CN115392127A - Prosthesis result automatic decision system and application thereof in prosthesis manufacturing method - Google Patents
Prosthesis result automatic decision system and application thereof in prosthesis manufacturing method Download PDFInfo
- Publication number
- CN115392127A CN115392127A CN202211051929.8A CN202211051929A CN115392127A CN 115392127 A CN115392127 A CN 115392127A CN 202211051929 A CN202211051929 A CN 202211051929A CN 115392127 A CN115392127 A CN 115392127A
- Authority
- CN
- China
- Prior art keywords
- value
- color difference
- prosthesis
- thickness
- abutment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 14
- 239000000463 material Substances 0.000 claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000008439 repair process Effects 0.000 claims abstract description 23
- 230000004075 alteration Effects 0.000 claims abstract description 9
- 230000004927 fusion Effects 0.000 claims description 22
- 210000000214 mouth Anatomy 0.000 claims description 13
- 230000007012 clinical effect Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000013461 design Methods 0.000 claims description 9
- 239000003086 colorant Substances 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 5
- 238000002790 cross-validation Methods 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 claims description 3
- 229910052573 porcelain Inorganic materials 0.000 claims description 3
- 238000012856 packing Methods 0.000 claims 1
- 238000012795 verification Methods 0.000 claims 1
- 238000002360 preparation method Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004321 preservation Methods 0.000 abstract description 2
- MCMNRKCIXSYSNV-UHFFFAOYSA-N Zirconium dioxide Chemical compound O=[Zr]=O MCMNRKCIXSYSNV-UHFFFAOYSA-N 0.000 description 10
- 239000002241 glass-ceramic Substances 0.000 description 6
- 239000000919 ceramic Substances 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012404 In vitro experiment Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910010293 ceramic material Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention provides a method for constructing a thickness-color difference database of a repair material. The invention also provides a prosthesis result automatic decision system which is characterized by comprising a thickness-chromatic aberration database and an automatic decision unit. The invention also provides an application of the restoration result automatic decision system in a restoration manufacturing method. The invention meets the requirement of clinical patients on aesthetic effect, simultaneously reduces the loss of the dental tissue as much as possible, and ensures that the prosthesis has aesthetic property, predictability and dental tissue preservation property. By adopting the technical scheme disclosed by the invention, a thickness-color difference database of all restoration materials on the market can be formed, the restoration material with the minimum tooth preparation amount and the minimum color difference value is provided for individuation of a patient, and the final restoration is printed by using a CAD/CAM technology.
Description
Technical Field
The invention relates to a prosthesis result automatic decision system capable of guiding prospective oral prosthesis design and manufacture, and also relates to a prosthesis manufacture method realized based on the prosthesis result automatic decision system, which is used for improving accurate calculation of oral clinical tooth preparation amount and guiding design and processing of a prosthesis, and belongs to the field of oral prosthesis design and manufacture for giving clinical decision by machine learning automation.
Background
With the development of economy and the improvement of living standard, people have gradually increased oral aesthetic requirements and awareness of oral cavity protection. In reality thicker restorative materials may provide better aesthetics, but thicker restorations generally require more tooth preparation, which is not in accordance with the oral protection awareness that the original healthy dental tissue is preserved as much as possible. Meanwhile, the oral cavity prosthesis materials are various in variety and different in aesthetic effect, so that the comprehensive decision scheme including the selection of the repair materials, the accurate prediction of the tooth tissue preparation amount and the visual prospective prosthesis manufacturing is personalized on the basis of the background color of the existing abutment of a patient, and the comprehensive decision scheme is favorable for increasing the health tooth storage amount, improving the doctor-patient communication efficiency, reducing the time beside a clinical chair and improving the clinical prognosis.
With the development of the digital oral scanning technology and the CAD/CAM technology, the oral prosthesis can accurately predict the shape and the thickness of the future prosthesis and manufacture the prosthesis according to the shape and the thickness, which is beneficial to the final realization of a comprehensive decision scheme.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method is used for obtaining a comprehensive decision scheme including repairing material selection, accurate prediction of tooth tissue preparation amount and visual prospective prosthesis manufacturing according to individuation on the basis of the existing abutment background color of a patient.
