A dental biometric feature detection method and system based on intelligent sensors

Abstract

The present application relates to the technical field of biological detection, in particular to a dental biological feature detection method and system based on intelligent sensors. The present application can comprehensively evaluate the health status of teeth and surrounding tissues by acquiring bone data of teeth through intelligent sensors and combining multi-dimensional information such as bone density distribution map, temperature data, occlusal force data and conductivity data. The present application can more accurately evaluate the health risk of teeth by comprehensively considering multi-dimensional biological feature data such as thermal expansion stress, occlusal stress, biomechanical response value and conductivity tensor. The present application can effectively judge potential lesion areas by calculating biological activity attenuation factor and comprehensive lesion risk value, greatly improving the accuracy of disease prediction. The present application effectively improves the accuracy, reliability and safety of dental biological feature detection by comprehensively using intelligent sensor technology, multi-angle and multi-dimensional detection and evaluation means.

Description

Technical Field

[0001] This invention relates to the field of biological detection technology, and in particular to a method and system for detecting dental biomarkers based on intelligent sensors. Background Technology

[0002] Dental biometrics refers to the collection of biometric data related to teeth and oral cavity through smart sensors or other devices for the identification, diagnosis, monitoring, or treatment of oral diseases. It mainly relies on biological information related to teeth, oral tissues, or saliva for detection and analysis, which can help doctors better understand the patient's oral health status and make accurate diagnoses and treatment plans.

[0003] Current dental biometric detection methods primarily utilize X-ray imaging technology. Specifically, X-rays penetrate the oral cavity to generate images of teeth and bones. By observing the structure, density, and shape of the teeth, as well as the condition of the bones, and comparing the X-ray absorption levels in different areas, the presence of cavities, pulp infection, or other lesions can be determined. However, these methods suffer from insufficient contrast and artifacts. Insufficient contrast in X-ray imaging sometimes obscures details between different tissues, affecting the accurate differentiation of structures such as teeth and bones. Furthermore, false images can interfere with diagnosis, potentially leading to misdiagnosis or missed diagnoses of lesions, resulting in inaccurate test results. Summary of the Invention

[0004] The main objective of this invention is to provide a dental biometric detection method based on intelligent sensors, aiming to solve the technical problems in the prior art.

[0005] This invention proposes a dental biometric detection method based on intelligent sensors, comprising:

[0006] Acquire dental bone data from multiple target regions of the tooth using scanning sensors, and obtain a corresponding bone density distribution map based on each dental bone data.

[0007] Obtain the corresponding bone abnormality index based on each bone density distribution map, and determine whether each bone abnormality index is greater than a preset first threshold.

[0008] If the bone abnormality index is greater than a preset first threshold, the target area corresponding to the bone abnormality index is determined to be a high-risk area, and the tooth temperature data, tooth occlusal force data and tooth conductivity data of the high-risk area are obtained.

[0009] The comprehensive thermal expansion stress is obtained based on the tooth temperature data, and the comprehensive occlusal stress is obtained based on the tooth occlusal force data.

[0010] The biomechanical response value is obtained based on the thermal expansion stress and the combined occlusal stress.

[0011] A conductivity tensor is obtained based on the tooth conductivity data, and a bioactivity attenuation factor is obtained based on the conductivity tensor.

[0012] A comprehensive lesion risk value is obtained based on the bioactivity attenuation factor and biomechanical response value, and it is determined whether the comprehensive lesion risk value is greater than a preset second threshold.

[0013] If the overall lesion risk value is greater than a preset second threshold, then the high-risk area is determined to have lesions.

[0014] Preferably, the step of obtaining the corresponding bone density distribution map based on the bone data of each tooth includes:

[0015] A two-dimensional mesh image of each target region is acquired, and the reflected signal, signal propagation path length, and signal propagation duration of each mesh detection point in the two-dimensional mesh image are obtained based on each tooth bone data.

[0016] The corresponding signal propagation speed is obtained based on the length of each signal propagation path and the duration of signal propagation.

[0017] The corresponding reflected signal strength and transmission power are obtained for each reflected signal, and the corresponding reflection coefficient is obtained for each reflected signal strength and transmission power;

[0018] Obtain the air acoustic impedance, and obtain the corresponding bone acoustic impedance based on the air acoustic impedance and each reflection coefficient;

[0019] The bone density of each grid detection point is obtained based on the acoustic impedance and signal propagation velocity of each bone.

[0020] Based on the two-dimensional grid image, the two-dimensional position information of each grid detection point is obtained, and a planar coordinate axis is established according to the two-dimensional position information of each grid detection point. The three-dimensional detection density axis is obtained by taking the bone density corresponding to each grid detection point as the Z-axis in the vertical direction of the planar coordinate axis.

[0021] The bone density corresponding to each grid detection point is plotted on the three-dimensional detection density axis using a bar chart to obtain a bone density distribution map.

[0022] Preferably, the step of obtaining the corresponding bone abnormality index based on each bone density distribution map includes:

[0023] The maximum and minimum bone densities are obtained from the bone density distribution map, and the bone distribution non-uniformity is obtained from the maximum and minimum bone densities.

[0024] Multiple density gradients are obtained based on the bone density distribution map, and the corresponding density gradient modulus is obtained based on each density gradient;

[0025] The density change rate is obtained based on the multiple density gradient moduli;

[0026] The second spatial partial derivative of the corresponding density distribution is obtained for each density gradient, and the density change rate curvature is obtained for the second spatial partial derivatives of multiple density distributions.

[0027] The skeletal abnormality index is obtained based on the density change rate curvature, density change rate, and bone distribution non-uniformity.

[0028] Preferably, the steps of obtaining the comprehensive thermal expansion stress based on the tooth temperature data and obtaining the comprehensive occlusal stress based on the tooth occlusal force data include:

[0029] The enamel and dentin characteristics of the teeth are obtained, and the enamel expansion coefficient and enamel elastic modulus are obtained based on the enamel characteristics.

[0030] The dentin expansion coefficient and dentin elastic modulus are obtained based on the dentin characteristics described.

[0031] The temperature change is obtained based on the tooth temperature data, and the thermal expansion stress of the enamel is obtained based on the temperature change, the enamel expansion coefficient, and the enamel elastic modulus.

[0032] The thermal expansion stress of dentin is obtained based on the temperature change, the coefficient of dentin expansion, and the elastic modulus of dentin, and the combined thermal expansion stress is obtained based on the thermal expansion stress of dentin and the thermal expansion stress of enamel.

[0033] Based on the tooth occlusal force data, multiple occlusal stresses at the enamel-dentin junction are obtained, and the average stress is obtained based on the multiple occlusal stresses.

[0034] The maximum engagement stress is selected from multiple engagement stresses as the maximum stress, and the stress concentration factor is obtained based on the maximum stress and the average stress.

[0035] The first normal stress and the first tangential stress of the enamel are obtained, and the first occlusal stress is calculated based on the first normal stress, the first tangential stress, and the stress concentration factor. The calculation formula is as follows:

[0036]

[0037] Where Y(HY) represents the first engagement stress, Y(JZ) represents the stress concentration factor, F(XY) represents the first normal stress, and Q(XY) represents the first tangential stress;

[0038] The second normal stress and the second tangential stress of dentin are obtained, and the second occlusal stress is obtained based on the second normal stress, the second tangential stress and the stress concentration factor;

[0039] The comprehensive bite stress is obtained based on the first bite stress and the second bite stress.

[0040] Preferably, the step of obtaining the conductivity tensor based on the tooth conductivity data includes:

[0041] Based on the tooth conductivity data, obtain the complex conductivity curve, high-frequency limiting conductivity, and static conductivity, and obtain the relaxation time and multiple relaxation peak position information based on the complex conductivity curve;

[0042] The fractional index is obtained based on the frequencies corresponding to the multiple relaxation peak position information, and the frequency corresponding to the second relaxation peak position information is selected as the critical angular frequency.

