Myopia onset and progression prediction method and system based on sclera and / or corneal biomechanical material properties

Abstract

The application provides a myopia occurrence and progression prediction method and system based on sclera and / or corneal biomechanical material properties, and relates to the technical field of ophthalmic examination. The method comprises the following steps: acquiring biomechanical material property data, geometric shape data and physiological parameter data of the eye of a target object, constructing an individualized eyeball biomechanical model of the target object based on the biomechanical material property data, geometric shape data and physiological parameter data, and predicting the myopia occurrence risk, eye axis growth trend and / or myopia progression risk level by numerically simulating the stress field distribution and / or deformation response of the eye based on the individualized eyeball biomechanical model of the target object. The method can fuse individualized sclera and / or corneal biomechanical material properties, realize early identification of myopia occurrence risk and accurate prediction of myopia progression.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of ophthalmic examination technology, and in particular to a method and system for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea. Background Technology

[0002] Myopia is a major challenge in the global public health field. Therefore, achieving early and accurate prediction, risk stratification, and individualized intervention for myopia in large populations is a core requirement for reducing the incidence of high myopia and alleviating the social medical burden.

[0003] Currently, myopia prediction and risk assessment mainly rely on physician experience, which is highly subjective and has limited accuracy. Traditional myopia assessment is based primarily on the clinical experience of ophthalmologists, combined with data from one or more refraction tests (refractive error, axial length, etc.) to make a judgment. This method is highly dependent on the physician's professional level, lacks objective quantitative standards, and is prone to diagnostic bias; moreover, it can only assess risk based on the current refractive state, cannot achieve ultra-early warning, and has a relatively late intervention window.

[0004] Therefore, there is an urgent need for a method and system that can achieve early identification of the risk of myopia. Summary of the Invention

[0005] This invention provides a method and system for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea, in order to at least partially solve the above-mentioned problems.

[0006] The first aspect of this invention provides a method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea, the method comprising: The method involves acquiring biomechanical material property data, geometric morphology data, and physiological parameter data of the target object's eye. The biomechanical material property data includes at least the shear modulus distribution and / or anisotropic mechanical parameters of the sclera and / or cornea. The geometric morphology data includes at least one or more of the following: ocular surface morphology distribution, scleral thickness distribution, corneal thickness distribution, ocular curvature distribution, and axial length. The physiological parameter data includes at least intraocular pressure. Based on the biomechanical material property data, geometric morphology data, and physiological parameter data, an individualized biomechanical model of the target eyeball is constructed. Based on the individualized ocular biomechanical model of the target object, the stress field distribution and / or deformation response of the eye are calculated by numerical simulation to predict one or more of the following results: risk of myopia, trend of axial length growth, and risk level of myopia progression.

[0007] A second aspect of this invention provides a myopia occurrence and progression prediction system based on the biomechanical material properties of the sclera and / or cornea, the system comprising: The data acquisition module is used to acquire biomechanical material property data, geometric morphology data, and physiological parameter data of the target object's eye. The biomechanical material property data includes at least the shear modulus distribution and / or anisotropic mechanical parameters of the sclera and / or cornea; the geometric morphology data includes at least one or more of the following: eyeball surface morphology distribution, scleral thickness distribution, corneal thickness distribution, eyeball curvature distribution, and axial length; the physiological parameter data includes at least intraocular pressure. The model building module is used to construct an individualized biomechanical model of the target object's eyeball based on the biomechanical material property data, geometric morphology data, and physiological parameter data. The prediction module is used to predict one or more of the following results based on the individualized ocular biomechanical model of the target object, by numerically simulating the stress field distribution and / or deformation response of the eye: risk of myopia, trend of axial length growth, and risk level of myopia progression.

[0008] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes a method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea as described in the first aspect of the present invention.

[0009] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea as described in the first aspect of the present invention.

[0010] A fifth aspect of the present invention provides a computer program product, including a computer program / instructions, which are implemented by a processor as the steps in the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea as described in the first aspect of the present invention.

[0011] Compared with the prior art, the present invention has the following beneficial effects: (1) Predictive window shift: By incorporating the biomechanical material properties of the sclera and / or cornea, it is possible to capture mechanical warning signals before the onset of myopia (before morphological changes), realize the early identification of the risk of myopia, and provide a basis for "prevention of disease".

[0012] (2) Covers the entire population: It can be applied to both non-myopic people (predicting the risk of myopia) and myopic people (predicting the rate of progression), with a wide range of applications.

[0013] (3) High degree of individualization: The model is constructed based on the measured mechanical parameters and geometric shape of individuals, which overcomes the problem of poor individual adaptability of traditional group statistical models and truly realizes accurate prediction of "one person, one model".

[0014] (4) Improved prediction accuracy: By integrating mechanical and morphological information, it has higher prediction accuracy than prediction methods that rely solely on linear extrapolation of axial length.