In order to solve the above technical problem, one technical solution of the present invention is to provide a method for constructing a thickness-color difference database of a repair material, which is characterized by comprising the following steps:
step 1, constructing a data set, comprising the following steps:
101, predefining material characteristics of a repair material, wherein if the repair material of the current type has the predefined material characteristics, the material characteristic value of the repair material of the current type is a numerical value one, and otherwise, the material characteristic value of the repair material of the current type is a numerical value two;
102, selecting multiple repair materials with different thicknesses, wherein the repair materials with the same type and the same thickness form a group, making a plurality of samples for each group, measuring and calculating the color difference value between the samples with different thicknesses and the background color A2 of the abutment under the background colors of eight abutments A1, A3.5, ND2, ND7, CC, MPA, B and W, and then obtaining the color difference value of the background colors of the abutments corresponding to the repair materials with different thicknesses and different material characteristic values;
103, setting a fluctuation degree value, wherein the fluctuation range of the first value is [ max (value one-fluctuation degree value, 0), value one + fluctuation degree value ], the fluctuation range of the second value is [ max (value two-fluctuation degree value, 0), value two + fluctuation degree value ], and the data obtained in the step 102 is subjected to data expansion by random value taking in the range by using a random number generation method, so that a data set is finally obtained;
step 2, constructing a fusion regression model based on a Stacking framework, taking the material characteristic value, the thickness value and the value of the background color of the abutment in the data set obtained in the step 1 as input data, taking the corresponding specific color difference value in the data set obtained in the step 1 as an output label, and training the fusion regression model by using the data set to obtain a trained fusion regression model;
and 3, aiming at each type of repairing material, performing comprehensive color difference prediction on all abutment background colors corresponding to different thickness values in a preset thickness range by using a fusion regression model obtained in the exhaustive search step 2 to obtain a color difference predicted value of each abutment background color corresponding to different thickness values of the current type of modified material, analyzing and determining a minimum thickness value of which the color difference is smaller than a threshold value I and a minimum thickness value of which the color difference is larger than a threshold value I and smaller than a threshold value II according to the color difference predicted value, wherein the threshold value I and the threshold value II are predetermined empirical values, the optimal clinical effect is achieved when the color difference is smaller than the threshold value I, and the acceptable clinical effect is achieved when the color difference is larger than the threshold value I and smaller than the threshold value II, so that a thickness-color difference database of the current type of repairing material is established.
Preferably, in step 101, the gap between the sample and the abutment background is closed using an optical gel before measuring and calculating the color difference value.
Preferably, in step 2, the data set obtained in step 1 is divided into a training set and an internal test set; training the fusion regression model by using a training set and adjusting the hyperparameters to obtain a trained fusion regression model; and (2) acquiring a data set based on other types of repair materials except the type of the repair material selected in the step (102) by adopting the same method in the step (1), taking the acquired data set as an external test set, evaluating the generalization ability of the trained fusion regression model, merging the external test set into the data set acquired in the step (103) if the generalization ability does not meet the requirement, and then retraining the fusion regression model by using the expanded data set.
Preferably, in step 2, the fused regression model is composed of two base learners and a meta learner for fusing the prediction results output by the two base learners, and the meta learner outputs the final prediction result of the fused regression model; when adjusting hyper-parameters of a fused regression model, R is used 2 And RMSE analyzes the output result of the fusion regression model, and a RandomizedSearchCV method is used for performing 10-fold cross validation and screening on the optimal hyperparameter for the base learner.
Another technical solution of the present invention is to provide a prosthesis result automatic decision system, which is characterized by comprising:
the thickness-chromatic aberration database of various repairing materials constructed by the method is used for obtaining the minimum thickness value required by the various repairing materials under the background color of the abutment in the oral cavity of the current patient when the best clinical effect and the acceptable clinical effect are achieved based on the thickness-chromatic aberration database;
and the automatic decision unit scans the abutment in the oral cavity of the patient, and then combines the Lab color obtained by the oral porcelain prosthesis color prediction system according to the minimum thickness value obtained by the thickness-color difference database and the background color of the abutment in the oral cavity of the current patient, and fills the part to be repaired of the abutment in the oral cavity of the patient with the Lab color so as to obtain a prospective prosthesis result.
