Methods for evaluating the fixation status of fixed crown restorations, and examination devices.
The integration of RFA with machine learning algorithms allows for precise and non-invasive detection of cement fixation loss and screw loosening in dental crowns and bridges, addressing the limitations of existing evaluation methods and enhancing clinical management.
Patent Information
- Application Number
- JP2026547431
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2025-02-20
- Filing Date
- 2026-02-19
- Publication Date
- 2026-11-19
- Estimated Expiration
- 2046-02-19
AI Technical Summary
Existing methods for evaluating the fixation state of fixed dental crown restorations, such as bridges and single crowns, lack the ability to accurately and non-invasively detect early-stage cement fixation loss and screw loosening, leading to potential irreversible damage and complications.
A method using resonant frequency analysis (RFA) combined with machine learning techniques, including supervised and unsupervised learning algorithms, to analyze the vibration response of dental crowns and bridges, determining the fixation state through anomaly detection models and anomaly scores.
Enables accurate and non-invasive evaluation of the fixation state of dental crowns and bridges, detecting early-stage cement fixation loss and screw loosening, thereby preventing complications and supporting informed treatment decisions.
Smart Images

Figure 0007953968000021 
Figure 0007953968000022 
Figure 0007953968000023
Abstract
Description
Technical Field
[0001] The present disclosure relates to a method for evaluating the fixation state of a fixed dental crown restoration and an examination apparatus.
Background Art
[0002] A fixed dental crown restoration (FPD) is a fixed restoration that is mounted on a natural tooth or an implant and applied to one or more teeth for the purpose of restoring tooth structure or prosthodontically replacing a missing tooth in cases of tooth structure defect or tooth loss. If the treatment planning, design, fabrication or mounting is inappropriate, early complications may occur, potentially causing irreversible damage to the teeth and supporting structures. It is stated that the main cause of complications occurring in FPD is a reduction in retention. Other complications include joint breakage, porcelain breakage, abutment tooth breakage, and gaps formed between the retainer or pontic and the abutment tooth. Such breakage can lead to the development of secondary caries and loss of the abutment tooth.
[0003] Deterioration of cement used for dental crown restorations is a frequent problem in clinical practice. Since this deterioration often progresses gradually, clear diagnosis is difficult in the initial stage, which poses a major clinical challenge. Particularly for bridges, when cement fixation is lost in some retainers while other retainers remain fixed, it is difficult to clinically evaluate the fixation state of the entire restoration. Such a condition can lead to secondary caries, mechanical damage to teeth, periodontal disease, and even tooth loss, requiring early diagnosis and appropriate response. Signs of reduced FPD retention are evaluated through clinical examinations such as visual inspection and palpation, radiographic examinations, electronic mobility tests, occlusal force analysis, and the like, but none of these methods are sufficient to detect minute changes in cement adhesion force or early-stage changes in the fixation state with high accuracy. Furthermore, for implant-supported FPDs, in addition to the reduction of the cement fixation state, early detection of screw loosening is also an important issue.
[0004] Patent Document 1 discloses a dental medical device that can share information on the measurement results of implant stability between different devices. This document discloses a configuration in which a measurement aid Ia made of magnetic material is attached to the top of the implant, and by exciting the measurement aid Ia, the implant and the measurement aid Ia are vibrated together, and the resonance frequency of the measurement aid Ia is detected. Since the implant and the measurement aid Ia vibrate together, the resonance frequency of the implant can be determined by detecting the resonance frequency of the measurement aid Ia. Then, based on the control program, an implant stability value (ISQ value), which is an index indicating the stability of the implant, is calculated from that resonance frequency. However, the technology described in Patent Document 1 is intended for evaluating the stability of the implant body itself that is embedded in the bone, and is not intended for evaluating the fixation state of FPDs including single crowns and bridges or detecting minute changes in the cement fixation state, nor is it intended for non-invasive and early evaluation of the fixation state of FPDs.
[0005] Resonant frequency analysis (RFA) is a non-invasive method for obtaining information about the internal state of structures and is used in various fields, including dentistry. In the dental field, a method for evaluating the stability of implants using RFA is known, and one example is the "Osstell Mentor" device. This device excites a "SmartPeg" that is attached to the implant body with a screw, and calculates a stability index based on its resonant frequency. However, since SmartPeg is designed to be attached to an implant body, it is difficult to screw-fix it to flat panel displays (FPDs) such as crowns and bridges, and therefore it could not be applied to evaluating the fixation state of FPDs.
[0006] The inventors have been studying a new RFA device equipped with a 3D acceleration sensor. This device can detect stability and looseness without screwing the sensor into the implant. Furthermore, it has been shown that the cement fixation state of tooth-supported FPDs can be evaluated using RFA and finite element analysis. However, accurately evaluating the resonant frequency characteristics of FPDs related to cement fixation loss based solely on conventional manual analysis and empirical judgment remains difficult, and challenges in terms of objectivity and reproducibility still exist. [Prior art documents] [Patent Documents]
[0007] [Patent Document 1] Japanese Patent Publication No. 2020-146072 [Overview of the Initiative] [Problems that the invention aims to solve]
[0008] The reduced retention of flat panel implants (FPDs) is a clinically frequent issue. However, diagnostic methods for early detection of abnormalities or loosening remain unestablished. While new RFA devices and finite element analysis have been attempted, objectively and accurately determining the resonant frequency characteristics of FPDs due to cement fixation loss remains a challenge. To address this challenge, there has been a need for a non-invasive and early evaluation method and diagnostic device for assessing the fixation status of FPDs attached to abutment teeth or implants.
[0009] This disclosure was made to solve the problems described above, and aims to provide an evaluation method for easily and accurately evaluating the fixation state of fixed dental crowns, and an examination device that enables such evaluation. [Means for solving the problem]
[0010] The method for evaluating the fixed state of an FPD according to this disclosure comprises the steps of: applying elastic wave stimulation to the FPD; acquiring the response waveform of the FPD to the elastic wave stimulation as a time history waveform; calculating frequency response characteristics based on the time history waveform; inputting the frequency response characteristics into a trained anomaly detection model to perform inference and obtain an anomaly score; and determining the fixed state of the FPD based on the anomaly score. According to the evaluation method described above, by applying machine learning techniques to the vibration response obtained by resonant frequency analysis (RFA), it becomes possible to objectively extract features related to the fixed state of the FPD and quantitatively determine the quality of the fixed state based on numerical indicators such as anomaly scores.