[0015] (5) Mechanism-driven and highly interpretable: The prediction model based on biomechanical mechanism has strong extrapolation ability and interpretability, and can output intermediate results such as stress field distribution and regional stress concentration mode.

[0016] (6) Flexible data sources: There are no restrictions on the way biomechanical material properties are obtained, and it is compatible with a variety of imaging technologies. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the steps in the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea provided in the embodiments of the present invention; Figure 2a and Figure 2b This is a schematic diagram illustrating the input of scleral and / or corneal biomechanical material properties in the myopia occurrence and progression prediction method based on scleral and / or corneal biomechanical material properties provided in this embodiment of the invention. Figure 2a This is a schematic diagram of scleral zonation. Figure 2b This is a pseudo-color image of the spatial distribution of the anterior scleral shear modulus.

[0019] Figure 3a and Figure 3b This is a schematic diagram illustrating the construction of an individualized ocular biomechanical model in the myopia occurrence and progression prediction method based on the biomechanical material properties of the sclera and / or cornea provided in this embodiment of the invention. Figure 3a This is a map showing the distribution of scleral thickness. Figure 3b A schematic diagram showing the setting of boundary conditions and loads for the model.

[0020] Figure 4a and Figure 4b This is a schematic diagram of the prediction result output interface in the myopia occurrence and progression prediction method based on the biomechanical material properties of the sclera and / or cornea provided in this embodiment of the invention, wherein... Figure 4a This is a curve showing the trend of axial length growth. Figure 4b This interface outputs the risk level of myopia occurrence and progression.

[0021] Figure 5 This is a comparison chart of the prediction accuracy between the myopia occurrence and progression prediction method based on the biomechanical material properties of the sclera and / or cornea provided in this embodiment of the invention and the traditional linear extrapolation method. Detailed Implementation

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] In this embodiment of the invention, the following shortcomings are considered in current myopia-related prediction technologies: (1) Lagging prediction window: Existing technologies mainly predict the progression of myopia in people who are already myopic. For children who are not yet myopic, there is a lack of effective tools to predict the risk of myopia. When morphological indicators change significantly, myopia has often entered an irreversible stage, and the early intervention window has been missed.

[0024] (2) Lack of mechanical information: Existing prediction models do not incorporate tissue biomechanical material properties, while changes in mechanical properties may precede morphological changes and are a more sensitive earlier indicator of the occurrence and progression of myopia.

[0025] (3) Low degree of individualization: Most existing prediction models are statistical models based on large sample populations, which are difficult to reflect the unique geometric shape and material distribution characteristics of individual eyeballs, thus limiting the prediction accuracy.

[0026] (4) Lack of a predictive framework for fusion of mechanical and morphological parameters: There is no systematic approach to integrate individualized scleral and / or corneal mechanical parameters with geometric morphological parameters for predicting the risk and progression of myopia.

[0027] The core structural feature of myopia progression is the continuous elongation of the axial length. Studies have shown that axial length elongation is closely related to changes in the mechanical properties of the sclera. The collagen fiber remodeling and decreased effective stiffness of the sclera make it more prone to expansion under intraocular pressure, which in turn leads to axial length elongation.

[0028] Therefore, embodiments of the present invention propose a method and system that can integrate individualized biomechanical material properties of the sclera and / or cornea to achieve early identification of myopia risk and accurate prediction of its progression.

[0029] Specifically, such as Figure 1The diagram illustrates a flowchart of the steps involved in predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea, as proposed in this invention. By acquiring multimodal ocular data, constructing individualized biomechanical models, and performing numerical simulations, the method achieves quantitative prediction and assessment of myopia risk in target individuals. Specifically, the method includes the following steps: S101, acquire biomechanical material property data, geometric morphology data and physiological parameter data of the target object's eye.

[0030] In this embodiment of the invention, the biomechanical material property data includes at least the shear modulus distribution and / or anisotropic mechanical parameters of the sclera and / or cornea.

[0031] The shear modulus distribution is spatially resolved three-dimensional distribution data. The shear modulus varies point-by-point in the three-dimensional space of the sclera and / or cornea, with a corresponding value at any coordinate point (x, y, z), forming a visualized 3D hardness distribution field. The shear modulus distribution of the anterior sclera is shown below. Figure 2a and Figure 2b As shown. Among them. Figure 2a The divisions of the anterior, middle, and posterior parts of the sclera were clearly defined; Figure 2b The spatial non-uniform field distribution of the anterior scleral shear modulus is illustrated, serving as the core mechanical property input of the model.

[0032] The anisotropic mechanical parameters are used to characterize the differences in the mechanical properties of materials in different directions.

[0033] In this embodiment of the invention, the geometric morphology data includes at least one or more of the following: eyeball surface morphology distribution, scleral thickness distribution, corneal thickness distribution, eyeball curvature distribution, and axial length.

