A method, device, equipment and medium for generating a myopia critical eye axis curve
By acquiring eye condition data of target users, optimizing the myopia critical axial length curve based on corneal curvature and physiological constraints, and generating personalized myopia critical axial length curves, the problem of insufficient accuracy in existing technologies is solved, enabling more refined early warning and intervention for myopia.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- JING DONG FANG YI YUN (CHENG DU) KE JI YOU XIAN GONG SI
- Filing Date
- 2026-05-12
- Publication Date
- 2026-07-14
AI Technical Summary
In existing technologies, myopia threshold tables based on population statistics lack fine-grained support at the month level, resulting in insufficient accuracy in assessing the myopia threshold axial length of children who are not full-year-olds, making it difficult to meet the needs of personalized myopia prevention and control.
By acquiring the target user's current age and eye condition data, including corneal curvature, intraocular pressure, and axial growth rate, static and dynamic compensation values are determined based on corneal curvature grouping. The myopia critical axial curve is optimized using preset physiological constraints to generate a personalized target myopia critical axial curve.
It significantly improves the accuracy and timeliness of myopia risk assessment, solves the error problem caused by interpolation estimation for non-integrity age groups, and achieves more refined early warning and intervention for myopia.
Smart Images
Figure CN122392986A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device and medium for generating a myopia critical axial length curve. Background Technology
[0002] In recent years, the incidence of myopia among children and adolescents has shown a continuous upward trend, making myopia prevention and control a critical issue urgently needing to be addressed in the field of public health. Axial length (AL), as a core biometric indicator for assessing myopia progression, shows a strong negative correlation between its increase and the degree of refractive error. When an individual's AL exceeds the normal reference range for their age, it often indicates a significantly increased risk of developing myopia or an accelerated rate of myopia progression. Therefore, establishing a precise AL assessment system for myopia thresholds is of significant value for early warning of myopia.
[0003] Currently, empirical threshold tables based on population statistics are commonly used for axial length assessment. For example, the "Childhood Myopia Threshold Table" provides average axial length and its percentile reference values for different ages, serving as a standard tool for clinical screening. However, existing assessment systems have significant technical limitations: current standards only provide data at whole-year age points (e.g., 6 years, 7 years), lacking support for fine-grained growth changes at the month level. In practical applications, medical personnel need to estimate the threshold value for children who are not whole-year-olds (e.g., 7 years and 6 months) through linear interpolation. This approximate calculation method inevitably introduces systematic errors, significantly affecting the accuracy of axial length assessment results for childhood myopia. This makes it difficult to meet the needs of personalized myopia prevention and control. Summary of the Invention
[0004] In view of this, the purpose of this application is to provide a method, device, equipment and medium for generating the critical axial length curve of myopia, which significantly improves the accuracy and timeliness of myopia risk assessment, solves the error problem caused by interpolation estimation of non-full age groups, and enables more refined early warning and intervention of myopia.
[0005] In a first aspect, embodiments of this application provide a method for generating a myopia threshold axial length curve, the method comprising: Obtain the target user's current age and current eye condition data; wherein, the current eye condition data includes corneal curvature, current intraocular pressure, and current axial length growth rate; The target curvature group of the target user is determined from multiple preset curvature groups based on the corneal curvature; The axial length compensation value for the target user under the target curvature group is determined based on the current eye state data; wherein, the axial length compensation value includes static compensation value and dynamic compensation value; The preset myopia critical axial length curve is optimized using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age.
[0006] Furthermore, the optimization of the preset myopia threshold axial length curve using the axial length compensation value and preset physiological constraints to obtain the target myopia threshold axial length curve for the target user at the current age includes: The constraint violation degree of the preset myopia critical axial length curve is calculated using the preset physiological constraint conditions, and the penalty coefficient in the objective function is adjusted based on the constraint violation degree and the axial length compensation value; wherein, the preset physiological constraint conditions include axial growth rate smoothness constraint and ocular biomechanical constraint. Calculate the loss function corresponding to the objective function, and update the curve parameters of the preset myopia critical axial length curve by gradient descent based on the loss function until the objective function meets the stopping iteration condition, thus obtaining the target myopia critical axial length curve.