[0011] Other features of this disclosure are outlined below. [Effects of the Invention]
[0012] The fixation status of fixed crown restorations can be easily and accurately evaluated. [Brief explanation of the drawing]
[0013] [Figure 1] This diagram shows an example of an experimental process. [Figure 2] This is a photograph of a mandible model. [Figure 3] This diagram shows the direction of the acceleration sensor and vibration stimulus. [Figure 4] This diagram shows the types of cement fixation and the measurement locations. [Figure 5] This figure shows the response frequencies obtained using the Fast Fourier Transform (FFT) for the waveforms from each accelerometer. [Figure 6] This is a diagram showing the structure of a random forest classifier. [Figure 7] This is a diagram showing the neural network structure for supervised learning. [Figure 8] This is a diagram showing the architecture of an autoencoder. [Figure 9] This figure shows the relationship between loss value and epoch. [Figure 10] This is a graph showing feature importance. [Figure 11] This is a graph showing feature importance. [Figure 12] This is a graph showing feature importance. [Figure 13] This is a graph showing feature importance. [Figure 14] This is a diagram showing the analysis results of an autoencoder. [Figure 15] This is a photograph of a jawbone model with two implants embedded therein. [Figure 16] This is a photograph of a custom-made surgical guide. [Figure 17] This is a diagram showing an acceleration sensor fixed to an abutment. [Figure 18] This is a feature importance analysis result for detecting screw loosening of a conical connection. [Figure 19] This is a feature importance analysis result for detecting screw loosening of a conical connection. [Figure 20] This is a diagram showing the frequency response abnormality score in the conical connection mode. [Figure 21] This is a feature importance analysis result for detecting screw loosening of an internal tri-channel connection. [Figure 22] This is a feature importance analysis result for detecting screw loosening of an internal tri-channel connection. [Figure 23] This is a diagram showing the frequency response abnormality score in the internal tri-channel connection. [Figure 24] This is a feature importance analysis result for detecting screw loosening of an external hexagonal connection. [Figure 25] This is a feature importance analysis result for detecting screw loosening of an external hexagonal connection. [Figure 26] This is a diagram showing the frequency response abnormality score in the external hexagonal connection. [Figure 27] This is a diagram showing an embodiment of a model experiment. [Figure 28] This figure shows an example of an acceleration waveform obtained from a healthy implant. [Figure 29] This figure shows the results of the FET analysis. [Figure 30] This figure shows the abnormal scores for healthy data and loose data. [Figure 31] This is a photograph showing human experimentation. [Figure 32] This figure shows the acceleration waveform of the bridge. [Figure 33] This is a diagram showing the frequency spectrum. [Modes for carrying out the invention]
[0014] Embodiment. An example of a method for evaluating the fixation status of a fixed crown restoration (FPD) related to this disclosure is described below. Sensor fixing The sensor is fixed to the FPD. Here, fixing includes mere contact. The type of FPD is not particularly limited and can be a single unit or a connected dental restoration. For example, a small piezoelectric 3D accelerometer can be used, but other types of sensors that can measure from approximately 0 to 10,000 Hz can be used. In addition to piezoelectric accelerometers, magnetostrictive sensors and non-contact laser vibrometers can also be used. For example, the sensor can be fixed to the top or side of the FPD using double-sided tape, adhesive, clips, etc.
[0015] Vibration of dental crowns The FPD is stimulated by vibration, for example, from the side. An exciter can be used to provide the vibration stimulation. For example, the exciter is attached to the FPD and provides vibration stimulation to the FPD. For example, the exciter is brought into contact with the jaw or cheek, indirectly providing vibration stimulation to the FPD through the human body. Examples of exciters include striking devices such as automatic striking devices, exciters, and bone conduction speakers, but other exciters that can provide frequency sweeps or white noise may also be used. For example, the exciter is capable of stimulating a frequency band of 0 to 10,000 Hz. Such exciters include the aforementioned automatic striking devices. Considering that vibration is applied to the FPD by the exciter and the response waveform of the FPD to that vibration stimulation is acquired by a sensor, the "vibration stimulation" can be expressed as "elastic wave stimulation".
[0016] Acquisition of response waveform The response of the FPD (flat panel detector) to vibration stimuli is recorded by a sensor. For example, the response waveform of the FPD to vibration stimuli is acquired as a time-history waveform. For example, the sampling frequency can be set to 20,000 Hz or higher.
[0017] Acquisition of frequency response characteristics data The frequency response characteristics are evaluated from the acquired time-history waveform. For example, the frequency response characteristics can be evaluated by performing a Fast Fourier Transform on the time-history waveform. In one example, the frequency bandwidth can be 0 to 10,000 Hz and the frequency resolution can be approximately 100 Hz. In this disclosure, a frequency spectrum representing the relationship between frequency and amplitude is used as an example, but it may also be converted into a spectrogram image representing time, frequency, and amplitude.
[0018] AI diagnostics using supervised learning The frequency response characteristics are used as training data to train a machine learning model. If labeled data for healthy and abnormal dental restorations is available beforehand, multi-class classification using common supervised learning methods such as neural networks and ensemble techniques becomes possible.
[0019] AI diagnostics using unsupervised learning If abnormal FPD data cannot be obtained in advance, a good product learning model is constructed using only data on the frequency response characteristics of healthy products to detect anomalies. For example, an autoencoder can be used as an unsupervised learning algorithm to train the anomaly detection model. In this disclosure, an autoencoder using a fully connected neural network is used as an example of a good product learning method, but various unsupervised learning methods, including convolutional autoencoders, can be used.
[0020] Model enhancement through transfer learning If sufficient training data is unavailable for the aforementioned "supervised learning-based AI diagnosis" and "unsupervised learning-based AI diagnosis," transfer learning is effective. This involves creating a pre-trained model using similar data and then retraining the model with a small amount of training data. For example, normalizing the frequency spectrum along the frequency axis eliminates dependence on gender, age, etc., and enables diagnosis of a fixed state even without data of a healthy, fixed state. Transfer learning can improve the generalization and discrimination performance of the model.
[0021] Calculation of abnormal score The frequency response data described above can be fed into the autoencoder of the "AI diagnosis using unsupervised learning" to reduce the dimensionality of the data and reconstruct it. The anomaly score e is defined by focusing on the difference between the input data fi and the reconstructed data gi. By smoothing the input fi and the reconstructed data gi using a moving average, the variability of the diagnosis can be reduced. The width of the moving average can be, for example, around 100 to 1000 Hz. Also, since much of the data is noise, if the absolute amount of fi-gi is smaller than the threshold, it is set to zero to clearly identify an abnormal FPD. The noise cut threshold can be set to a maximum amplitude ratio of around 0 to 0.3. In this way, the frequency response characteristics are input into the anomaly detection model and an anomaly score is obtained as an inference result.
[0022] Determination of normal / abnormal The fixation status of the FPD is determined from the aforementioned anomaly score. The determination is, for example, normal / abnormal. Normal indicates that the FPD is properly fixed to the abutment tooth or implant, while abnormal indicates that there is an abnormality in the fixation status of the FPD to the abutment tooth or implant. For example, the anomaly score of the training data can be calculated using the aforementioned "AI diagnosis using unsupervised learning" model, and the top 5% of those anomaly scores can be set as the anomaly detection threshold.
[0023] For example, the diagnostic device may be equipped with an "AI diagnostic device" that acquires sensor output and outputs a large abnormality score if the retention force of the FPD to the abutment tooth or implant is small. For example, the AI diagnostic device may output feature importance.
[0024] The following provides a more detailed explanation of the method for evaluating the fixation state of FPDs and the examination device, but this disclosure is not limited to these specific examples and encompasses various variations and modifications.
[0025] 1. Detection of abnormalities in the bridge's fixed state Materials and methods Figure 1 shows an example of the experimental process. The methodology is divided into clear stages: sample preparation, experimental procedure, data collection, and subsequent data analysis using machine learning techniques. Figure 2 is a photograph of the mandibular model. The in vitro mandibular model consists of a single crown fabricated on the left first molar and a three-unit bridge fabricated from the right second molar to the second premolar, both manufactured using high-gold alloy. In this example, to reproduce the periodontal ligament, the prepared teeth were inserted into sockets of the mandibular model (mandibular E50-512, Nisshin Dental Products Co., Ltd., Kyoto, Japan) using a general-purpose impression material (Fusion II Extra Wash Type, GC Corporation, Tokyo, Japan).