[0034] The ocular surface morphology is composed of a continuous three-dimensional spatial coordinate lattice, characterized as a two-dimensional curved surface embedded in three-dimensional space. The scleral thickness distribution and corneal thickness distribution are data distributed point-by-point on the ocular surface morphology; specifically, the thickness value has a corresponding value at any coordinate on the surface of the sclera and / or cornea, such as... Figure 3a As shown, it illustrates the scleral thickness distribution extracted based on individual measured data, indicating the thickness values ​​of different regions under the current cross-section.

[0035] In this embodiment of the invention, the physiological parameter data includes at least intraocular pressure.

[0036] In this embodiment of the invention, the method of acquiring the above data is not limited, and can be one or more of optical coherence elastography, ultrasonic elastography, magnetic resonance elastography, optical coherence tomography, ultrasonic biomicroscopy, in vitro mechanical testing, or literature reference values.

[0037] The scleral thickness distribution is obtained by optical coherence tomography combined with an image segmentation algorithm, which includes an automatic segmentation method based on deep learning.

[0038] S102, Based on the biomechanical material property data, geometric morphology data and physiological parameter data, construct an individualized biomechanical model of the target object's eyeball.

[0039] In this embodiment of the invention, an individualized ocular biomechanical model can be constructed. The model parameters of the individualized ocular biomechanical model can be updated according to individual measured data, so that each target object corresponds to an exclusive model.

[0040] In this embodiment of the invention, step S102 specifically includes the following sub-steps: S1021, Establish a biomechanical model of the eyeball. The model type includes, but is not limited to: fiber-reinforced thin shell model, finite element model, boundary element model, or reduced-order mechanical model. S1022, the biomechanical material property data, geometric morphology data, and physiological parameter data of the target object's eye are used as model inputs, such as... Figure 3b As shown, an individualized ocular biomechanical model corresponding to the actual state of the target individual is constructed. The model's load and boundary condition settings are shown, with intraocular pressure applied to the inner surfaces of the cornea and sclera, and corresponding displacement constraints set in the equatorial region and posterior pole.

[0041] In this embodiment of the invention, the fiber-reinforced thin-shell model is constructed based on the dynamics theory of curved thin-shells, introducing fiber reinforcement and anisotropic constitutive model into the traditional thin-shell model; it can describe the stress-strain response and deformation characteristics of the eyeball under intraocular pressure and external force, and incorporates the fiber reinforcement characteristics and material anisotropy of the sclera and / or cornea into the governing equations. It is specifically used for predicting the risk of myopia and the trend of axial elongation.

[0042] S103, based on the individualized ocular biomechanical model of the target object, calculate the stress field distribution and / or deformation response of the eye through numerical simulation, and predict one or more of the following results: risk of myopia, trend of axial length growth, and risk level of myopia progression.

[0043] In this embodiment of the invention, numerical simulation can be performed based on the individualized ocular biomechanical model using methods such as the finite element method or the boundary element method to solve the control equations under specific physiological parameter boundary conditions and calculate the stress field distribution and / or deformation response of the eye.

[0044] In one specific embodiment, step S103 includes the following sub-steps: S1031, based on the individualized ocular biomechanical model of the target object, the shear modulus distribution is used as the material property input of the model region, the ocular surface morphology and scleral thickness distribution are used as the geometric input, the intraocular pressure is used as the load boundary condition, and displacement constraints are set in the equatorial region and the posterior pole. The stress distribution of each region of the ocular body under physiological load is calculated. Then, through sensitivity analysis, stress field extreme value identification or deviation comparison with normal reference values, key regions are determined. The key regions include, but are not limited to, the anterior sclera, the middle sclera, the posterior sclera, the equatorial region, and the posterior pole.

[0045] S1032, based on the shear modulus, anisotropy index and stress of the key region of the target object, predict the probability of axial elongation of the target object within multiple preset time windows in the future; S1033, if the shear modulus of the key area is lower than the normal reference value for the same age, the anisotropy index is lower than the normal reference value for the same age, and the stress is higher than the normal reference value, the target object is determined to be at high risk of developing myopia. S1034, based on the shear modulus, anisotropy index and stress of the key area of ​​the target object, determine the probability of myopia development in the target object within one or more preset time windows in the future.

[0046] In this embodiment of the invention, based on ocular biomechanical state parameters (including: σ critical , G critical , γ critical , Δt Assess the probability of axial length growth (GP); in, σ critical For stress in critical areas; G critical The average shear modulus of the critical region; γ critical Anisotropy index for key regions; Δt To predict the time window, a machine learning model or empirical formula trained on a large sample of historical follow-up dataset can be used to assess the probability of axial elongation with ocular biomechanical parameters as input.