[0007] Furthermore, determining the axial length compensation value for the target user under the target curvature group based on the current eye state data includes: Based on the corneal curvature, the static compensation value for the target user under the target curvature group is determined; The dynamic compensation value is determined using the current age, the current intraocular pressure, and the current axial length growth rate. The sum of the static compensation value and the dynamic compensation value is taken as the axial length compensation value.
[0008] Furthermore, determining the static compensation value for the target user under the target curvature group based on the corneal curvature includes: Based on the target curvature grouping, the corresponding target compensation coefficient is determined from a plurality of preset compensation coefficients; The product of the curvature difference and the target compensation coefficient is used as the static compensation value; wherein, the curvature difference is the difference between the corneal curvature reference value corresponding to the target curvature group and the corneal curvature of the target user.
[0009] Furthermore, determining the dynamic compensation value using the current age, the current intraocular pressure, and the current axial length growth rate includes: Substitute the current intraocular pressure and the current age into the intraocular pressure compensation formula to obtain the intraocular pressure compensation value; Substitute the current axial length growth rate and the current age into the growth acceleration compensation formula to obtain the growth acceleration compensation value; The sum of the intraocular pressure compensation value and the growth acceleration compensation value is used as the dynamic compensation value.
[0010] Furthermore, after obtaining the target myopia threshold axial length curve, the generation method further includes: When the target myopia threshold axial length curve is detected to not meet the physiological constraints, a corresponding warning message is generated; wherein, the physiological constraints include the axial length increasing monotonically with age, and the axial length decreasing as the corneal curvature increases.
[0011] Secondly, embodiments of this application also provide a device for generating a myopia threshold axial length curve, the device comprising: The data acquisition module is used to acquire the target user's current age and current eye condition data; wherein, the current eye condition data includes corneal curvature, current intraocular pressure, and current axial length growth rate; The curvature grouping determination module is used to determine the target curvature group of the target user from multiple preset curvature groups based on the corneal curvature; An axial length compensation value determination module is used to determine the axial length compensation value of the target user under the target curvature group based on the current eye state data; wherein, the axial length compensation value includes a static compensation value and a dynamic compensation value; The target axial length curve generation module is used to optimize the preset myopia critical axial length curve using the axial length compensation value and preset physiological constraints, so as to obtain the target myopia critical axial length curve of the target user at the current age.
[0012] Furthermore, when the target axial length curve generation module optimizes the preset myopia critical axial length curve using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age, the target axial length curve generation module is also used for: The constraint violation degree of the preset myopia critical axial length curve is calculated using the preset physiological constraint conditions, and the penalty coefficient in the objective function is adjusted based on the constraint violation degree and the axial length compensation value; wherein, the preset physiological constraint conditions include axial growth rate smoothness constraint and ocular biomechanical constraint. Calculate the loss function corresponding to the objective function, and update the curve parameters of the preset myopia critical axial length curve by gradient descent based on the loss function until the objective function meets the stopping iteration condition, thus obtaining the target myopia critical axial length curve.
[0013] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the method for generating the myopia critical axial length curve described above are performed.
[0014] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method for generating the critical axial length curve for myopia as described above.
[0015] This application provides a method, apparatus, device, and medium for generating a myopia critical axial length curve. First, it acquires the current age and current eye condition data of a target user; wherein the current eye condition data includes corneal curvature, current intraocular pressure, and current axial growth rate. Then, based on the corneal curvature, it determines a target curvature group for the target user from multiple preset curvature groups; based on the current eye condition data, it determines the axial length compensation value for the target user under the target curvature group; wherein the axial length compensation value includes a static compensation value and a dynamic compensation value; finally, it optimizes a preset myopia critical axial length curve using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age.