[0026] Two cementation conditions were established between a single crown and its abutment tooth: a crown that was completely cemented and a crown that was not cemented. Additionally, the following four cementation conditions were established between a three-unit bridge and its abutment tooth. Secure both crowns firmly with cement. Only the premolar crown is fixed with cement. Only the molar crown is fixed with cement. Do not fix both crowns with cement.
[0027] The RFA equipment used in this study includes the following instruments: Data acquisition system (PowerLab ML880, AD Instruments Ltd., Oxford, UK) Constant current source (Power Unit 4114B1, Dytran Instruments Inc., California, USA) 3D accelerometer (3133A1, Dytran Instruments) Software package (LabChart 7 for Windows, AD Instruments).
[0028] The 3D accelerometer was attached to the occlusal surface of the test tooth using, for example, 0.15 mm thick double-sided tape (NICETACK NW-K15, Nichiban Co., Ltd., Tokyo, Japan). For each cement fixation condition, a tooth and implant stability tester (Periotest Classic, Medizintechnik Gulden e. K., Modautal, Germany) was used to apply 4 Hz vibration excitation in the buccal-lingual direction to the buccal surface of the abutment for 4 seconds, generating 16 impact vibrations at 0.25-second intervals (see Figure 3). Figure 3 shows the 3D accelerometer 10 attached to the occlusal surface of the test tooth. The 3D accelerometer 10 was used for data acquisition.
[0029] Measurements were performed on single crowns that were fully cemented (Full-Mos) or single crowns that were not cemented (Un-Mos). Measurements on 3-unit bridges were also performed under the following conditions (measurements on molars: MO, measurements on premolars: PRE): Both crowns were cemented in place (Full-MO, Full-PRE). Only the premolars were cemented (Pre-MO, Pre-PRE). Only the molars were cemented in place (Mo-MO, Mo-PRE). Both crowns are not cemented in place (Un-MO, Un-PRE).
[0030] The type of cement fixation (X) and the measurement site (Y) were specified using XY notation. For example, as shown in Figure 4A, the vibration applied to a single crown was defined as Full-Mos or Un-Mos. Mos means a single crown, while Full and Un mean with and without cement, respectively. As shown in Figure 4B, the vibrations applied to the second molars of a 3-unit bridge were Full-MO, Mo-MO, Pre-MO, or Un-MO, and the vibrations applied to the second premolars were Full-PRE, Mo-PRE, Pre-PRE, or Un-PRE. Here, Full means that both the molars and premolars are cemented, Pre means that only the premolars are cemented, Mo means that only the molars are cemented, and Un means that neither the molars nor premolars are cemented. White crowns indicate teeth that are not cemented. The arrows indicate the measurement sites.
[0031] When an impulse load was applied, the 3D accelerometer recorded an increase in amplitude exceeding a certain threshold. Next, a Fast Fourier Transform was performed on 128 plots for each spatial dimension (x, y, z) to extract the time history of acceleration. The resulting frequency response function had a resolution of 78.1 Hz and covered a frequency band of 0 to 4920 Hz. As a result, the machine learning model used 64 parameters for each direction (x, y, z) as features, using a total of 192 parameters (64 parameters × 3 directions) of one-dimensional (1D) data. The frequency response function was normalized to the maximum amplitude to reduce the variation in oscillatory excitations (see Figure 5).
[0032] The training data was expanded by shifting the frequency response function by up to ±2 parameters in the frequency axis direction, increasing the amount of training data fivefold. The parameters at both ends affected by the shift were set to zero for all data. In the context of unsupervised learning, even with identical test setups and conditions, the measured frequency response varies around the resonant frequency. In unsupervised learning, the amount of training data was increased fivefold by copying and shifting the frequency response function, shifting it to a frequency resolution of 78.1 Hz × (-2 to +2) in the frequency axis. This method is effective in improving the performance of unsupervised machine learning with large amounts of training data.
[0033] Each cement fixation condition was labeled as follows: Full-MO (1), Un-MO (2), Pre-MO (3), Mo-MO (4), Full-PRE (5), Un-PRE (6), Mo-PRE (7), Pre-PRE (8). Two supervised learning methods, a random forest classifier and a neural network classifier, were used to classify these conditions. The random forest classifier was implemented using the sklearn.ensemble.RandomForestClassifier module from the Scikit-learn library (version 0.24.1). The model parameters were set to 100 for the number of decision trees, and other settings used the default values of Scikit-learn. Figure 6 shows the structure of the random forest classifier. The neural network classifier was also implemented using the MLPClassifier module from Scikit-learn (version 0.24.1). This model has four hidden layers, with the number of nodes in each layer set to 96, 48, 24, and 12 from the input layer to the output layer, respectively. Figure 7 shows the neural network structure for supervised learning. Other parameters were set to Scikit-learn's default values (using the Adam optimizer), with a learning rate of 0.001 and 200 epochs.
[0034] The training dataset was split into 70% and the test dataset into 30%. 80 frequency response functions were generated for each experimental case, and these were randomly split, with approximately 56 assigned to the training dataset and 24 to the test dataset. This splitting was performed using the scikit-learn `train_test_split` module. To evaluate the performance of machine learning models, confusion matrices and accuracy were calculated using neural network and random forest models. The confusion matrix provides an overview of the overall model performance by counting the number of true positives, false positives, true negatives, and false negatives. Model accuracy was evaluated by comparing the actual labels in the test data with the predicted labels.
[0035] We used a random forest algorithm to generate a feature importance graph and calculate feature importance scores. These scores indicate which features or characteristics in the data are most relevant to a particular task. Features with high scores are considered to have a greater impact on the outcome, while those with low scores are considered to have a smaller impact. Visualizing feature importance as graphs and rankings allowed for a clearer understanding of the key factors involved in the model's decision-making. This information is expected to be useful in identifying critical elements in disease diagnosis, optimizing product design, and understanding the most influential variables in data-driven decision-making processes. This study evaluated the effects of different cement conditions on the y-direction vibration of FPDs. Feature importance graphs visually represent the importance of each feature in the dataset across different frequency ranges, proving useful for evaluating complex 3D vibration behavior in both bridge and single-crown models.
[0036] Furthermore, an unsupervised learning algorithm was used to identify patterns in the data and group them based on similarity. For this purpose, an autoencoder (AE) architecture consisting of 192 input nodes compressed via three hidden encoding layers with 96, 48, and 24 nodes was employed. Figure 8 illustrates such an autoencoder architecture for adhesion condition evaluation. Decoding was performed by executing the same process in reverse. The activation function used in the model was a normalized linear unit (ReLU), and a sigmoid function was used in the output layer. TensorFlow (version 2.3.0) was used to build and train the model. During training, the AE learned how to match the input and output data. The mean squared error was used as the loss function, the learning rate was set to 0.001, and 500 training epochs were performed. Adam was used as the optimizer, and the batch size was set to 32 (see Figure 9). The frequency response function was used as a criterion for comparing the input and output data of the AE.
[0037] Next, anomaly scores were calculated using the output frequency response function and input function reconstructed by AE. This applied an unsupervised learning method to detect anomalies in the cement fixing conditions of the FPD. It should be noted that the number of training data instances for Full-Mo and Full-Pre connection conditions differs from the number of data used in supervised learning. In this study, a total of 240 frequency response functions obtained from three sets of tapping tests were used as training data. Using a sufficient amount of training data is important to improve the performance of unsupervised learning and to more effectively identify anomalies in cement fixing conditions.