[0047] Specifically, ocular biomechanical state assessment data (shear modulus, anisotropy index, and stress in key areas) from large-sample historical follow-up data, along with the corresponding sample subjects' axial length growth within a preset time window, can be used as samples to train a machine learning model, yielding the desired results. f 1, then f 1. The probability of axial elongation can be predicted based on ocular biomechanical assessment.

[0048] In this embodiment of the invention, if the calculated stress in the critical region is higher than the normal reference value, and the shear modulus of the critical region obtained by the data acquisition module is lower than the normal reference value for the same age, and the anisotropy index is lower than the normal reference value for the same age, the target object is determined to be at high risk of developing myopia.

[0049] In this embodiment of the invention, the probability of myopia development in the target object within one or more preset time windows can be determined based on a pre-obtained machine learning model or empirical formula.

[0050] Specifically, it can be based on the extraction of the first... i A mechanical or morphological characteristic variable X i ( i = 1, 2, ..., n) Output the probability of myopia occurring within a preset future time window (e.g., 1 year, 2 years).

[0051] Among them, X i Including but not limited to: key region stress, key region average shear modulus, key region anisotropy index, and prediction time window; specifically, this can be achieved using machine learning models or empirical formulas with X as the key region. i The input and output are the probability of developing myopia within a preset time window (e.g., 1 year, 2 years). The machine learning model can be a logistic regression model. ; in β i The i-th regression coefficient is obtained by training with a large sample historical follow-up dataset.

[0052] In conjunction with the above embodiments, in another specific embodiment, step S103 further includes the following sub-steps: S1035, the target object is determined based on the shear modulus, anisotropy index and stress of the key region of the target object, and the axial length growth of the target object is predicted within multiple preset time windows in the future. S1036, Determine the axial length growth trend based on the axial length growth within the multiple preset time windows in the future; S1037, Determine the risk level of myopia progression based on the axial length growth trend.

[0053] In this embodiment of the invention, the amount of axial length growth within a preset time window (such as 3 months, 6 months, or 12 months) can be predicted based on ocular biomechanical state parameters (shear modulus of key regions, anisotropy index, and stress of key regions). Specifically, the amount of axial length growth can be predicted based on machine learning models or empirical formulas, using ocular biomechanical state parameters as input.

[0054] Specifically, ocular biomechanical state assessment data (shear modulus, anisotropy index, and stress in key areas) from large-sample historical follow-up data, along with the corresponding axial length growth of the sample subjects within a preset time window, can be used as samples to train a machine learning model, yielding... f 3, then f 3. Axial axial length growth can be predicted based on ocular biomechanics.

[0055] For those who are already nearsighted, the rate of myopia progression can be predicted based on the biomechanical state of the eye.

[0056] In this embodiment of the invention, a risk level can be further output based on the predicted axial length growth trend. The risk levels include rapidly progressive, moderately progressive, and stable.

[0057] In one specific embodiment, the method further includes: S104, acquire updated biomechanical material property data, geometric morphology data and physiological parameter data of the target object at subsequent follow-up time points, and use the updated data to dynamically update the individualized ocular biomechanical model to achieve rolling risk prediction.

[0058] In this embodiment of the invention, updated biomechanical material properties, geometric morphology, and physiological parameters of the target object can be obtained at subsequent follow-up time points. The updated data is used to dynamically update the individualized ocular biomechanical model, achieving rolling risk prediction and gradually improving prediction accuracy as follow-up data accumulates.

[0059] The following describes the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea provided by the present invention, based on specific embodiments: Example 1: Longitudinal prediction validation based on animal models 1. Experimental Subjects and Model Construction A monocular negative lens defocusing rabbit eye model was constructed using six New Zealand white rabbits. The experimental eye was fitted with a -10 D negative lens to induce myopia, while the contralateral eye served as a self-control. The experiment lasted for eight weeks.

[0060] 2. Data Acquisition The following measurements were taken at baseline (week 0) and at weeks 2, 4, 6, and 8: (1) Biomechanical material property data: The three-dimensional shear modulus distribution and anisotropy parameters of the anterior sclera and equatorial region were obtained using an optical coherent elastography system. Specifically, the center wavelength of the swept-frequency light source OCT system was 1310 nm, the A-scan rate was 1 MHz, and elastic waves were excited at 2-3 mm outside the limbus of the cornea and sclera by air-coupled pulsed ultrasound. Three-dimensional spatiotemporal displacement field data were collected, and the spatial distribution map of shear modulus was obtained by full waveform inversion.

[0061] (2) Geometric morphological data: Three-dimensional images of the anterior sclera were acquired using OCT with a swept frequency light source. The boundaries between the anterior and posterior surfaces of the sclera were extracted using an image segmentation algorithm, and the scleral thickness at each spatial location was calculated to generate a scleral thickness distribution map. The axial length was measured using an A-mode ultrasound biometer.