[0016] This application obtains the target user's current age and multidimensional ocular status data, including corneal curvature, current intraocular pressure, and current axial growth rate. Users are grouped based on corneal curvature to determine a personalized axial compensation value, composed of static and dynamic compensation values. This axial compensation value is then used to optimize a preset myopia threshold axial curve, resulting in a personalized target myopia threshold axial curve for each user. Compared to traditional threshold curves that rely solely on statistical data from whole-age groups, this application significantly improves the accuracy and timeliness of myopia risk assessment, resolving errors caused by interpolation estimation for non-whole-age groups, thus enabling more precise early warning and intervention for myopia.
[0017] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description
[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 A flowchart illustrating a method for generating a myopia threshold axial length curve provided in an embodiment of this application; Figure 2 One of the structural schematic diagrams of a device for generating a myopia critical axial length curve provided in an embodiment of this application; Figure 3 A second schematic diagram of a device for generating a myopia critical axial length curve provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.
[0021] First, the applicable scenarios for this application will be introduced. This application can be applied to the field of computer technology.
[0022] In recent years, the incidence of myopia among children and adolescents has shown a continuous upward trend, making myopia prevention and control a critical issue urgently needing to be addressed in the field of public health. Axial length (AL), as a core biometric indicator for assessing myopia progression, shows a strong negative correlation between its increase and the degree of refractive error. When an individual's AL exceeds the normal reference range for their age, it often indicates a significantly increased risk of developing myopia or an accelerated rate of myopia progression. Therefore, establishing a precise AL assessment system for myopia thresholds is of significant value for early warning of myopia.
[0023] Research has found that current empirical threshold tables based on population statistics are commonly used for axial length assessment. For example, the "Childhood Myopia Threshold Table" provides average axial length and its percentile reference values for different ages, serving as a standard tool for clinical screening. However, the existing assessment system has significant technical limitations: current standards only provide data at whole-year age points (e.g., 6 years, 7 years), lacking support for fine-grained growth changes at the month level. In practical applications, medical personnel need to estimate the threshold value for children who are not whole-year-olds (e.g., 7 years and 6 months), and this approximate calculation method inevitably introduces systematic errors, significantly affecting the accuracy of the axial length assessment results for childhood myopia thresholds. This makes it difficult to meet the needs of personalized myopia prevention and control.
[0024] Based on this, the embodiments of this application provide a method for generating the critical axial length curve of myopia, which significantly improves the accuracy and timeliness of myopia risk assessment and solves the error problem caused by interpolation estimation of non-full age groups, so as to achieve more refined early warning and intervention of myopia.
[0025] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for generating a myopia threshold axial length curve, as provided in an embodiment of this application. Figure 1 As shown in the embodiments of this application, the generation method includes: S101, obtain the target user's current age and current eye condition data.
[0026] Regarding step S101 above, in specific implementation, the target user's current age and current eye condition data are acquired. Here, as an example, the current age is in years, with month-level precision supported (e.g., 7 years and 6 months). The current eye condition data includes the target user's corneal curvature, current intraocular pressure, and current axial length growth rate; these parameters can be automatically collected using standard ophthalmic examination equipment.
[0027] S102, based on the corneal curvature, determine the target curvature group of the target user from multiple preset curvature groups.
[0028] Regarding step S102 above, in specific implementation, based on the obtained corneal curvature value of the target user, matching is performed among multiple preset curvature groups to determine the target curvature group most suitable for the user. Here, according to the embodiment provided in this application, the corneal curvature K is divided into three intervals: low, medium, and high. For the low curvature group, For medium curvature group, The target user's corneal curvature is determined by comparing it with the curvature range corresponding to each preset curvature group.
[0029] S103, determine the axial length compensation value of the target user under the target curvature group based on the current eye state data.
[0030] Regarding step S103 above, in specific implementation, the corresponding axial length compensation value is determined using the target user's current eye state data. Specifically, according to the embodiments provided in this application, the axial length compensation value consists of two parts: a static compensation value and a dynamic compensation value. The static compensation reflects the impact of the individual corneal curvature deviating from the ideal state on the critical axial length value, while the dynamic compensation reflects the impact of two dynamic factors—the current intraocular pressure level and the rate of axial length growth—on the critical axial length value.