Another technical solution of the present invention is to provide an application of the above prosthesis result automatic decision system in a prosthesis manufacturing method, which is characterized by comprising the following steps:
firstly, judging the background color of a clinical practical abutment of a patient, and scanning the abutment in the oral cavity of the patient to obtain a scanning file;
secondly, inputting the background color of the clinical practical abutment of the patient and the scanning file into the prosthesis result automatic decision system, and outputting a prospective prosthesis result design file by the prosthesis result automatic decision system;
thirdly, adjusting a prospective prosthesis result design file by combining the requirements of the patient and the clinical tooth tissue residual quantity;
and fourthly, manufacturing a final restoration according to the adjusted prospective restoration result design file.
Considering that the mass acquisition of clinical data is difficult to realize in practice and the measurement of each thickness is difficult to realize in vitro experiments, the invention makes up the deficiency by data expansion in a reasonable fluctuation range. However, as the data is relatively single, in order to avoid large deviation of the prediction result, the invention adopts an integration idea that in one integration, a group of basic learners can be trained into a powerful learner, bagging and boosting are two methods which are most commonly used for constructing an integration model, but the two methods are respectively enhanced from variance and deviation, and the stacking model adopted by the invention can fuse the models and optimize and predict the result, thereby just solving the problem of common enhancement of the variance and the deviation.
The invention meets the requirement of clinical patients on aesthetic effect, simultaneously reduces the loss of the dental tissue as much as possible, and ensures that the prosthesis has aesthetic property, predictability and dental tissue preservation property. By adopting the technical scheme disclosed by the invention, a thickness-color difference database of all restoration materials on the market can be formed, the restoration material with the minimum tooth preparation amount and the minimum color difference value is provided for individuation of a patient, and the final restoration is printed by using a CAD/CAM technology.
Drawings
FIG. 1 illustrates a system build and use flow diagram;
FIG. 2 shows a scatter plot of training data predicted values versus actual values for a model;
FIG. 3 shows a test data predicted value versus actual value versus scatter plot for a model;
FIG. 4 illustrates a graph of weight coefficients of a base learner in a meta learner;
FIG. 5 illustrates an exhaustive search of all prediction results graphs;
fig. 6 shows a crown prosthesis automatic decision flow diagram;
FIG. 7 illustrates a prospective prosthesis results graph;
figure 8 shows the final clinical effect graph.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention can be made by those skilled in the art after reading the teaching of the present invention, and these equivalents also fall within the scope of the claims appended to the present application.
Example 1
Construction of dental prosthesis material-chromatic aberration machine learning system
As shown in fig. 1, the build material-color difference machine learning system includes the steps of:
step 1: raw data were selected, in this example, four intraoral common ceramic materials (domestic glass ceramic, domestic zirconia ceramic, imported glass ceramic, and imported zirconia ceramic) of three thicknesses (0.5, 1, and 2 mm) were used, 10 samples were respectively made, and gaps between the samples and the background were closed with an optical gel, and the color difference values of the samples of different thicknesses from A2 under 8 kinds of abutment background colors, such as A1, a3.5, ND2, ND7, CC, MPA, B, and W, were measured and calculated.
Step 2: the material characteristics are predefined (the material characteristics required to be defined can be determined according to actual experience), 0 and 1 are used for representing whether the restoration materials (domestic glass ceramics, domestic zirconia ceramics, imported glass ceramics and imported zirconia ceramics) corresponding to each sample in the step 1 have the material characteristics, if so, the material characteristics are 1, otherwise, the material characteristics are 0, and further, the material characteristics of the restoration materials of various types can be represented by 0 and 1. The individual thicknesses in step 1 are then processed according to the measured values. In consideration of the limitation of data and the difficulty of obtaining clinical data, the invention carries out reasonable fluctuation processing on the data obtained in the step 1 for data expansion, and specifically comprises the following steps: the degree of fluctuation is set for the material characteristic value, and in this example, the degree of fluctuation is set to 0.1, the fluctuation range of 0 is 0 to 0.1, and the fluctuation range of 1 is 0.95 to 1.05. Randomly taking values in a fluctuation range by using a random number generation method, finally obtaining a data set with 960 samples based on the samples obtained in the step 1, and segmenting the data set obtained by expansion into a training set and an internal test set, wherein the selected segmentation proportion is 8:2.