[0043] The relaxor conductivity is obtained based on the relaxation time, fractional exponent, critical angular frequency, high-frequency limiting conductivity, and static conductivity.

[0044] Extract high-frequency curve segments with frequencies greater than a preset frequency from the complex conductivity curve, and obtain the slope of the imaginary part of the impedance of the high-frequency segment based on the high-frequency curve segments.

[0045] The orientation polarization conductivity is obtained based on the slope of the imaginary part of the impedance and the critical angular frequency, and the conductivity tensor is obtained based on the high-frequency limiting conductivity, orientation polarization conductivity, and relaxation conductivity.

[0046] Preferably, the step of obtaining the bioactivity attenuation factor based on the conductivity tensor includes:

[0047] Obtain the complex conductivity curve, and obtain the corresponding impedance based on each conductivity in the complex conductivity curve;

[0048] The actual impedance spectrum is obtained based on the multiple impedances, and the actual real part value is obtained based on the actual impedance spectrum;

[0049] Obtain the reference impedance spectrum of a standard tooth, obtain the reference real part value based on the reference impedance spectrum, and obtain the relative real part difference value based on the actual real part value and the reference real part value.

[0050] The bioactivity decay factor is obtained based on the conductivity tensor and the difference between the relative real parts.

[0051] This application also provides a dental biometric detection system based on intelligent sensors, including:

[0052] The first acquisition module is used to acquire tooth bone data detected by scanning sensors for multiple target areas of the tooth, and to acquire a corresponding bone density distribution map based on each tooth bone data.

[0053] The first judgment module is used to obtain the corresponding bone abnormality index based on each bone density distribution map, and to determine whether each bone abnormality index is greater than a preset first threshold.

[0054] If the bone abnormality index is greater than a preset first threshold, the target area corresponding to the bone abnormality index is determined to be a high-risk area, and the tooth temperature data, tooth occlusal force data and tooth conductivity data of the high-risk area are obtained.

[0055] The second acquisition module is used to acquire comprehensive thermal expansion stress based on the tooth temperature data and comprehensive occlusal stress based on the tooth occlusal force data.

[0056] The third acquisition module is used to acquire biomechanical response values ​​based on the thermal expansion stress and the comprehensive occlusal stress.

[0057] The fourth acquisition module is used to acquire a conductivity tensor based on the tooth conductivity data, and to acquire a bioactivity attenuation factor based on the conductivity tensor.

[0058] The second judgment module is used to obtain a comprehensive lesion risk value based on the bioactivity attenuation factor and the biomechanical response value, and to determine whether the comprehensive lesion risk value is greater than a preset second threshold.

[0059] If the overall lesion risk value is greater than a preset second threshold, then the high-risk area is determined to have lesions.

[0060] Preferably, the first acquisition module includes:

[0061] The first acquisition unit is used to acquire a two-dimensional grid image of each target region, and to acquire the reflection signal, signal propagation path length and signal propagation duration of each grid detection point in the two-dimensional grid image based on each of the tooth bone data;

[0062] The second acquisition unit is used to acquire the corresponding signal propagation speed based on the length of each signal propagation path and the signal propagation duration.

[0063] The third acquisition unit is used to acquire the corresponding reflected signal strength and transmission power according to each reflected signal, and to acquire the corresponding reflection coefficient according to each reflected signal strength and transmission power;

[0064] The fourth acquisition unit is used to acquire the air acoustic impedance and acquire the corresponding bone acoustic impedance based on the air acoustic impedance and each reflection coefficient;

[0065] The fifth acquisition unit is used to acquire the bone density of each grid detection point based on the acoustic impedance of each bone and the signal propagation speed.

[0066] A unit is established to obtain the two-dimensional position information of each grid detection point based on the two-dimensional grid image, and to establish a planar coordinate axis based on the two-dimensional position information of each grid detection point. The three-dimensional detection density axis is obtained by taking the bone density corresponding to each grid detection point as the Z-axis in the vertical direction of the planar coordinate axis.

[0067] The drawing unit is used to plot the bone density corresponding to each grid detection point on the three-dimensional detection density axis using a bar chart, thus obtaining a bone density distribution map.

[0068] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described dental biometric detection method based on intelligent sensors.

[0069] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described dental biometric detection method based on intelligent sensors.

[0070] The beneficial effects of this invention are as follows: This invention acquires bone data of teeth through intelligent sensors and combines it with multi-dimensional information such as bone density distribution maps, temperature data, occlusal force data, and conductivity data. This allows for a comprehensive assessment of the health status of teeth and surrounding tissues, overcoming the problems of insufficient contrast and artifacts that may occur in X-ray imaging, and avoiding misdiagnosis and missed diagnosis due to poor image quality. By integrating multi-dimensional biometric data such as thermal expansion stress, occlusal stress, biomechanical response values, and conductivity tensors, this method can more accurately assess the health risks of teeth. Through the calculation of bioactivity attenuation factors and comprehensive lesion risk values, it can effectively identify potential lesion areas, greatly improving the accuracy of disease assessment. The accuracy of disease prediction, through the judgment of skeletal abnormality index, can accurately identify high-risk areas in the early stage, and further collect more data in the area for in-depth analysis, which can help to detect lesions in a timely manner and intervene, avoiding the problems of delayed diagnosis and treatment that may exist in traditional methods. Compared with traditional X-ray imaging, intelligent sensor technology does not rely on radiation and is not easily affected by artifacts, and can provide clearer and more accurate data, thereby effectively reducing misleading factors in the diagnostic process and improving the reliability of diagnosis. By comprehensively using intelligent sensor technology and multi-angle, multi-dimensional detection and evaluation methods, the accuracy, reliability and safety of dental biometric detection are effectively improved. Attached Figure Description

[0071] Figure 1This is a schematic diagram of a method flow according to an embodiment of the present invention.

[0072] Figure 2 This is a schematic diagram of the system structure according to an embodiment of the present invention.

[0073] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of this application.

[0074] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0075] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0076] like Figure 1 As shown, this application provides a dental biometric detection method based on intelligent sensors, including:

[0077] S1. Obtain tooth bone data from multiple target areas of the tooth detected by scanning sensors, and obtain a corresponding bone density distribution map based on each tooth bone data.

[0078] S2. Obtain the corresponding bone abnormality index based on each bone density distribution map, and determine whether each bone abnormality index is greater than a preset first threshold.

[0079] If the bone abnormality index is greater than a preset first threshold, the target area corresponding to the bone abnormality index is determined to be a high-risk area, and the tooth temperature data, tooth occlusal force data and tooth conductivity data of the high-risk area are obtained.

[0080] S3. Obtain the comprehensive thermal expansion stress based on the tooth temperature data, and obtain the comprehensive occlusal stress based on the tooth occlusal force data;

[0081] S4. Obtain the biomechanical response value based on the sum of the thermal expansion stress and the comprehensive occlusal stress;

[0082] S5. Obtain a conductivity tensor based on the tooth conductivity data, and obtain a bioactivity attenuation factor based on the conductivity tensor.

[0083] S6. Obtain a comprehensive lesion risk value based on the bioactivity attenuation factor and biomechanical response value, and determine whether the comprehensive lesion risk value is greater than a preset second threshold.

[0084] If the overall lesion risk value is greater than a preset second threshold, then the high-risk area is determined to have lesions.