[0031] As an optional embodiment, regarding step S103 above, determining the axial length compensation value for the target user under the target curvature group based on the current eye state data includes: Step 1031: Determine the static compensation value of the target user under the target curvature group based on the corneal curvature.
[0032] Regarding step 1031 above, in specific implementation, the static compensation value of the target user under the target curvature group is determined based on the corneal curvature corresponding to the target user.
[0033] Specifically, regarding step 1031 above, determining the static compensation value for the target user under the target curvature group based on the corneal curvature includes: Step 10311: Determine the corresponding target compensation coefficient from multiple preset compensation coefficients based on the target curvature grouping.
[0034] Regarding step 10311 above, in specific implementation, the corresponding target compensation coefficient is determined from multiple preset compensation coefficients by using the target curvature group corresponding to the target user. Please refer to Table 1 below, which is an example table of compensation coefficients based on curvature grouping provided in the embodiments of this application.
[0035] Table 1. Example of compensation coefficients based on curvature grouping
[0036] As shown in Table 1 above, when the curvature group is the low curvature group, the corresponding compensation coefficient is... When the curvature group is the medium curvature group, the corresponding compensation coefficient is... When the curvature group is a high curvature group, the corresponding compensation coefficient is... .
[0037] Step 10312: The product of the curvature difference and the target compensation coefficient is taken as the static compensation value.
[0038] Regarding step 10312 above, in specific implementation, the curvature difference is first calculated. Here, the curvature difference is the difference between the corneal curvature reference value corresponding to the target curvature group and the corneal curvature of the target user. Then, the product of the curvature difference and the target compensation coefficient is used as the static compensation value. Specifically, the static compensation value... The calculation formula is expressed as follows:
[0039] Step 1032: Determine the dynamic compensation value using the current age, the current intraocular pressure, and the current axial length growth rate.
[0040] Regarding step 1032 above, in specific implementation, the dynamic compensation value of the target user is calculated based on the target user's current age, current intraocular pressure, and current axial length growth rate.
[0041] Specifically, regarding step 1032 above, determining the dynamic compensation value using the current age, the current intraocular pressure, and the current axial length growth rate includes: Step 10321: Substitute the current intraocular pressure and the current age into the intraocular pressure compensation formula to obtain the intraocular pressure compensation value.
[0042] Regarding step 10321 above, in specific implementation, the target user's current intraocular pressure and current age are substituted into the intraocular pressure compensation formula to obtain the intraocular pressure compensation value. Specifically, the intraocular pressure compensation formula is expressed as follows:
[0043] in, The intraocular pressure compensation value for the target user. The target user's current intraocular pressure.
[0044] Step 10322: Substitute the current axial length growth rate and the current age into the growth acceleration compensation formula to obtain the growth acceleration compensation value.
[0045] Regarding step 10322 above, in specific implementation, the target user's current axial length growth rate and current age are substituted into the growth acceleration compensation formula to obtain the growth acceleration compensation value. Specifically, the growth acceleration compensation formula is expressed as follows:
[0046] in, The growth acceleration compensation value for the target users, The current axial length growth rate of the target user.
[0047] Step 10323: The sum of the intraocular pressure compensation value and the growth acceleration compensation value is taken as the dynamic compensation value.
[0048] Regarding step 10323 above, in specific implementation, the intraocular pressure compensation value calculated in step 10321 is used... The growth acceleration compensation value calculated in step 10322 The sum serves as the dynamic compensation value for the target user. .
[0049] Step 1033: The sum of the static compensation value and the dynamic compensation value is taken as the axial length compensation value.
[0050] Regarding step 1033 above, in specific implementation, after both the static compensation value and the dynamic compensation value are determined, the sum of the static compensation value and the dynamic compensation value is used as the axial length compensation value for the target user.
[0051] S104, the preset myopia critical axial length curve is optimized using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age.
