A corneal biomechanical state evaluation method, device, equipment and medium
By segmenting the corneal layers and calculating the strain ratio, the problem of the inability to assess the mechanical coupling state between the corneal layers in the existing technology has been solved, enabling accurate assessment of the progression trend of keratoconus and improving the interpretability of risk interpretation and the automation of assessment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- WENZHOU MEDICAL UNIV
- Filing Date
- 2026-05-12
- Publication Date
- 2026-07-31
AI Technical Summary
Existing technologies cannot effectively extract indicators that reflect the mechanical coupling state between corneal layers from single measurement data, resulting in an inability to accurately assess the progression trend of keratoconus. Furthermore, the physical meaning of existing indicators is unclear and their interpretability is poor.
By acquiring a sequence of cross-sectional images of the cornea under mechanical load, interlaminar segmentation is performed to track the displacement of the anterior and posterior stromal regions, the interlaminar strain ratio (LSR) is calculated, and the dynamic evolution of the biomechanical state is assessed by combining the rate of change from multiple measurements.
It significantly improves the interpretability of risk assessment, can sensitively capture early local mechanical imbalance signals, provides clear mechanical meaning assessment, is easy to deploy on existing equipment, and enables automated and objective assessment of corneal change trends.
Smart Images
Figure CN122492645A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of medical assessment, specifically relating to a method, device, equipment, and medium for processing corneal biomechanical state data. Background Technology
[0002] Keratoconus is a corneal structural abnormality characterized by progressive thinning and cone-shaped bulging of the cornea, and is one of the leading causes of vision impairment in adolescents. For individuals with potential risk of progression or a genetic predisposition, early identification of risk based on objective examination data will help clinicians develop more proactive and appropriate follow-up observation plans or intervention programs.
[0003] Currently, conventional methods for assessing corneal mechanical properties primarily rely on the measurement of macroscopic biomechanical parameters. For example, the clinically used visual corneal biomechanical analyzer (Corvis ST) can record the overall deformation process of the cornea under airflow loads, and derive parameters such as the corneal biomechanical index (CBI) and stress-strain index (SSI). Among them, SSI, as a material constant corrected for intraocular pressure and thickness, is considered an indicator reflecting the overall stiffness of the cornea.
[0004] However, existing technologies generally suffer from the following shortcomings, which collectively point to different aspects of the same technical problem: Existing SSI parameters are calculated based on the overall deformation of the entire cornea. This evaluation method assumes that the cornea is an isotropic material and ignores the depth-dependent mechanical anisotropy of the corneal stroma in its microstructure. The averaging of macroscopic parameters masks early local mechanical property degradation signals within the corneal stroma, especially between the anterior and posterior regions, making it impossible to extract the mechanical contributions at different levels from a single measurement.
[0005] Furthermore, although existing studies have proposed stiffness-related indices such as the anisotropic stress-strain index (ASSI), these indices are essentially still calculations based on the stress-to-strain ratio (i.e., stiffness), and typically reflect the average characteristics of the entire corneal layer. Such indices cannot directly characterize the actual deformation differences between the anterior and posterior corneal regions under the same load.
[0006] Furthermore, although some studies have attempted to use baseline biomechanical parameters to construct multi-parameter machine learning fusion models to predict future trends, such as the corneal biomechanical progression index (BEPI), these models often lack clear physical meaning and have poor interpretability. Existing interlaminar stiffness ratio indices can only reflect the static differences between those with existing structural abnormalities and those with normal structures in the current state.
[0007] In summary, the core deficiency of existing technologies at the data processing level is that they cannot extract indicators that reflect the mechanical coupling state between corneal layers from a single measurement, and therefore cannot provide assessment information with clear physical meaning on the longitudinal structural change trend of individuals who have not yet shown obvious abnormalities based on these indicators. Summary of the Invention
[0008] To address the problem that existing technologies cannot assess the progression trend of keratoconus based on multiple measurement data, this invention provides a method, device, equipment, and medium for assessing corneal biomechanical status.
[0009] To achieve the above objectives, the present invention provides the following technical solution: A method for assessing corneal biomechanical status, the method comprising: Obtain a sequence of cross-sectional images of the cornea before and after being subjected to mechanical load; The corneal stroma in the image sequence is segmented to distinguish between the anterior and posterior stroma regions; Based on the segmentation results, the displacement of the interlayer boundary between the front matrix region and the rear matrix region during the loading process is tracked, and the maximum strain value of the front matrix region and the maximum strain value of the rear matrix region are determined respectively. The ratio of the maximum strain value of the posterior stromal region to the maximum strain value of the anterior stromal region is determined, and this ratio is defined as the interlaminar strain ratio, which reflects the corneal interlaminar layer's ability to resist excessive deformation. Multiple interlaminar strain ratios at different time points are obtained for the same subject; the rate of change of the interlaminar strain ratios over time is calculated; and the dynamic evolution trend of the biomechanical state of the tested cornea is evaluated based on the rate of change.
[0010] Optionally, determining the maximum strain value of the front matrix region and the maximum strain value of the rear matrix region respectively includes: The displacement components of the interlayer boundary in the direction of load application are tracked using optical flow or digital image correlation techniques. Based on the displacement components, the strain of each region is calculated according to the following formula: The strain εa of the forematrix region is determined by the ratio of the relative displacement of the interlayer boundary of the forematrix region to the original thickness of the forematrix region. The calculation formula is: εa = |ΔLa| / Ta. Where Ta is the original thickness of the pre-matrix region, and ΔLa is the relative displacement of the interlayer boundary of the pre-matrix region under load. The strain εp in the back matrix region is determined by the ratio of the relative displacement of the interlayer boundary in the back matrix region to the original thickness of the back matrix region. The calculation formula is: εp = |ΔLp| / Tp. Where Tp is the original thickness of the back matrix region, and ΔLp is the relative displacement of the interlayer boundary of the back matrix region under load; Extract the maximum values of the strain in the front matrix region and the strain in the rear matrix region during the loading process.