[0062] (3) Physiological parameters: Intraocular pressure was measured using a handheld tonometer, and each measurement was repeated 3 times and the average value was taken.

[0063] 3. Construction and calculation of individualized ocular biomechanical models A finite element model of the eyeball was constructed using baseline geometric data. The model employed a fiber-reinforced hyperelastic material constitutive model. The shear modulus distribution of the anterior sclera and equatorial region measured at baseline was used as the material property input for the model region, and intraocular pressure was used as the load boundary condition. Displacement constraints were set at the equatorial region and the posterior pole. The stress distribution of the eyeball in each region under physiological load was numerically calculated.

[0064] 4. Prediction and Verification Using 4 weeks and 8 weeks as prediction time windows (Δt), the average shear modulus and anisotropy index of the key region measured by the optical coherence elastography system, as well as the stress distribution of the key region calculated above, were input into the axial length growth trend prediction module to predict the axial length growth at weeks 4 and 8. The comparison between the prediction results and the actual measured values ​​is shown in Table 1.

[0065]

[0066] Table 1. Comparison of model-predicted axial length growth with actual measurements (unit: mm) The results showed that the prediction error was 0.01 mm in week 4 and 0.02 mm in week 8, with a correlation coefficient R² > 0.85 between the predicted and actual measurements. A schematic diagram of the prediction result output interface can be found below. Figure 4a and Figure 4b ..in Figure 4a The curve showing the growth trend of axial length illustrates the evolution trend of axial length within the prediction time window; Figure 4b This is an interface for displaying the risk level of myopia development and progression, showing the probability of myopia onset, the risk level of onset, the risk level of progression, and individualized recommended treatment plans. This interface is a functional layout illustration and does not limit the specific style of the actual software interface.

[0067] The prediction results for week 8 of this invention are compared with a prediction method that uses linear extrapolation based solely on baseline axial length. Figure 5As shown, a performance comparison between the method of this invention and traditional prediction methods is illustrated. By comparing the mean absolute error of axial length growth prediction, the significant contribution of incorporating biomechanical material properties to improving prediction accuracy is clearly demonstrated. It can be seen that in the prediction at week 8, the mean absolute error of the method of this invention is 0.02 mm, while the mean absolute error of the linear extrapolation method is 0.08 mm, representing a reduction in prediction error of approximately 75% for the method of this invention. The results indicate that incorporating biomechanical material properties significantly improves the accuracy of axial length growth prediction.

[0068] Example 2: Prediction of the risk of myopia development in children without myopia 1. Subjects An 8-year-old child without myopia, whose parents are both myopic, with an equivalent spherical power of +0.50 D and an axial length of 22.8 mm.

[0069] 2. Data Acquisition (1) Biomechanical material property data: The shear modulus distribution of the anterior sclera and equatorial region was measured using an optical coherence elastography system. The results showed that the average shear modulus in the equatorial region was 48.2 kPa, which was significantly lower than the normal reference value for the same age (65.2 ± 5.3 kPa). The anisotropy index was 0.55, which was lower than the normal reference value (0.75 ± 0.08).

[0070] (2) Geometric data: The scleral thickness distribution was obtained by scanning frequency light source OCT. The results showed that the thickness in the equatorial region was 0.48 mm (normal reference value 0.52 ± 0.03 mm), which was relatively thin; the axial length was 22.8 mm (average of 22.5 mm for the same age, which was slightly longer).

[0071] (3) Physiological parameters: Intraocular pressure 16.2 mmHg (normal range).

[0072] 3. Construction and calculation of individualized ocular biomechanical models The above data are input into an individualized ocular biomechanics model to simulate the ocular deformation response under intraocular pressure. The stress distribution in key areas is calculated.

[0073] 4. Prediction Results Using a 2-year prediction time window (Δt), the average shear modulus, anisotropy index, and stress distribution of the key region obtained from optical coherence elastography (OCE) were input into the axial length growth trend prediction module and the myopia risk prediction module, respectively, to predict the axial length growth and the probability of myopia occurrence within 2 years. The prediction results are shown in Table 2 below.

[0074]

[0075] Table 2. Predictive results of axial elongation and myopia incidence probability 5. Conclusion The subject's scleral biomechanics showed softening, reduced anisotropy, and stress concentration in the equatorial region, indicating significant potential for axial elongation. The predicted probability of developing myopia within two years is 78% (high risk). Recommendations: Increase outdoor activity time and have axial elongation and scleral biomechanics checked every 6 months.

[0076] Example 3: Retrospective validation based on adolescent clinical data 1. Research Subjects Fifty myopic children and adolescents aged 6 to 16 years were included in this study. All participants had a standardized follow-up record of at least 12 consecutive months. Inclusion criteria: equivalent spherical power ≤ -0.50 D, with at least 12 months of follow-up records. Exclusion criteria: coexisting ocular diseases affecting scleral structure or intraocular pressure, such as keratoconus, glaucoma, or uveitis; history of refractive surgery; or history of severe ocular trauma.