[0085] As described in steps S1-S6 above, this invention acquires dental bone data from multiple target areas of the tooth through scanning sensors. This dental bone data is obtained by placing an ultrasonic scanning sensor on the tooth surface and transmitting high-frequency ultrasonic waves to the dental bone surface. The ultrasonic sensor excites ultrasonic pulses and measures their propagation speed. Based on different real-time feedback signals (different tooth structures), the ultrasonic frequency and waveform are automatically adjusted. Specifically, the spectrum is extracted from the ultrasonic echo signal, and based on the spectrum combined with real-time signal feedback and a preset algorithm, the ultrasonic emission frequency and waveform are automatically adjusted through closed-loop control. The signal changes can be processed by real-time data processing algorithms (such as machine learning, modeling, etc.). The system analyzes tooth structure changes (such as pattern recognition) and then automatically adjusts the emission settings to optimize signal quality and resolution. The intelligent algorithm uses machine learning-based models to classify different tooth tissue structures in real time, thereby predicting and automatically adjusting the most suitable ultrasonic frequency and waveform. For example, deep learning can be used to train a model to predict the type and state of different tissues based on the characteristics of the echo signal, thus adjusting the corresponding ultrasonic settings. By analyzing the spectrum of the echo signal, the response characteristics of different structures can be detected. This is because different tooth structures have different effects on the reflection, transmission, and attenuation of ultrasonic waves. Enamel is generally more sensitive to high-frequency sound waves, while dentin may be more suitable for low-frequency sound waves. In real-time signal feedback, the system identifies the signal... The frequency of the ultrasound waves is adjusted according to changes in the ultrasound frequency and echo characteristics to more effectively acquire data from different structures. Short pulse waveforms can be selected when higher resolution is required based on the ultrasound frequency and echo characteristics, while continuous waveforms are used when a high signal-to-noise ratio is needed, or when the response to waveform amplitude and attenuation is more sensitive. This allows for easier detection of different tissue layers and the acquisition of corresponding bone density distribution maps based on the bone data of each tooth. Compared to X-ray imaging, scanning sensors can acquire high-precision tooth data non-invasively and in real-time, avoiding the problem of unclear details due to insufficient contrast in X-ray technology. The scanned data has high spatial resolution, clearly distinguishing structures such as teeth and bones, reducing artifact interference, and thus providing more accurate structural information. By generating bone density distribution maps, the structural density distribution inside teeth can be accurately reflected. Compared with X-ray technology, bone density distribution maps avoid the contrast problems present in X-rays, and can more clearly display different tissue structures of teeth, helping to improve diagnostic accuracy. Each bone density distribution map yields a corresponding bone abnormality index, which provides a quantitative indicator that directly reflects the health of the dental skeleton. Compared with traditional X-ray imaging methods, this indicator effectively avoids misjudgments caused by poor image quality, while providing more objective assessment results, reducing the influence of human factors on diagnostic results, and determining whether each bone abnormality index exceeds a preset first threshold. If the bone abnormality index exceeds the preset first threshold...The target area corresponding to the skeletal abnormality index is then identified as a high-risk area. Data on tooth temperature, occlusal force, and electrical conductivity within this high-risk area are acquired. Tooth temperature data is obtained by using an infrared temperature sensor to detect infrared radiation emitted from the tooth surface and outputting a temperature-related electrical signal (the infrared sensor can be calibrated based on ambient temperature and tooth surface reflectivity to eliminate the influence of external factors). Occlusal force data is obtained by attaching or integrating strain gauge sensors onto the tooth surface or dental tray. The pressure sensor converts the sensed strain or pressure changes into electrical signals, which are then processed by an amplifier and an analog-to-digital converter to obtain the occlusal force data. Specifically, this is achieved through tooth biting... A micro-strain gauge sensor array is installed on the tooth surface to measure the deformation of the tooth under force in real time. The strain gauge sensors have built-in microprocessors that process and analyze the sensor signals, adjusting the sensitivity according to different occlusal intensities to obtain occlusal force data within a high-precision range. Tooth conductivity data is obtained by placing a conductivity sensor near the tooth; the sensor emits a small current and measures the resistance as the current passes through the tooth. The conductivity sensor acquires tooth conductivity data by measuring the current conduction capacity inside and on the tooth surface. Specifically, the conductivity sensor applies a small current and measures the voltage change to obtain conductivity. The conductivity sensor adapts to different conductivity changes on the tooth surface and inner layer, adjusting the measurement frequency and signal strength in real time to ensure accuracy. To ensure the accuracy of electrical conductivity data, automated screening can be achieved by setting thresholds, reducing the need for manual intervention and accurately identifying high-risk areas, thus minimizing the possibility of missed diagnoses. This automated assessment method is faster and more efficient than traditional diagnostic methods, enabling timely detection of potential risk areas. Through comprehensive analysis of biometric data such as tooth temperature, occlusal force, and electrical conductivity in high-risk areas, the condition of teeth can be understood from multiple dimensions. Temperature data reflects thermal expansion stress, occlusal force data assesses the physical load on the teeth, and electrical conductivity data reveals the electrical properties of the teeth. This data provides a multi-dimensional analysis of dental health, overcoming the limitations of single imaging methods. By obtaining thermal expansion stress data from tooth temperature data... The calculation of force and thermal expansion stress can reflect the biomechanical response of teeth under temperature changes, avoiding the stress changes in tooth materials that cannot be captured by traditional imaging. This allows for a more comprehensive assessment of the physical state of teeth. By obtaining comprehensive occlusal stress from occlusal force data, which reflects the physical pressure exerted on teeth during actual occlusion, dentists can understand whether teeth are subjected to uneven pressure, preventing damage or lesions caused by occlusal problems. The biomechanical response value obtained through thermal expansion stress and comprehensive occlusal stress comprehensively reflects the health status of teeth under different environments and conditions. Compared to X-ray imaging, traditional imaging cannot directly provide such mechanical analysis data.This method effectively avoids misdiagnosis or missed diagnosis due to insufficient image contrast. It obtains impedance spectra and conductivity tensors from tooth conductivity data. Changes in conductivity reveal the internal structural state of the tooth. Impedance spectra and conductivity tensors provide important quantitative indicators for studying the bioelectricity of teeth, effectively identifying the presence of lesions or abnormalities. Furthermore, it obtains bioactivity attenuation factors from the impedance spectra, reflecting the health status of the teeth and effectively assessing their bioactivity level. This provides a more detailed and in-depth health assessment than traditional X-ray imaging, helping doctors make more accurate diagnoses. A comprehensive lesion risk value is obtained through bioactivity attenuation factors, conductivity tensors, and biomechanical response values, and it is determined whether the comprehensive lesion risk value exceeds a preset second threshold. If the comprehensive lesion risk value exceeds a preset second threshold, the high-risk area is determined to have a lesion. The comprehensive lesion risk value provides a quantitative risk assessment of whether a tooth has a lesion, making the diagnostic process more objective and accurate. Compared to X-ray imaging, the comprehensive risk assessment considers more biomechanical, electrical, and bioactive factors, thus providing doctors with more diagnostic evidence. By setting a second threshold, the diagnostic process can be automated, improving efficiency and reducing human error. This invention provides a high-precision, comprehensive, and non-invasive method for dental health detection through multi-dimensional data analysis. Compared to traditional X-ray imaging methods, this invention solves the problems of insufficient contrast and artifacts in X-ray imaging, reducing misdiagnosis and missed diagnosis, and ensuring more accurate diagnostic results.

