A bone density prediction system and osteoporosis screening method based on panoramic images

Abstract

The present invention relates to the technical field of bone density prediction, and specifically to a bone density prediction system based on panoramic images and an osteoporosis screening method, the system comprising an oral panoramic X-ray apparatus, a visual detection module, an information setting module, a control module, a communication module, and an alarm module; the control module calculates a position offset value, a patient position influence index, a soft tissue contrast value, a soft tissue influence index, and a calculated value of mandibular bone density according to data obtained by the oral panoramic X-ray apparatus, the visual detection module, and the information setting module, and transmits the calculated value of mandibular bone density to the communication module; the communication module transmits the calculated value of mandibular bone density to a doctor's end. The control module takes into account the soft tissue influence index and the patient position influence index when calculating the calculated value of mandibular bone density, thereby improving the accuracy of the calculation.

Description

Technical Field

[0001] The present invention relates to the technical field of bone density prediction, and in particular to a bone density prediction system based on panoramic images and an osteoporosis screening method. Background Art

[0002] Osteoporosis is a disease of the skeletal system characterized by a decrease in the density and mass of bone tissue, which makes bones brittle and prone to fracture. Normal bone tissue should be strong and dense, but in osteoporotic patients, bone density is reduced, trabeculae become thinner, and the bone structure becomes porous, making bones more susceptible to compression fractures.

[0003] Publication number CN112603354A discloses an oral bone density measurement method and device, the device comprising a ray generating mechanism for sending high-energy X-rays toward a scanned body; a ray receiving mechanism, comprising: a filtering mechanism for attenuating the high-energy X-rays to obtain low-energy X-rays, and a detector for receiving the high-energy X-rays and the low-energy X-rays that pass through the scanned body.

[0004] The devices in the prior art do not take into account the relevant detection errors when measuring bone density, resulting in an over-predicted bone density and reduced prediction accuracy. Summary of the invention

[0005] The purpose of the present invention is to improve the accuracy of bone density prediction. In view of the above-mentioned shortcomings, a bone density prediction system and an osteoporosis screening method based on panoramic images are proposed.

[0006] The present invention adopts the following technical solution:

[0007] A bone density prediction system based on panoramic images, the system comprising an oral panoramic X-ray device, a visual detection module, an information setting module, a control module, a communication module, and an alarm module;

[0008] The oral panoramic X-ray instrument detects the inside of the patient's oral cavity through X-rays and obtains the measured value of the mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area, and transmits them to the control module;

[0009] The visual detection module is used to capture and analyze the abscissa of the center of the bite strip in the oral panoramic X-ray instrument during the a-th detection, the abscissa of the left inner eye corner of the patient during the a-th detection, and the abscissa of the right inner eye corner of the patient during the a-th detection, and transmit them to the control module;

[0010] The information setting module is used to set the total number of coordinate detections, the selection threshold of the soft tissue contrast value, and the selection threshold of the position offset value, and transmit them to the control module;

[0011] The control module calculates the position offset value, the patient position influence index, the soft tissue contrast value, the soft tissue influence index, and the calculated value of the mandibular bone density based on the data obtained by the oral panoramic X-ray device, the visual detection module, and the information setting module, and transmits the calculated value of the mandibular bone density to the communication module;

[0012] The communication module transmits the calculated value of mandibular bone density to the doctor's end.

[0013] Optionally, the oral panoramic X-ray apparatus includes an X-ray submodule, an image analysis submodule, and a data analysis submodule;

[0014] The X-ray submodule is used to perform X-ray imaging and obtain a panoramic image of the inside of the patient's oral cavity, and transmit the panoramic image of the inside of the patient's oral cavity to the image analysis submodule;

[0015] The image analysis submodule identifies the mandibular area and soft tissue area of ​​the panoramic image of the patient's oral cavity based on a convolutional neural network, and transmits the images to the data analysis submodule;

[0016] The data analysis submodule obtains the measured value of mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area based on the analysis of the mandibular area and the soft tissue area, and transmits them to the control module.

[0017] Optionally, the image analysis submodule includes a data collection unit, a data preprocessing unit, a model building unit, and an analysis unit;

[0018] The data collection unit is used to collect data sets of mandibular bones and soft tissues in the oral cavity and transmit them to the data preprocessing unit;

[0019] The data preprocessing unit normalizes the data set and transmits the normalized data set to the model building unit;

[0020] The model building unit learns the features of the mandibular bone and soft tissue through the normalized data set;

[0021] The analysis unit is used to analyze the panoramic image of the patient's oral cavity and identify the mandibular area and soft tissue area, and transmit them to the data analysis submodule.

[0022] Optionally, the visual detection module includes a shooting submodule, a feature recognition submodule, and a coordinate acquisition submodule;

[0023] The shooting submodule is used to shoot and obtain an initial image, and transmit the initial image to the feature recognition submodule;

[0024] The feature recognition submodule recognizes the center of the bite bar in the oral panoramic X-ray apparatus, the left inner corner of the patient's eye, and the right inner corner of the patient's eye in the initial image according to the features, and transmits them to the coordinate acquisition submodule;

[0025] The coordinate acquisition submodule is used to analyze and obtain the horizontal coordinate of the bite bar center in the oral panoramic X-ray device during the ath detection, the horizontal coordinate of the left inner corner of the patient's eye during the ath detection, and the horizontal coordinate of the right inner corner of the patient's eye during the ath detection, and transmit them to the control module.

[0026] Optionally, when the control module calculates the calculated value of mandibular bone density, the following formula is satisfied:

[0027] GM = gm sc × rz × wz ;

[0028]

[0029] Among them, GM is the calculated value of mandibular bone density, gm sc is the measured value of mandibular bone density, w rz is the soft tissue impact index, w wz is the patient position impact index;

[0030] sf is the soft tissue contrast value, sf ref The threshold for selecting the soft tissue contrast value;

[0031] g max is the maximum grayscale value of the soft tissue area, g min is the minimum gray value of the soft tissue area;

[0032] p is the position offset value, p ref A threshold for selecting the position offset value;

[0033] A is the total number of coordinate detections, CY a is the horizontal coordinate of the bite bar center in the oral panoramic X-ray instrument during the ath test, CL a is the horizontal coordinate of the left inner corner of the patient's eye at the ath test, CR a is the horizontal coordinate of the patient's right inner eye corner during the ath test.

[0034] Optionally, the system further comprises an alarm module;

[0035] The control module obtains information on the risk of mandibular osteoporosis predicted by bone density according to the calculated value of mandibular bone density, and simultaneously transmits the information on the risk of mandibular osteoporosis predicted by bone density to the communication module and the alarm module;

[0036] The communication module transmits information on the risk of mandibular osteoporosis predicted by bone density to the doctor end;

[0037] The alarm module generates a real-time alarm based on the information of mandibular osteoporosis risk predicted by bone density.

[0038] The present invention also provides an osteoporosis screening method, which is applied to a bone density prediction system based on panoramic images, and comprises the following steps:

[0039] S1: The oral panoramic X-ray instrument detects the inside of the patient's oral cavity through X-rays and obtains the measured value of the mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area, and transmits them to the control module;

[0040] S2: The visual detection module takes and analyzes the horizontal coordinate of the center of the bite strip in the oral panoramic X-ray instrument during the a-th detection, the horizontal coordinate of the left inner corner of the patient's eye during the a-th detection, and the horizontal coordinate of the right inner corner of the patient's eye during the a-th detection, and transmits them to the control module;

[0041] S3: The information setting module is used to set the total number of coordinate detections, the selection threshold of the soft tissue contrast value, the selection threshold of the position offset value, and the selection threshold of the calculated value of the mandibular bone density, and transmit the information to the control module;

[0042] S4: The control module calculates the position offset value, the patient position influence index, the soft tissue contrast value, the soft tissue influence index, and the calculated value of the mandibular bone density according to the data obtained by the oral panoramic X-ray apparatus, the visual detection module, and the information setting module, and obtains the information of the mandibular osteoporosis risk predicted by the bone density according to the calculated value of the mandibular bone density, and simultaneously transmits the information of the mandibular osteoporosis risk predicted by the bone density to the communication module and the alarm module, wherein, when the calculated value of the mandibular bone density is greater than or equal to the selected threshold value of the calculated value of the mandibular bone density, it indicates that the mandibular osteoporosis risk predicted by the bone density is low, and when the calculated value of the mandibular bone density is less than the selected threshold value of the calculated value of the mandibular bone density, it indicates that the mandibular osteoporosis risk predicted by the bone density is high, and a bone density detection alarm signal is issued;

[0043] S5: The communication module transmits the information of mandibular osteoporosis risk predicted by bone density to the doctor end;

[0044] S6: The alarm module generates a real-time alarm based on the information of mandibular osteoporosis risk predicted by bone density.

[0045] The beneficial effects achieved by the present invention are:

[0046] 1. The control module takes into account the soft tissue influence index and the patient position influence index when calculating the mandibular bone density, thereby improving the accuracy of the calculation;

[0047] 2. The system uses visual detection and convolutional neural networks to help improve the speed and accuracy of system operation;

[0048] 3. When it is calculated that the patient has a high risk of osteoporosis, the alarm module can implement an alarm and medical staff will be reminded in time.

[0049] To further understand the features and technical contents of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are only for reference and description and are not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0051] Figure 2 It is a structural schematic diagram of the oral panoramic X-ray apparatus in the present invention;

[0052] Figure 3 It is a structural schematic diagram of the visual detection module in the present invention;

[0053] Figure 4 It is a schematic diagram of the structure used in calculating the relevant horizontal coordinates in the present invention;

[0054] Figure 5 It is a flow chart of the present invention;

[0055] Figure 6 It is a schematic diagram of the overall structure of the second embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following is an explanation of the embodiments of the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted according to actual dimensions. It is stated in advance. The following embodiments will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

[0057] Embodiment 1: This embodiment provides a bone density prediction system based on panoramic images, combined with Figures 1 to 5 shown.

[0058] A bone density prediction system based on panoramic images, the system comprising an oral panoramic X-ray device, a visual detection module, an information setting module, a control module, a communication module, and an alarm module;

[0059] The oral panoramic X-ray instrument detects the inside of the patient's oral cavity through X-rays and obtains the measured value of the mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area, and transmits them to the control module;

[0060] The visual detection module is used to capture and analyze the abscissa of the center of the bite strip in the oral panoramic X-ray instrument during the a-th detection, the abscissa of the left inner eye corner of the patient during the a-th detection, and the abscissa of the right inner eye corner of the patient during the a-th detection, and transmit them to the control module;

[0061] The information setting module is used to set the total number of coordinate detections, the selection threshold of the soft tissue contrast value, and the selection threshold of the position offset value, and transmit them to the control module;

[0062] The control module calculates the position offset value, the patient position influence index, the soft tissue contrast value, the soft tissue influence index, and the calculated value of the mandibular bone density based on the data obtained by the oral panoramic X-ray device, the visual detection module, and the information setting module, and transmits the calculated value of the mandibular bone density to the communication module;

[0063] The communication module transmits the calculated value of mandibular bone density to the doctor's end.

[0064] Specifically, the control module obtains the position offset value according to the total number of coordinate detections, the horizontal coordinate of the center of the bite strip in the oral panoramic X-ray device during the a-th detection, the horizontal coordinate of the left inner corner of the patient's eye during the a-th detection, and the horizontal coordinate of the right inner corner of the patient's eye during the a-th detection; obtains the patient position influence index according to the position offset value and a selection threshold of the position offset value; obtains the soft tissue contrast value according to the maximum grayscale value of the soft tissue area and the minimum grayscale value of the soft tissue area; obtains the soft tissue influence index according to the soft tissue contrast value and a selection threshold of the soft tissue contrast value; and obtains the calculated value of the mandibular bone density according to the soft tissue influence index, the measured value of the mandibular bone density, and the patient position influence index.

[0065] Optionally, the oral panoramic X-ray apparatus includes an X-ray submodule, an image analysis submodule, and a data analysis submodule;

[0066] The X-ray submodule is used to perform X-ray imaging and obtain a panoramic image of the inside of the patient's oral cavity, and transmit the panoramic image of the inside of the patient's oral cavity to the image analysis submodule;

[0067] The image analysis submodule identifies the mandibular area and soft tissue area of ​​the panoramic image of the patient's oral cavity based on a convolutional neural network, and transmits the images to the data analysis submodule;

[0068] The data analysis submodule obtains the measured value of mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area based on the analysis of the mandibular area and the soft tissue area, and transmits them to the control module.

[0069] Optionally, the image analysis submodule includes a data collection unit, a data preprocessing unit, a model building unit, and an analysis unit;

[0070] The data collection unit is used to collect data sets of mandibular bones and soft tissues in the oral cavity and transmit them to the data preprocessing unit;

[0071] The data preprocessing unit normalizes the data set and transmits the normalized data set to the model building unit;

[0072] The model building unit learns the features of the mandibular bone and soft tissue through the normalized data set;

[0073] The analysis unit is used to analyze the panoramic image of the patient's oral cavity and identify the mandibular area and soft tissue area, and transmit them to the data analysis submodule.

[0074] Optionally, the visual detection module includes a shooting submodule, a feature recognition submodule, and a coordinate acquisition submodule;

[0075] The shooting submodule is used to shoot and obtain an initial image, and transmit the initial image to the feature recognition submodule;

[0076] The feature recognition submodule recognizes the center of the bite bar in the oral panoramic X-ray apparatus, the left inner corner of the patient's eye, and the right inner corner of the patient's eye in the initial image according to the features, and transmits them to the coordinate acquisition submodule;

[0077] The coordinate acquisition submodule is used to analyze and obtain the horizontal coordinate of the bite bar center in the oral panoramic X-ray device during the ath detection, the horizontal coordinate of the left inner corner of the patient's eye during the ath detection, and the horizontal coordinate of the right inner corner of the patient's eye during the ath detection, and transmit them to the control module.

[0078] Optionally, when the control module calculates the calculated value of mandibular bone density, the following formula is satisfied:

[0079] GM = gm sc × rz × wz ;

[0080]

[0081] Among them, GM is the calculated value of mandibular bone density, gm sc is the measured value of mandibular bone density, w rz is the soft tissue impact index, w wzis the patient position impact index;

[0082] sf is the soft tissue contrast value, sf ref The threshold for selecting the soft tissue contrast value;

[0083] g max is the maximum grayscale value of the soft tissue area, g min is the minimum gray value of the soft tissue area;

[0084] p is the position offset value, p ref A threshold for selecting the position offset value;

[0085] A is the total number of coordinate detections, CY a is the horizontal coordinate of the bite bar center in the oral panoramic X-ray instrument during the ath test, CL a is the horizontal coordinate of the left inner corner of the patient's eye at the ath test, CR a is the horizontal coordinate of the patient's right inner eye corner during the ath test.

[0086] Specifically, the unit of the measured value of mandibular bone density is grams per square centimeter; the following matters need to be noted when calculating the soft tissue influence index: "soft tissue" refers to the non-bone part in the oral cavity and mandibular area, including the following parts: tongue, buccal mucosa, oral floor palatine muscles, oral mucosa and submucosal layer, glands and duct systems. The soft tissue parts mentioned above have high absorption of X-rays, so they appear as relatively bright areas in X-ray imaging. This difference in absorption will affect the transmission of X-rays between soft tissues and mandibles, thereby affecting the measured value of mandibular bone density. For example, the presence of soft tissue makes X-rays more easily absorbed, resulting in the soft tissue appearing as a brighter area in the X-ray image (the larger the value of the soft tissue contrast value), resulting in a larger measured value of mandibular bone density. Since the oral panoramic X-ray image indirectly evaluates the bone density value by measuring the degree of absorption of X-rays between soft tissues and mandibles, a soft tissue influence index is added as error compensation; the selection threshold of the soft tissue contrast value is set by technicians in this field based on experiments and patient age; (refer to Figure 4The following items should be noted when calculating the patient position influence index (as shown). Position refers to the relative position of the patient's key point and the center of the bite strip when using an oral panoramic X-ray device for detection. During the detection, the patient bites the bite strip of the oral panoramic X-ray device with his teeth. Under ideal conditions, the horizontal coordinate of the center point between the patient's two eyes is consistent with the horizontal coordinate of the center of the bite strip (the reference point is marked on the surface of the bite strip in advance as the center, and the vertical position of the reference point is not specified. The horizontal position of the reference point is obtained according to the average value of the sum of the left and right positions of the bite strip). In actual conditions, the patient's bite position is biased to the left or right, and then This results in an increase in the projected area of ​​the mandible in the measurement area, which causes the actual measured value of the mandibular bone density to be too large. Therefore, a patient position influence index is added as an error compensation; the selection threshold of the position offset value is set by technical personnel in this field according to experimental accuracy. Generally, the selection threshold of the position offset value is set to 20 mm; the units of the abscissa of the center of the bite strip in the oral panoramic X-ray apparatus during the a-th detection, the abscissa of the left inner corner of the patient's eye during the a-th detection, and the abscissa of the right inner corner of the patient's eye during the a-th detection are all millimeters; the selection threshold of the calculated value of the mandibular bone density is set by technical personnel in this field according to experiments and patient age.

[0087] The above units are only examples, and those skilled in the art may set different horizontal axis units according to actual needs when implementing the present solution.

[0088] Optionally, the system further comprises an alarm module;

[0089] The control module obtains information on the risk of mandibular osteoporosis predicted by bone density according to the calculated value of mandibular bone density, and simultaneously transmits the information on the risk of mandibular osteoporosis predicted by bone density to the communication module and the alarm module;

[0090] The communication module transmits information on the risk of mandibular osteoporosis predicted by bone density to the doctor end;

[0091] The alarm module generates a real-time alarm based on the information of mandibular osteoporosis risk predicted by bone density.

[0092] Specifically, the control module compares the calculated value of the mandibular bone density with the selected threshold of the calculated value of the mandibular bone density. When the calculated value of the mandibular bone density is greater than or equal to the selected threshold of the calculated value of the mandibular bone density, it indicates that the risk of mandibular osteoporosis predicted by the bone density is low. When the calculated value of the mandibular bone density is less than the selected threshold of the calculated value of the mandibular bone density, it indicates that the risk of mandibular osteoporosis predicted by the bone density is high, and a bone density detection alarm signal is issued.

[0093] The present invention also provides an osteoporosis screening method, which is applied to a panoramic image-based bone density prediction system, comprising the following steps:

[0094] S1: The oral panoramic X-ray instrument detects the inside of the patient's oral cavity through X-rays and obtains the measured value of the mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area, and transmits them to the control module;

[0095] S2: The visual detection module takes and analyzes the horizontal coordinate of the center of the bite strip in the oral panoramic X-ray instrument during the a-th detection, the horizontal coordinate of the left inner corner of the patient's eye during the a-th detection, and the horizontal coordinate of the right inner corner of the patient's eye during the a-th detection, and transmits them to the control module;

[0096] S3: The information setting module is used to set the total number of coordinate detections, the selection threshold of the soft tissue contrast value, the selection threshold of the position offset value, and the selection threshold of the calculated value of the mandibular bone density, and transmit the information to the control module;

[0097] S4: The control module calculates the position offset value, the patient position influence index, the soft tissue contrast value, the soft tissue influence index, and the calculated value of the mandibular bone density according to the data obtained by the oral panoramic X-ray apparatus, the visual detection module, and the information setting module, and obtains the information of the mandibular osteoporosis risk predicted by the bone density according to the calculated value of the mandibular bone density, and simultaneously transmits the information of the mandibular osteoporosis risk predicted by the bone density to the communication module and the alarm module, wherein, when the calculated value of the mandibular bone density is greater than or equal to the selected threshold value of the calculated value of the mandibular bone density, it indicates that the mandibular osteoporosis risk predicted by the bone density is low, and when the calculated value of the mandibular bone density is less than the selected threshold value of the calculated value of the mandibular bone density, it indicates that the mandibular osteoporosis risk predicted by the bone density is high, and a bone density detection alarm signal is issued;

[0098] S5: The communication module transmits the information of mandibular osteoporosis risk predicted by bone density to the doctor end;

[0099] S6: The alarm module generates a real-time alarm based on the information of mandibular osteoporosis risk predicted by bone density.

[0100] This embodiment solves the problem of low calculation accuracy of traditional bone density prediction systems. Specifically, the control module of this embodiment takes into account the soft tissue influence index and the patient position influence index when calculating the calculated value of mandibular bone density, thereby improving the accuracy of the calculation.

[0101] In addition, the system uses visual detection and convolutional neural networks to help improve the speed and accuracy of the system's operation. When it is calculated that the patient has a high risk of osteoporosis, the alarm module can sound an alarm and medical staff will be reminded in time.

[0102] Embodiment 2: This embodiment includes all the contents of embodiment 1, and provides a bone density prediction system based on panoramic images. Figure 6 shown.

[0103] A bone density prediction system based on panoramic images, the system also includes a BMI detection module and an information statistics module;

[0104] The BMI detection module is used to detect the patient's weight and height, analyze and obtain a weight reference index, and transmit it to the control module;

[0105] The information statistics module is used to count the patient's information and obtain the genetic reference index, smoking history reference index, drinking history reference index, exercise reference index, the total number of fracture sites of the patient, the total number of fractures at the bth site, and the frequency of fractures at the bth site, and transmit the information to the control module;

[0106] The control module obtains the osteoporosis clinical assessment factor according to the total number of fracture sites of the patient, the total number of fractures at the bth site, and the frequency of fractures at the bth site, obtains the information of the clinical assessment risk of mandibular osteoporosis according to the osteoporosis clinical assessment factor, and transmits it to the communication module and the alarm module synchronously; the control module obtains the osteoporosis clinical risk factor according to the weight reference index, the weight weight index, the genetic reference index, the genetic weight index, the smoking history reference index, the smoking weight index, the drinking history reference index, the drinking weight index, the exercise reference index, and the exercise weight index, obtains the information of the clinical risk of mandibular osteoporosis according to the osteoporosis clinical risk factor, and transmits it to the communication module and the alarm module synchronously;

[0107] The communication module transmits the information of the mandibular osteoporosis risk of clinical assessment and the mandibular osteoporosis risk of clinical risk to the doctor end;

[0108] The alarm module implements an alarm based on the information of the mandibular osteoporosis risk assessed clinically and the mandibular osteoporosis risk of clinical risk.

[0109] Optionally, when the control module calculates the osteoporosis clinical risk factor and the osteoporosis clinical assessment factor, the following formula is satisfied:

[0110] lcfx=bmi×qz bmi +yc×qz yc +xy×qz xy +hj×qz hj +sp×qz sp ;

[0111] qz bmi +qz yc +qz xy +qz hj +qz sp =100%;

[0112]

[0113] Among them, lcfx is the clinical risk factor for osteoporosis, bmi is the weight reference index, and bmi has the following values: bmi=1 or bmi=2. When bmi=2, BMI belongs to normal weight, and in other cases, bmi=1. bmi is the weight weight index, yc is the genetic reference index, yc has the following values, yc = 1 or yc = 2, when yc = 2, there is no osteoporosis in the direct relatives, and in other cases, yc = 1, qz yc is the genetic weight index, xy is the smoking history reference index, xy has the following values, xy=1 or xy=2, when xy=2, the patient does not have long-term smoking behavior, and the rest are xy=2, qz xy is the smoking weight index, hj is the reference index of drinking history, hj has the following values, hj = 1 or hj = 2, when hj = 2, the patient does not have long-term drinking behavior, otherwise hj = 1, qz hj is the drinking weight index, sp is the exercise reference index, sp has the following values, sp = 1 or sp = 2, when sp = 2, the patient is currently doing aerobic exercise and / or weight training, otherwise sp = 1, qz sp is the exercise weight index;

[0114] When the osteoporosis clinical risk factor is greater than or equal to the selection threshold of the osteoporosis clinical risk factor, it indicates that the clinical risk of mandibular osteoporosis is low; when the osteoporosis clinical risk factor is less than the selection threshold of the osteoporosis clinical risk factor, it indicates that the clinical risk of mandibular osteoporosis is high, and a clinical risk alarm signal is issued;

[0115] lcpg is the clinical assessment factor for osteoporosis, B is the total number of fracture sites in the patient, gt b is the total number of fractures at the bth site, pl b is the frequency of fracture at the bth site;

[0116] When the osteoporosis clinical assessment factor is greater than or equal to the selection threshold of the osteoporosis clinical assessment factor, it indicates that the clinical assessment risk of mandibular osteoporosis is low. When the osteoporosis clinical assessment factor is less than the selection threshold of the osteoporosis clinical assessment factor, it indicates that the clinical assessment risk of mandibular osteoporosis is high, and a clinical assessment alarm signal is issued.

[0117] Specifically, BMI is a commonly used weight classification method, which evaluates the patient's weight status based on the ratio of weight to height, and the unit is kilograms per square meter. For example, when the patient is an adult, a BMI of less than 18.5 is underweight, a BMI between 18.5 and 24.9 is normal weight, a BMI between 25 and 29.9 is overweight, a BMI between 30 and 34.9 is obese, a BMI between 35 and 39.9 is severely obese, and a BMI greater than or equal to 40 is severely obese; the following items should be noted when calculating the smoking history reference index: the patient does not have a long-term smoking behavior, which means that the patient has smoked less than 8 times so far; the following items should be noted when calculating the drinking weight index: the patient does not have a long-term drinking behavior, which means that the patient has drunk less than 6 times so far; the weight weight index, genetic weight index, smoking weight index, drinking weight index, and exercise weight index are set by technicians in this field according to experiments. In this embodiment, the weight weight index is set to 30%, the genetic weight index is set to 5 %, smoking weight index is 20%, drinking weight index is 20%, and exercise weight index is 25%; genetic reference index, smoking history reference index, drinking history reference index, and exercise reference index are all obtained through patient self-report; the total number of fracture sites of the patient, the total number of fractures at the bth site, and the frequency of fractures at the bth site are obtained through the hospital networking system; the following matters need to be noted when calculating the total number of fracture sites of the patient, an adult human body has approximately 206 bones, and the corresponding 206 bones are taken as the smallest unit; the following matters need to be noted when calculating the frequency of fractures at the bth site, assuming that the left clavicle has two fractures, and the time of the fracture is determined by the doctor as the day of the fracture, the time of the first fracture of the left clavicle is March 1, 2023, and the time of the second fracture is March 15, 2023, then the corresponding frequency is 15-1=14, 14 days divided by 2 times, which is 7 days each time; the selection threshold of osteoporosis clinical evaluation factors and the selection threshold of osteoporosis clinical risk factors are set by technical personnel in this field according to experiments.

[0118] The above units are only examples, and those skilled in the art may set different frequency units according to actual needs when implementing this solution.

[0119] This embodiment solves the problem that the traditional bone density prediction system has a relatively single analysis. In this embodiment, the control module predicts bone density from three different directions and can send out different bone density detection alarm signals, clinical risk detection alarm signals, and clinical assessment detection alarm signals, thereby improving the practicality and objectivity of the detection.

[0120] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention description and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. A bone density prediction system based on panoramic images, characterized in that: The system includes an oral panoramic X-ray device, a visual detection module, an information setting module, a control module, a communication module, and an alarm module; The oral panoramic X-ray instrument detects the inside of the patient's oral cavity through X-rays and obtains the measured value of the mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area, and transmits them to the control module; The visual detection module is used to capture and analyze the The horizontal coordinate of the center of the bite strip in the oral panoramic X-ray instrument during the first test, The horizontal coordinate of the left inner corner of the patient's eye during the second test, The horizontal coordinate of the right inner corner of the patient's eye during the second test is transmitted to the control module; The information setting module is used to set the total number of coordinate detections, the selection threshold of the soft tissue contrast value, and the selection threshold of the position offset value, and transmit them to the control module; The control module calculates the position offset value, the patient position influence index, the soft tissue contrast value, the soft tissue influence index, and the calculated value of the mandibular bone density based on the data obtained by the oral panoramic X-ray device, the visual detection module, and the information setting module, and transmits the calculated value of the mandibular bone density to the communication module; The communication module transmits the calculated value of mandibular bone density to the doctor end; When the control module calculates the calculated value of mandibular bone density, the following formula is satisfied: ； in, is the calculated value of mandibular bone density, is the measured value of mandibular bone density, is the soft tissue impact index, is the patient position impact index; is the soft tissue contrast value, The threshold for selecting the soft tissue contrast value; is the maximum grayscale value of the soft tissue area, is the minimum gray value of the soft tissue area; is the position offset value, A threshold for selecting the position offset value; is the total number of coordinate detections, For the The horizontal coordinate of the center of the bite bar in the oral panoramic X-ray instrument during the first test, For the The horizontal coordinate of the left inner corner of the patient's eye during the second test, For the The horizontal coordinate of the patient's right inner corner of the eye during the second test.

2. A panoramic image-based bone density prediction system as claimed in claim 1, characterized in that: The oral panoramic X-ray instrument includes an X-ray submodule, an image analysis submodule, and a data analysis submodule; The X-ray submodule is used to perform X-ray imaging and obtain a panoramic image of the inside of the patient's oral cavity, and transmit the panoramic image of the inside of the patient's oral cavity to the image analysis submodule; The image analysis submodule identifies the mandibular area and soft tissue area of ​​the panoramic image of the patient's oral cavity based on a convolutional neural network, and transmits the images to the data analysis submodule; The data analysis submodule obtains the measured value of mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area based on the analysis of the mandibular area and the soft tissue area, and transmits them to the control module.