and step 3: constructing a fusion regression model based on a stacking framework, as shown in fig. 1, the fusion regression model is composed of two layers: the first layer is a combined base learner, and combines an Extrates model LightGBM model; the second layer is a meta learner, using the ridge regression RidgeCV method. The fusion regression model was trained using a k-fold (k = 10) cross-validation approach.
And 4, step 4: using R 2 Analysis of results with RMSE (in this example, R 2 The value range is 0-1, the root mean square error is less than or equal to 0.1), and the base learner performs 10-fold cross validation and screening on the optimal hyperparameter by using a RandomizedSearchCV method. The parameters for Extratees screening are random _ state, n _ estimators, min _ impurity _ decoder, min _ samples _ split, max _ features, max _ depth, criterion; the parameters of LightGBM screening are n _ estimators, min _ child _ weight, max _ depth, objective, opportunity _ type, boosting _ type, learning _ rate, reg _ alpha, random _ state, subsample, and colsample _ byte.
Fig. 2 shows the comparison between the predicted value and the actual value of the training data of the model. Wherein a is a Stacking model, b is an extrreees model, and c is a LightGBM model.
FIG. 3 shows the comparison of the predicted and actual values of the validation data for the model. Wherein a is a Stacking model, b is an extrreees model, and c is a LightGBM model.
Fig. 4 shows the weighting coefficients of the two basis learners at the meta-learner to predict the final result. It can be seen that the ETs model predicts the most important results.
The optimal hyper-parameters screened by the RandomizedSearchCV method by the base learner are shown in the following Table 1:
TABLE 1
Table 2 shows the model index results, where R 2 The closer to 1, the higher the accuracy, the smaller the RMSE, the higher the accuracy. It can be seen that the Stacking model has some improvement in prediction accuracy over the extrtreses model and the LightGBM model alone.
And 5: and performing comprehensive color difference prediction on all backgrounds corresponding to different thicknesses within the thickness range of 0.5-2mm by using exhaustive search, and analyzing and determining the minimum thickness values of less than 2.6 and more than 2.6 and less than 5.5 in the color difference according to the predicted values under 512 conditions.
Fig. 5 shows the distribution of chromatic aberration of materials with different thicknesses in different backgrounds, which can be seen by exhaustive search of all the predicted results.
Table 3 shows the minimum thickness values of the color difference of less than 2.6 for different backgrounds according to the invention from an exhaustive search.
Note: * The predicted values are all larger than 2.6
TABLE 3
Table 4 shows the minimum thickness values of the invention for color differences of different backgrounds of more than 2.6 and less than 5.5, according to an exhaustive search.
Note: * Indicates that the predicted values are all more than 5.5, and indicates that the predicted values are all less than 2.6
TABLE 4
Example 2
System for establishing automatic decision function
FIG. 6 illustrates a crown prosthesis automatic decision flow diagram
Step 1, firstly, according to the clinical patient, determining which of A1, A3.5, ND2, ND7, CC, MPA, B and W the background color of the abutment belongs to, in this example, the background color of the abutment is CC, and according to the background color, providing a decision matrix (shown in figure 6) that 4 tested materials respectively satisfy the best clinical effect (the color difference is less than 2.6) and the clinically acceptable effect (the color difference is more than 2.6 and less than 5.5). It was found that if the best clinical effect is to be achieved, the domestic glass ceramic needs a thickness of at least 2.1 mm, whereas the imported glass ceramic needs a thickness of 1.8 mm, whereas the thickness of one third of the labial and gingival of the anterior crown prosthesis is less than 1.5 mm, so that the computer decision to select zirconia ceramic.
