustrating an artificial organ production algorithm (50) according to an embodiment of the present invention. FIG. 11 is a detailed block diagram illustrating a model constituting the artificial organ production algorithm (50) of FIG. 10.

[0063] The data reverse engineering model (60) generates data required for learning the artificial organ production model (70) using reverse engineering technology.

[0064] And the artificial organ production model (70) performs machine learning with data generated by the data reverse engineering model (60), and then controls the bio printer (40) to produce a user-customized artificial organ using the user's requirements as input values.

[0065] The data reverse engineering model (60) is explained as follows.

[0066] Because the physical properties of human organs vary greatly from patient to patient, securing raw materials with diverse physical properties for artificial organs is essential to attracting a large customer base. However, due to the diversity and complexity of raw materials, directly synthesizing all raw materials with target properties is time-consuming and cost-intensive. Therefore, in this embodiment, a reverse engineering technique for raw materials using machine learning was used, based on a data reverse engineering model (60).

[0067] The data reverse engineering model (60) generated virtual data for learning the artificial organ production model (70) as follows. That is, in order to resolve the lack of experimental data and improve the performance of the reverse engineering model, the data reverse engineering model (60) used a technology for generating new data points (virtual data) on-demand.

[0068] This data reverse engineering model (60) may include a surrogate model (61), a reverse engineering deep learning model (63), and a virtual data model (65). In this case, the data reverse engineering model (60) was developed with the goal of achieving a target property prediction accuracy of 90% and a reverse engineering process variable estimation accuracy of 80%.

[0069] The surrogate model (61) extracts features from raw materials through molecular fingerprinting and predicts target properties (mechanical properties, electrical properties, 3D printability).

[0070] The reverse engineering deep learning model (63) performs process variable and raw material selection that can synthesize target properties.

[0071] And the virtual data model (65) generates virtual data by estimating the data distribution of a wide synthetic variable space.

[0072] The artificial organ production model (70) includes a machine learning model (71), an artificial function model (73), and a printer control model (75).

[0073] Although optimal design parameters for artificial organs vary significantly depending on the user's (patient's) physiological, age, and gender conditions, no existing method exists to predict these parameters and provide customized artificial organs. Even if optimal target design parameters are determined, the experimental data used by the data reverse engineering model (60) for machine learning has limitations in estimating the entire variable space.

[0074] Therefore, in this embodiment, the artificial organ manufacturing model (70) estimates the design parameters of the target organ according to various patient conditions and establishes an efficient process for systematically modifying the manufacturing process and material composition ratio from limited data.

[0075] The artificial organ production model (70) was produced with the goal of 80% accuracy in predicting the patient's optimal design variables and an average of 5 repetitions of modifications to the production process and composition to obtain target variables.

[0076] The machine learning model (71) derives the optimal design for each organ tissue based on the user's requirements, such as physiological (BMI, 3D tissue model, etc.), genetic, and demographic (age, gender, etc.) information of various patients.

[0077] The artificial intelligence model (73) can design an automated synthesis process including process variables using various machine learning techniques based on big data. The artificial intelligence model (73) can select and use an appropriate machine learning algorithm based on the data contained in the big data. For example, the artificial intelligence model (73) can design an automated synthesis process including optimized process variables based on Gaussian processes and Bayesian techniques, but is not limited thereto.

[0078] And the printer control model (75) applies the process variables designed in the artificial intelligence model (73) to the control of the 3D bioprinter to produce a customized artificial organ.

[0079] The process of manufacturing an artificial organ by inputting an input value into the artificial organ manufacturing algorithm (50) is explained as follows with an example.

[0080] And by inputting the artificial organ modeling file (STL) into the 3D bioprinter, the artificial organ is produced using 3D bioprinting.

[0081] According to this embodiment, artificial organs can be manufactured based on big data related to artificial organs, responding to user requests. In other words, based on big data acquired during the manufacturing process of various artificial organs, customized artificial organs can be manufactured using bioprinting, using the user's requested conditions as input values.

[0082] Since the input values ​​are numerical values ​​for the hardness, tensile strength, toughness, and ductility of the artificial organ, an artificial organ can be manufactured by inputting numerical values, which has the advantage of enabling mass production.

[0083] And since the artificial organ production system (100) according to the present embodiment is based on big data, the time required for experimentation, manufacturing, and verification can be reduced.

[0084] Meanwhile, the embodiments disclosed in this specification and drawings are merely specific examples to aid understanding and are not intended to limit the scope of the present invention. It will be apparent to those skilled in the art that other modifications based on the technical concepts of the present invention are possible in addition to the embodiments disclosed herein.

[0085] [Explanation of symbols]

[0086] 10: Input section

[0087] 20: Database Department

[0088] 30: Control unit

[0089] 40: Bioprinter

[0090] 50: Artificial organ production algorithm

[0091] 60: Data reverse engineering model

[0092] 61: Surrogate Model

[0093] 63: Reverse engineering deep learning model

[0094] 65: Virtual Data Model

[0095] 70: Artificial organ production model

[0096] 71: Machine learning model

[0097] 73: Artificial function model

[0098] 75: Printer Control Model

[0099] 100: Artificial Organ Production System

Claims

1. Input section that receives user requirements for the artificial organ to be manufactured as input values; Database section that stores big data required for producing artificial organs; A control unit that inputs the above input values ​​into an artificial organ production algorithm learned based on the above database unit to produce process variables capable of producing artificial organs; and A bioprinter that produces an artificial organ with the process variables under the control of the above control unit; A big data-based artificial organ production system including .

2. In paragraph 1, A big data-based artificial organ manufacturing system, characterized in that the above input values ​​include hardness, tensile strength, toughness, and ductility of the artificial organ.

3. In paragraph 1, A big data-based artificial organ production system characterized in that the above input values ​​are numerical values.

4. In paragraph 1, A big data-based artificial organ production system characterized in that the above database unit stores data on multiple raw materials required for producing artificial organs, the weight of each raw material, preprocessing conditions, temperature, catalyst conditions, and reaction time.

5. In paragraph 4, A big data-based artificial organ manufacturing system characterized in that the above database unit stores mechanical property data including Young's modulus, ultimate tensile strength, toughness, and fracture point according to the ratio of raw materials when synthesizing multiple raw materials.

6. In paragraph 1, A big data-based artificial organ production system characterized in that the database section stores data on agarose, acrylamide, N, N'-methylenebis(acrylamide) (MBA), tetramethylethylenediamine (TEMED), deionized water, ammonium sulfate (APS), and temperature.

7. In paragraph 1, A big data-based artificial organ production system characterized in that the above bioprinter is a 3D bioprinter.

8. In paragraph 1, The above control unit generates an artificial organ modeling file (STL) including the process variables using an artificial organ production algorithm learned with the input values, and provides the generated artificial organ modeling file (STL) to the bio printer to bioprint the artificial organ, which is a big data-based artificial organ production system.

9. In paragraph 1, the artificial organ production algorithm, A data reverse engineering model that generates virtual data required for machine learning using reverse engineering technology; and An artificial organ production model that performs machine learning with virtual data generated by the above data reverse engineering model and then controls the bio printer to produce a customized artificial organ using the user's requirements as input values; A big data-based artificial organ production system characterized by including:

10. In paragraph 9, the data reverse engineering model is, Surrogate models that extract features from raw materials through molecular fingerprinting and predict target properties (mechanical properties, electrical properties, and 3D printability); A reverse engineering deep learning model that performs process variable and raw material selection to synthesize target properties; and A virtual data model that generates virtual data by estimating the data distribution of a synthetic variable space; A big data-based artificial organ production system characterized by including:

11. In the 10th paragraph, the artificial organ production model is A machine learning model that derives the optimal design for each organ tissue based on the user's requirements (patient's physiological (BMI, 3D tissue model), genetic, and demographic (age, gender) information); An artificial intelligence model that designs an automated synthetic process including process variables using machine learning based on the above big data; and A printer control model for producing a customized artificial organ by applying the above process variables to the control of the bioprinter; A big data-based artificial organ production system characterized by including:

Citation Information

Patent Citations

  • Customized 3D printing spinal column reconstruction apparatus and preparation method thereof

    CN107137166A

  • Degradable metal bone implant design method based on machine learning

    CN113420504A

  • Film forming method and film forming apparatus

    KR1020200020614A

  • Gas sensor and package for monitoring a thermal runaway of a battery including the same

    KR1020240026372A

  • Assembly to reduce floor noise

    KR102571935B1