[0086] In one embodiment, step S1, which involves obtaining a corresponding bone density distribution map based on each of the tooth bone data, includes:

[0087] S11. Obtain a two-dimensional grid image of each target region, and obtain the reflection signal, signal propagation path length and signal propagation duration of each grid detection point in the two-dimensional grid image based on each of the tooth bone data;

[0088] S12. Obtain the corresponding signal propagation speed based on the length of each signal propagation path and the signal propagation duration;

[0089] S13. Obtain the corresponding reflected signal strength and transmission power for each reflected signal, and calculate the corresponding reflection coefficient based on the propagation path length, reflected signal strength, and transmission power for each signal. The calculation formula is as follows:

[0090]

[0091] Where F(SX) represents the reflection coefficient, F(XQ) represents the reflected signal strength, F(GL) represents the transmission power, X(CJ) represents the signal propagation path length, and C(CJ) represents the reference propagation distance (i.e., the preset detection distance);

[0092] S14. Obtain the air acoustic impedance, and calculate the corresponding bone acoustic impedance based on the air acoustic impedance and each reflection coefficient, wherein the calculation formula is:

[0093]

[0094] Where G(ZK) represents the acoustic impedance of the bone, K(ZK) represents the acoustic impedance of the air, and F(SX) represents the reflection coefficient;

[0095] S15. Calculate and obtain the bone density of each grid detection point based on the ratio of the acoustic impedance of each bone to the signal propagation speed.

[0096] S16. Using the two-dimensional grid image as a reference, obtain the two-dimensional position information of each grid detection point, and establish a planar coordinate axis based on the two-dimensional position information of each grid detection point. In the vertical direction of the planar coordinate axis, take the bone density corresponding to each grid detection point as the Z-axis to obtain the three-dimensional detection density axis.

[0097] S17. Plot the bone density corresponding to each grid detection point on the three-dimensional detection density axis using a bar chart to obtain a bone density distribution map.

[0098] As described in steps S11-S17 above, this invention acquires a two-dimensional grid image of each target region. By acquiring this image, detailed information about the tooth or bone structure can be accurately captured, ensuring the accuracy of the data input. This two-dimensional image facilitates more detailed signal analysis in subsequent steps, avoiding potential local missing or noise problems in traditional imaging methods. Compared to traditional X-ray imaging, the two-dimensional grid image provides a more comprehensive view. Furthermore, based on the data from each tooth or bone, the reflected signal intensity, signal propagation path length, and signal propagation duration at each grid detection point in the two-dimensional grid image are obtained. By collecting the reflected signal, propagation path length, and propagation duration at each grid detection point, it is possible to... To gain a more accurate understanding of signal propagation characteristics in bones or teeth, this data can provide more precise information on bone or tooth density and structural distribution, offering high-precision foundational data for subsequent analysis. Compared to traditional X-ray imaging, it effectively reduces contrast deficiencies and artifacts caused by limitations in imaging technology. By calculating the length of each signal propagation path and the duration of signal propagation, the corresponding signal propagation velocity can be obtained. Signal propagation velocity is a crucial physical parameter that directly reflects the density and structure of bones or teeth. Calculating the signal propagation velocity ensures the precise propagation path of the signal, enabling further assessment of tissue characteristics in the target area and reducing unnecessary errors. The calculation of signal propagation velocity not only improves detection accuracy but also effectively avoids... To avoid false lesion detection caused by measurement errors, the corresponding reflected signal intensity and transmission power are obtained for each reflected signal. The corresponding reflection coefficient is calculated based on the propagation path length, reflected signal intensity, and transmission power of each signal. Obtaining the reflected signal intensity and transmission power helps analyze the acoustic characteristics of different tissues, especially the acoustic reflection characteristics of bone and teeth, effectively improving contrast and increasing the resolution of tissues such as bone and teeth. The reflection coefficient is an important parameter reflecting the properties of the medium, helping to determine the acoustic impedance characteristics of different tissues or materials. By calculating the reflection coefficient, the acoustic characteristics of different tissues can be further analyzed more precisely, thereby improving the overall detection accuracy. This is achieved by obtaining the air acoustic impedance and calculating the air acoustic impedance and the corresponding reflection coefficient for each reflected signal. The calculation of acoustic impedance corresponding to bone is crucial for identifying the physical properties of bone tissue. By acquiring the acoustic impedance of air and calculating the acoustic impedance of bone, the density and hardness characteristics of bone can be accurately estimated, further improving image quality and tissue discrimination. This helps overcome the limitations of accurately distinguishing bones in X-ray imaging, reducing artifacts and contrast problems. The bone density of each grid detection point is obtained by calculating the ratio of the acoustic impedance of each bone to the signal propagation velocity. This method is extremely important for the diagnosis of teeth and bones, especially in the early diagnosis of diseases such as osteoporosis and dental lesions, providing a more accurate basis for judgment.Compared to traditional X-ray imaging, this method offers higher resolution and avoids diagnostic errors caused by insufficient contrast. It uses a two-dimensional grid image as a reference to acquire the two-dimensional position information of each grid detection point. A planar coordinate axis is then established based on this information. A three-dimensional detection density axis is obtained by plotting the bone density corresponding to each grid detection point as the Z-axis in the vertical direction of the planar coordinate axis. A bone density distribution map is obtained by plotting the bone density corresponding to each grid detection point as a bar chart on the three-dimensional detection density axis. The establishment of the three-dimensional detection density axis with bone density as the Z-axis in the vertical direction of the planar coordinate axis clearly displays… The density distribution of the target area visually displays changes in bone or teeth density. This three-dimensional visualization method allows medical personnel to more easily identify lesion areas and provide more accurate diagnostic data. By displaying bone density on a three-dimensional density axis using a bar chart, doctors can intuitively view the density distribution in different areas. This method is more visually appealing and easier to operate than traditional two-dimensional imaging, effectively highlighting key areas and helping diagnosticians quickly identify abnormalities, thus improving diagnostic efficiency. It effectively solves problems such as insufficient contrast and artifact interference in traditional X-ray imaging, providing more accurate detection results and contributing to improved diagnostic accuracy and reliability.

[0099] In one embodiment, step S2, which involves obtaining the corresponding bone abnormality index based on each bone density distribution map, includes:

[0100] S21. Obtain the maximum bone density and minimum bone density according to the bone density distribution map, and obtain the bone distribution non-uniformity according to the difference of the natural logarithm of the maximum bone density and the minimum bone density.

[0101] S22. Obtain multiple density gradients based on the bone density distribution map, and obtain the corresponding density gradient modulus for each density gradient;

[0102] S23. Obtain the density change rate based on the multiple density gradient moduli;

[0103] S24. Obtain the second spatial partial derivative of the corresponding density distribution based on each density gradient, and obtain the density change rate curvature based on the second spatial partial derivatives of multiple density distributions.

[0104] S25. The bone abnormality index is calculated by weighted summation based on the density change rate curvature, density change rate and bone distribution unevenness.

[0105] As described in steps S21-S25 above, multiple density gradients refer to the density gradient of each grid detection point. The density gradient is the first-order spatial partial derivative, and the second-order spatial partial derivative is the derivative of the density gradient. The second-order derivative can be calculated using the Laplacian operator. The density change rate is obtained by averaging multiple density gradient moduli. The density gradient modulus represents the rate of density change in space; it is the magnitude of the density gradient vector. The second-order spatial partial derivative of the density distribution is obtained by averaging multiple density gradients. It reflects the curvature of density change in space and represents the acceleration of the density change rate. It is the derivative of the density gradient (first-order spatial partial derivative) and describes the change in the rate of density change. This invention obtains the maximum density gradient through the bone density distribution map. Bone density and minimum bone density are calculated, and the non-uniformity of bone distribution is obtained by calculating the difference between the natural logarithm of the maximum and minimum bone densities. The maximum and minimum bone density values ​​reflect the most extreme states of the bone, helping to identify the densest and sparsest areas and providing a clear standard for subsequent analysis. This allows the overall condition of the bone to be quantified. The comparison between the maximum and minimum bone densities provides benchmark data for analyzing the non-uniformity of bone density distribution, thus helping to distinguish between normal and abnormal bone density states. Calculating the non-uniformity of bone density distribution through the logarithmic difference quantifies the range of bone density variation. Logarithmic operations transform large-scale density differences into more reasonable and easily analyzed quantities, thereby improving diagnostic sensitivity. To avoid the impact of a single extreme value on the accuracy of the results, multiple density gradients are obtained from the bone density distribution map, and the corresponding density gradient modulus is calculated for each density gradient. The acquisition of multiple density gradients allows for a detailed decomposition of the bone density distribution, reflecting subtle changes in local areas. The calculation of the density gradient modulus helps reveal the dynamic process of density changes, enabling better identification of abnormal change rates in bone regions. For example, a sudden change in bone density may indicate the occurrence of disease, and this information can be directly fed back to clinicians. The density change rate obtained through multiple density gradient moduli directly reveals the speed of bone density changes, reflecting the dynamic progression of osteoporosis or other diseases. This rate allows for the early identification of abnormal changes. By monitoring the rate of change in density, abnormal trends in bone density changes can be detected in the early stages of disease, providing effective data support for early diagnosis and treatment. The quadratic spatial partial derivative of the corresponding density distribution is obtained for each density gradient, and the curvature of the rate of change in density is derived from the quadratic spatial partial derivatives of multiple density distributions. The quadratic spatial partial derivative reveals the curvature of bone density changes in space, enabling the identification of abnormal structural changes in local areas. This facilitates the localization and detailed analysis of lesions. Through the calculation of spatial partial derivatives, precise mathematical modeling of bone density distribution can be performed, thereby improving the sensitivity and accuracy of detecting changes in bone structure. The curvature of the rate of change in density can help identify areas of abrupt density changes.These areas may represent key sites of osteoporosis. Compared to considering only the rate of density change, curvature provides a higher level of analytical capability, enabling the detection of more complex skeletal abnormalities. By combining curvature and rate, a more comprehensive assessment of skeletal health can be achieved, identifying different types of bone abnormalities, such as localized bone loss or bone hyperplasia. The skeletal abnormality index is calculated by weighted summation of density change rate curvature, density change rate, and bone distribution heterogeneity. This weighted summation method comprehensively considers the impact of multiple factors on skeletal health, avoiding the problem that a single indicator is insufficient to fully reflect skeletal status. This makes the test results more comprehensive and objective. By combining various indicators through weighted calculation, the health status of bones can be more accurately assessed, thereby improving the sensitivity and accuracy of abnormality detection.

[0106] In one embodiment, step S3, which involves obtaining the comprehensive thermal expansion stress based on the tooth temperature data and the comprehensive occlusal stress based on the tooth occlusal force data, includes:

[0107] S31. Obtain the enamel and dentin characteristics of the teeth, and obtain the enamel expansion coefficient and enamel elastic modulus based on the enamel characteristics;

[0108] S32. Obtain the dentin expansion coefficient and dentin elastic modulus based on the dentin characteristics;

[0109] S33. Obtain the temperature change based on the tooth temperature data, and calculate the enamel thermal expansion stress based on the product of the temperature change, the enamel expansion coefficient, and the enamel elastic modulus.

[0110] S34. The dentin thermal expansion stress is calculated based on the product of the temperature change, the dentin expansion coefficient, and the dentin elastic modulus, and the comprehensive thermal expansion stress is calculated based on the sum of the dentin thermal expansion stress and the enamel thermal expansion stress.

[0111] S35. Obtain multiple occlusal stresses at the junction of enamel and dentin based on the tooth occlusal force data, and obtain the average stress based on the multiple occlusal stresses;

[0112] S36. Select the largest biting stress from multiple biting stresses as the maximum stress, and obtain the stress concentration factor according to the ratio of the maximum stress to the average stress.

[0113] S37. Obtain the first normal stress and the first tangential stress of the enamel, and calculate the first occlusal stress based on the first normal stress, the first tangential stress, and the stress concentration factor, wherein the calculation formula is:

[0114]

[0115] Where Y(HY) represents the first engagement stress, Y(JZ) represents the stress concentration factor, F(XY) represents the first normal stress, and Q(XY) represents the first tangential stress;

[0116] S38. Obtain the second normal stress and the second tangential stress of the dentin, and obtain the second occlusal stress based on the second normal stress, the second tangential stress and the stress concentration factor;

[0117] S39. The comprehensive bite stress is calculated based on the sum of the first bite stress and the second bite stress.

[0118] As described in steps S31-S39 above, the calculation formula for the second occlusal stress is the same as that for the first occlusal stress, and will not be repeated here. This invention obtains the enamel and dentin characteristics of teeth. By acquiring these characteristics, the physical and structural properties of teeth can be accurately described. Unlike traditional X-ray imaging, the feature extraction method does not depend on image quality, avoiding potential issues such as insufficient contrast and artifacts during imaging. Obtaining the enamel expansion coefficient and elastic modulus is crucial for analyzing the thermal expansion stress of teeth, directly affecting the accuracy of subsequent thermal expansion stress calculations. Calculations based on the physical characteristics of enamel make the data more accurate and operable, avoiding reliance on images or computer-aided imaging. This method improves measurement accuracy by minimizing errors and reducing the possibility of misdiagnosis and missed diagnosis. It obtains the enamel expansion coefficient and elastic modulus based on enamel characteristics, and the dentin expansion coefficient and elastic modulus based on dentin characteristics. Dentin is a crucial component of teeth, and obtaining its expansion coefficient and elastic modulus is essential for thermal stress analysis. Similar to enamel characteristics, obtaining dentin physical characteristics allows for differentiation between different materials, avoiding blurring and artifacts at the X-ray interface between the two tissues. Temperature changes are obtained from tooth temperature data, and the thermal expansion stress of enamel is calculated by multiplying the temperature change, enamel expansion coefficient, and enamel elastic modulus. The temperature change directly affects the tooth's performance during biting. By monitoring the thermal expansion of the oral cavity environment in real time, this method avoids capturing dynamic information that X-ray imaging cannot capture, ensuring more accurate stress analysis. Combining the enamel's coefficient of thermal expansion, elastic modulus, and temperature change, it can more accurately calculate the thermal expansion stress of enamel. Compared to traditional methods, this method calculates directly using a physical model, independent of image results, avoiding errors caused by image quality and providing precise stress data. This allows for better prediction of tooth performance under different temperature changes, avoiding uncertainties based on images. The dentin thermal expansion stress is obtained by calculating the product of temperature change, dentin coefficient of thermal expansion, and dentin elastic modulus, similar to the calculation of enamel thermal expansion stress. Expansion stress is also calculated by combining its physical properties with temperature changes, making the analysis more comprehensive. It takes into account the actual performance of dentin, a crucial component, and is more direct and accurate than traditional imaging methods. It is unaffected by errors in X-ray imaging, ensuring more realistic results. The comprehensive thermal expansion stress is calculated by summing the thermal expansion stress of dentin and enamel. By integrating the thermal expansion stresses of enamel and dentin, a comprehensive thermal stress assessment can be obtained. This comprehensive calculation avoids local errors arising from single tissues, making the overall assessment more accurate. Multiple occlusal stresses at the enamel-dentin interface are obtained from tooth occlusal force data, and the average stress is calculated from these multiple occlusal stresses.By directly acquiring occlusal force data, the stress on teeth in the actual oral environment can be simulated more realistically, avoiding the dynamic information that traditional X-ray imaging cannot provide. Calculating the average stress helps provide pressure distribution analysis across the entire tooth area, enabling a comprehensive assessment of the tooth's stress. Compared to the localized analysis of X-rays, it allows for multi-dimensional data processing, improving the accuracy of the overall analysis. By selecting the largest occlusal stress from multiple stresses as the maximum stress, and obtaining the stress concentration factor based on the ratio of the maximum stress to the average stress, selecting the maximum stress as key data can avoid missed or misdiagnosed cases, ensuring the rigor of diagnostic results. The maximum stress usually represents the most extreme stress on the tooth, providing more crucial information for treatment decisions. The stress concentration factor effectively reveals areas of concentrated tooth stress, helping doctors identify potential cracks, cavities, and other lesions, providing a more detailed stress analysis and compensating for the microscopic details that traditional imaging methods cannot provide. By acquiring the first method of enamel... The first occlusal stress is calculated by taking the first normal stress and the first tangential stress, and then calculating the first occlusal stress based on the first normal stress, the first tangential stress, and the stress concentration factor. The second occlusal stress is obtained by acquiring the second normal stress and the second tangential stress of the dentin, and then calculating the second occlusal stress based on the second normal stress, the second tangential stress, and the stress concentration factor. The calculation of the first normal stress and the tangential stress can comprehensively assess the stress situation of the enamel in different directions, thus providing a more accurate simulation of occlusal stress. The stress analysis of dentin combined with that of enamel can more comprehensively describe the stress situation of the entire tooth, helping doctors obtain more accurate diagnostic data. It can simultaneously consider the stress distribution of different tissues, avoiding the bias caused by single analysis. The comprehensive occlusal stress is obtained by calculating the sum of the first occlusal stress and the second occlusal stress. The calculation of the comprehensive occlusal stress helps to fully understand the stress distribution of the tooth in complex environments, providing more scientific basis for diagnosis and treatment, providing a more comprehensive analysis of the stress situation, avoiding the full picture information that traditional imaging diagnosis cannot reveal, and ensuring higher accuracy.

[0119] In one embodiment, step S5, which involves obtaining the conductivity tensor based on the tooth conductivity data, includes:

[0120] S51. Obtain complex conductivity curve, high-frequency limiting conductivity and static conductivity based on the tooth conductivity data, and obtain relaxation time and multiple relaxation peak position information based on the complex conductivity curve;

[0121] S52. Obtain the fractional index based on the frequencies corresponding to the multiple relaxation peak position information, and select the frequency corresponding to the second relaxation peak position information as the critical angular frequency.

[0122] S53. Calculate the relaxation conductivity based on the relaxation time, fractional exponent, critical angular frequency, high-frequency limiting conductivity, and static conductivity, wherein the calculation formula is:

[0123]

[0124] Where C(YD) represents the relaxor conductivity, J(TD) represents the static conductivity, G(JD) represents the high-frequency limiting conductivity, Y(CS) represents the relaxation time, L(JP) represents the critical angular frequency, and F(ZS) represents the fractional exponent.

[0125] S54. Extract the high-frequency curve segment with a frequency greater than a preset frequency from the complex conductivity curve, and obtain the slope of the imaginary part of the impedance of the high-frequency segment based on the high-frequency curve segment.

[0126] S55. Calculate the orientation polarization conductivity based on the slope of the imaginary part of the impedance and the critical angular frequency, wherein the calculation formula is:

[0127]

[0128] Where Q(JD) represents the orientation polarization conductivity, Z(KX) represents the slope of the imaginary part of the impedance, and L(JP) represents the critical angular frequency;

[0129] S56. Obtain the conductivity tensor based on the sum of the high-frequency limiting conductivity, orientation polarization conductivity, and relaxation conductivity.

[0130] As described in steps S51-S56 above, the critical angular frequency refers to the turning frequency at which the second relaxation peak appears in the complex conductivity curve. It is usually the frequency associated with the turning point in the charge or polarization process. The high-frequency limiting conductivity represents the conductivity at extremely high frequencies, where the polarization relaxation effect can be ignored. The static conductivity describes the conductivity at zero frequency. The relaxation time characterizes the characteristic time scale of the polarization or carrier response delay; the longer the relaxation time, the slower the relaxation. This invention obtains the complex conductivity curve, high-frequency limiting conductivity, and static conductivity from tooth conductivity data, and obtains the relaxation time and multiple relaxation peak position information based on the complex conductivity curve. By measuring the conductivity data of teeth and obtaining the complex conductivity curve, high-frequency limiting conductivity, and static conductivity, accurate... Accurate assessment of the electrical properties of teeth, compared to traditional X-ray imaging, not only avoids the potential harm of radiation to the human body but also provides higher resolution and more detailed tissue structure information. Unlike the insufficient contrast and artifacts that may occur with X-ray imaging, conductivity data can truly reflect the physical properties of teeth, avoiding interference from false images and providing more accurate detection results. The relaxation time and multiple relaxation peak positions in the complex conductivity curve can reveal changes in the microstructure of the material, which helps to analyze the internal electrical properties of teeth and the conductive behavior of materials. This is of great significance for the identification of different types of dental tissues or lesions, improving the ability to distinguish tissue details and avoiding the contrast issues that may occur in traditional X-ray imaging. To overcome the limitations of X-ray imaging in accurately analyzing tooth materials and mitigating artifacts, fractional exponents are obtained by analyzing the frequencies corresponding to the positions of multiple relaxation peaks. These frequencies provide a deeper understanding of the physical state of the tooth material. Calculating the fractional exponents further reveals the electrical response characteristics of teeth at different electric field frequencies, improving the accuracy of identifying different tooth tissues and avoiding the complex processing and potential errors inherent in traditional imaging techniques. Furthermore, the frequency corresponding to the second relaxation peak is selected as the critical angular frequency. The critical angular frequency is a crucial electrical characteristic of materials under specific conditions, reflecting the conductivity changes of teeth at different frequencies. This allows for obtaining the electrical response of teeth within a higher frequency range, compensating for the limitations of X-ray imaging in accurately analyzing tooth materials. By overcoming the limitations of traditional methods and addressing the shortcomings of conventional electrical characteristics, this method calculates relaxor conductivity using relaxation time, fractional exponent, critical angular frequency, high-frequency limiting conductivity, and static conductivity. This comprehensive approach reflects the electrical properties of teeth, combining multiple electrical parameters for more accurate and reliable conductivity calculations. Unlike traditional X-ray imaging, conductivity-based measurements provide more objective physical data, avoiding artifacts in imaging techniques and offering more reliable tooth detection results. Furthermore, orientation-polarized conductivity is calculated using the slope of the imaginary part of impedance and the critical angular frequency. This calculation reveals the electrical behavior of different structures within the tooth, particularly its variations in the high-frequency range.Orientation polarization conductivity provides detailed information about the electrical conductivity of tooth materials and their relative polarization properties, aiding in the diagnosis of abnormal electrical characteristics in teeth. Compared to traditional X-ray techniques, this invention offers greater detail, revealing the microscopic electrical properties of teeth and providing more diagnostic information. The conductivity tensor is obtained by summing the high-frequency limiting conductivity, orientation polarization conductivity, and relaxation conductivity. This conductivity tensor provides a more comprehensive description of the electrical properties of teeth. By integrating various electrical parameters, the conductivity tensor provides comprehensive information about the conductive behavior of teeth in different directions and states. Unlike X-ray imaging, the conductivity tensor can more precisely describe the non-homogeneity of tooth materials, helping to analyze minute structural changes and their electrical properties within teeth, avoiding the limitations of traditional imaging techniques in identifying tissue details.

[0131] In one embodiment, step S5, which involves obtaining the bioactivity decay factor based on the conductivity tensor, includes:

[0132] S57. Obtain the complex conductivity curve, and obtain the corresponding impedance based on each conductivity in the complex conductivity curve;

[0133] S58. Obtain the actual impedance spectrum based on the multiple impedances, and obtain the actual real part value based on the actual impedance spectrum;

[0134] S59. Obtain the reference impedance spectrum of a standard tooth, obtain the reference real part value based on the reference impedance spectrum, and obtain the relative real part difference value based on the actual real part value and the reference real part value.

[0135] S510. Obtain the bioactivity decay factor based on the difference between the conductivity tensor and the relative real part.

[0136] As described in steps S57-S510 above, this invention obtains a complex conductivity curve and acquires the corresponding impedance based on each conductivity in the curve. Impedance is a function of conductivity and frequency. By extracting each conductivity from the complex conductivity curve and calculating the corresponding impedance, more refined measurement results can be provided for the electrical properties of different tissues or materials. Impedance measurement examines the electrical response of materials under different environments through multi-frequency changes, which can better distinguish between healthy and diseased tissues. In traditional X-ray imaging, the density contrast difference of tissues is limited, but impedance measurement can effectively overcome this limitation, making the electrical differences between different tissues more obvious, thereby improving the accuracy of diagnosis. Impedance spectroscopy obtains the actual impedance spectrum, and the actual real part value is obtained from the actual impedance spectrum. By measuring multiple impedance points, a comprehensive actual impedance spectrum can be established. This spectrum can accurately reflect the electrical characteristics of the sample at different frequencies, thus better comparing the differences between healthy and diseased tissues. Compared with traditional single-frequency measurements, impedance spectroscopy provides more dimensions of electrical information, making the detection results more comprehensive and accurate, and enabling more precise tissue identification. Especially when dealing with complex lesions or multiple overlapping tissues, it can provide more reference data, helping to improve diagnostic accuracy. The real part value reflects the energy storage characteristics of the material and is closely related to the health status of the sample. Obtaining the actual real part value can directly reflect the conductivity and health of biological tissues. By comparing changes in the real part values ​​of different teeth, the difference between diseased and healthy areas can be effectively detected. By obtaining the reference impedance spectrum of a standard tooth, the reference real part value is obtained from the reference impedance spectrum, and the relative real part difference is obtained based on the actual real part value and the reference real part value. Establishing a reference impedance spectrum for standard teeth provides standardized reference data for diagnosis. The reference real part value is one of the core indicators for evaluating the electrical properties of standard teeth. By obtaining the reference real part value of standard teeth, the differences in electrical properties between different tissues can be further clarified. Calculating the relative real part difference directly reflects the difference between the electrical properties of the sample and the reference healthy value, helping to accurately quantify the electrical changes of tissues. Through this difference analysis, a clearer understanding of the differences can be achieved. This imaging technique effectively distinguishes subtle changes between diseased and healthy tissues, particularly early-stage minute lesions. It is more sensitive than traditional X-ray imaging because it reveals more nuanced electrical differences and is less susceptible to artifacts and insufficient contrast. By using the conductivity tensor and the relative real part difference to obtain the bioactivity attenuation factor, and considering that the conductivity tensor comprehensively reflects the conductivity characteristics of a sample at different directions and frequencies, combined with the relative real part difference to further obtain the bioactivity attenuation factor, it can provide a more accurate dynamic assessment of the health status of biological tissues. This helps identify the degree of aging, lesions, or damage in teeth or other biological tissues, providing more scientific and quantitative data support for clinical practice. Compared to the two-dimensional images of X-ray imaging, this technique offers significant advantages.This comprehensive electrical analysis can better reveal internal changes in biological tissues, improving the accuracy and reliability of diagnosis.

[0137] like Figure 2 As shown, this application also provides a dental biometric detection system based on intelligent sensors, comprising:

[0138] The first acquisition module is used to acquire tooth bone data detected by scanning sensors for multiple target areas of the tooth, and to acquire a corresponding bone density distribution map based on each tooth bone data.

[0139] The first judgment module is used to obtain the corresponding bone abnormality index based on each bone density distribution map, and to determine whether each bone abnormality index is greater than a preset first threshold.

[0140] If the bone abnormality index is greater than a preset first threshold, the target area corresponding to the bone abnormality index is determined to be a high-risk area, and the tooth temperature data, tooth occlusal force data and tooth conductivity data of the high-risk area are obtained.

[0141] The second acquisition module is used to acquire comprehensive thermal expansion stress based on the tooth temperature data and comprehensive occlusal stress based on the tooth occlusal force data.

[0142] The third acquisition module is used to acquire biomechanical response values ​​based on the thermal expansion stress and the comprehensive occlusal stress.

[0143] The fourth acquisition module is used to acquire a conductivity tensor based on the tooth conductivity data, and to acquire a bioactivity attenuation factor based on the conductivity tensor.

[0144] The second judgment module is used to obtain a comprehensive lesion risk value based on the bioactivity attenuation factor and the biomechanical response value, and to determine whether the comprehensive lesion risk value is greater than a preset second threshold.

[0145] If the overall lesion risk value is greater than a preset second threshold, then the high-risk area is determined to have lesions.

[0146] In one embodiment, the first acquisition module includes:

[0147] The first acquisition unit is used to acquire a two-dimensional grid image of each target region, and to acquire the reflection signal, signal propagation path length and signal propagation duration of each grid detection point in the two-dimensional grid image based on each of the tooth bone data;

[0148] The second acquisition unit is used to acquire the corresponding signal propagation speed based on the length of each signal propagation path and the signal propagation duration.

[0149] The third acquisition unit is used to acquire the corresponding reflected signal strength and transmission power according to each reflected signal, and to acquire the corresponding reflection coefficient according to each reflected signal strength and transmission power;

[0150] The fourth acquisition unit is used to acquire the air acoustic impedance and acquire the corresponding bone acoustic impedance based on the air acoustic impedance and each reflection coefficient;

[0151] The fifth acquisition unit is used to acquire the bone density of each grid detection point based on the acoustic impedance of each bone and the signal propagation speed.

[0152] A unit is established to create a planar coordinate axis based on a two-dimensional grid image. A vertical coordinate axis is set in the direction perpendicular to the planar coordinate axis to obtain a three-dimensional detection density axis.

[0153] The drawing unit is used to plot the bone density corresponding to each grid detection point on the three-dimensional detection density axis using a bar chart, thus obtaining a bone density distribution map.

[0154] It should be noted that each module and unit in the dental biometrics detection system based on intelligent sensors corresponds one-to-one with the steps in the dental biometrics detection method based on intelligent sensors.

[0155] like Figure 3 As shown, this application also provides a computer device, which can be a server, and its internal structure can be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores all data required for the process of the dental biometric detection method based on intelligent sensors. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the dental biometric detection method based on intelligent sensors.

[0156] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer equipment on which the present application is applied.

[0157] An embodiment of this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described dental biometric detection methods based on smart sensors.

[0158] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media provided in this application and in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0159] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0160] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for detecting dental biometric features based on intelligent sensors, characterized in that, include: Acquire dental bone data from multiple target regions of the tooth using scanning sensors, and obtain a corresponding bone density distribution map based on each dental bone data. Obtain the corresponding bone abnormality index based on each bone density distribution map, and determine whether each bone abnormality index is greater than a preset first threshold. If the bone abnormality index is greater than a preset first threshold, the target area corresponding to the bone abnormality index is determined to be a high-risk area, and the tooth temperature data, tooth occlusal force data and tooth conductivity data of the high-risk area are obtained. The comprehensive thermal expansion stress is obtained based on the tooth temperature data, and the comprehensive occlusal stress is obtained based on the tooth occlusal force data. The biomechanical response value is obtained based on the thermal expansion stress and the combined occlusal stress. A conductivity tensor is obtained based on the tooth conductivity data, and a bioactivity attenuation factor is obtained based on the conductivity tensor. A comprehensive lesion risk value is obtained based on the bioactivity attenuation factor and biomechanical response value, and it is determined whether the comprehensive lesion risk value is greater than a preset second threshold. If the overall lesion risk value is greater than a preset second threshold, then the high-risk area is determined to have lesions.