And 2, scanning the abutment teeth in the oral cavity of the patient, combining a Lab color predicted value obtained by an oral porcelain prosthesis color prediction system, a construction method and a prediction method (application number: 202210829996.1) (in the patent, a Gradient Boosting Regression method is used for establishing a Regression prediction model of thickness-Lab color space components (L, a and b), obtaining the Lab color predicted value based on the input thickness by the Regression prediction model), and outputting a prospective prosthesis result of the step 1 (as shown in figure 7).
Example 3
Realizing the manufacture of the prosthesis
Clinical discussion with the patient, the final restoration was made using CADCAM, and fig. 8 shows the final restoration results.
The technical scheme disclosed by the embodiment is based on the chromatic aberration measurement data of different thickness prosthesis samples under different background colors, a prosthesis material-chromatic aberration machine learning system is established by using machine learning, a prospective prosthesis with the optimal clinical and/or clinically acceptable oral aesthetic effect is given by combining the background color of a clinical abutment and the selection of a patient on the prosthesis material, the shape of the prosthesis is determined after the prosthesis is communicated with the patient, and the final prosthesis is manufactured by CAD/CAM.
Claims (6)
1. A method for constructing a thickness-chromatic aberration database of a repair material is characterized by comprising the following steps of:
step 1, constructing a data set, comprising the following steps:
101, predefining material characteristics of a repair material, wherein if the repair material of the current type has the predefined material characteristics, the material characteristic value of the repair material of the current type is a value one, and otherwise, the material characteristic value of the repair material of the current type is a value two;
102, selecting multiple repair materials with different thicknesses, wherein the repair materials with the same thickness and the same kind are in a group, making a plurality of samples for each group, measuring and calculating the color difference value between the samples with different thicknesses and the background color A2 of the abutment under the background colors of eight abutments A1, A3.5, ND2, ND7, CC, MPA, B and W, and then obtaining the color difference value of the background colors of the abutment corresponding to the repair materials with different thicknesses and different material characteristic values;
103, setting a fluctuation degree value, wherein the fluctuation range of the first value is [ max (the first value is a fluctuation degree value, 0), the first value is a fluctuation degree value, the fluctuation range of the second value is [ max (the second value is a fluctuation degree value, 0), the second value is a fluctuation degree value ], carrying out data expansion on the data obtained in the step 102 by using a random number generation method to randomly take values in the range, and finally obtaining a data set;
step 2, constructing a fusion regression model based on a packing framework, taking the material characteristic value, the thickness value and the abutment background color value in the data set obtained in the step 1 as input data, taking the specific color difference value corresponding to the data set obtained in the step 1 as an output label, and training the fusion regression model by using the data set to obtain a trained fusion regression model;
and 3, aiming at each type of repairing material, performing comprehensive color difference prediction on all abutment background colors corresponding to different thickness values in a preset thickness range by using a fusion regression model obtained in the exhaustive search step 2 to obtain a color difference predicted value of each abutment background color corresponding to different thickness values of the current type of modified material, analyzing and determining a minimum thickness value of which the color difference is smaller than a threshold value I and a minimum thickness value of which the color difference is larger than a threshold value I and smaller than a threshold value II according to the color difference predicted value, wherein the threshold value I and the threshold value II are predetermined empirical values, the optimal clinical effect is achieved when the color difference is smaller than the threshold value I, and the acceptable clinical effect is achieved when the color difference is larger than the threshold value I and smaller than the threshold value II, so that a thickness-color difference database of the current type of repairing material is established.
2. The method according to claim 1, wherein in step 101, before measuring and calculating the chromatic aberration, an optical gel is used to close the gap between the sample and the abutment background.
3. The method for constructing the database of thickness-color difference of repair materials according to claim 1, wherein in step 2, the data set obtained in step 1 is divided into a training set and an internal test set; training the fusion regression model by using a training set, and adjusting the hyper-parameters of the fusion regression model by using a verification set to obtain a trained fusion regression model; and (2) acquiring a data set based on other types of repair materials except the type of the repair material selected in the step (102) by adopting the same method in the step (1), taking the acquired data set as an external test set, evaluating the generalization ability of the trained fusion regression model, merging the external test set into the data set acquired in the step (103) if the generalization ability does not meet the requirement, and then retraining the fusion regression model by using the expanded data set.