[0038] Noise reduction and anomaly score calculation To more effectively evaluate the cement fixing conditions, several processes were implemented. First, moving averages of the input and output functions were obtained. A 10-parameter moving average was applied to improve data smoothness. Next, since some frequency ranges may contain only noise, 0.2 was subtracted from the input and output frequency response function values to mitigate its influence. After this process, any negative results were set to zero. After applying these noise reduction processes, the anomaly score e was calculated using the following formula.
[0039]
number
[0040] Here, fi and gi (1 ≤ i ≤ 192) represent the input frequency response function and the reconstructed output frequency response function, respectively.
[0041] result Single Crown Neural networks and random forest algorithms were trained using acceleration datasets in the x, y, and z directions. The training results (Table 1) show that both methods achieved a positive confusion matrix and demonstrated high accuracy. Specifically, the neural network achieved 100% accuracy, and the random forest achieved 99% accuracy.
[0042] [Table 1]
[0043] Figure 10 is a graph showing the result of calculating feature importance related to cement fixation conditions using the random forest algorithm. This graph evaluates the frequency response in the x, y, and z directions under cement fixation conditions. Specifically, Figure 10A shows the feature importance of the frequency response in the x direction calculated from the acceleration under single-crown cement fixation conditions. Figure 10B shows the feature importance of the frequency response in the y direction calculated from the acceleration under single-crown cement fixation conditions. Figure 10C shows the feature importance of the frequency response in the z direction calculated from the acceleration under single-crown cement fixation conditions. The results show that the dynamic response in the y direction is greater than the responses in the x and z directions. This suggests that in the single-crown model, the dynamic characteristics in the y direction are more pronounced than in the other directions and play an important role in evaluating cement fixation conditions.
[0044] Training a supervised machine learning algorithm using only the y-acceleration dataset. Training a dataset of y-direction acceleration data using neural networks and random forest algorithms (Table 2) confirmed that both methods achieved high accuracy. Specifically, the neural network achieved an accuracy of 97%, and the random forest achieved an accuracy of 96%. Furthermore, favorable confusion matrices were obtained for each model, indicating superior predictive performance.
[0045] [Table 2]
[0046] This result demonstrates that even when using only acceleration data in the y-direction, supervised learning algorithms have the ability to accurately classify the cement fixing conditions of a 3-unit bridge. In other words, supervised machine learning algorithms using only acceleration data in a specific direction can be used to train anomaly detection models. The feature importance graph was created using the random forest method. Figure 11 shows the frequency range with the highest score when measurements were taken on molars. Figure 11 is a feature importance graph of the frequency response function calculated using y-acceleration data of a 3-unit bridge where the measurement site is the second molar. From Figure 11A, it can be seen that in the comparison between Full-MO and Un-MO conditions, frequencies in the range of 0 to 500 Hz show feature importance. From Figure 11B, it can be seen that in the comparison between Full-MO and Pre-MO conditions, frequencies around 1000 Hz show importance. From Figure 11C, it can be seen that in the comparison between Full-MO and Mo-MO conditions, frequencies around 3000 Hz show importance.
[0047] Figure 12 shows the frequency range with the highest score when measurements were taken at the premolars. Figure 12 is a feature importance graph of the frequency response function calculated using y-acceleration data of a 3-unit bridge where the measurement site is the second premolar. From Figure 12A, it can be seen that the range of 0 to 500 Hz shows feature importance when comparing the Full-PRE condition and the Un-PRE condition. From Figure 12B, it can be seen that the frequency of approximately 2000 Hz shows importance when comparing the Full-PRE condition and the Mo-PRE condition. From Figure 12C, it can be seen that the frequency of approximately 3000 Hz shows importance when comparing the Full-PRE condition and the Pre-PRE condition.
[0048] The results shown in Figures 11 and 12 indicate that the frequency range of 0–500 Hz is important when evaluating Un-MO and Un-PRE cement fixation conditions. On the other hand, for Pre-MO and Mo-PRE cement fixation conditions, the range of 1000–2000 Hz was found to be the most important. Furthermore, the resonant frequency for Full-MO, Full-PRE, Mo-MO, and Pre-PRE conditions was approximately 3000 Hz, confirming high rigidity under these conditions.
[0049] Training supervised machine learning algorithms using 3D acceleration datasets Training a 3D acceleration dataset using neural networks and random forest algorithms (Table 3) yielded positive confusion matrices and demonstrated high accuracy for both approaches. Neural networks achieved 98% accuracy, while random forests achieved 99% accuracy.
[0050] [Table 3]
[0051] Using a random forest algorithm, the analysis was performed, and as shown in Figure 13, the feature importance for eight cement fixation conditions was evaluated as a function of the frequency response in the x, y, and z directions. Figure 13A is a feature importance graph calculated from the acceleration of the FPD cement state, showing the frequency response in the x direction. Figure 13B is a feature importance graph calculated from the acceleration of the FPD cement state, showing the frequency response in the y direction. Figure 13C is a feature importance graph calculated from the acceleration of the FPD cement state, showing the frequency response in the z direction. Figure 13 shows that the acceleration in the x direction is significantly greater than the acceleration in the y and z directions. This confirms that the x direction has particularly important features in the analysis using 3D acceleration data.
[0052] Training of unsupervised learning algorithms Figure 14 shows the analysis results using an autoencoder (AE) trained with the y-direction frequency response obtained from standard data under Full-MO cementation conditions. This figure shows a comparison of the input and output data under Full-MO and Un-MO conditions. Specifically, the input frequency response function under Full-MO conditions was accurately reconstructed based on the standard data under Full-MO conditions (Figure 14A). On the other hand, the model was unable to accurately reconstruct the input frequency response function when using anomalous data under Un-MO conditions (Figure 14B). Anomaly scores were calculated using the Full-MO (Table 4A), Full-PRE (Table 4B), and Full-MO / Full-PRE (Table 4C) conditions for training. This analysis used 1D and 3D acceleration datasets for all cement fixation conditions. The results showed that using 3D acceleration data improved the coefficient of variation (CV) between anomaly scores and enhanced the ability to detect anomalies.
[0053] [Table 4]
[0054] The data in the table showed that using data from the fully cemented condition yielded the lowest anomaly score, suggesting that this condition was the most stable. On the other hand, the non-cemented and partially cemented conditions yielded higher anomaly scores, indicating that these conditions were more susceptible to anomalies.
[0055] Consideration The results of this study suggest the potential of machine learning algorithms to rapidly and accurately identify the cement fixation status between FPDs (fixed partial dentures) and their abutments. This method can not only detect cement loss from FPDs but also classify the cement fixation status. This is expected to enable clinicians and researchers to make informed treatment decisions and prevent complications. Random forests are effective algorithms for estimating the importance of features in a dataset. The importance score of each feature is based on the reduction in impurity (or loss) when the data is split at the nodes of the decision tree. The reduction in impurity is averaged across all trees in the forest, and a single score is assigned to each feature. This makes it possible to identify the most important features, analyze them to gain a deeper understanding of the underlying relationships in the data, and improve the performance of the model.