2. The dental biometric detection method based on intelligent sensors according to claim 1, characterized in that, The step of obtaining the corresponding bone density distribution map based on the bone data of each tooth includes: A two-dimensional mesh image of each target region is acquired, and the reflected signal, signal propagation path length, and signal propagation duration of each mesh detection point in the two-dimensional mesh image are obtained based on each tooth bone data. The corresponding signal propagation speed is obtained based on the length of each signal propagation path and the duration of signal propagation. The corresponding reflected signal strength and transmission power are obtained for each reflected signal, and the corresponding reflection coefficient is obtained for each reflected signal strength and transmission power; Obtain the air acoustic impedance, and obtain the corresponding bone acoustic impedance based on the air acoustic impedance and each reflection coefficient; The bone density of each grid detection point is obtained based on the acoustic impedance and signal propagation velocity of each bone. Based on the two-dimensional grid image, the two-dimensional position information of each grid detection point is obtained, and a planar coordinate axis is established according to the two-dimensional position information of each grid detection point. The three-dimensional detection density axis is obtained by taking the bone density corresponding to each grid detection point as the Z-axis in the vertical direction of the planar coordinate axis. The bone density corresponding to each grid detection point is plotted on the three-dimensional detection density axis using a bar chart to obtain a bone density distribution map.

3. The dental biometric detection method based on intelligent sensors according to claim 1, characterized in that, The step of obtaining the corresponding bone abnormality index based on each bone density distribution map includes: The maximum and minimum bone densities are obtained from the bone density distribution map, and the bone distribution non-uniformity is obtained from the maximum and minimum bone densities. Multiple density gradients are obtained based on the bone density distribution map, and the corresponding density gradient modulus is obtained based on each density gradient; The density change rate is obtained based on the multiple density gradient moduli; The second spatial partial derivative of the corresponding density distribution is obtained for each density gradient, and the density change rate curvature is obtained for the second spatial partial derivatives of multiple density distributions. The skeletal abnormality index is obtained based on the density change rate curvature, density change rate, and bone distribution non-uniformity.

4. The dental biometric detection method based on intelligent sensors according to claim 1, characterized in that, The steps of obtaining comprehensive thermal expansion stress based on the tooth temperature data and obtaining comprehensive occlusal stress based on the tooth occlusal force data include: The enamel and dentin characteristics of the teeth are obtained, and the enamel expansion coefficient and enamel elastic modulus are obtained based on the enamel characteristics. The dentin expansion coefficient and dentin elastic modulus are obtained based on the dentin characteristics described. The temperature change is obtained based on the tooth temperature data, and the thermal expansion stress of the enamel is obtained based on the temperature change, the enamel expansion coefficient, and the enamel elastic modulus. The thermal expansion stress of dentin is obtained based on the temperature change, the coefficient of dentin expansion, and the elastic modulus of dentin, and the combined thermal expansion stress is obtained based on the thermal expansion stress of dentin and the thermal expansion stress of enamel. Based on the tooth occlusal force data, multiple occlusal stresses at the enamel-dentin junction are obtained, and the average stress is obtained based on the multiple occlusal stresses. The maximum engagement stress is selected from multiple engagement stresses as the maximum stress, and the stress concentration factor is obtained based on the maximum stress and the average stress. The first normal stress and the first tangential stress of the enamel are obtained, and the first occlusal stress is calculated based on the first normal stress, the first tangential stress, and the stress concentration factor. The calculation formula is as follows: Where Y(HY) represents the first engagement stress, Y(JZ) represents the stress concentration factor, F(XY) represents the first normal stress, and Q(XY) represents the first tangential stress; The second normal stress and the second tangential stress of dentin are obtained, and the second occlusal stress is obtained based on the second normal stress, the second tangential stress and the stress concentration factor; The comprehensive bite stress is obtained based on the first bite stress and the second bite stress.

5. The dental biometric detection method based on intelligent sensors according to claim 1, characterized in that, The step of obtaining the conductivity tensor based on the tooth conductivity data includes: Based on the tooth conductivity data, obtain the complex conductivity curve, high-frequency limiting conductivity, and static conductivity, and obtain the relaxation time and multiple relaxation peak position information based on the complex conductivity curve; The fractional index is obtained based on the frequencies corresponding to the multiple relaxation peak position information, and the frequency corresponding to the second relaxation peak position information is selected as the critical angular frequency. The relaxor conductivity is obtained based on the relaxation time, fractional exponent, critical angular frequency, high-frequency limiting conductivity, and static conductivity. Extract high-frequency curve segments with frequencies greater than a preset frequency from the complex conductivity curve, and obtain the slope of the imaginary part of the impedance of the high-frequency segment based on the high-frequency curve segments. The orientation polarization conductivity is obtained based on the slope of the imaginary part of the impedance and the critical angular frequency, and the conductivity tensor is obtained based on the high-frequency limiting conductivity, the orientation polarization conductivity, and the relaxation conductivity.

6. The dental biometric detection method based on intelligent sensors according to claim 1, characterized in that, The step of obtaining the bioactivity attenuation factor based on the conductivity tensor includes: Obtain the complex conductivity curve, and obtain the corresponding impedance based on each conductivity in the complex conductivity curve; The actual impedance spectrum is obtained based on the multiple impedances, and the actual real part value is obtained based on the actual impedance spectrum; Obtain the reference impedance spectrum of a standard tooth, obtain the reference real part value based on the reference impedance spectrum, and obtain the relative real part difference value based on the actual real part value and the reference real part value. The bioactivity decay factor is obtained based on the conductivity tensor and the difference between the relative real parts.

7. A dental biometric detection system based on intelligent sensors, characterized in that, include: The first acquisition module is used to acquire tooth bone data detected by scanning sensors for multiple target areas of the tooth, and to acquire a corresponding bone density distribution map based on each tooth bone data. The first judgment module is used to obtain the corresponding bone abnormality index based on each bone density distribution map, and to determine whether each bone abnormality index is greater than a preset first threshold. If the bone abnormality index is greater than a preset first threshold, the target area corresponding to the bone abnormality index is determined to be a high-risk area, and the tooth temperature data, tooth occlusal force data and tooth conductivity data of the high-risk area are obtained. The second acquisition module is used to acquire comprehensive thermal expansion stress based on the tooth temperature data and comprehensive occlusal stress based on the tooth occlusal force data. The third acquisition module is used to acquire biomechanical response values ​​based on the thermal expansion stress and the comprehensive occlusal stress. The fourth acquisition module is used to acquire a conductivity tensor based on the tooth conductivity data, and to acquire a bioactivity attenuation factor based on the conductivity tensor. The second judgment module is used to obtain a comprehensive lesion risk value based on the bioactivity attenuation factor and the biomechanical response value, and to determine whether the comprehensive lesion risk value is greater than a preset second threshold. If the overall lesion risk value is greater than a preset second threshold, then the high-risk area is determined to have lesions.

8. The dental biometric detection system based on intelligent sensors according to claim 7, characterized in that, The first acquisition module includes: The first acquisition unit is used to acquire a two-dimensional grid image of each target region, and to acquire the reflection signal, signal propagation path length and signal propagation duration of each grid detection point in the two-dimensional grid image based on each of the tooth bone data; The second acquisition unit is used to acquire the corresponding signal propagation speed based on the length of each signal propagation path and the signal propagation duration. The third acquisition unit is used to acquire the corresponding reflected signal strength and transmission power according to each reflected signal, and to acquire the corresponding reflection coefficient according to each reflected signal strength and transmission power; The fourth acquisition unit is used to acquire the air acoustic impedance and acquire the corresponding bone acoustic impedance based on the air acoustic impedance and each reflection coefficient; The fifth acquisition unit is used to acquire the bone density of each grid detection point based on the acoustic impedance of each bone and the signal propagation speed. A unit is established to obtain the two-dimensional position information of each grid detection point based on the two-dimensional grid image, and to establish a planar coordinate axis based on the two-dimensional position information of each grid detection point. The three-dimensional detection density axis is obtained by taking the bone density corresponding to each grid detection point as the Z-axis in the vertical direction of the planar coordinate axis. The drawing unit is used to plot the bone density corresponding to each grid detection point on the three-dimensional detection density axis using a bar chart, thus obtaining a bone density distribution map.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images