[0052] Here, the myopia threshold axial length curve refers to a dynamic reference trajectory line used to determine whether an individual is likely to develop pathological myopia during growth and development. The preset myopia threshold axial length curve is constructed based on large-scale population data. This curve represents the development trend of the general population and indicates the safe upper limit of the target user's axial length at different age stages. When the actual measured axial length exceeds the corresponding value in the curve, it indicates a risk of high myopia.
[0053] Regarding step S104 above, in specific implementation, the preset myopia critical axial length curve is optimized and adjusted using the target user's axial length compensation value. By introducing individualized information and combining it with preset physiological constraints, the curve is nonlinearly corrected to generate a target critical axial length curve specific to that user, which is used for subsequent myopia progression early warning and intervention strategy formulation.
[0054] As an optional embodiment, regarding step S104 above, optimizing the preset myopia critical axial length curve using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age includes: Step 1041: Calculate the constraint violation degree of the preset myopia critical axial length curve using the preset physiological constraint conditions, and adjust the penalty coefficient in the objective function based on the constraint violation degree and the axial length compensation value.
[0055] Here, according to the embodiments provided in this application, a preset myopia critical axial length curve is constructed by using cubic B-splines and cubic polynomial basis function expansion to construct a bivariate smooth function relating age and corneal curvature K. Specifically, the preset myopia critical axial length curve is expressed by the following formula:
[0056] in, For age The cubic B-spline basis functions (ensuring a smooth curve) are cubic basis functions; Let be the quadratic polynomial basis functions of corneal curvature K, forming a three-piece function where j takes the values 0, 1, and 2; The coefficient matrix has a total of 12 parameters to be solved in the above formula.
[0057] The constraint violation degree of a preset myopia threshold axial length curve is calculated using preset physiological constraints. According to the embodiments provided in this application, the preset physiological constraints include constraints on the smoothness of axial growth rate and constraints on ocular biomechanics. The constraint on the smoothness of axial growth rate refers to the fact that, under normal circumstances, the rate of axial length growth with age should remain continuous and change gradually, without drastic jumps or non-physiological oscillations. The ocular biomechanical constraint refers to the negative correlation between corneal curvature and axial length, i.e., the flatter the cornea, the longer the axial length is generally.
[0058] Specifically, the degree of constraint violation regarding the smooth line constraint of axial growth rate. Calculated using the following formula:
[0059] in, It represents the second derivative of the critical axial length value with respect to time in the preset myopia critical axial length curve, and represents the curvature or degree of bending of the preset myopia critical axial length curve. The sum of squares of the curvature of the preset myopia threshold axial length curve f at all time points t was calculated.
[0060] Constraint violation degree for ocular biomechanical constraints Calculated using the following formula:
[0061] in, It represents the partial derivative of the critical axial length value with respect to corneal curvature in the preset myopia critical axial length curve, and measures the sensitivity of axial length to changes in corneal curvature.
[0062] Furthermore, the objective function is expressed by the following formula:
[0063] = + +
[0064] in, This represents the actual observed value of the i-th sample (e.g., a certain measurement index in biomedicine: length, thickness, etc.). and The penalty coefficient is... For static compensation, For dynamic compensation. in, For time, Based on corneal curvature, corresponding to low curvature, medium curvature, and high curvature groups. Intraocular pressure, To output the predicted value, These are the parameters to be optimized. Least squares loss measures the degree of fit between the model's predicted values and the actual values; the smaller the loss, the better the fit.
[0065] The constraint violation degree calculated in the above steps and The axial length compensation value is then substituted into the objective function to adjust the penalty coefficient. Specifically, if the violation of a constraint is high, its penalty coefficient is increased accordingly to correct this violation in the next optimization step. Conversely, if the violation is low, it can be appropriately decreased to allow the model to focus more on reducing prediction error.
[0066] Step 1042: Calculate the loss function corresponding to the objective function, and update the curve parameters of the preset myopia critical axial length curve by gradient descent based on the loss function until the objective function meets the stopping iteration condition, thus obtaining the target myopia critical axial length curve.