[0077] 2. Data Acquisition (1) Biomechanical material property data: At baseline, the three-dimensional shear modulus distribution and anisotropy parameters of the anterior sclera were measured using an optical coherence elastography system. The measurement area covered the outer edge of the limbus to the equator, with a spatial resolution better than 100 μm.

[0078] (2) Geometric morphological data: During the baseline period, the surface morphology of the eyeball, the distribution of scleral thickness and the distribution of corneal thickness were obtained by sweep frequency light source OCT; the axial length was measured by optical coherence biometry.

[0079] (3) Physiological parameters: Intraocular pressure was measured using a non-contact tonometer during the baseline period.

[0080] 3. Construction and prediction of individualized ocular biomechanical models An individualized digital twin model of ocular biomechanics was constructed for each subject. The model employed the dynamics theory of curved fiber-reinforced thin shells, using the anterior scleral shear modulus distribution as the regional material property input, the ocular surface morphology and scleral thickness distribution as the geometric input, and intraocular pressure as the load input. The model calculated the stress field distribution and axial deformation trend of the eyeball under intraocular pressure. Using a 12-month prediction time window (Δt), the average shear modulus and anisotropy index of key regions measured by an optical coherence elastography system, along with the numerically calculated circumferential stress distribution of key regions, were input into the axial growth trend prediction module, outputting the predicted axial growth value for the next 12 months.

[0081] 4. Predictive Performance Evaluation The predictive efficacy of the model was evaluated using actual 12-month axial length growth as the gold standard. Subjects were divided into three groups according to their actual axial length growth rate: rapid progression group (≥0.30 mm / year, n = 18), moderate progression group (0.10-0.30 mm / year, n = 16), and stable group (≤0.10 mm / year, n = 16).

[0082] Receiver operating characteristic (ROC) curve analysis showed that the area under the curve (AUC) for the rapid progression and stable disease groups predicted by the model of this invention was 0.89 (95% CI: 0.81–0.96). As a control, the AUC based solely on linear extrapolation of baseline axial length was 0.71 (95% CI: 0.60–0.82). The difference in AUC between the two groups was statistically significant (p<0.01). Calibration curves showed that the predicted probabilities of the model of this invention were in good agreement with the actual observed probabilities, with a Hosmer-Lemeshow p-value of 0.63.

[0083] 5. Screening of key mechanical indicators Multivariate logistic regression analysis was conducted, using the predicted 12-month axial length growth as the dependent variable. Variables obtained at baseline, including the mean shear modulus of key regions, biomechanical anisotropy index, stress in key regions, axial deformation, axial length, and intraocular pressure, were used as candidate independent variables. Stepwise regression (inclusion criterion α = 0.05, exclusion criterion α = 0.10) was used to screen for independent predictors. After adjusting for baseline axial length and intraocular pressure, the key biomechanical indicators that contributed most to predicting rapid myopia progression were identified as: mean shear modulus of the anterior sclera equatorial region (OR = 3.5 per 10 kPa decrease, 95% CI: 1.8–6.9, p<0.001) and biomechanical anisotropy index (OR = 2.8 per 0.1 decrease, 95% CI: 1.4–5.6, p<0.01).

[0084] A simplified risk stratification standard is established based on the above indicators: High risk: Average shear modulus in the equatorial region is below 45 kPa and anisotropy index is below 0.6. Medium risk: Average shear modulus in the equatorial region 45-65 kPa or anisotropy index 0.6-0.8 Low risk: Equatorial region average shear modulus above 65 kPa and anisotropy index above 0.8. The risk stratification criterion has a sensitivity of 83.3% and a specificity of 81.3% on the validation set.

[0085] Example 4: Rolling Prediction Based on Dynamic Updates 1. Data Acquisition and Baseline Model Construction Following the methods of Example 2 or Example 3, biomechanical material property data, geometric morphology data, and physiological parameter data of the subjects during the baseline period were obtained to construct an initial individualized ocular biomechanical model.

[0086] 2. Follow-up and model updates Updated data were obtained from the subjects at follow-up months 3, 6, and 9, including: Updated critical region shear modulus distribution Updated axial length Updated intraocular pressure The initial model was calibrated using updated data from month 3 to align the model's material properties with the subjects' current mechanical state. The calibrated model was then used to predict axial length growth trends from month 3 to month 6. After obtaining new measurement data in month 6, the model was updated again to predict axial length growth trends from month 6 to month 9. This process was repeated to achieve rolling risk prediction.