[0056] In this study, the resonant frequency of the molar crowns in a fully cemented bridge on a mandibular model (Figure 11) was approximately 3000 Hz, consistent with previous research results. This value indicates that the crown or bridge is firmly fixed to the natural teeth. Generally, highly rigid objects resist deformation and require high energy for vibration. Therefore, they tend to vibrate at high frequencies when subjected to external forces or vibrations. On the other hand, in bridges that are not cemented, the resonant frequency of the crowns falls within the range of 0 to 500 Hz. This is because, due to the absence of cement, less energy is required for vibration, resulting in a tendency to vibrate at low frequencies. Furthermore, in partially cemented bridges, the feature importance score for the uncemented crown was highest at approximately 1000 Hz, indicating that the rigidity of partially cemented bridges is lower than that of fully cemented bridges. However, the resonant frequency of the crown in partially cemented bridges was similar to that of fully cemented bridges (approximately 3000 Hz), and the peak of the feature importance score showed a similar value. A similar trend was observed in the measurement of the resonant frequency of premolars (Figure 12). When the crown was not cemented, the resonant frequency varied in the range of 0 to 500 Hz. On the other hand, when cemented, a maximum of 3000 Hz was recorded. In addition, the resonant frequency under MO-PRE conditions was approximately 2000 Hz, exceeding that of Pre-MO conditions (approximately 1000 Hz). This difference is thought to be because the resonant frequency of an object depends on its natural vibration mode, shape, and size. Larger objects tend to have greater mass and lower vibration frequencies, while smaller objects vibrate at higher frequencies because they react quickly to external forces. Position and boundary conditions also affect the resonant frequency. For example, different resonant frequencies arise depending on whether an object is fixed or released.
[0057] Figures 10 and 13 show that in the bridge model, x-direction acceleration is more important than y-direction acceleration, while in the single crown model, the y-direction feature importance score is the highest. In the single crown model, there are no constraints in the x or y direction, and when an impact load is applied in the y direction, the tooth moves freely in the x direction, resulting in a low importance score in the x direction. On the other hand, in the bridge model, the x direction is constrained, so the tooth cannot move freely, resulting in a high importance score in the x direction. In addition, the constraint in the x direction generates complex 3D vibrations, and the z-direction feature importance is higher than in the single crown model. This result demonstrates the usefulness of machine learning in complex 3D vibration analysis.
[0058] Unsupervised learning is an algorithm that does not require labeled data and identifies patterns in data through clustering, dimensionality reduction, and density estimation. In this study, an autoencoder (AE) was used as the unsupervised learning algorithm. An AE is a neural network that compresses input data into a low-dimensionality and learns the data through reconstruction. When comparing data in a fully fixed state and an unfixed state using an AE, the data in the fully fixed state could be reconstructed accurately, while the data in the unfixed state could not. This suggests that the unfixed state may contain anomalous patterns for the AE.
[0059] Anomaly detection is a field of machine learning that identifies anomalous data points that deviate significantly from the expected behavior of the data. The anomaly score is an index that quantifies whether the data is anomalous, with a higher score indicating a higher probability of anomaly. In this study, the performance of the anomaly detection algorithm was improved by using 3D acceleration data. This is because 3D data comprehensively captures deviations from normal behavior. As a result, the fully fixed state was the most stable, and the number of anomalous data points tended to increase in the unfixed and partially fixed states.
[0060] Identifying the fixation state between the FPD and the abutment using machine learning algorithms is useful in FPD management and serves as a powerful tool to support treatment decision-making in clinical settings. In this study, the highest scores were observed at approximately 3000 Hz for fully fixed states, 1000-2000 Hz for partially fixed states, and 0-500 Hz for unfixed states. Further improvements were obtained by including 3D vibration analysis. Fully cemented fixation resulted in low abnormality scores, while unfixed and partially fixed states resulted in high abnormality scores. The stiffness and vibration characteristics of the FPD differed depending on the measurement conditions and acceleration direction. These results suggest the potential to contribute to improving the accuracy of RFA (Resonant Frequency Analysis) in FPD models and to early abnormality detection. While this disclosure evaluated the fixation state of a specific FPD, it is believed that, in principle, the fixation state and abnormalities can be detected for any FPD using the method described herein.
[0061] 2. In vitro (out-of-vivo) investigation of abnormal screw loosening detection in different implant-abutment connection methods. Screw loosening is a common mechanical complication in implant-supported prostheses, typically occurring in 4.3% to 10% of patients after functional loading has been applied. Screw loosening can lead to problems such as implant-abutment instability, pain, increased risk of bacterial invasion, peri-implantitis, and potential marginal bone loss.
[0062] Resonant frequency analysis (RFA) is a non-invasive and objective method widely used in implant dentistry to evaluate implant stability. It measures the vibration frequency of the implant and calculates and displays it as an Implant Stability Quotient (ISQ). RFA readings can be influenced by bone quality, implant design and materials, soft tissue condition, patient-specific factors, and even measurement and environmental variations. Advanced data analysis techniques, particularly machine learning algorithms, can help improve the accuracy and reliability of RFA evaluation. Machine learning algorithms can be broadly categorized into supervised approaches, such as neural networks and random forests, which are trained on labeled data to predict outcomes, and unsupervised approaches, which detect patterns from unlabeled data. However, well-known studies have focused on the retention force of the prosthesis (cement loss) rather than screw loosening between the implant and the abutment. Screw loosening is a common mechanical complication in implant-supported restorations, but its early detection remains difficult due to a lack of non-invasive and quantitative evaluation tools. Therefore, the inventors applied a combination of RFA and machine learning to detect screw loosening in different implant-abutment connection (IAC) configurations. The null hypothesis was that even when RFA is combined with machine learning, it is not possible to reliably detect early screw loosening in different IAC configurations.
[0063] Materials and methods Three distinctly different implant-abutment connection types were tested: conical connection (NobelParallel CC; Nobel Biocare), internal tri-channel connection (Replace Select Tapered; Nobel Biocare), and external hexagonal connection (Branemark System Mk III; Nobel Biocare). All implants were standardized to a length of 10 mm, with the conical and internal tri-channel implants having a diameter of 4.3 mm, while the external hexagonal implant had a diameter of 4.0 mm. Three jawbone models (EX-7 and 1017A; Nissin) were prepared, and two implants were placed in the first molar region of each model. Figure 15 is a photograph of the jawbone model with two implants. A custom-made surgical guide was used to standardize the implant placement and ensure accuracy. Figure 16 is a photograph of the custom-made surgical guide.
[0064] RFA device and measurement RFA measurements were performed using a 3-axis piezoelectric pickup sensor (Model 3133A1; Dytran Instruments, Inc.), a power unit (Model 4114B1; Dytran Instruments, Inc.), a PowerLab data acquisition system (Model ML880; Dytran Instruments, Inc.), and a software package (LabChart 7; Dytran Instruments, Inc.). The 3D accelerometer was securely attached to the lingual surface of the abutment cap or jig. Figure 17 is a photograph of the 3D accelerometer fixed to the abutment. In Figure 17A, the direction on the mandibular model is defined. Figure 17B is a plan view of the accelerometer. Vibration was applied buccal-lingually at 4 Hz using an implant stability tester (Periotest Classic; Medizintechnik Gulden), with 16 impulse strikes at 0.25-second intervals. The accelerometer recorded responses along three axes (x: mesiodistal, y: buccolingual, z: implant longitudinal axis) at a sampling rate of 20,000 Hz. To reduce variations due to impact force and angle, the frequency response functions (FRFs) were normalized to the maximum amplitude.