4. The method according to claim 2, wherein in step 2, the fused regression model is composed of two basis learners and a meta-learner for fusing the predicted results output by the two basis learners, and the meta-learner outputs the final predicted result of the fused regression model; when adjusting hyper-parameters of a fused regression model, R is used 2 And RMSE analyzes the output result of the fusion regression model, and performs 10-fold cross validation screening on the optimal hyper-parameters by using a RandomizedSearchCV method for the base learner.
5. A prosthesis result automatic decision system is characterized by comprising:
using the thickness-color difference database of various restorative materials constructed by the method of claim 1, and obtaining the minimum thickness value required by the various restorative materials to achieve the optimal clinical effect and the acceptable clinical effect under the background color of the abutment in the oral cavity of the patient based on the thickness-color difference database;
and the automatic decision unit scans the abutment in the oral cavity of the patient, and then combines the Lab color obtained by the oral porcelain prosthesis color prediction system according to the minimum thickness value obtained by the thickness-color difference database and the background color of the abutment in the oral cavity of the current patient, and fills the part to be repaired of the abutment in the oral cavity of the patient with the Lab color so as to obtain a prospective prosthesis result.
6. Use of the prosthesis outcome automatic decision system as defined in claim 5 in a prosthesis production method, comprising the steps of:
firstly, judging the background color of a clinical practical abutment of a patient, and scanning the abutment in the oral cavity of the patient to obtain a scanning file;
secondly, inputting the background color of the clinical practical abutment of the patient and a scanning file into the prosthesis result automatic decision-making system as claimed in claim 5, and outputting a prospective prosthesis result design file by the prosthesis result automatic decision-making system;
thirdly, adjusting a prospective prosthesis result design file by combining the requirements of the patient and the clinical tooth tissue residual quantity;
and fourthly, manufacturing a final restoration according to the adjusted prospective restoration result design file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211051929.8A CN115392127B (en) | 2022-08-31 | 2022-08-31 | Automatic decision-making system for prosthesis result and application of automatic decision-making system in manufacturing method of prosthesis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211051929.8A CN115392127B (en) | 2022-08-31 | 2022-08-31 | Automatic decision-making system for prosthesis result and application of automatic decision-making system in manufacturing method of prosthesis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115392127A true CN115392127A (en) | 2022-11-25 |
| CN115392127B CN115392127B (en) | 2023-12-15 |
Family
ID=84124869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211051929.8A Active CN115392127B (en) | 2022-08-31 | 2022-08-31 | Automatic decision-making system for prosthesis result and application of automatic decision-making system in manufacturing method of prosthesis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392127B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080160485A1 (en) * | 2006-10-31 | 2008-07-03 | Touchstone C Alex | Method and apparatus for selecting translucent dental materials |
| US20130282351A1 (en) * | 2011-01-07 | 2013-10-24 | Straumann Holding Ag | Method and tooth restoration determination system for determining tooth restorations |
| US20200000563A1 (en) * | 2017-03-08 | 2020-01-02 | Ivoclar Vivadent Ag | Method For Specifying A Material Color Of A Dental Restoration |
| CN111981980A (en) * | 2020-08-18 | 2020-11-24 | 重庆医科大学附属口腔医院 | Method and system for testing suitability deviation of dental prosthesis CAD and manufacturing process |
-
2022
- 2022-08-31 CN CN202211051929.8A patent/CN115392127B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080160485A1 (en) * | 2006-10-31 | 2008-07-03 | Touchstone C Alex | Method and apparatus for selecting translucent dental materials |