[0087] 3. Predictive effect A rolling predictive analysis of 20 subjects showed the following results: The cumulative 12-month prediction error for a single forecast (using only baseline data) is 0.08 ± 0.05 mm. The 12-month cumulative forecast error for rolling forecasts (using data updated in 3, 6, and 9 months) is 0.04 ± 0.03 mm. The dynamic update strategy reduced the prediction error by about 50%, indicating that the model prediction accuracy can be gradually improved as follow-up data accumulates.

[0088] Based on the same inventive concept, embodiments of the present invention also provide a myopia occurrence and progression prediction system based on the biomechanical material properties of the sclera and / or cornea, the system comprising: The data acquisition module is used to acquire biomechanical material property data, geometric morphology data, and physiological parameter data of the target object's eye. The biomechanical material property data includes at least the shear modulus distribution and / or anisotropic mechanical parameters of the sclera and / or cornea; the geometric morphology data includes at least one or more of the following: eyeball surface morphology distribution, scleral thickness distribution, corneal thickness distribution, eyeball curvature distribution, and axial length; the physiological parameter data includes at least intraocular pressure. The model building module is used to construct an individualized biomechanical model of the target object's eyeball based on the biomechanical material property data, geometric morphology data, and physiological parameter data. The prediction module is used to predict one or more of the following results based on the individualized ocular biomechanical model of the target object, by numerically simulating the stress field distribution and / or deformation response of the eye: risk of myopia, trend of axial length growth, and risk level of myopia progression.

[0089] Optionally, the model building module is used for: Establish a biomechanical model of the eyeball. The model types include, but are not limited to: fiber-reinforced thin-shell model, finite element model, boundary element model, or reduced-order mechanical model. The biomechanical material properties, geometric morphology, and physiological parameters of the target object's eye are used as model inputs to construct an individualized ocular biomechanical model corresponding to the actual state of the target object.

[0090] Optionally, the fiber-reinforced thin-shell model is constructed based on the dynamics theory of curved thin-shells, describing the stress-strain response and deformation characteristics of the eyeball under intraocular pressure and external force, and incorporating the fiber reinforcement characteristics and material anisotropy of the sclera and / or cornea into the governing equations.

[0091] Optionally, the prediction module is used to: Based on the individualized biomechanical model of the target object, the shear modulus distribution is used as the material property input of the model region, the surface morphology of the eyeball and the scleral thickness distribution are used as the geometric input, the intraocular pressure is used as the load boundary condition, and displacement constraints are set in the equatorial region and the posterior pole to calculate the stress distribution of each region of the eyeball under physiological load. Based on the shear modulus, anisotropy index and stress of the key region of the target object, the probability of axial elongation of the target object in one or more preset time windows in the future is predicted. If the shear modulus in the critical area is lower than the normal reference value for the same age, the anisotropy index is lower than the normal reference value for the same age, and the stress is higher than the normal reference value, the target object is determined to be at high risk of developing myopia. Based on the shear modulus, anisotropy index, and stress of the key region of the target object, the probability of myopia development in the target object within one or more preset time windows in the future is determined.

[0092] Optionally, the prediction module is used to: The target object is determined based on the shear modulus, anisotropy index and stress in the key region of the target object, and the axial length growth of the target object is predicted within multiple preset time windows in the future. Based on the axial length growth within the aforementioned multiple preset time windows, the axial length growth trend is determined. The risk level of myopia progression is determined based on the aforementioned axial length growth trend.

[0093] Optionally, the system further includes: The update module is used to acquire updated biomechanical material property data, geometric morphology data and physiological parameter data of the target object at subsequent follow-up time points, and use the updated data to dynamically update the individualized ocular biomechanical model to achieve rolling risk prediction.

[0094] Optionally, the scleral thickness distribution is spatially resolved three-dimensional distribution data, obtained by optical coherence tomography combined with an image segmentation algorithm, wherein the image segmentation algorithm includes an automatic segmentation method based on deep learning.

[0095] The present invention provides an embodiment of a myopia occurrence and progression prediction device based on the biomechanical material properties of the sclera and / or cornea. This device can be applied to any device with data processing capabilities, such as a computer. The device embodiment can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of any data processing device loading the corresponding computer program instructions from non-volatile memory into memory for execution.

[0096] Based on the same inventive concept, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea as described in any of the above embodiments.

[0097] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea as described in any of the above embodiments.

[0098] Based on the same inventive concept, embodiments of the present invention provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps in the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea as described in any of the above embodiments.