[0067] Regarding step 1042 above, in specific implementation, after adjusting the penalty coefficient in the objective function, the loss function corresponding to the objective function is calculated, and the curve parameters of the preset myopia critical axial length curve are updated by gradient descent based on the loss function. Here, gradient calculation and parameter update are expressed by the following formula:
[0068] in, This refers to all parameters in the preset myopia threshold axial length curve. For learning rate, The partial derivative of the parameter is the constraint violation degree calculated in the above steps, which is here. .
[0069] After each update, the new constraint violation degree is re-evaluated and calculated, and then the penalty coefficient is adjusted adaptively, forming a closed-loop feedback mechanism. Each adjustment of the penalty coefficient will calculate a new loss function, until the loss function is less than a preset threshold. At this point, the objective function is considered to have met the stopping iteration condition, and the target myopia critical axial length curve is obtained. The stopping iteration condition can also be that the number of iterations reaches a preset number, which is not specifically limited in this application.
[0070] Based on steps 1041-1042 above, after obtaining the axial length compensation value, the preset curve is corrected using the axial length compensation value as the anchor point. Then, by quantifying the degree of constraint violation of the preset curve in the smoothness of axial length growth rate and the relationship between ocular biomechanics, the penalty coefficient is dynamically adjusted, thereby guiding the gradient descent algorithm to iteratively update the curve parameters. The myopia critical axial length curve generated by this application is consistent with the individual measured trend at the key age point and also meets the reasonable physiological evolution law in medicine, thus having stronger rationality.
[0071] As an optional embodiment, after obtaining the target myopia threshold axial length curve, the generation method provided in this application further includes: When the target myopia critical axial length curve is detected to not meet the physiological constraints, a corresponding warning message is generated.
[0072] Regarding the above steps, in specific implementation, after obtaining the target critical axial length curve, it is determined whether the target critical axial length curve meets the physiological constraints. Specifically, the physiological constraints include the monotonous increase of axial length with age, i.e. The critical axial length increases with age. This also includes the decrease in axial length as corneal curvature increases. Increased curvature lowers the critical axial length. If the target critical axial length curve does not meet the above physiological constraints, a corresponding warning message is generated to alert the user that the generated curve may be abnormal.
[0073] The method for generating a myopia critical axial length curve provided in this application embodiment first obtains the current age and current eye condition data of the target user; wherein, the current eye condition data includes corneal curvature, current intraocular pressure, and current axial growth rate; then, based on the corneal curvature, a target curvature group for the target user is determined from multiple preset curvature groups; based on the current eye condition data, an axial length compensation value for the target user under the target curvature group is determined; wherein, the axial length compensation value includes a static compensation value and a dynamic compensation value; finally, the preset myopia critical axial length curve is optimized using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age.
[0074] This application obtains the target user's current age and multidimensional ocular status data, including corneal curvature, current intraocular pressure, and current axial growth rate. Users are grouped based on corneal curvature to determine a personalized axial compensation value, composed of static and dynamic compensation values. This axial compensation value is then used to optimize a preset myopia threshold axial curve, resulting in a personalized target myopia threshold axial curve for each user. Compared to traditional threshold curves that rely solely on statistical data from whole-age groups, this application significantly improves the accuracy and timeliness of myopia risk assessment, resolving errors caused by interpolation estimation for non-whole-age groups, thus enabling more precise early warning and intervention for myopia.
[0075] Please see Figure 2 , Figure 3 , Figure 2 This is one of the structural schematic diagrams of a device for generating a myopia threshold axial length curve provided in an embodiment of this application. Figure 3 This is a second schematic diagram of a device for generating a myopia threshold axial length curve provided in an embodiment of this application. Figure 2 As shown, the generating apparatus 200 includes: The data acquisition module 201 is used to acquire the target user's current age and current eye condition data; wherein, the current eye condition data includes corneal curvature, current intraocular pressure, and current axial length growth rate; Curvature grouping determination module 202 is used to determine the target curvature group of the target user from multiple preset curvature groups based on the corneal curvature; The axial length compensation value determination module 203 is used to determine the axial length compensation value of the target user under the target curvature group based on the current eye state data; wherein, the axial length compensation value includes a static compensation value and a dynamic compensation value; The target axial length curve generation module 204 is used to optimize the preset myopia critical axial length curve using the axial length compensation value and preset physiological constraints, so as to obtain the target myopia critical axial length curve of the target user at the current age.
[0076] Furthermore, when the target axial length curve generation module 204 is used to optimize the preset myopia critical axial length curve using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age, the target axial length curve generation module 204 is also used to: The constraint violation degree of the preset myopia critical axial length curve is calculated using the preset physiological constraint conditions, and the penalty coefficient in the objective function is adjusted based on the constraint violation degree and the axial length compensation value; wherein, the preset physiological constraint conditions include axial growth rate smoothness constraint and ocular biomechanical constraint. Calculate the loss function corresponding to the objective function, and update the curve parameters of the preset myopia critical axial length curve by gradient descent based on the loss function until the objective function meets the stopping iteration condition, thus obtaining the target myopia critical axial length curve.
[0077] Furthermore, when determining the axial length compensation value determination module 203 based on the current eye state data to determine the axial length compensation value of the target user under the target curvature group, the axial length compensation value determination module 203 is also used for: Based on the corneal curvature, the static compensation value for the target user under the target curvature group is determined; The dynamic compensation value is determined using the current age, the current intraocular pressure, and the current axial length growth rate. The sum of the static compensation value and the dynamic compensation value is taken as the axial length compensation value.
[0078] Furthermore, when the axial length compensation value determination module 203 is used to determine the static compensation value of the target user under the target curvature group based on the corneal curvature, the axial length compensation value determination module 203 is also used to: Based on the target curvature grouping, the corresponding target compensation coefficient is determined from a plurality of preset compensation coefficients; The product of the curvature difference and the target compensation coefficient is used as the static compensation value; wherein, the curvature difference is the difference between the corneal curvature reference value corresponding to the target curvature group and the corneal curvature of the target user.
[0079] Furthermore, when the axial length compensation value determination module 203 is used to determine the dynamic compensation value using the current age, the current intraocular pressure, and the current axial length growth rate, the axial length compensation value determination module 203 is also used to: Substitute the current intraocular pressure and the current age into the intraocular pressure compensation formula to obtain the intraocular pressure compensation value; Substitute the current axial length growth rate and the current age into the growth acceleration compensation formula to obtain the growth acceleration compensation value; The sum of the intraocular pressure compensation value and the growth acceleration compensation value is used as the dynamic compensation value.
[0080] Please see Figure 3 The generating device 200 further includes a curve detection module 205, which, after obtaining the target myopia threshold axial length curve, is used to: When the target myopia threshold axial length curve is detected to not meet the physiological constraints, a corresponding warning message is generated; wherein, the physiological constraints include the axial length increasing monotonically with age, and the axial length decreasing as the corneal curvature increases.
[0081] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.
[0082] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, they can perform the operations described above. Figure 1 The steps of the method for generating the myopia critical axial length curve in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.
[0083] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it can execute the steps of the method for generating the myopia critical axial length curve as shown in the above-mentioned method embodiment. For specific implementation details, please refer to the method embodiment, which will not be repeated here.
[0084] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0085] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0086] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0087] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0088] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0089] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for generating a critical axial length curve for myopia, characterized in that, The generation method includes: Obtain the target user's current age and current eye condition data; wherein, the current eye condition data includes corneal curvature, current intraocular pressure, and current axial length growth rate; The target curvature group of the target user is determined from multiple preset curvature groups based on the corneal curvature; The axial length compensation value for the target user under the target curvature group is determined based on the current eye state data; wherein, the axial length compensation value includes static compensation value and dynamic compensation value; The preset myopia critical axial length curve is optimized using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age.
2. The generation method according to claim 1, characterized in that, The step of optimizing the preset myopia threshold axial length curve using the axial length compensation value and preset physiological constraints to obtain the target myopia threshold axial length curve for the target user at the current age includes: The constraint violation degree of the preset myopia critical axial length curve is calculated using the preset physiological constraint conditions, and the penalty coefficient in the objective function is adjusted based on the constraint violation degree and the axial length compensation value; wherein, the preset physiological constraint conditions include axial growth rate smoothness constraint and ocular biomechanical constraint. Calculate the loss function corresponding to the objective function, and update the curve parameters of the preset myopia critical axial length curve by gradient descent based on the loss function until the objective function meets the stopping iteration condition, thus obtaining the target myopia critical axial length curve.
3. The generation method according to claim 1, characterized in that, Determining the axial length compensation value for the target user under the target curvature group based on the current eye state data includes: Based on the corneal curvature, the static compensation value for the target user under the target curvature group is determined; The dynamic compensation value is determined using the current age, the current intraocular pressure, and the current axial length growth rate. The sum of the static compensation value and the dynamic compensation value is taken as the axial length compensation value.
4. The generation method according to claim 3, characterized in that, The step of determining the static compensation value for the target user under the target curvature group based on the corneal curvature includes: Based on the target curvature grouping, the corresponding target compensation coefficient is determined from a plurality of preset compensation coefficients; The product of the curvature difference and the target compensation coefficient is used as the static compensation value; wherein, the curvature difference is the difference between the corneal curvature reference value corresponding to the target curvature group and the corneal curvature of the target user.
5. The generation method according to claim 3, characterized in that, Determining the dynamic compensation value using the current age, the current intraocular pressure, and the current axial length growth rate includes: Substitute the current intraocular pressure and the current age into the intraocular pressure compensation formula to obtain the intraocular pressure compensation value; Substitute the current axial length growth rate and the current age into the growth acceleration compensation formula to obtain the growth acceleration compensation value; The sum of the intraocular pressure compensation value and the growth acceleration compensation value is used as the dynamic compensation value.
6. The generation method according to claim 1, characterized in that, After obtaining the target myopia threshold axial length curve, the generation method further includes: When the target myopia threshold axial length curve is detected to not meet the physiological constraints, a corresponding warning message is generated; wherein, the physiological constraints include the axial length increasing monotonically with age, and the axial length decreasing as the corneal curvature increases.
7. A device for generating a myopia threshold axial length curve, characterized in that, The generating apparatus includes: The data acquisition module is used to acquire the target user's current age and current eye condition data; wherein, the current eye condition data includes corneal curvature, current intraocular pressure, and current axial length growth rate; The curvature grouping determination module is used to determine the target curvature group of the target user from multiple preset curvature groups based on the corneal curvature; An axial length compensation value determination module is used to determine the axial length compensation value of the target user under the target curvature group based on the current eye state data; wherein, the axial length compensation value includes a static compensation value and a dynamic compensation value; The target axial length curve generation module is used to optimize the preset myopia critical axial length curve using the axial length compensation value and preset physiological constraints, so as to obtain the target myopia critical axial length curve of the target user at the current age.
8. The generating apparatus according to claim 7, characterized in that, When the target axial length curve generation module is used to optimize the preset myopia critical axial length curve using the axial length compensation value and preset physiological constraints to obtain the target myopia critical axial length curve for the target user at the current age, the target axial length curve generation module is also used for: The constraint violation degree of the preset myopia critical axial length curve is calculated using the preset physiological constraint conditions, and the penalty coefficient in the objective function is adjusted based on the constraint violation degree and the axial length compensation value; wherein, the preset physiological constraint conditions include axial growth rate smoothness constraint and ocular biomechanical constraint. Calculate the loss function corresponding to the objective function, and update the curve parameters of the preset myopia critical axial length curve by gradient descent based on the loss function until the objective function meets the stopping iteration condition, thus obtaining the target myopia critical axial length curve.
9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of the method for generating the myopia critical axial length curve as described in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method for generating the critical axial length curve for myopia as described in any one of claims 1 to 6.