| US20130282351A1 (en) * | 2011-01-07 | 2013-10-24 | Straumann Holding Ag | Method and tooth restoration determination system for determining tooth restorations |
| US20200000563A1 (en) * | 2017-03-08 | 2020-01-02 | Ivoclar Vivadent Ag | Method For Specifying A Material Color Of A Dental Restoration |
| CN111981980A (en) * | 2020-08-18 | 2020-11-24 | 重庆医科大学附属口腔医院 | Method and system for testing suitability deviation of dental prosthesis CAD and manufacturing process |
Non-Patent Citations (5)
| Title |
|---|
| WALLER TOBIAS 等: "Perceptibility and Acceptability of Color Differences of Single-Tooth Implants at the Restoration and Mucosa Levels: An Exploratory Clinical Study", INTERNATIONAL JOURNAL OF PROSTHODONTICS, vol. 33, no. 5, pages 1 - 5 * |
| 张晓真 等: "红、白美学评价CAD/CAM个性化基台与全瓷冠在前牙区的应用", 口腔生物医学, vol. 4, no. 4, pages 1 - 5 * |
| 王远勤 , 王臻 , 廖府明 , 白春明 , 任立勇: "前牙美学修复智能选色设计系统的初步研究", 中华医学美学美容杂志, no. 06, pages 1 - 4 * |
| 邱宜农;杨国强;白黎露;刘晓辉;关德林;: "瓷修复体颜色选择相关因素的回顾分析", 中国美容医学, no. 11, pages 1 - 3 * |
| 高陶磊;程政;代泉;陈诚;: "3Shape Trios口内扫描与精细硅橡胶印模技术在临床瓷贴面修复中的应用比较", 山西医科大学学报, no. 09, pages 1 - 5 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115392127B (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Goodacre et al. | Comparison of denture tooth movement between CAD-CAM and conventional fabrication techniques | |
| Kattadiyil et al. | Clinical complications and quality assessments with computer-engineered complete dentures: A systematic review | |
| Avetisyan et al. | Characteristics of periodontal tissues in prosthetic treatment with fixed dental prostheses | |
| Renne et al. | Evaluation of the marginal fit of CAD/CAM crowns fabricated using two different chairside CAD/CAM systems on preparations of varying quality | |
| DK2325771T3 (en) | System and apparatus for the design and manufacture of denture elements | |
| US7623942B2 (en) | Method and apparatus for selecting non-opacious dental materials | |
| Leblanc et al. | Patterns of tooth development and replacement in captorhinid reptiles: a comparative approach for understanding the origin of multiple tooth rows | |
| WO2018022752A1 (en) | Dental cad automation using deep learning | |
| Sampaio et al. | Effects of manufacturing methods on the survival rate of ceramic and indirect composite restorations: A systematic review and meta‐analysis | |
| Alqahtani | Marginal fit of all-ceramic crowns fabricated using two extraoral CAD/CAM systems in comparison with the conventional technique | |
| Yuan et al. | Personalized design technique for the dental occlusal surface based on conditional generative adversarial networks | |
| CN108735292A (en) | Removable partial denture decision-making method based on artificial intelligence and system | |
| US20060147874A1 (en) | Method and apparatus for selecting non-opacious dental materials | |
| KR102284579B1 (en) | Dental diagnosis system using big data-based artificial intelligence | |
| Svanborg | A systematic review on the accuracy of zirconia crowns and fixed dental prostheses | |
| US20230066220A1 (en) | System and method for augmented intelligence in dental pattern recognition | |
| Dahl et al. | Digital evaluation of marginal and internal fit of single‐crown fixed dental prostheses | |
| Dimitrova et al. | Color stability determination of CAD/CAM milled and 3D printed acrylic resins for denture bases: A narrative review | |
| Jouhar et al. | An overview of shade selection in clinical dentistry | |
| WO2023202143A1 (en) | Deep learning-based automatic design method and system for dental prosthesis | |
| Haddadi et al. | Marginal and internal fit of crowns based on additive or subtractive manufacturing | |
| CN109346179A (en) | Recurrence prediction model and its modeling method, device after a kind of coronary intervention | |
| Serra-Pastor et al. | Periodontal behavior and patient satisfaction of anterior teeth restored with single zirconia crowns using a biologically oriented preparation technique: a 6-year prospective clinical study | |
| Wang et al. | Comparison and evaluation of the morphology of crowns generated by biogeneric design technique with CEREC chairside system | |
| Amesti-Garaizabal et al. | Influence of angulation in cervical prosthetic emergences relative to the gingival tissue of teeth treated under the biologically oriented preparation technique (BOPT) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |