Construction method of osteoporotic fracture risk prediction model

Abstract

The invention relates to the technical field of medical informatics, in particular to a construction method of an osteoporotic fracture risk prediction model. The method comprises the following steps: acquiring an included angle between a foot and the ground, a step speed and a CT image of a target person in a monitoring process; dividing pixel points in the CT image into a plurality of bone tissue areas; according to the shape distribution characteristics of the edge lines in the bone tissue area, bone characteristic values of the bone structure are obtained; obtaining a posture control factor of each gait according to the included angles between the left and right feet of the target person in each gait and the ground; determining an abnormal posture index of each gait in combination with the posture control factor and the corresponding step speed; obtaining a control disorder coefficient of each time period according to the numerical distribution characteristics and the change characteristics of all the posture control factors in each time period; and determining an osteoporosis evaluation value by integrating the bone characteristic value and the disorder control coefficient of the skeleton structure. The accuracy of the bone comprehensive evaluation result of the target person is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical informatics, and particularly to a method for constructing an osteoporosis fracture risk prediction model. Background Art

[0002] Osteoporosis is a disease characterized by decreased bone density, destruction of bone tissue microstructure, and reduced bone strength, which significantly increases the risk of fractures. The osteoporosis fracture risk prediction model integrates multi-dimensional variables such as bone density, clinical risk factors, and lifestyle, and uses statistical or machine learning algorithms to evaluate the probability of an individual having an osteoporosis fracture within a specific time period. The core goal of this model is to accurately identify high-risk individuals, thereby guiding early intervention and reducing the fracture incidence.

[0003] Traditional fracture risk prediction methods are limited by the representation ability of single-modal data, such as bone density or static images. Existing multi-modal fusion models are difficult to quantify the high-frequency dynamic evolution characteristics of the bone metabolism microenvironment, such as the non-linear attenuation of trabecular bone topology and the entropy increase of stress distribution, due to the cross-source data heterogeneity (such as the dimensional differences in images, biochemical indicators, and mechanical parameters) and the lack of ability to model temporal dynamic associations. This leads to a decrease in the sensitivity and specificity of the model, and an inability to obtain an accurate comprehensive index for reflecting the comprehensive bone condition of the detected person, thus unable to provide an effective reference basis for doctors. Summary of the Invention

[0004] In order to solve the problem that the existing methods cannot accurately obtain a comprehensive index for reflecting the comprehensive bone condition of the detected person, the purpose of the present invention is to provide a method for constructing an osteoporosis fracture risk prediction model, and the specific technical solution adopted is as follows: The present invention provides a method for constructing an osteoporosis fracture risk prediction model, which includes the following steps: Obtain the angle between the foot and the ground, the walking speed, and the CT image during the monitoring of the target person; Divide the pixel points into several bone tissue regions based on the gray-scale distribution of the pixel points in the CT image; obtain the bone mass characteristic values of the bone structure according to the shape distribution characteristics of the inner edge lines in the bone tissue regions; Obtain the posture control factor for each gait according to the angle between the left and right feet of the target person and the ground for each gait; determine the posture abnormality index for each gait by combining the posture control factor and the corresponding walking speed; obtain the control disorder coefficient for each time period according to the numerical distribution characteristics and change characteristics of all the posture control factors within each time period; Determine the osteoporosis evaluation value of the target person based on the bone mass characteristic values of the comprehensive bone structure, the control disorder coefficient of the current time period, the overall distribution of all posture abnormality indicators in the current time period, and the correlation between the bone mass characteristic values and the control disorder coefficient in all time periods during the monitoring process.

[0005] Preferably, dividing the pixel points into several bone tissue regions based on the gray-scale distribution of the pixel points in the CT image, including: Select the pixel points with gray-scale values greater than the preset gray-scale threshold in the CT image as seed points, and perform region growing on the pixel points in the CT image to obtain several bone tissue regions. Among them, the rule of region growing is that the gray-scale value difference between the neighborhood pixel points and the seed points is less than the preset gray-scale difference threshold.

[0006] Preferably, obtaining the bone mass characteristic values of the bone structure according to the shape distribution characteristics of the inner edge lines in the bone tissue regions, including: For any bone tissue region: Calculate the average Euclidean distance between all edge pixel points in the any bone tissue region; Perform linear fitting on each edge line in the any bone tissue region respectively to obtain the corresponding goodness of fit, and calculate the average value of the goodness of fit corresponding to all edge lines in the any bone tissue region; According to the average Euclidean distance and the average value of the goodness of fit, obtain the shape irregularity value of any bone tissue region. The average Euclidean distance has a positive correlation with the shape irregularity value, and the average value of the goodness of fit has a negative correlation with the shape irregularity value; Integrate the average gray-scale value of the pixel points in all bone tissue regions and the shape irregularity value to obtain the bone mass characteristic values of the bone structure.

[0007] Preferably, integrating the average gray-scale value of the pixel points in all bone tissue regions and the shape irregularity value to obtain the bone mass characteristic values of the bone structure, including: Calculate the first product of the average gray-scale value of the pixel points in each bone tissue region and the shape irregularity value; Determine the average value of the first products of all bone tissue regions as the bone mass characteristic values of the bone structure.

[0008] Preferably, obtaining the posture control factor of each gait according to the angle between the left and right feet of the target person and the ground for each gait, including: For any one gait: Take the difference between the driving indices of the left and right feet as the driving asymmetry coefficient; the driving index is the normalized value of the maximum angle between the sole of the foot and the ground when the toe leaves the ground; Taking the difference in braking indices between the left and right feet as the braking asymmetry coefficient, where the braking index is the normalized value of the maximum angle between the sole of the foot and the ground when the heel touches the ground; Taking the sum of the driving asymmetry coefficient and the braking asymmetry coefficient as the posture control factor for any one gait.

[0009] Preferably, combining the posture control factor and the corresponding walking speed to determine the posture abnormality index for each gait, including: Taking the ratio between the posture control factor of any one gait and the corresponding walking speed as the posture abnormality index for any one gait.

[0010] Preferably, obtaining the control disorder coefficient for each time period based on the numerical distribution characteristics and change characteristics of all posture control factors within each time period, including: For any one time period: Performing curve fitting on all posture control factors within the any one time period to obtain the corresponding first fitting curve; Obtaining the window corresponding to each point on the first fitting curve; respectively calculating the frequency of occurrence of the data value of each point within the window corresponding to each point in the first fitting curve and the slope of each point on the first fitting curve; Combining the frequency of occurrence of the data value of each point within the window corresponding to each point in the first fitting curve and the slope to obtain the control disorder coefficient for the any one time period.

[0011] Preferably, combining the frequency of occurrence of the data value of each point within the window corresponding to each point in the first fitting curve and the slope to obtain the control disorder coefficient for the any one time period, including: Taking the ratio between the slope of each point within the window corresponding to each point and the frequency of occurrence of the data value of each point within the window corresponding to each point in the first fitting curve as the first ratio of each point within the window corresponding to each point; Combining the first ratios of all points within the windows corresponding to all points on the first fitting curve to obtain the control disorder coefficient for the any one time period.

[0012] Preferably, obtaining the osteoporosis evaluation value of the target person, including: Calculating the first sum value of the average of all posture abnormality indices in the current time period and the control disorder coefficient in the current time period; Calculating the second product of the bone mass characteristic value in the current time period and the first sum value; Taking the sum of the second product and the correlation between the bone mass characteristic values and the control disorder coefficients in all time periods during the monitoring process as the osteoporosis evaluation value of the target person.

[0013] Preferably, obtaining the correlation between the bone mass characteristic values and the control disorder coefficient during all time periods of the monitoring process includes: Taking the Pearson correlation coefficient between the bone mass characteristic value sequence and the control disorder coefficient sequence as the correlation between the bone mass characteristic values and the control disorder coefficient during all time periods of the monitoring process; The bone mass characteristic value sequence is composed of the bone mass characteristic values during all time periods of the monitoring process, and the control disorder coefficient sequence is composed of the control disorder coefficient during all time periods of the monitoring process.

[0014] The present invention has at least the following beneficial effects: By integrating the gray-scale distribution of pixel points and the morphological distribution characteristics of edge lines in the static CT images of the target person, the present invention evaluates the bone structure of the target person, quantifies the sparsity, irregularity and edge shape distribution of the bone microstructure in the CT images of the target person, obtains the bone mass characteristic values of the bone structure, and then combines the dynamic gait data to evaluate the gait control situation of the target person according to the angles between the left and right feet of the target person and the ground and the walking speed during each gait, dynamically captures the non-linear evolution characteristics of bone degradation, obtains the control disorder coefficient, and finally fuses the dynamic characteristics and static characteristics of the target person to obtain the osteoporosis evaluation value of the target person. The osteoporosis evaluation value can accurately reflect the comprehensive condition of the bone mass of the target person, overcomes the problems of insufficient representation ability of traditional single-modal data and difficulty in fusing cross-source heterogeneous data, improves the accuracy of the evaluation result, and can provide an effective reference basis for doctors. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of a method for constructing an osteoporosis fracture risk prediction model provided by an embodiment of the present invention; Figure 2 It is a structural block diagram of a system for constructing an osteoporosis fracture risk prediction model provided by an embodiment of the present invention. Detailed Embodiments

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will describe in detail a method for constructing an osteoporosis fracture risk prediction model according to the present invention with reference to the drawings and preferred embodiments.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0019] The following specifically describes the specific solution of a method for constructing an osteoporosis fracture risk prediction model provided by the present invention in conjunction with the accompanying drawings.

[0020] An embodiment of a method for constructing an osteoporosis fracture risk prediction model: The specific scenario targeted by this embodiment is: when analyzing the comprehensive bone condition of a target person, by integrating the bone density, trabecular bone structure and morphological characteristics in the static CT images of the target person, and combining the time series analysis of dynamic gait data, a determination model of a multi-modal fusion comprehensive bone index is constructed to obtain an accurate osteoporosis evaluation value, providing an effective reference basis for doctors.

[0021] This embodiment proposes a method for constructing an osteoporosis fracture risk prediction model, as Figure 1 shown, a method for constructing an osteoporosis fracture risk prediction model of this embodiment includes the following steps: Step S1, obtain the angle between the foot and the ground, the walking speed, and the CT image during the monitoring of the target person.

[0022] First, for the target person, a standardized abdominal CT and chest CT scanning protocol is adopted to collect the lumbar CT (L1 to L4) images of the target person. Set the tube voltage to 120 KV, and the tube current and scanning time are automatically matched. The scanning field of view is greater than 400 mm, the slice thickness is 0.5 mm, and the slice interval is 0.5 mm. For the L1 to L4 vertebral bodies in the CT image, a standard bone window reconstruction algorithm is used to reconstruct the slice thickness of 0.1 mm or 0.5 mm and transfer it to the image archiving.

[0023] At the same time, an intelligent insole integrated with an accelerometer and a gyroscope is worn for the target person, and the walking speed data and the angle between the foot and the ground of each gait of the patient during daily activities are collected in real time through the built-in sensors. It should be noted that: in this embodiment, a complete gait includes the process that both feet have completed leaving the ground and returning to the ground.

[0024] So far, this embodiment has obtained the angle between the foot and the ground, the walking speed, and the CT image of the target person during the monitoring process. Among them, the monitoring process is a set composed of all historical moments whose time interval from the current moment is less than or equal to the preset duration. In this embodiment, the preset duration is 1 week. In specific applications, the implementer can set it according to specific situations.

[0025] Step S2: Divide the pixel points into several bone tissue regions based on the gray-scale distribution of the pixel points in the lumbar spine CT image; obtain the bone mass characteristic values of the bone structure according to the shape distribution characteristics of the edge lines within the bone tissue regions.

[0026] Considering that there are certain differences among different individuals, such as differences in basic physical conditions, the bone structures of patients show different osteoporosis characteristics. Therefore, next, bone density, trabecular bone structure, morphological characteristics, etc. will be extracted from the CT image of the target person as static input features of the model.

[0027] In the CT image of the target person, within the same bone tissue or structure region, due to the stability of the structure or tissue density and the scanning consistency, the pixel value distribution of the pixel points within the region is usually relatively consistent.

[0028] Select the pixel points with gray-scale values greater than the preset gray-scale threshold in the CT image of the target person as seed points. These seed points are usually located in the bone tissue regions because the X-ray absorption value of the bone is relatively high and the gray-scale value is relatively significant; use the region growing algorithm to perform region growing on the pixel points in the CT image, and regard each region obtained after region growing as a bone tissue region, that is, multiple bone tissue regions are obtained. Among them, the rule of region growing is: when the gray-scale value difference between the neighborhood pixel point and the seed point is less than the preset gray-scale difference threshold, the neighborhood pixel point and the seed point are merged. In this embodiment, the preset gray-scale threshold is 80, and the preset gray-scale difference threshold is 3. In specific applications, the implementer can set according to the specific situation. The neighborhood size in this embodiment is a four-neighborhood, and the region growing algorithm is a prior art and will not be elaborated here too much.

[0029] As the osteoporosis symptoms worsen, long-term osteoporosis will cause changes in the bone morphology of the patient and trigger degenerative joint surface lesions, such as widening of the joint space and irregularity of the joint surface. As the supporting network of the bone, trabecular bone will show thinning, sparseness, and even fracture during the process of osteoporosis. In the CT image, the trabecular bone structure of the patient shows obvious sparseness and irregularity, and imaging features such as trabecular bone fracture or structural damage appear, further affecting the mechanical properties and stability of the bone. Therefore, this embodiment will evaluate the irregular degree of the bone tissue structure.

[0030] Next, this embodiment takes a bone tissue region in the CT image of the target person as an example for illustration, and the method provided by this embodiment can be used to process other bone tissue regions in the CT image of the target person.

[0031] Specifically, for any bone tissue region: Adopt a deep learning-based segmentation model, such as the U-Net network model, to extract the binary edge map of the bone tissue region and extract all the edge lines within the bone tissue region. Calculate the mean Euclidean distance between all the edge pixels within the bone tissue region according to the Euclidean distance between pairwise edge pixels within the bone tissue region.

[0032] Use the least squares method and linear fitting to perform linear fitting on each edge line within the bone tissue region to obtain the corresponding goodness of fit. Each edge line within the bone tissue region corresponds to a goodness of fit; calculate the mean of the goodness of fit corresponding to all the edge lines within the bone tissue region.

[0033] The smaller the mean of the goodness of fit corresponding to all the edge lines within the bone tissue region, the greater the difference between the edge lines within the bone tissue region and their corresponding fitted lines, that is, the more inflection points of the edge curve and the more complex and irregular the edge structure. The greater the mean Euclidean distance between all the edge pixels within the bone tissue region, the sparser the bone edge structure within the bone tissue region, reflecting that the support network of the regional bone structure is more abnormal.

[0034] Based on the above features, in this embodiment, the shape irregularity value of the bone tissue region will be obtained according to the mean Euclidean distance between all the edge pixels within the bone tissue region and the mean of the goodness of fit corresponding to all the edge lines within the bone tissue region. The shape irregularity value is used to reflect the complexity and irregularity of the bone structure. The mean Euclidean distance has a positive correlation with the shape irregularity value, and the mean of the goodness of fit has a negative correlation with the shape irregularity value.

[0035] Among them, the positive correlation means that the dependent variable will increase as the independent variable increases and the dependent variable will decrease as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by the actual application; the negative correlation means that the dependent variable will decrease as the independent variable increases and the dependent variable will increase as the independent variable decreases. It can be a subtractive relationship, a divisive relationship, etc., which is determined by the actual application.

[0036] In this embodiment, a specific calculation formula for the shape irregularity value is given. The shape irregularity value of the m-th bone tissue region in the lumbar spine CT image of the target person can be expressed as: Among them, represents the shape irregularity value of the m-th bone tissue region in the lumbar spine CT image of the target person, represents the mean Euclidean distance between all the edge pixels within the m-th bone tissue region, represents the mean of the goodness of fit corresponding to all the edge lines within the m-th bone tissue region.

[0037] In this embodiment, adding 0.01 to the denominator of the calculation formula of the shape irregularity value is to prevent the denominator from being 0. In specific applications, the implementer can set it according to specific circumstances. When the average Euclidean distance between all edge pixels in the m-th bone tissue region is larger and the average goodness of fit corresponding to all edge lines in the m-th bone tissue region is smaller, it indicates that the edges of the bone structure in the m-th bone tissue region are more dispersed and irregular, reflecting a more serious degree of osteoporosis, and the stability and mechanical properties of the bone may be poor.

[0038] By using the above method, the shape irregularity value of each bone tissue region can be obtained.

[0039] During the process of osteoporosis, it is usually manifested as a decrease in bone density of the bone structure, resulting in a decrease in the gray value of the pixels in the bone region image. Therefore, in this embodiment, according to the gray value of each pixel in each bone tissue region, the average value of the gray values of all pixels in each bone tissue region is calculated, denoted as the average gray value of the pixels in each bone tissue region. Each bone tissue region has a corresponding average gray value. The smaller the average gray value, the more obvious the degradation of the bone structure in the bone tissue region, the decrease in bone density, which may thus lead to the occurrence of osteoporosis and affect the mechanical properties and stability of the bone.

[0040] Next, by comprehensively considering the average gray value of the pixels in all bone tissue regions and the shape irregularity value, the bone mass characteristic value of the bone structure is obtained. Specifically, calculate the product of the average gray value of the pixels in each bone tissue region and the shape irregularity value, and denote this product as the first product; each bone tissue region has a corresponding first product, and the average value of the first products of all bone tissue regions is determined as the bone mass characteristic value of the bone structure.

[0041] In this embodiment, the specific calculation formula of the bone mass characteristic value is given, which can be expressed as: Among them, represents the bone mass characteristic value of the bone structure, represents the number of bone tissue regions in the CT image of the target person, represents the average gray value of the pixels in the m-th bone tissue region in the CT image of the target person, represents the shape irregularity value of the m-th bone tissue region in the CT image of the target person. represents the first product of the m-th bone tissue region.

[0042] The bone quality characteristic value of the bone structure is used to reflect the stability and mechanical properties of the target person's bone structure. When the grayscale mean value of the pixel points in all bone tissue regions in the CT image of the target person is larger and the shape irregularity value is also larger, it indicates that the mechanical properties and stability of the target person's bones are poor, and the risk of fracture is higher, that is, the larger the bone quality characteristic value of the bone structure.

[0043] So far, by using the above method, the bone quality characteristic value of the bone structure has been obtained.

[0044] Step S3: Obtain the posture control factor for each gait of the target person according to the angle between the left and right feet and the ground in each gait; combine the posture control factor and the corresponding walking speed to determine the posture abnormality index for each gait; according to the numerical distribution characteristics and change characteristics of all posture control factors within each time period, obtain the control disorder coefficient for each time period.

[0045] By analyzing gait parameters, the motor function and coordination of the patient can be evaluated, and then the non-linear decline of the bone structure with time and lifestyle changes can be inferred, and the high-frequency dynamic change characteristics of bone density and stress distribution can be further captured, so as to assist in predicting the potential risk of fracture.

[0046] The changes in the patient's gait reflect the development trend of osteoporosis. As bone density decreases and bone fragility increases, the patient's motor ability and activity level are affected, resulting in a slow or unstable gait; specifically, due to the pain caused by osteoporosis, especially the pain in the spine and joints, the normal motor function of the patient is restricted, which in turn causes gait changes. Patients with pain and restricted motor function usually show irregular gaits, such as shortened stride length, slowed gait, etc., which increases the risk of fracture. Based on this, next, this embodiment will separately analyze each gait of the target person.

[0047] This embodiment takes one gait as an example for illustration, and the method provided in this embodiment can be used to process other gaits.

[0048] Specifically, for any one gait: Take the difference between the driving indices of the left and right feet as the driving asymmetry coefficient; the driving index is the normalized value of the maximum angle between the sole of the foot and the ground when the toe leaves the ground; in this embodiment, the method for obtaining the difference between the driving indices of the left and right feet is: calculate the absolute value of the difference between the driving indices of the left and right feet, and take this absolute value as the driving asymmetry coefficient. The larger the driving asymmetry coefficient, the more obvious the asymmetry between the driving actions of the left and right feet, reflecting the driving instability of the patient's gait.

[0049] The difference in braking indices between the left and right feet is used as the braking asymmetry coefficient, and the braking index is the normalized value of the maximum angle between the sole of the foot and the ground when the heel touches the ground; in this embodiment, the method for obtaining the difference in braking indices between the left and right feet is: calculating the absolute value of the difference between the braking indices of the left and right feet, and taking this absolute value as the difference in braking indices between the left and right feet. In this embodiment, there are many methods for normalizing the angle. In specific applications, the implementer selects according to specific circumstances to make the normalization result fall within [0, 1], and will not elaborate further here.

[0050] The sum of the driving asymmetry coefficient and the braking asymmetry coefficient is used as the posture control factor for this gait.

[0051] Considering individual differences, gait complexity, and minor gait changes, there may be certain errors in measuring gait stability solely based on the driving asymmetry coefficient and the braking asymmetry coefficient; healthy individuals usually exhibit slight gait asymmetry, but it will not have a significant impact on overall gait stability. Osteoporosis patients, especially those with more severe conditions, show significant gait asymmetry, which will lead to gait instability, accompanied by manifestations such as a slow walking speed. Therefore, next, the degree of postural abnormality is evaluated by combining the posture control factor and the walking speed to obtain a postural abnormality index.

[0052] Specifically, for any gait: the ratio between the posture control factor of this gait and the corresponding walking speed is determined as the postural abnormality index for this gait; when the posture control factor of this gait is larger and the walking speed is slower, it indicates that the gait of the target person shows stronger disorder characteristics, that is, the asymmetry and instability in the gait of the target person are more obvious, that is, the postural abnormality index is larger.

[0053] By using the above method, the postural abnormality index of each gait of the target person can be obtained.

[0054] The patient's bone structure undergoes non-linear degradation over time and with changes in lifestyle, and the gait pattern will show disorder. Specifically, the gait stability of the patient in daily activities gradually decreases, which is reflected in the reduced stability of postural control in each time period. This change indicates that the gait behavior pattern of the patient is affected by bone decline, resulting in impaired postural control function, which in turn affects their overall gait performance.

[0055] The monitoring process is divided into time periods, and the duration of each time period is 1 hour. In specific applications, the implementer can set it according to specific circumstances.

[0056] Next, this embodiment separately analyzes each time period in the monitoring process.

[0057] For any time period: In chronological order, curve fitting is performed on all posture control factors within this time period to obtain the corresponding fitting curve, and this fitting curve is denoted as the first fitting curve. Curve fitting is a prior art and will not be elaborated here.

[0058] Taking each point on this fitting curve as the center of the window respectively, a window with a preset length is obtained, and this window is used as the window corresponding to each point on this fitting curve. In this embodiment, the preset length is 21. In specific applications, the implementer can set it according to the specific situation.

[0059] The frequency of the data value of each point within the window corresponding to each point and the slope of each point on the first fitting curve are obtained respectively. The ratio between the slope of each point within the window corresponding to each point and the frequency of the data value of each point within the window corresponding to each point in the first fitting curve is denoted as the first ratio of each point within the window corresponding to each point. By synthesizing the first ratios of all points within the windows corresponding to all points on the first fitting curve, the control disorder coefficient for any time period is obtained.

[0060] In this embodiment, a specific calculation formula for the control disorder coefficient is given. The control disorder coefficient for the r-th time period can be expressed as: Among them, represents the control disorder coefficient for the r-th time period, represents the number of points on the first fitting curve corresponding to the r-th time period, represents the number of points within the window corresponding to the n-th point on the first fitting curve corresponding to the r-th time period, represents the slope of the -th point within the window corresponding to the n-th point on the first fitting curve corresponding to the r-th time period, represents the frequency of the data value of the -th point within the window corresponding to the n-th point on the first fitting curve corresponding to the r-th time period in its corresponding first fitting curve.

[0061] represents the first ratio of the -th point within the window corresponding to the n-th point on the first fitting curve corresponding to the r-th time period. When the first ratios of all points within the windows corresponding to each point on the first fitting curve are larger, it indicates that during daily activities, the target person becomes more unstable in gait control, showing a larger gait disorder, meaning that the patient's bone degeneration is severe, the non-linear attenuation of the bone structure is more intense, resulting in a decline in their gait posture control ability.

[0062] By using the above method, the control disorder coefficient of the target person in each time period during the monitoring process can be obtained.

[0063] Step S4: Determine the osteoporosis evaluation value of the target person by integrating the bone mass characteristic value of the bone structure, the control disorder coefficient of the current time period, the overall distribution of all posture abnormality indicators in the current time period, and the correlation between the bone mass characteristic values and the control disorder coefficients in all time periods during the monitoring process.

[0064] Arrange the bone mass characteristic values in all time periods during the monitoring process in chronological order to obtain a bone mass characteristic value sequence; similarly, arrange the control disorder coefficients in all time periods during the monitoring process in chronological order to obtain a control disorder coefficient sequence.

[0065] Calculate the Pearson correlation coefficient between the bone mass characteristic value sequence and the control disorder coefficient sequence. The calculation method of the Pearson correlation coefficient is a prior art and will not be elaborated here. Take the Pearson correlation coefficient between the bone mass characteristic value sequence and the control disorder coefficient sequence as the correlation between the bone mass characteristic values and the control disorder coefficients in all time periods during the monitoring process. The value range of the correlation is [-1, 1]. The closer its value is to 1, the more positive the correlation between the degree of osteoporosis and gait instability is, indicating that the gait control disorder of the target person may be exacerbated due to the fragile bones caused by their own osteoporosis, thus increasing the risk of the target person falling and fracturing.

[0066] Furthermore, according to the posture abnormality indicators of each gait in the current time period, calculate the average value of all posture abnormality indicators in the current time period; then, calculate the sum value of the average value of all posture abnormality indicators in the current time period and the control disorder coefficient of the current time period, and record this sum value as the first sum value; calculate the product of the bone mass characteristic value of the current time period and the first sum value, and record this product as the second product; then, determine the sum of the second product and the correlation between the bone mass characteristic values and the control disorder coefficients in all time periods during the monitoring process as the osteoporosis evaluation value of the target person.

[0067] In this embodiment, a specific calculation formula for the osteoporosis evaluation value of the target person is given. The osteoporosis evaluation value of the target person can be expressed as: Among them, represents the osteoporosis evaluation value of the target person, represents the bone mass characteristic value of the bone structure, represents the average value of all posture abnormality indicators in the current time period, represents the control disorder coefficient of the current time period, represents the bone mass characteristic value sequence, represents the control disorder coefficient sequence, represents the correlation between the bone mass characteristic values and the control disorder coefficient during all time periods of the monitoring process.

[0068] represents the first sum value, reflecting the degree of gait disorder of the target person; represents the second product, which reflects the combined effect of osteoporosis and gait disorder. The correlation between the bone mass characteristic values and the control disorder coefficient during all time periods of the monitoring process quantifies the mutual correlation strength between the two. This comprehensive evaluation reveals the deficiencies of the target person in bone fragility and motor coordination, may be accompanied by a greater degree of physiological degradation, indicates a higher risk of fracture, and requires continuous monitoring and intervention for their bone health and motor function.

[0069] So far, the method provided in this embodiment has completed the analysis of the comprehensive bone condition of the target person, obtained the osteoporosis evaluation value of the target person. The larger the osteoporosis evaluation value of the target person, the greater the severity of gait control disorder of the target patient, and higher attention should be given to this patient subsequently.

[0070] In this embodiment, by integrating the gray-scale distribution of pixel points and the morphological distribution characteristics of edge lines in the static CT image of the target person, the bone structure of the target person is evaluated, the sparsity, irregularity and edge shape distribution of the bone microstructure in the CT image of the target person are quantified, and the bone mass characteristic value of the bone structure is obtained. Then, combined with the dynamic gait data, according to the angle between the left and right feet of the target person and the ground and the walking speed during each gait, the gait control situation of the target person is evaluated, the non-linear evolution characteristics of bone degradation are dynamically captured, and the control disorder coefficient is obtained. Finally, by fusing the dynamic characteristics and static characteristics of the target person, the osteoporosis evaluation value of the target person is obtained. The osteoporosis evaluation value can accurately reflect the comprehensive bone condition of the target person, overcomes the problems of insufficient representation ability of traditional single-modal data and difficulty in fusing cross-source heterogeneous data, improves the accuracy of the evaluation result, and can provide an effective reference basis for doctors.

[0071] An embodiment of a system for constructing an osteoporosis fracture risk prediction model: Refer to Figure 2 , which shows the structural block diagram of a system for constructing an osteoporosis fracture risk prediction model provided by an embodiment of the present invention. The system may include a data acquisition module, a static analysis module, a dynamic analysis module and a comprehensive evaluation module; Among them, the data acquisition module is used to obtain the angle between the feet and the ground, the walking speed and the CT image during the monitoring process of the target person; A static analysis module, configured to divide pixel points into several bone tissue regions based on the gray - scale distribution of pixel points in CT images; and obtain bone mass characteristic values of the bone structure according to the shape distribution characteristics of the edge lines within the bone tissue regions. A dynamic analysis module, configured to obtain a posture control factor for each gait based on the angle between the left and right feet of the target person and the ground for each gait; determine a posture abnormality index for each gait by combining the posture control factor and the corresponding walking speed; and obtain a control disorder coefficient for each time period according to the numerical distribution characteristics and change characteristics of all the posture control factors within each time period. A comprehensive evaluation module, configured to determine an osteoporosis evaluation value of the target person by comprehensively considering the bone mass characteristic values of the bone structure, the control disorder coefficient of the current time period, the overall distribution of all the posture abnormality indexes of the current time period, and the correlation between the bone mass characteristic values and the control disorder coefficients of all the time periods during the monitoring process.

[0072] It should be understood that Figure 2 The structural block diagram and modules of a system for constructing an osteoporosis fracture risk prediction model as shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented through hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above - mentioned methods and systems can be implemented using computer - executable instructions and / or included in processor control code. For example, such code is provided on a carrier medium such as a disk, CD, or DVD - ROM, a programmable memory such as a read - only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can be implemented not only by hardware circuits such as very - large - scale integrated circuits or gate arrays, semiconductors such as logic chips and transistors, or programmable hardware devices such as field - programmable gate arrays and programmable logic devices, but also by software executed by various types of processors, or by a combination of the above - mentioned hardware circuits and software (e.g., firmware).

[0073] For more details about the above - mentioned respective modules, reference can be made to other parts of this specification, and details will not be elaborated here.

[0074] In other embodiments, a medium is further provided. The medium stores at least one computer - executable program. When the at least one program is run by a computer, the computer is made to execute the steps in the method for constructing an osteoporosis fracture risk prediction model in the above - mentioned embodiments. The medium can be a computer - readable storage medium.

[0075] Among them, the provided system and medium are both used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be elaborated here.

[0076] It should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for constructing an osteoporosis fracture risk prediction model, characterized in that, The method includes the following steps: Obtain the angle between the foot and the ground, the walking speed, and the CT image during the monitoring of the target person; Divide the pixel points into several bone tissue regions based on the gray-scale distribution of the pixel points in the CT image; according to the shape distribution characteristics of the inner edge lines in the bone tissue regions, obtain the bone quality characteristic values of the bone structure; Obtain the posture control factor for each gait according to the angle between the left and right feet and the ground for each gait of the target person; combine the posture control factor and the corresponding walking speed to determine the posture abnormality index for each gait; according to the numerical distribution characteristics and change characteristics of all the posture control factor values in each time period, obtain the control disorder coefficient for each time period; Comprehensively determine the osteoporosis evaluation value of the target person based on the bone quality characteristic values of the bone structure, the control disorder coefficient of the current time period, the overall distribution of all the posture abnormality indexes in the current time period, and the correlation between the bone quality characteristic values and the control disorder coefficients in all the time periods during the monitoring process.

2. The method for constructing an osteoporosis fracture risk prediction model according to claim 1, wherein The dividing the pixel points into several bone tissue regions based on the gray-scale distribution of the pixel points in the CT image includes: Select the pixel points with gray-scale values greater than the preset gray-scale threshold in the CT image as seed points, perform region growing on the pixel points in the CT image to obtain several bone tissue regions, where the rule of region growing is: the gray-scale value difference between the neighborhood pixel points and the seed points is less than the preset gray-scale difference threshold.

