Artificial intelligence-based method and system for manufacturing medullary cavity-retained crowns

Abstract

The present invention relates to the field of dental crown manufacturing technology, and specifically to a method and system for manufacturing a medullary cavity-retained crown based on artificial intelligence. The method comprises the following steps: obtaining an oral CBCT image and an oral scan model; synthesizing the oral CBCT image and the oral scan model into a synthesized model; inputting the synthesized model into a trained AI model, and having the AI ​​model generate a medullary cavity-retained crown model based on the synthesized model; performing a simulated stress test on the medullary cavity-retained crown model, and regenerating the medullary cavity-retained crown model when the stress in any area of ​​the medullary cavity-retained crown model is greater than a predetermined value; performing a simulated trial wear test on the medullary cavity-retained crown model that has passed the simulated stress test; adjusting the medullary cavity-retained crown model based on the results of the simulated trial wear test; inputting the adjusted medullary cavity-retained crown model into a printing device and printing to generate a semi-finished medullary cavity-retained crown; and curing the semi-finished medullary cavity-retained crown to generate a finished medullary cavity-retained crown. This application improves patient experience.

Description

Technical Field

[0001] The present invention relates to the technical field of dental crown manufacturing, and in particular to an artificial intelligence-based method and system for manufacturing a pulp-retained crown. Background Art

[0002] In the field of dental restoration, endodontic crowns are an important method for restoring damaged teeth. They leverage the endodontic structure of the remaining tooth tissue to provide retention, playing a key role in repairing tooth defects. Traditionally, endodontic crowns have relied primarily on manual manufacturing, where the doctor manually completes a series of steps, including tooth preparation, impression taking, model pouring, and wax-up creation.

[0003] The existing method of manually manufacturing medullary cavity-retaining crowns has significant defects, as follows:

[0004] 1. During the manual manufacturing process, many links rely on the personal experience and operational proficiency of professional dental technicians, making it difficult to achieve precise quantitative control;

[0005] 2. The manual manufacturing process is cumbersome. For example, the wax model needs to be repeatedly modified, the entire manufacturing cycle is long, and production efficiency is low. As a result, patients need to go back and forth to medical institutions for treatment many times, which increases the patient's time cost and affects the patient's medical experience.

[0006] 3. Due to the lack of precise digital design guidance, the shape of the restoration and the compatibility between the restoration and the pulp cavity are solely based on the doctor's subjective judgment, which is prone to human errors and leads to poor compatibility between the restoration and the patient's tooth tissue. Many adjustments are often required on site, which prolongs the patient's consultation time.

[0007] Therefore, how to solve the above-mentioned deficiencies in the prior art has become the subject to be studied and solved by the present invention. Summary of the Invention

[0008] The purpose of the present invention is to provide a method and system for manufacturing a medullary cavity-retaining crown based on artificial intelligence.

[0009] In order to achieve the above object, the technical solution adopted by the present invention is:

[0010] The artificial intelligence-based method for manufacturing medullary cavity-retained crowns includes:

[0011] Step 1: Obtain oral CBCT images and oral scan models;

[0012] Step 2: synthesizing the oral CBCT image and the oral scan model into a synthetic model;

[0013] Step 3: inputting the synthesized model into the trained AI model, and generating a medullary cavity retention crown model based on the synthesized model by the AI ​​model;

[0014] Step 4: performing a simulated stress test on the medullary cavity retention crown model, and regenerating the medullary cavity retention crown model when the stress in any region of the medullary cavity retention crown model is greater than a predetermined value;

[0015] Step 5: Performing a simulated trial wear test on the medullary cavity-retained crown model that has passed the simulated force test;

[0016] Step 6: adjusting the medullary cavity-retained crown model according to the results of the simulated trial-wear test;

[0017] Step 7: inputting the adjusted medullary cavity-retained crown model into a printing device and printing to generate a semi-finished medullary cavity-retained crown;

[0018] Step eight: curing the semi-finished medullary cavity retaining crown to generate a finished medullary cavity retaining crown.

[0019] CBCT images and oral scan models are the existing settings, which are briefly introduced here: CBCT images (cone beam computed tomography) are radiological imaging technologies that provide hard tissue information such as jaw morphology, neural canal course, and maxillary sinus position through X-ray three-dimensional scanning; oral scan models (oral scan data) are optical three-dimensional surface scanning technologies that are radiation-free and quickly obtain the surface morphology of tooth crowns and gums, making them suitable for restoration design and orthodontic simulation; the two are synergistically applied through software fusion, and the crown data of oral scans are combined with the bone structure data of CBCT to generate a complete three-dimensional model; in addition, two-dimensional radiological images such as periapical films and curved surface films can be introduced.

[0020] The training method of the AI ​​model is as follows:

[0021] Collect jaw 3D data and oral scan optical data from CBCT scans;

[0022] Oral specialists will mark the pulp cavity boundaries, edge design type (butt joint / wraparound), and material selection (e.g., lithium disilicate ceramic).

[0023] A dual-channel 3D CNN is used to process CBCT voxel data and oral scan point cloud data, and features are fused through cross-attention;

[0024] Built-in mechanical simulation module, real-time calculation of stress distribution (such as von Mises stress) to constrain design rationality;

[0025] Use historical repair cases for supervised learning to optimize design errors and mechanical compliance;

[0026] Reinforcement learning optimization is performed based on clinical success rate, and manual correction feedback is provided for complex cases.

[0027] The simulated stress test is primarily performed using finite element analysis (FEA), which is not detailed here. When the stress in any region of the medullary canal-retained crown model exceeds a predetermined value, the canal-retained crown model is regenerated by updating the proxy model and annotating the defective areas for calculation.

[0028] The simulated try-in test is achieved through virtual try-in technology. The technical implementation principle is as follows: the restoration model (medullary cavity retention crown model) is superimposed on the patient's oral digital model (synthetic model) through augmented reality technology.

[0029] When printing and generating semi-finished medullary cavity-retaining crowns, composite resins can be used for printing.

[0030] During the curing process, a dual-curing resin cement (such as All Ceram Core) is used. It uses a dual mechanism of light-induced rapid curing (light trigger) and chemical-induced deep curing (continuous reaction in the dark) to ensure that the restoration (medullary cavity retaining crown) can be fully cured even in areas with insufficient light transmission, providing reliable bonding strength.

[0031] In the prior art, a series of processes, including tooth preparation, mold taking, model pouring, and wax-up production, are completed manually by professional dental technicians. In this application, in summary, a trained AI model is used to generate a medullary cavity-retained crown model, which is then printed using a printing device to generate a (semi-finished) medullary cavity-retained crown, thereby shortening the manufacturing time of the medullary cavity-retained crown.

[0032] The method of manufacturing medullary cavity retaining crowns provided in this application does not rely on professional dental technicians and can achieve precise quantitative control.

[0033] The medullary cavity retention crown model generated by this application can be manufactured relatively quickly by a 3D printer, so the repair can be completed in one go, reducing the cost for doctors and patients and improving the patient's medical experience.

[0034] Before manufacturing the finished medullary cavity-retaining crown, the medullary cavity-retaining crown model is subjected to a simulated force test and a simulated trial wear test. The double test reduces the risk that the finished medullary cavity-retaining crown is not suitable for the patient, avoids prolonged patient consultation time due to frequent on-site adjustments to the finished medullary cavity-retaining crown, and avoids shortening the service life of the finished medullary cavity-retaining crown due to its lower-than-expected force-bearing capacity.

[0035] In the double test, the simulated force test is performed before the simulated trial-fit test, so as to avoid the need to re-perform the simulated trial-fit test due to the regeneration of the medullary cavity-retained crown model, thereby avoiding extending the manufacturing time of the finished medullary cavity-retained crown.

[0036] By improving the manufacturing method of medullary cavity-retained crowns, the manufacturing difficulty can be reduced and the manufacturing speed can be increased, making clinics and other places more capable of independently manufacturing medullary cavity-retained crowns (especially for simple cases), avoiding the need for patients to visit the doctor multiple times.

[0037] This application uses artificial intelligence to participate in the design of medullary cavity retention crowns to avoid mistakes caused by over-reliance on the experience and judgment of professional dental technicians.

[0038] This application allows for customizing a pulp-retained crown, allowing it to be individually tailored to the specific circumstances of the affected tooth, minimizing the removal of healthy tooth tissue while also achieving excellent retention and sufficient strength for future use. This approach allows for minimally invasive crown restoration, preserving approximately 2mm of dentin shoulder, and eliminating the need for metal posts in the root canal. This avoids root damage during root canal preparation, maximizes the preservation of remaining tooth tissue, reduces the risk of tooth fracture, and extends the lifespan of the tooth.

[0039] In a further technical solution, in step three, the step of generating a medullary cavity retention crown model includes:

[0040] S1. generating a retaining portion for retaining in the medullary cavity;

[0041] S2, generating an occlusal part for cooperating with the opposing teeth and adjacent teeth;

[0042] S3. Generate a marginal portion for matching with the remaining tooth.

[0043] In S1, on the one hand, a three-dimensional spiral retention structure design is adopted, specifically, the bionic anchoring principle is adopted to design a spiral groove structure with a gradient pitch, which enhances the interface bonding strength while ensuring the removal force; on the other hand, a porous reinforcement structure is designed, specifically, a structure with multiple supports (such as honeycomb, columnar or tree-like) is integrated inside the retention part, which reduces the weight of the crown while increasing the strength of the crown.

[0044] In S2, multi-dimensional occlusal contact optimization is achieved by applying a virtual occlusion analysis system (such as Dentalocclusion Analyzer 4.0) and generating an optimal occlusal contact point distribution model through a machine learning algorithm to avoid interference between the occlusal part and other teeth.

[0045] In S3, 3D U-Net is used to generate edge contours.

[0046] According to a further technical solution, an outer wall of the retaining portion forms a bonding surface, and a surface roughness of the bonding surface is in the range of 0.2 μm-0.5 μm.

[0047] The surface roughness in this embodiment refers to the surface roughness of the outer wall of the retaining portion.

[0048] Surface roughness affects the mechanical interlocking between the adhesive and the substrate (retention portion). When the bonding surface is non-smooth, the adhesive, from a microscopic perspective, penetrates the concave and convex structures on the bonding surface and cures, creating an anchoring effect and enhancing the bond.

[0049] Surface roughness affects the bonding strength of the adhesive as follows:

[0050] When the surface roughness is too low (<0.2μm), the bonding surface is too smooth, resulting in insufficient mechanical interlocking force and a significant decrease in bonding strength;

[0051] When the surface roughness is too high (>0.5μm), the bonding surface is too rough, resulting in the adhesive being unable to fully penetrate the concave and convex structure on the bonding surface, causing stress concentration or microcracks, and the bonding strength is reduced.

[0052] Surface roughness also affects plaque control as follows:

[0053] When the surface roughness is too high (>0.5 μm), bacteria are more likely to adhere to the bonding surface, thereby accelerating the formation of plaque and increasing the risk of secondary caries.

[0054] When the surface roughness is too low (<0.2μm), the number of bacterial attachment points is reduced, which is beneficial to controlling the speed of plaque formation.

[0055] In summary, when the surface roughness is within the range of 0.2μm-0.5μm, it not only ensures the bonding strength of the adhesive but also limits the speed of plaque formation, achieving a balance between bonding strength and plaque control.

[0056] According to a further technical solution, in step three S1, the surface roughness of each area of ​​the bonding surface is determined based on the trained topography-surface roughness correlation model.

[0057] The purpose of this embodiment is to dynamically adjust the surface roughness of each area of ​​the bonding surface. One possible implementation method is as follows: Based on the scan data, CAD software is used to analyze shape features (such as grooves, sharp edges, and flat areas) to determine the differences in the requirements for bonding strength and plaque control in each area.

[0058] The operation mode of the morphological feature-surface roughness correlation model is supplemented here: the input features are matched with the clinical standard values ​​in the database through a deep neural network (such as the SSA-BiLSTM model), and the recommended roughness range is output.

[0059] The training process of the morphological feature-surface roughness correlation model refers to the training process of the above-mentioned AI model.

[0060] According to a further technical solution, in step 4, the step of simulating the stress test includes:

[0061] S1, applying a vertical load of magnitude A to the medullary cavity retention crown model;

[0062] S2, applying an oblique load of magnitude B to the medullary cavity retention crown model;

[0063] S3, obtaining stress change data of each region of the medullary cavity-retained crown model;

[0064] S4. Compare the maximum stress value during the simulated stress test with the dentin tensile strength. When the maximum stress value is greater than the dentin tensile strength, regenerate the pulp cavity retention crown model.

[0065] In this embodiment, all parts of the medullary cavity retaining crown model are first generated, and then the simulated force test is performed together, thereby shortening the manufacturing process of the finished medullary cavity retaining crown.

[0066] In a further technical solution, in step six, the content of adjusting the medullary cavity retention crown model includes:

[0067] adjusting the degree of polymerization of the shaft wall of the retaining portion;

[0068] adjusting the surface roughness of the retaining portion;

[0069] The distribution of the bite contact points on the bite portion is adjusted.

[0070] The degree of convergence of the shaft wall can be understood as the inclination angle.

[0071] This embodiment clarifies the adjustment content in step six, and further ensures the compatibility of the medullary cavity retaining crown model with the patient through multiple adjustments, thereby avoiding prolonged patient consultation time due to multiple on-site adjustments to the finished medullary cavity retaining crown.