[0099] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0100] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (apparatus), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable terminal device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable terminal device to cause a series of operational steps to be performed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0104] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0105] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0106] The foregoing has provided a detailed description of a method and system for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea, characterized in that, The method includes the following steps: Acquire biomechanical material property data, geometric morphology data, and physiological parameter data of the target object's eye; the biomechanical material property data includes at least the shear modulus distribution and / or anisotropic mechanical parameters of the sclera and / or cornea; the geometric morphology data includes at least one or more of the following: eyeball surface morphology distribution, scleral thickness distribution, corneal thickness distribution, eyeball curvature distribution, and axial length; the physiological parameter data includes at least intraocular pressure. Based on the biomechanical material property data, geometric morphology data, and physiological parameter data, an individualized biomechanical model of the target eyeball is constructed. Based on the individualized ocular biomechanical model of the target object, the stress field distribution and / or deformation response of the eye are calculated by numerical simulation to predict one or more of the following results: risk of myopia, trend of axial length growth, and risk level of myopia progression.

2. The method according to claim 1, characterized in that, Based on the biomechanical material property data, geometric morphology data, and physiological parameter data, an individualized biomechanical model of the target object's eyeball is constructed, including: Establish a biomechanical model of the eyeball. The model types include, but are not limited to: fiber-reinforced thin-shell model, finite element model, boundary element model, or reduced-order mechanical model. The biomechanical material properties, geometric morphology, and physiological parameters of the target object's eye are used as model inputs to construct an individualized ocular biomechanical model corresponding to the actual state of the target object.

3. The method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea according to claim 2, characterized in that, The fiber-reinforced thin-shell model is constructed based on the dynamics theory of curved thin shells. It describes the stress-strain response and deformation characteristics of the eyeball under intraocular pressure and external force, and incorporates the fiber reinforcement characteristics and material anisotropy of the sclera and / or cornea into the governing equations.

4. The method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea according to claim 1, characterized in that, Based on the individualized ocular biomechanical model of the target object, the risk of myopia is predicted by numerical simulation to calculate the stress field distribution and / or deformation response of the eye, including: Based on the individualized ocular biomechanical model of the target object, the shear modulus distribution is used as the material property input of the model region, the ocular surface morphology and scleral thickness distribution are used as the geometric input, and the intraocular pressure is used as the load boundary condition. Displacement constraints are set in the equatorial region and the posterior pole to calculate the stress distribution of each region of the ocular body under physiological load. Then, the key regions are determined, including but not limited to the anterior sclera, middle sclera, posterior sclera, equatorial region, and posterior pole. Based on the shear modulus, anisotropy index and stress of the key region of the target object, the probability of axial elongation of the target object in one or more preset time windows in the future is predicted. If the shear modulus in the critical area is lower than the normal reference value for the same age, the anisotropy index is lower than the normal reference value for the same age, and the stress is higher than the normal reference value, the target object is determined to be at high risk of developing myopia. Based on the shear modulus, anisotropy index, and stress of the key region of the target object, the probability of myopia development in the target object within one or more preset time windows in the future is determined.

5. The method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea according to claim 4, characterized in that, Based on the individualized ocular biomechanical model of the target object, the stress field distribution and / or deformation response of the eye are calculated through numerical simulation to predict the trend of axial elongation and the risk level of myopia progression, including: The target object is determined based on the shear modulus, anisotropy index and stress in the key region of the target object, and the axial length growth of the target object is predicted within multiple preset time windows in the future. Based on the axial length growth within the aforementioned multiple preset time windows, the axial length growth trend is determined. The risk level of myopia progression is determined based on the aforementioned axial length growth trend.

6. The method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea according to claim 1, characterized in that, The method further includes: The updated biomechanical material properties, geometric morphology, and physiological parameters of the target subject are obtained at subsequent follow-up time points. The updated data is then used to dynamically update the individualized ocular biomechanical model to achieve rolling risk prediction.

7. The method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea according to claim 1, characterized in that, The scleral thickness distribution is spatially resolved three-dimensional distribution data, obtained by optical coherence tomography combined with an image segmentation algorithm, which includes an automatic segmentation method based on deep learning.

8. A myopia occurrence and progression prediction system based on the biomechanical material properties of the sclera and / or cornea, characterized in that, The system includes: The data acquisition module is used to acquire biomechanical material property data, geometric morphology data, and physiological parameter data of the target object's eye. The biomechanical material property data includes at least the shear modulus distribution and / or anisotropic mechanical parameters of the sclera and / or cornea; the geometric morphology data includes at least one or more of the following: eyeball surface morphology distribution, scleral thickness distribution, corneal thickness distribution, eyeball curvature distribution, and axial length; the physiological parameter data includes at least intraocular pressure. The model building module is used to construct an individualized biomechanical model of the target object's eyeball based on the biomechanical material property data, geometric morphology data, and physiological parameter data. The prediction module is used to predict one or more of the following results based on the individualized ocular biomechanical model of the target object, by numerically simulating the stress field distribution and / or deformation response of the eye: risk of myopia, trend of axial length growth, and risk level of myopia progression.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea as described in any one of claims 1-7.

10. A readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for predicting the occurrence and progression of myopia based on the biomechanical material properties of the sclera and / or cornea as described in any one of claims 1-7.

Images