3. The method for constructing an osteoporosis fracture risk prediction model according to claim 1, wherein The obtaining the bone quality characteristic values of the bone structure according to the shape distribution characteristics of the inner edge lines in the bone tissue regions includes: For any bone tissue region: Calculate the mean Euclidean distance between all the edge pixel points in the any bone tissue region; Perform linear fitting on each edge line in the any bone tissue region respectively to obtain the corresponding goodness of fit, and calculate the mean value of the goodness of fit corresponding to all the edge lines in the any bone tissue region; According to the mean Euclidean distance and the mean value of the goodness of fit, obtain the shape irregularity value of the any bone tissue region, where the mean Euclidean distance is positively correlated with the shape irregularity value, and the mean value of the goodness of fit is negatively correlated with the shape irregularity value; Comprehensively obtain the bone quality characteristic values of the bone structure based on the gray-scale mean value of the pixel points in all the bone tissue regions and the shape irregularity value.

4. The method for constructing an osteoporosis fracture risk prediction model according to claim 3, characterized in that, Comprehensively obtaining the bone quality characteristic values of the bone structure based on the gray-scale mean value of the pixel points in all the bone tissue regions and the shape irregularity value includes: Calculate the first product of the gray-scale mean value of the pixel points in each bone tissue region and the shape irregularity value; Determine the average value of the first products of all the bone tissue regions as the bone quality characteristic values of the bone structure.

5. The method for constructing an osteoporosis fracture risk prediction model according to claim 1, wherein The obtaining the posture control factor for each gait according to the angle between the left and right feet and the ground for each gait of the target person includes: For any gait: Take the difference between the driving indexes of the left and right feet as the driving asymmetry coefficient; the driving index is the normalized value of the maximum angle between the sole and the ground when the toe leaves the ground; Take the difference between the braking indexes of the left and right feet as the braking asymmetry coefficient, and the braking index is the normalized value of the maximum angle between the sole and the ground when the heel touches the ground; Take the sum of the driving asymmetry coefficient and the braking asymmetry coefficient as the posture control factor for any one gait.

6. The method for constructing an osteoporosis fracture risk prediction model according to claim 5, characterized in that Combine the posture control factor and the corresponding walking speed to determine the posture abnormality index for each gait, including: Determine the ratio between the posture control factor of any one gait and the corresponding walking speed as the posture abnormality index for any one gait.

7. The method for constructing an osteoporosis fracture risk prediction model according to claim 1, characterized in that Obtain the control disorder coefficient for each time period according to the numerical distribution characteristics and change characteristics of all posture control factors within each time period, including: For any one time period: Perform curve fitting on all posture control factors within the any one time period to obtain the corresponding first fitting curve; Obtain the window corresponding to each point on the first fitting curve; calculate the frequency of the data value of each point within the window corresponding to each point appearing in the first fitting curve and the slope of each point on the first fitting curve respectively; Combine the frequency of the data value of each point within the window corresponding to each point appearing in the first fitting curve and the slope to obtain the control disorder coefficient for the any one time period.

8. The method for constructing an osteoporosis fracture risk prediction model according to claim 7, wherein Combine the frequency of the data value of each point within the window corresponding to each point appearing in the first fitting curve and the slope to obtain the control disorder coefficient for the any one time period, including: Record the ratio between the slope of each point within the window corresponding to each point and the frequency of the data value of each point within the window corresponding to each point appearing in the first fitting curve as the first ratio of each point within the window corresponding to each point; Combine the first ratios of all points within the windows corresponding to all points on the first fitting curve to obtain the control disorder coefficient for the any one time period.

9. The method for constructing an osteoporosis fracture risk prediction model according to claim 1, characterized in that The acquisition of the osteoporosis evaluation value of the target person includes: Calculate the first sum value of the average value of all posture abnormality indexes in the current time period and the control disorder coefficient in the current time period; Calculate the second product of the bone mass characteristic value in the current time period and the first sum value; Determine the sum of the second product and the correlation between the bone mass characteristic values and the control disorder coefficients in all time periods during the monitoring process as the osteoporosis evaluation value of the target person.

10. The method for constructing an osteoporosis fracture risk prediction model according to claim 1, wherein The acquisition of the correlation between the bone mass characteristic values and the control disorder coefficients in all time periods during the monitoring process includes: Take the Pearson correlation coefficient between the bone mass characteristic value sequence and the control disorder coefficient sequence as the correlation between the bone mass characteristic values and the control disorder coefficients in all time periods during the monitoring process; The bone mass characteristic value sequence is composed of the bone mass characteristic values in all time periods during the monitoring process, and the control disorder coefficient sequence is composed of the control disorder coefficients in all time periods during the monitoring process.

Images