[0065] To simulate various degrees of screw loosening, the abutment screw was first tightened to 15 Ncm (0-degree loosening). Then, it was gradually loosened in 5° increments up to 30°, creating six different loosening conditions: 5°, 10°, 15°, 20°, 25°, and 30°. Under the intact condition, each specimen was subjected to 20 vibration cycles (320 total impacts), while under the loosened conditions, each specimen was tested with 4 vibration cycles (384 total impacts). Frequency response functions (FRFs) were recorded for all seven conditions, and resonant frequencies were captured along all three axes.
[0066] Supervised learning model The supervised learning model was developed using a random forest algorithm implemented via the machine learning library (Scikit-learn, version 0.24.1; Python Software Foundation) (the random forest architecture is shown in Figure 6). 100 decision trees and default parameters were used. The following two classification tasks were performed: Binary classification: 320 normal samples (0°) were designated as label 0, and 384 relaxed samples (64 samples from each of the six relaxed angles from 5° to 30°) were combined and designated as label 1. Multi-class classification: 64 samples were selected from each of the seven conditions (in 5-degree increments from 0° to 30°), for a total of 448 samples, which were then classified into labels 0 to 6. The dataset was split into 80% for training and 20% for testing. Model performance was evaluated using accuracy metrics and confusion matrices, and key resonant frequency features related to screw loosening detection were identified through feature importance analysis. To confirm reliability, classification using random forests and neural networks was repeated over 200 trials.
[0067] Unsupervised learning models As an unsupervised learning method, a convolutional autoencoder (CAE) was constructed using a deep learning framework (TensorFlow, version 2.8.0; Google LLC) and a neural network library (Keras, version 2.8.0; Google LLC) (see Table 5 for the CAE architecture and Figure 8 for a schematic diagram of the CAE).
[0068] [Table 5]
[0069] The CAE performed data compression and reconstruction using a one-dimensional CNN. This included convolutional layers for extracting local features, a stride 2 compression layer, a fully connected layer, and an upsampling layer to increase resolution. All layers except the sigmoid function in the final layer used the ReLU (Rectified Linear Unit) activation function. The model was trained to match inputs and outputs using Mean Squared Error as the loss function. Training was performed for 500 epochs, with a learning rate of 0.001, using the Adam optimizer and a batch size of 16. The frequency response functions (FRFs) of implants in a normal state were used as the baseline condition. The dataset consisted of 64 samples for each of the seven loosening angles. To account for data variability, evaluation was repeated over more than 200 trials. The stability of the learning was evaluated by plotting the loss function using 80% of the data for training and 20% for validation, with the x-axis representing the number of epochs and the y-axis representing the loss value.
[0070] Enhanced anomaly detection To enhance anomaly detection, a moving average filter with a window size of five consecutive frequency bins (corresponding to approximately 781 Hz) was applied to both the input and output FRFs. The effect of noise was mitigated by subtracting 0.1 from the value, negative results were set to zero, and the anomaly score e was calculated using the following formula, similar to the formula described above.
[0071]
number
[0072] Here, fi and gi (1<i<192) are the input and reconstructed output frequency response functions, respectively. The abnormality determination threshold was defined as the top 10% of abnormality scores obtained from normal specimens, which ensured a reliability of approximately 90% in normal classification. Specimens exceeding this threshold were classified as abnormal and considered to indicate potential screw loosening. It was shown that slight fluctuations in the threshold had little effect on the results, and strict tuning was not essential for model performance.
[0073] Results The results of this study showed that the proposed method is effective in detecting and classifying different degrees of screw loosening in various implant-abutment connection modes. The diagnostic value was limited by visual interpretation of the frequency response function (FRF) alone, as the spectral changes accompanying loosening are subtle and clinically difficult to interpret. Therefore, machine learning was applied to extract highly discriminative features from the FRF data for classification.
[0074] Supervised learning models using random forest and neural network algorithms classified screw loosening based on triaxial vibration patterns in the conical connection mode. In binary classification, the random forest achieved accuracies of 100% for the first specimen and 99.7% for the second specimen (Table 6), while the neural network achieved 100% and 99.9% (Table 7).
[0075] [Table 6]
[0076] [Table 7]
[0077] In multi-class classification, the accuracy was 83.7% and 90.1% with random forests (Table 8), and 82.8% and 89.1% with neural networks (Table 9). Feature importance analysis showed that resonant frequencies along all spatial axes were consistently important for distinguishing the severity of loosening. Figure 18 shows the results of feature importance analysis using the random forest algorithm for conical-connected screw loosening detection after testing of intact and abnormal groups, with A for the first sample and B for the second sample. Figure 19 shows the results of feature importance analysis using the random forest algorithm for conical-connected screw loosening detection after testing seven screw loosening conditions, with A for the first sample and B for the second sample.
[0078] [Table 8]
[0079] [Table 9]
[0080] Unsupervised learning was performed using a CAE trained on triaxial frequency response and evaluated across seven screw loosening conditions. Figure 20 shows the detection of frequency response anomaly scores for various screw loosening angles in a conical ligament configuration, with A for the first sample and B for the second sample. The anomaly scores shown in Figure 20 indicate the degree of deviation from the normal state. A threshold based on the top 10% of scores for normal samples identified the anomaly. Even a loosening of just 5° consistently exceeded this threshold, demonstrating the high sensitivity of the CAE to subtle changes in implant-abutment stability.
[0081] To evaluate screw loosening, supervised learning analyses using random forest and neural network models were performed on two internal tri-channel coupled samples. In binary classification, both models achieved high accuracy, with random forest achieving 100% and 99.9% (Table 10) and neural network achieving 100% and 99.7% (Table 11).
[0082] [Table 10]
[0083] [Table 11]
[0084] The confusion matrix confirmed reliable separation between normal and relaxed states. In multi-class classification, accuracy was achieved with random forests at 89.8% and 86.7% (Table 12), and with neural networks at 91.6% and 86.7% (Table 13).
[0085] [Table 12]
[0086] [Table 13]
[0087] Figure 21 shows the results of feature importance analysis using a random forest algorithm for internal tri-channel linked screw loosening detection after testing of intact and abnormal samples, where A represents the first sample and B represents the second sample. Figure 22 shows the results of feature importance analysis using a random forest algorithm for internal tri-channel linked screw loosening detection after testing seven screw loosening conditions, where A represents the first sample and B represents the second sample. These feature importance analyses (Figures 21 and 22) continued to emphasize the resonant frequencies across all axes as the most relevant features for detecting and classifying the severity of loosening.
[0088] Unsupervised learning analysis was performed using a CAE trained on the frequency responses of the X, Y, and Z axes. The CAE evaluated all screw loosening conditions, and the results are shown in Figure 23. Figure 23 shows the detection of frequency response anomaly scores for various screw loosening angles in an internal tri-channel linked configuration, with A for the first sample and B for the second sample. A threshold set at the top 10% of anomaly scores from the normal state played a role in identifying anomalies. In both samples, the 5° loosening condition consistently exceeded this threshold, demonstrating that the CAE is sensitive to subtle deviations from the normal state.
[0089] Supervised learning analysis was performed on two external hexagonal connected samples using random forest and neural network models. In binary classification, the random forest achieved accuracy of 99.4% and 98.3% (Table 14), while the neural network achieved accuracy of 99.8% and 99.6% (Table 15).
[0090] [Table 14]
[0091] [Table 15]
[0092] The confusion matrix confirmed reliable separation between normal and relaxed states. In multi-class classification, accuracy was achieved with random forests at 94.5% and 89.9% (Table 16), and with neural networks at 95.3% and 85.4% (Table 17).
[0093] [Table 16]
[0094] [Table 17]
[0095] Figure 24 shows the results of feature importance analysis using a random forest algorithm for detecting external hexagonal linked screw loosening after testing of intact and abnormal samples, where A represents the first sample and B represents the second sample. Figure 25 shows the results of feature importance analysis using a random forest algorithm for detecting external hexagonal linked screw loosening after testing seven screw loosening conditions, where A represents the first sample and B represents the second sample. The feature importance analysis (Figures 24 and 25) consistently showed that the most important features for detecting and evaluating the severity of screw loosening were the resonant frequencies along the X, Y, and Z axes.
[0096] An unsupervised learning analysis was performed using a CAE trained on frequency responses along the X, Y, and Z axes. The anomaly scores for all screw loosening conditions are shown in Figure 26. Figure 26 shows the detection of frequency response anomaly scores for various screw loosening angles in an external hexagonal coupling manner, with A for the first sample and B for the second sample. A threshold set at the top 10% of the score from the normal state identified the anomaly, and the 5° loosening condition consistently exceeded this threshold.
[0097] Table 18 summarizes the CAE performance over 200 trials for each implant condition. Accuracy is defined as the percentage of correctly detected loosened specimens (384 specimens per trial). The CAE achieved nearly 100% accuracy for all implant types and loosening angles, and was clinically acceptable, although slightly lower at 92% for external hexagonal coupling. The coefficient of variation was approximately 7%, demonstrating strong consistency and reproducibility. These results support the potential of this unsupervised approach for reliable screw loosening detection across implant designs. Plotting the training and validation loss functions to confirm model convergence and assess the risk of overfitting showed stable convergence with no divergence between curves, indicating appropriate generalization to unseen data.
[0098] [Table 18]
[0099] Consideration The null hypothesis that a combination of RFA and machine learning could not reliably detect screw loosening across different implant-abutment connections was rejected. This method provided early, accurate, and non-invasive screw loosening detection in conical, internal tri-channel, and external hexagonal designs. RFA results revealed patterns specific to each connection type, which are thought to be due to the unique mechanical and structural characteristics of each implant system. Biomechanical studies have shown these connections exhibit different torque-displacement responses, supporting the observed variations in vibrational behavior.
[0100] Conical joints employ a tapered design that creates a friction fit between the implant and abutment, providing large surface contact and a self-locking mechanism when fully tightened, thereby enhancing stability. Mechanical analyses using analytical and finite element methods have shown that engagement due to contact pressure and friction determines the pull-out force and loosening torque, and that even slight relative movement reduces friction, leading to decreased stiffness and increased vibrational oscillation. Furthermore, if the abutment is not fully seated, vertical displacement of 22.6 to 62.2 μm can occur, which reduces the engagement of the anti-rotation and anti-flexion functions and impairs stability. When loosening occurs, the taper allows small displacements between the implant and abutment, weakening frictional stability, increasing resonance amplitude, and reflecting a decrease in mechanical stiffness at the interface.
[0101] Internal tri-channel and external hexagonal connections rely on mechanical locking mechanisms such as screws or interlocking channels rather than friction, resulting in less surface contact than conical connections. Stability depends on the engagement of these locking elements and weakens when loosening occurs. Previous studies have reported that internal connections, due to their geometry and large contact area, exhibit larger microdisplacements than external hexagonal connections when preload is lost. These microdisplacements make internal connections more deformable under functional load, amplifying vibration responses detectable by periodic analysis and resonant frequency analysis. In contrast, external hexagonal designs, with their smaller contact area and reliance on screw stabilization, exhibit less displacement and less pronounced vibration changes after loosening. These differences highlight how the geometry of the implant-abutment connection influences both mechanical stability and vibration behavior under screw loosening.
[0102] The high accuracy in detecting and classifying screw looseness may be due to several factors. Each implant-abutment coupling design exhibits unique resonant frequency patterns under different loosening conditions, providing highly discriminative input information for machine learning. Data from a 3-axis accelerometer captures subtle vibrations across all three axes, providing a rich set of multidimensional features. A random forest estimates feature importance by averaging impurity reductions across the entire tree, identifying key features and improving model performance. In this study, this algorithm achieved perfect accuracy in binary classification and 83% to 92% accuracy in multi-class classification. Feature importance consistently focused on resonant frequencies along the X, Y, and Z axes, supporting its usefulness in detecting varying degrees of looseness.
[0103] CAE provided valuable insights by detecting anomalies associated with screw loosening. Established for unsupervised anomaly detection, this method demonstrated its potential to complement supervised methods without labeled data, identifying deviations from normal conditions even with slight loosening (5°). Trained on X, Y, and Z axis frequency responses, CAE consistently detected subtle vibrational changes across all implant-abutment connection configurations. A threshold set at the top 10% of anomaly scores from normal specimens effectively distinguished between normal and abnormal conditions while minimizing false positives.
[0104] This study provided proof-of-concept evidence that screw loosening can be detected by combining RFA and machine learning. Clear vibration changes were observed as the severity of loosening increased, and the machine learning model demonstrated high classification accuracy. Such a method is also applicable to screw loosening detection in implant-abutment connection types not described above, i.e., connection types other than conical, internal tri-channel, and external hexagonal.
[0105] 3. Anomaly detection method that applies vibrational stimulation to fixed dental crowns using a bone conduction speaker. Depending on the position of fixed crown restorations, it may be difficult to insert an exciter into the oral cavity. Furthermore, while jaw models were used in the examples above, there were cases where it was not possible to place an exciter, such as an impactor, in the appropriate location within the actual oral cavity. Therefore, as an alternative to the tapping-based vibration method, we investigated a method of vibrating teeth using bone conduction speakers.
[0106] Model experiment Figure 27 shows an embodiment of the model experiment. A 3D acceleration sensor 52 was attached to the implant of the mandibular model 50. The 3D acceleration sensor 52 was attached to the implant in both a state where the implant was not loose (healthy) and a state where it was loosened by about 20° (loose). A smartphone 58 was connected to the 3D acceleration sensor 52 via a signal conditioner 56. White noise in the range of 1,000-10,000 Hz was reproduced by a bone conduction speaker 54 and the tabletop was vibrated. White noise is a wave that uniformly contains the entire frequency range and has the same characteristics as impact. While impact is a wave that contains the entire frequency range in a short time, white noise is a wave that contains the entire frequency range and is applied continuously. White noise differs from impact in that it has superior vibration accuracy and can generate a steady signal, so a continuous response can be observed. The mandibular model 50 was placed near the bone conduction speaker 54. The bone conduction speaker 54 and the mandibular model 50 were not mechanically fixed together.
[0107] The bone conduction speaker 54 was repeatedly used to induce vibration and then stopped vibration on a desk. Vibration measurements were taken 90 times for the healthy state and 10 times for the relaxed state. In the machine learning study described later, the 80 measurements in the healthy state were used as training data, and the 10 measurements in the healthy state and the 10 measurements in the relaxed state were combined to form the test data. The signal from the acceleration sensor 52 was captured by the smartphone 58 through the signal conditioner 56 and saved as an audio file in WAV format. The sampling frequency was set to 48,000 Hz.
[0108] Figure 28 shows an example of an acceleration waveform obtained from a healthy implant. The upper and lower panels in the figure represent the horizontal acceleration in the circumferential and perpendicular directions, respectively. The circumferential direction is the mesiodistal direction, and the perpendicular direction is the buccolingual direction. The implant was vibrated and stopped approximately 10 times using a bone conduction speaker on a table, and it was confirmed that the amplitude increased during vibration and decreased when stopped. This showed that vibrations can be excited in the implant by a bone conduction speaker. In this experiment, the acceleration in the perpendicular direction was greater than that in the circumferential direction, so in subsequent analyses, only the acceleration waveform in the perpendicular direction was frequency analyzed.
[0109] The response during excitation was extracted from the waveform of the healthy state shown in Figure 28 and subjected to FFT analysis. The number of FFT data plots was 512, and the result of averaging 30 frequency spectra is shown in Figure 29A. From Figure 29A, it was found that the variation from trial to trial was small, and the resonant frequency corresponding to the amplitude peak was 1980 Hz. Next, the frequency spectrum obtained from the loosened implant is shown in Figure 29B. In the loosened state, the frequency response in the 2000-3000 Hz range changed, and the resonant frequency decreased to 1290 Hz.
[0110] The results so far suggest the possibility of detecting implant anomalies by focusing on the resonant frequency, especially in cases of significant loosening of around 20°. Furthermore, we also investigated implant anomaly detection using machine learning (autoencoder). The autoencoder used a fully connected neural network, with the input layer providing the frequency spectrum as one-dimensional data (256 parameters). Dimensionality was reduced to 128, 64, and 32 parameters through three hidden layers, and then reconstructed into a 256-parameter frequency spectrum by the reverse process. The anomaly score of the test data (10 healthy data + 10 loose data) was evaluated using a trained model with 80 healthy data points. Figure 30 shows the anomaly scores for the healthy and loose data. The anomaly score on the vertical axis of Figure 30 is the input-output reconstruction error divided by the output data. From Figure 30, the healthy data (Nos. 1-10) showed low anomaly scores, while the loose data (Nos. 11-20) showed high anomaly scores. Based on the above, we have confirmed the possibility of detecting implant abnormalities using bone conduction speakers and machine learning, as an alternative to conventional tapping test methods.
[0111] Human experimentation We hypothesized that fixed dental crowns could be vibrated through the human body by placing a bone conduction speaker in contact with the jaw or cheek. Therefore, we conducted an experiment on a subject who was missing a front tooth and had a three-unit bridge. Figure 31 shows a photograph of the experiment. A bone conduction speaker 54 was placed against the cheek and repeatedly vibrated and stopped, while an acceleration sensor 52 was placed in contact with the three upper front teeth (bridge) by a dentist. Figure 32 shows the acceleration waveforms obtained by the sensors. The upper and lower panels represent acceleration in the circumferential and perpendicular directions, respectively. As illustrated in Figure 32, the acceleration in the perpendicular direction was not obscured by noise, allowing us to measure the vibrations excited by the bone conduction speaker. On the other hand, the response in the circumferential direction was small, suggesting that a high-sensitivity sensor would be effective for measuring vibrations in that direction. Furthermore, the quality of the obtained vibrations can be improved by interposing a viscous "contact medium" between the sensor and the tooth.
[0112] The excitation response in the direction perpendicular to the circumference of Figure 32 was extracted, and the frequency spectrum shown in Figure 33 was obtained by FFT analysis. From Figure 33, it was found that the frequency characteristics of the subject's bridge could be clearly measured using a bone conduction speaker and an acceleration sensor.
[0113] Through model experiments and human trials, we proposed a prototype of a medical examination device combining a bone conduction speaker, an accelerometer, and a smartphone. This device allows for vibrational stimulation of fixed dental restorations by contacting the bone conduction speaker with the jaw or cheek, eliminating the need to insert an exciter into the mouth. Furthermore, by attaching a small accelerometer to a rod-shaped material such as a dental mirror, it is expected that vibration characteristics can be easily measured by contacting the accelerometer with the molars.
[0114] The above-mentioned examination device and fixation evaluation method using bone conduction speakers is just one example; other examination devices and fixation evaluation methods can be used. For example, a system with bone conduction speakers, an accelerometer, and a smartphone contributes to the construction of an examination device with reduced total cost. A pre-trained model is implemented on the smartphone, and transfer learning data reflecting the patient's characteristics is added to the smartphone for tuning. The computational resources of the smartphone are sufficient for tuning. By using a device that connects a 3-axis accelerometer to the smartphone, the accuracy of the examination can be further improved.
Claims
1. Applying elastic wave stimulation to fixed crown restorations, To acquire the response waveform of the fixed crown restoration to the elastic wave stimulation as a time history waveform, Evaluate the frequency response characteristics from the aforementioned time-history waveform. The frequency response characteristics are input to the anomaly detection model to obtain an anomaly score as an inference result. A method for evaluating the fixation status of a fixed dental crown, comprising determining the fixation status of the fixed dental crown from the abnormal score.
2. The method for evaluating a fixed state according to claim 1, wherein the elastic wave stimulation is provided by an exciter.
3. The method for evaluating a fixed state according to claim 1, wherein the elastic wave stimulation is provided by directly vibrating using a striking device or by vibrating a bone conduction speaker in contact with the jaw or cheek.
4. The method for evaluating the fixed state according to claim 1, wherein a three-dimensional acceleration sensor, piezoelectric sensor, or magnetostrictive sensor in contact with the fixed crown restoration, or a non-contact laser vibrometer, is used to acquire the response waveform.
5. The fixed state evaluation method according to claim 1, wherein the anomaly detection model is trained using a supervised machine learning algorithm that uses only acceleration data in a specific direction.
6. The fixed state evaluation method according to claim 1, wherein an unsupervised learning algorithm is used to train the anomaly detection model.
7. The fixed-state evaluation method according to claim 1, further comprising calculating feature importance using a random forest algorithm.
8. The fixed state evaluation method according to claim 7, wherein the aforementioned feature importance is displayed as a graph or ranking.
9. The fixation state evaluation method according to claim 1, wherein the determination of the fixation state determines whether it is normal or abnormal, and normal indicates that the fixed crown restoration is properly fixed to the abutment tooth or implant body, and abnormal indicates that there is an abnormality in the fixation state of the fixed crown restoration to the abutment tooth or implant body.
10. An exciter that applies elastic wave stimulation to a fixed crown restoration attached to a fixed crown restoration, A sensor that acquires the response waveform of the fixed dental crown restoration, A device for examining fixed dental crowns, comprising: an AI diagnostic device that acquires the output of the aforementioned sensor and outputs a large abnormality score if the retention force of the fixed dental crown restoration to the abutment tooth or implant is small.
11. The medical examination device according to claim 10, in which the AI diagnostic device outputs feature importance.
12. The exciter is a striking device or a bone conduction speaker. The medical examination apparatus according to claim 10, wherein the sensor is a three-dimensional acceleration sensor, a piezoelectric sensor, a magnetostrictive sensor, or a laser vibrometer.
Citation Information
Patent Citations
Methods and apparatus for testing objects
JP2006527627A
Dental installation quality inspection device
JP2014507194A
Method for evaluating installation strength of orthopedic implant, orthopedic implant, and orthopedic jig
JP2017144061A
Dental medical device
JP2020146072A
Method and system for measuring and assessing the stability of medical implants
JP2020515311A