[0072] We also provide an artificial intelligence-based medullary cavity-retained crown manufacturing system, including:

[0073] Acquisition module, used to obtain oral CBCT images and oral scan models;

[0074] a processing module, configured to synthesize the oral CBCT image and the oral scan model into a synthesized model;

[0075] A generation module, configured to generate a medullary cavity retention crown model based on the synthetic model using the trained AI model;

[0076] An analysis module, used for performing a simulated stress test on the medullary cavity retention crown model;

[0077] The review module is used to perform a simulated trial-wear test on the medullary cavity retention crown model that has passed the simulated force test.

[0078] For the relevant descriptions in this embodiment, reference can be made to the descriptions of the relevant parts in the above embodiment. It should be noted that there is no limitation on the specific structure of each module, as long as it meets the requirements.

[0079] In a further technical solution, the medullary cavity retention crown model includes:

[0080] The retaining part is used for retaining with the medullary cavity;

[0081] The occlusal part is used to cooperate with the opposing teeth and adjacent teeth;

[0082] The edge portion is used to fit with the remaining tooth.

[0083] In this embodiment, the medullary cavity-retained crown model is divided into a retaining part, an occlusal part, and a marginal part, so that different schemes can be selected according to this division to generate the medullary cavity-retained crown model to meet various needs.

[0084] According to a further technical solution, an outer wall of the retaining portion forms a bonding surface, and a surface roughness of the bonding surface is in the range of 0.2 μm-0.5 μm.

[0085] When the surface roughness is within the range of 0.2μm-0.5μm, it not only ensures the bonding strength of the adhesive but also limits the speed of plaque formation, achieving a balance between bonding strength and plaque control.

[0086] The terms “include”, “including”, “have”, etc. used in this document are open-ended terms, meaning including but not limited to.

[0087] Unless otherwise noted, the terms used herein generally have their ordinary meanings in the art, in the context of the present invention, and in the specific context. Certain terms used to describe the present invention are discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art regarding the description of the present invention.

[0088] The working principle and advantages of the present invention are as follows:

[0089] In the prior art, a series of processes, including tooth preparation, mold taking, model pouring, and wax-up production, are completed manually by professional dental technicians. In this application, in summary, a medullary-retained crown model is generated using a trained AI model, and then the medullary-retained crown is printed using a printing device, thereby shortening the manufacturing time of the medullary-retained crown.

[0090] The method of manufacturing medullary cavity retaining crowns provided in this application does not rely on professional dental technicians and can achieve precise quantitative control.

[0091] The medullary cavity retention crown model generated by this application can be manufactured relatively quickly by a 3D printer, so the repair can be completed in one go, reducing the costs for doctors and patients (such as time costs) and improving the patient's medical experience.

[0092] Before manufacturing the finished medullary cavity-retaining crown, the medullary cavity-retaining crown model is subjected to a simulated force test and a simulated trial wear test. The double test reduces the risk that the finished medullary cavity-retaining crown is not suitable for the patient, avoids prolonged patient consultation time due to frequent on-site adjustments to the finished medullary cavity-retaining crown, and avoids shortening the service life of the finished medullary cavity-retaining crown due to its lower-than-expected force-bearing capacity.

[0093] In the double test, the simulated force test is performed before the simulated trial-fit test, so as to avoid the need to re-perform the simulated trial-fit test due to the regeneration of the medullary cavity-retained crown model, thereby avoiding extending the manufacturing time of the finished medullary cavity-retained crown.

[0094] By improving the manufacturing method of medullary cavity-retained crowns, the manufacturing difficulty can be reduced and the manufacturing speed can be increased, making clinics and other places more capable of independently manufacturing medullary cavity-retained crowns (especially for simple cases), avoiding the need for patients to visit the doctor multiple times.

[0095] This application uses artificial intelligence to participate in the design of medullary cavity retention crowns to avoid mistakes caused by over-reliance on the experience and judgment of professional dental technicians.

[0096] The present application can customize the pulp cavity retaining crown, so it can be individually customized according to the specific situation of the affected tooth, minimizing the removal of healthy tooth body, and also achieving good retention and sufficient strength to meet future use. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] Figure 1 Schematic diagram of the process of manufacturing a medullary cavity-retained crown according to an embodiment of the present invention;

[0098] Figure 2 Schematic diagram of the structure of the intramedullary retaining crown manufacturing system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0099] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0100] Embodiment: The present invention will be clearly illustrated below with drawings and detailed descriptions. After understanding the embodiments of the present invention, any person skilled in the art can make changes and modifications based on the techniques taught by the present invention without departing from the spirit and scope of the present invention.

[0101] The terms used herein are for describing specific embodiments only and are not intended to be limiting of the present invention. Singular forms such as "a," "the," "this," "this," and "the" as used herein also include plural forms.

[0102] See also Figure 1 , an artificial intelligence-based method for manufacturing medullary cavity-retained crowns, including:

[0103] Step 1: Obtain oral CBCT images and oral scan models;

[0104] Step 2: synthesizing the oral CBCT image and the oral scan model into a synthetic model;

[0105] Step 3: inputting the synthesized model into the trained AI model, and generating a medullary cavity retention crown model based on the synthesized model by the AI ​​model;

[0106] Step 4: performing a simulated stress test on the medullary cavity retention crown model, and regenerating the medullary cavity retention crown model when the stress in any region of the medullary cavity retention crown model is greater than a predetermined value;

[0107] Step 5: Performing a simulated trial wear test on the medullary cavity-retained crown model that has passed the simulated force test;

[0108] Step 6: adjusting the medullary cavity-retained crown model according to the results of the simulated trial-wear test;

[0109] Step 7: inputting the adjusted medullary cavity-retained crown model into a printing device and printing to generate a semi-finished medullary cavity-retained crown;

[0110] Step eight: curing the semi-finished medullary cavity retaining crown to generate a finished medullary cavity retaining crown.

[0111] CBCT images and oral scan models are the existing settings, which are briefly introduced here: CBCT images (cone beam computed tomography) are radiological imaging technologies that provide hard tissue information such as jaw morphology, neural canal course, and maxillary sinus position through X-ray three-dimensional scanning; oral scan models (oral scan data) are optical three-dimensional surface scanning technologies that are radiation-free and quickly obtain the surface morphology of tooth crowns and gums, making them suitable for restoration design and orthodontic simulation; the two are synergistically applied through software fusion, and the crown data of oral scans are combined with the bone structure data of CBCT to generate a complete three-dimensional model; in addition, two-dimensional radiological images such as periapical films and curved surface films can be introduced.

[0112] In some embodiments, the format of the CBCT image is DICOM, the format of the oral scan model is STL, and the synthesis process uses the ICP algorithm for comparison.

[0113] This application is based on artificial intelligence and uses an AI model. The training method of the AI ​​model is as follows:

[0114] Collect jaw 3D data and oral scan optical data from CBCT scans;

[0115] Oral specialists will mark the pulp cavity boundaries, edge design type (butt joint / wraparound), and material selection (e.g., lithium disilicate ceramic).

[0116] A dual-channel 3D CNN is used to process CBCT voxel data and oral scan point cloud data, and features are fused through cross-attention;

[0117] Built-in mechanical simulation module, real-time calculation of stress distribution (such as von Mises stress) to constrain design rationality;

[0118] Use historical repair cases for supervised learning to optimize design errors and mechanical compliance;

[0119] Reinforcement learning optimization is performed based on clinical success rate, and manual correction feedback is provided for complex cases.

[0120] The simulated stress test is primarily performed using finite element analysis (FEA), which is not detailed here. When the stress in any region of the medullary canal-retained crown model exceeds a predetermined value, the canal-retained crown model is regenerated by updating the proxy model and annotating the defective areas for calculation.

[0121] The simulated try-in test is performed using virtual try-in technology. The technology works as follows: The restoration model (canal-retained crown model) is superimposed on the patient's oral digital model (synthetic model) using augmented reality technology. If the canal-retained crown model does not require adjustment, skip step 6.

[0122] When printing and generating semi-finished medullary cavity-retaining crowns, composite resins can be used for printing.

[0123] During the curing process, a dual-curing resin cement (such as All Ceram Core) is used. It uses a dual mechanism of light-induced rapid curing (light trigger) and chemical-induced deep curing (continuous reaction in the dark) to ensure that the restoration (medullary cavity retaining crown) can be fully cured even in areas with insufficient light transmission, providing reliable bonding strength.

[0124] In the prior art, a series of processes, including tooth preparation, mold taking, model pouring, and wax-up production, are completed manually by professional dental technicians. In this application, in summary, a medullary-retained crown model is generated using a trained AI model, and then the medullary-retained crown is printed using a printing device, thereby shortening the manufacturing time of the medullary-retained crown.

[0125] The method of manufacturing medullary cavity retaining crowns provided in this application does not rely on professional dental technicians and can achieve precise quantitative control.

[0126] The medullary cavity retention crown model generated by this application can be manufactured relatively quickly by a 3D printer, so the repair can be completed in one go, reducing the costs for doctors and patients (such as time costs) and improving the patient's medical experience.

[0127] Before manufacturing the finished medullary cavity-retaining crown, the medullary cavity-retaining crown model is subjected to a simulated force test and a simulated trial wear test. The double test reduces the risk that the finished medullary cavity-retaining crown is not suitable for the patient, avoids prolonged patient consultation time due to frequent on-site adjustments to the finished medullary cavity-retaining crown, and avoids shortening the service life of the finished medullary cavity-retaining crown due to its lower-than-expected force-bearing capacity.

[0128] In the double test, the simulated force test is performed before the simulated trial-fit test, so as to avoid the need to re-perform the simulated trial-fit test due to the regeneration of the medullary cavity-retained crown model, thereby avoiding extending the manufacturing time of the finished medullary cavity-retained crown.

[0129] By improving the manufacturing method of medullary cavity-retained crowns, the manufacturing difficulty can be reduced and the manufacturing speed can be increased, making clinics and other places more capable of independently manufacturing medullary cavity-retained crowns (especially for simple cases), avoiding the need for patients to visit the doctor multiple times.

[0130] This application uses artificial intelligence to participate in the design of medullary cavity retention crowns to avoid mistakes caused by over-reliance on the experience and judgment of professional dental technicians.

[0131] This application allows for customizing a pulp-retained crown, allowing it to be individually tailored to the specific circumstances of the affected tooth, minimizing the removal of healthy tooth tissue while also achieving excellent retention and sufficient strength for future use. This approach allows for minimally invasive crown restoration, preserving approximately 2mm of dentin shoulder, and eliminating the need for metal posts in the root canal. This avoids root damage during root canal preparation, maximizes the preservation of remaining tooth tissue, reduces the risk of tooth fracture, and extends the lifespan of the tooth.

[0132] In this embodiment, in step three, the step of generating a medullary cavity retention crown model includes:

[0133] S1. generating a retaining portion for retaining in the medullary cavity;

[0134] S2, generating an occlusal part for cooperating with the opposing teeth and adjacent teeth;

[0135] S3. Generate a marginal portion for mating with the remaining tooth (e.g., dentin collar).

[0136] In S1, on the one hand, a three-dimensional spiral retention structure design is adopted, specifically, the bionic anchoring principle is adopted to design a spiral groove structure with a gradient pitch, which enhances the interface bonding strength while ensuring the removal force; on the other hand, a porous reinforcement structure is designed, specifically, a structure with multiple supports (such as honeycomb, columnar or tree-like) is integrated inside the retention part, which reduces the weight of the crown while increasing the strength of the crown.

[0137] In S2, multi-dimensional occlusal contact optimization is achieved by applying a virtual occlusion analysis system (such as Dentalocclusion Analyzer 4.0) and generating an optimal occlusal contact point distribution model through a machine learning algorithm to avoid interference between the occlusal part and other teeth.

[0138] In S3, 3D U-Net is used to generate edge contours.

[0139] In this embodiment, the outer wall of the retaining portion forms a bonding surface, and the surface roughness of the bonding surface is in the range of 0.2 μm-0.5 μm.

[0140] The surface roughness described in this embodiment refers to the surface roughness of the outer wall of the retaining part.

[0141] Surface roughness affects the mechanical interlocking between the adhesive and the substrate (retention portion). When the bonding surface is non-smooth, the adhesive, from a microscopic perspective, penetrates the concave and convex structures on the bonding surface and cures, creating an anchoring effect and enhancing the bond.

[0142] Surface roughness affects the bonding strength of the adhesive as follows:

[0143] When the surface roughness is too low (<0.2μm), the bonding surface is too smooth, resulting in insufficient mechanical interlocking force and a significant decrease in bonding strength;

[0144] When the surface roughness is too high (>0.5μm), the bonding surface is too rough, resulting in the adhesive being unable to fully penetrate the concave and convex structure on the bonding surface, causing stress concentration or microcracks, and the bonding strength is reduced.

[0145] Surface roughness also affects plaque control as follows:

[0146] When the surface roughness is too high (>0.5 μm), bacteria are more likely to adhere to the bonding surface, thereby accelerating the formation of plaque and increasing the risk of secondary caries.

[0147] When the surface roughness is too low (<0.2μm), the number of bacterial attachment points is reduced, which is beneficial to controlling the speed of plaque formation.

[0148] In summary, when the surface roughness is within the range of 0.2μm-0.5μm, it not only ensures the bonding strength of the adhesive but also limits the speed of plaque formation, achieving a balance between bonding strength and plaque control.

[0149] In this embodiment, in step 3 S1, the surface roughness of each area of ​​the bonding surface is determined based on the trained topography-surface roughness correlation model.

[0150] The purpose of this embodiment is to dynamically adjust the surface roughness of each area of ​​the bonding surface. One possible implementation method is as follows: Based on the scan data, CAD software is used to analyze shape features (such as grooves, sharp edges, and flat areas) to determine the differences in the requirements for bonding strength and plaque control in each area.

[0151] The operation mode of the morphological feature-surface roughness correlation model is supplemented here: the input features are matched with the clinical standard values ​​in the database through a deep neural network (such as the SSA-BiLSTM model), and the recommended roughness range is output (such as 0.5μm is recommended for flat areas).

[0152] The training process of the morphological feature-surface roughness correlation model refers to the training process of the above-mentioned AI model.

[0153] In this embodiment, in step 4, the step of simulating the stress test includes:

[0154] S1, applying a vertical load of magnitude A to the medullary cavity retention crown model;

[0155] S2, applying an oblique load of magnitude B to the medullary cavity retention crown model;

[0156] S3, obtaining stress change data of each region of the medullary cavity-retained crown model;

[0157] S4. Compare the maximum stress value during the simulated stress test with the dentin tensile strength. When the maximum stress value is greater than the dentin tensile strength, regenerate the pulp cavity retention crown model.

[0158] In this embodiment, all parts of the intramedullary canal-retained crown model are first generated, and then the simulated force test is performed together, thereby shortening the manufacturing process of the finished intramedullary canal-retained crown. The specific settings of the vertical load and the oblique load (such as the load size) are adjusted according to actual needs.

[0159] In some embodiments, A and B are 100N.

[0160] In some embodiments, when an oblique load of magnitude B is applied, the angle is set to 45 degrees.

[0161] In some embodiments, an asymmetric dynamic load spectrum (0.5-30 Hz frequency range) is constructed based on electromyographic (EMG) signals and chewing motion trajectory data.

[0162] In some embodiments, a penalty function method + Lagrange multiplier hybrid algorithm is used to process the dynamic contact between the crown and the opposing tooth to simulate stick-slip friction behavior.

[0163] In some embodiments, a saliva viscoelastic lubrication model (generalized Maxwell constitutive model) is introduced to analyze the effects of interfacial energy reduction and capillary effect on edge microleakage in a wet environment.

[0164] In some embodiments, a thermal-mechanical coupling simulation is performed to simulate the thermal expansion mismatch stress at the ceramic-metal interface caused by thermal cycling (5°C↔55°C).

[0165] In this embodiment, in step six, adjusting the medullary cavity retention crown model includes:

[0166] adjusting the degree of polymerization of the shaft wall of the retaining portion;

[0167] adjusting the surface roughness of the retaining portion;

[0168] The distribution of the bite contact points on the bite portion is adjusted.

[0169] The degree of convergence of the shaft wall can be understood as the inclination angle.

[0170] This embodiment clarifies the adjustment content in step six, and further ensures the compatibility of the medullary cavity retaining crown model with the patient through multiple adjustments, thereby avoiding the patient's consultation time being extended due to (many) adjustments to the finished medullary cavity retaining crown on site.

[0171] See also Figure 2 , we also provide an artificial intelligence-based medullary cavity-retained crown manufacturing system, including:

[0172] Acquisition module, used to obtain oral CBCT images and oral scan models;

[0173] a processing module, configured to synthesize the oral CBCT image and the oral scan model into a synthesized model;

[0174] A generation module, configured to generate a medullary cavity retention crown model based on the synthetic model using the trained AI model;

[0175] An analysis module, used for performing a simulated stress test on the medullary cavity retention crown model;

[0176] The review module is used to perform a simulated trial-wear test on the medullary cavity retention crown model that has passed the simulated force test.

[0177] For the relevant descriptions in this embodiment, reference can be made to the descriptions of the relevant parts in the above embodiments. It should be noted that there is no limitation on the specific structure of each module, as long as it meets the requirements.

[0178] In this embodiment, the medullary cavity retention crown model includes:

[0179] The retaining part is used for retaining with the medullary cavity;

[0180] The occlusal part is used to cooperate with the opposing teeth and adjacent teeth;

[0181] The edge portion is used to fit with the remaining tooth.

[0182] In this embodiment, the medullary cavity-retained crown model is divided into a retaining part, an occlusal part, and a marginal part, so that different schemes can be selected according to this division to generate the medullary cavity-retained crown model to meet various needs.

[0183] In this embodiment, the outer wall of the retaining portion forms a bonding surface, and the surface roughness of the bonding surface is in the range of 0.2 μm-0.5 μm.

[0184] When the surface roughness is within the range of 0.2μm-0.5μm, it not only ensures the bonding strength of the adhesive but also limits the speed of plaque formation, achieving a balance between bonding strength and plaque control.

[0185] The above embodiments are intended only to illustrate the technical concepts and features of the present invention. Their purpose is to enable those skilled in the art to understand the contents of the present invention and implement them accordingly. They are not intended to limit the scope of protection of the present invention. Any equivalent changes or modifications made in accordance with the spirit of the present invention are intended to be covered by the scope of protection of the present invention.

Claims

1. A method for manufacturing a medullary cavity-retained crown based on artificial intelligence, characterized in that: include: Step 1: Obtain oral CBCT images and oral scan models; Step 2: synthesizing the oral CBCT image and the oral scan model into a synthetic model; Step 3: inputting the synthesized model into the trained AI model, and generating a medullary cavity retention crown model based on the synthesized model by the AI ​​model; Step 4: performing a simulated stress test on the medullary cavity retention crown model, and regenerating the medullary cavity retention crown model when the stress in any region of the medullary cavity retention crown model is greater than a predetermined value; Step 5: Performing a simulated trial wear test on the medullary cavity-retained crown model that has passed the simulated force test; Step 6: adjusting the medullary cavity-retained crown model according to the results of the simulated trial-wear test; Step 7: inputting the adjusted medullary cavity-retained crown model into a printing device and printing to generate a semi-finished medullary cavity-retained crown; Step eight, curing the semi-finished medullary cavity-retaining crown to produce a finished medullary cavity-retaining crown; In step three, the step of generating a medullary cavity retention crown model includes: S1. generating a retaining portion for retaining in the medullary cavity; S2, generating an occlusal part for cooperating with the opposing teeth and adjacent teeth; S3, generating a marginal portion for matching with the remaining tooth; In step 4, the step of simulating the stress test includes: S1, applying a vertical load of magnitude A to the medullary cavity retention crown model; S2, applying an oblique load of magnitude B to the medullary cavity retention crown model; S3, obtaining stress change data of each region of the medullary cavity-retained crown model; S4. Compare the maximum stress value during the simulated stress test with the dentin tensile strength. When the maximum stress value is greater than the dentin tensile strength, regenerate the pulp cavity retention crown model.

2. The method for manufacturing a medullary cavity-retained crown based on artificial intelligence according to claim 1, characterized in that: The outer wall of the retaining portion forms a bonding surface, and the surface roughness of the bonding surface is in the range of 0.2 μm-0.5 μm.

3. The method for manufacturing a medullary cavity-retained crown based on artificial intelligence according to claim 2, characterized in that: In step 3 S1 , the surface roughness of each area of ​​the bonding surface is determined based on the trained topography-surface roughness correlation model.

4. The method for manufacturing a medullary cavity-retained crown based on artificial intelligence according to claim 1, characterized in that: In step six, the content of adjusting the medullary cavity retention crown model includes: adjusting the degree of polymerization of the shaft wall of the retaining portion; adjusting the surface roughness of the retaining portion; The distribution of the bite contact points on the bite portion is adjusted.

5. Artificial intelligence-based intramedullary crown manufacturing system, characterized by: Applying the artificial intelligence-based medullary cavity-retained crown manufacturing method of claim 1, the medullary cavity-retained crown manufacturing system includes: Acquisition module, used to obtain oral CBCT images and oral scan models; a processing module, configured to synthesize the oral CBCT image and the oral scan model into a synthesized model; A generation module, configured to generate a medullary cavity retention crown model based on the synthetic model using the trained AI model; An analysis module, used for performing a simulated stress test on the medullary cavity retention crown model; The review module is used to perform a simulated trial-wear test on the medullary cavity retention crown model that has passed the simulated force test.

6. The artificial intelligence-based intramedullary crown manufacturing system according to claim 5, characterized in that: The medullary cavity retention crown model includes: The retaining part is used for retaining with the medullary cavity; The occlusal part is used to cooperate with the opposing teeth and adjacent teeth; The edge portion is used to fit with the remaining tooth.

7. The artificial intelligence-based intramedullary crown manufacturing system according to claim 6, characterized in that: The outer wall of the retaining portion forms a bonding surface, and the surface roughness of the bonding surface is in the range of 0.2 μm-0.5 μm.

Images