3. A panoramic image-based bone density prediction system as claimed in claim 2, characterized in that: The image analysis submodule includes a data collection unit, a data preprocessing unit, a model building unit, and an analysis unit; The data collection unit is used to collect data sets of mandibular bones and soft tissues in the oral cavity and transmit them to the data preprocessing unit; The data preprocessing unit normalizes the data set and transmits the normalized data set to the model building unit; The model building unit learns the features of the mandibular bone and soft tissue through the normalized data set; The analysis unit is used to analyze the panoramic image of the patient's oral cavity and identify the mandibular area and soft tissue area, and transmit them to the data analysis submodule.

4. A panoramic image-based bone density prediction system as claimed in claim 3, characterized in that: The visual detection module includes a shooting submodule, a feature recognition submodule, and a coordinate acquisition submodule; The shooting submodule is used to shoot and obtain an initial image, and transmit the initial image to the feature recognition submodule; The feature recognition submodule recognizes the center of the bite bar in the oral panoramic X-ray apparatus, the left inner corner of the patient's eye, and the right inner corner of the patient's eye in the initial image according to the features, and transmits them to the coordinate acquisition submodule; The coordinate acquisition submodule is used to analyze and obtain the The horizontal coordinate of the center of the bite strip in the oral panoramic X-ray instrument during the first test, The horizontal coordinate of the left inner corner of the patient's eye during the second test, The horizontal coordinate of the right inner corner of the patient's eye during the second detection is transmitted to the control module.

5. A panoramic image-based bone density prediction system as claimed in claim 4, characterized in that: The system also includes an alarm module; The control module obtains information on the risk of mandibular osteoporosis predicted by bone density according to the calculated value of mandibular bone density, and simultaneously transmits the information on the risk of mandibular osteoporosis predicted by bone density to the communication module and the alarm module; The communication module transmits information on the risk of mandibular osteoporosis predicted by bone density to the doctor end; The alarm module generates a real-time alarm based on the information of mandibular osteoporosis risk predicted by bone density.

6. An osteoporosis screening method, applied to a panoramic image-based bone density prediction system as claimed in any one of claims 1 to 5, characterized in that: The following steps are involved: S1: The oral panoramic X-ray instrument detects the inside of the patient's oral cavity through X-rays and obtains the measured value of the mandibular bone density, the minimum grayscale value of the soft tissue area, and the maximum grayscale value of the soft tissue area, and transmits them to the control module; S2: The visual inspection module takes pictures and analyzes the results. The horizontal coordinate of the center of the bite strip in the oral panoramic X-ray instrument during the first test, The horizontal coordinate of the left inner corner of the patient's eye during the second test, The horizontal coordinate of the right inner corner of the patient's eye during the second test is transmitted to the control module; S3: The information setting module is used to set the total number of coordinate detections, the selection threshold of the soft tissue contrast value, the selection threshold of the position offset value, and the selection threshold of the calculated value of the mandibular bone density, and transmit the information to the control module; S4: The control module calculates the position offset value, the patient position influence index, the soft tissue contrast value, the soft tissue influence index, and the calculated value of the mandibular bone density according to the data obtained by the oral panoramic X-ray apparatus, the visual detection module, and the information setting module, and obtains the information of the mandibular osteoporosis risk predicted by the bone density according to the calculated value of the mandibular bone density, and simultaneously transmits the information of the mandibular osteoporosis risk predicted by the bone density to the communication module and the alarm module, wherein, when the calculated value of the mandibular bone density is greater than or equal to the selected threshold value of the calculated value of the mandibular bone density, it indicates that the mandibular osteoporosis risk predicted by the bone density is low, and when the calculated value of the mandibular bone density is less than the selected threshold value of the calculated value of the mandibular bone density, it indicates that the mandibular osteoporosis risk predicted by the bone density is high, and a bone density detection alarm signal is issued; S5: The communication module transmits the information of mandibular osteoporosis risk predicted by bone density to the doctor end; S6: The alarm module generates a real-time alarm based on the information of mandibular osteoporosis risk predicted by bone density.

Images