[0011] Optionally, segmenting the corneal stroma in the image sequence includes: The image sequence is input into a pre-trained deep learning segmentation model, which automatically identifies and segments the boundaries between the anterior and posterior matrix regions.
[0012] Optionally, the formula for calculating the interlaminar strain ratio (LSR) is: LSR = εp / εa Where εp is the maximum strain value in the rear matrix region and εa is the maximum strain value in the front matrix region.
[0013] Optionally, assessing the dynamic evolution trend of the biomechanical state of the examined cornea based on the rate of change includes: When the interlaminar strain ratio is within the normal reference range, it is determined that the corneal interlaminar mechanical balance is achieved, and the risk level is low. When the interlaminar strain ratio is higher than the upper limit of the normal reference range, it is determined to be an early corneal interlaminar mechanical imbalance with excessive stromal deformation, and the risk level is moderate. When the interlaminar strain ratio gradually decreases from the upper limit of the normal reference range, and the rate of change of two or more consecutive measurements is negative, it is determined that the interlaminar mechanical state of the cornea is evolving towards homogenization, indicating disease progression, and the risk level is extremely high. When the interlaminar strain ratio shows an increasing trend in multiple consecutive measurements, it is determined that the corneal interlaminar mechanical state is evolving in the direction of progression, and the risk level is high risk; wherein, the normal reference value range is obtained through statistical analysis.
[0014] Optionally, the method further includes: Obtain the value of at least one other corneal biomechanical parameter, said other corneal biomechanical parameter including corneal interlaminar stiffness ratio, stress-strain index and anisotropic stress-strain index; Calculate the rate of change of the other corneal biomechanical parameters over time; Based on the rate of change of the interlaminar strain ratio combined with the rate of change of other parameters, the dynamic evolution trend of the biomechanical state of the examined cornea and the intervention effect are evaluated.
[0015] Optionally, the dynamic evolution trend and intervention effect of the tested corneal biomechanical state are evaluated by combining the rate of change of the interlaminar strain ratio with the rate of change of other parameters, including: The calculated rate of change of the interlayer strain ratio and the rate of change of other parameters are input into a pre-constructed progress risk assessment model; wherein, the progress risk assessment model is one of the following: Cox proportional hazards model, time-dependent covariate Cox model, Logistic regression model, random survival forest, and deep learning survival model; The progress risk assessment model is built based on historical cohort data. It uses the rate of change of interlaminar strain ratio and the rate of change of other parameters as the main predictors, and outputs individualized corneal biomechanical status and its corresponding risk level and intervention effect.
[0016] A corneal biomechanical status assessment device, the device comprising: The acquisition module is used to acquire cross-sectional image sequences of the cornea before and after being subjected to mechanical load; The segmentation module is used to perform interlayer segmentation of the corneal stroma layer in the image sequence, distinguishing the anterior stroma region and the posterior stroma region; The calculation module is used to track the displacement of the interlayer boundary between the front matrix region and the rear matrix region during the loading process based on the segmentation results, and to determine the maximum strain value of the front matrix region and the maximum strain value of the rear matrix region, respectively. The determination module is used to determine the ratio of the maximum strain value of the posterior stromal region to the maximum strain value of the anterior stromal region, and defines this ratio as the interlaminar strain ratio, which reflects the corneal interlaminar layer's ability to resist excessive deformation. The evaluation module is used to obtain multiple interlaminar strain ratio values at different time points for the same subject; calculate the rate of change of the interlaminar strain ratio values over time; and evaluate the dynamic evolution trend of the biomechanical state of the examined cornea based on the rate of change.
[0017] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for assessing corneal biomechanical status.
[0018] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the aforementioned method for assessing corneal biomechanical status.
[0019] The corneal biomechanical state assessment method provided by this invention has the following beneficial effects: This invention acquires a sequence of cross-sectional images of the cornea under mechanical load, segments the corneal stroma within the images to distinguish between the anterior and posterior stromal regions, tracks the displacement of the interlaminar boundaries, calculates the maximum strain values of the two regions, and uses the ratio of the two strain values as the interlaminar strain ratio to assess the corneal biomechanical reserve state and output a risk assessment result. This directly extracts key parameters that quantify the degree of interlaminar mechanical coupling from a single measurement. This method overcomes the obscuring of anisotropy and depth-dependent characteristics by traditional macroscopic parameters, revealing the deformation differences between the anterior and posterior stromal layers under the same external force. It can sensitively capture early local mechanical imbalance signals that are not yet reflected by overall mechanical parameters. Furthermore, the longitudinal assessment approach based on the interlaminar strain ratio provides predictive information with a clear mechanical meaning, significantly improving the interpretability of risk assessment. The calculation process does not rely on complex finite element modeling assumptions and is easily deployed on existing biomechanical measurement equipment, providing clinicians with a corneal change trend assessment tool that balances automation, objectivity, and the reliability of mechanical principles. Attached Figure Description
[0020] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. 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.
[0021] Figure 1 This is a schematic flowchart of a corneal biomechanical state assessment method provided by the present invention according to an exemplary embodiment.
[0022] Figure 2 This is a schematic diagram illustrating a clinical data change indicator according to an exemplary embodiment of the present invention.
[0023] Figure 3 This is a block diagram of a corneal biomechanical state assessment device provided by the present invention according to an exemplary embodiment. Detailed Implementation
[0024] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.
[0025] The technical solutions provided by the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0026] First, this invention provides a method for assessing the biomechanical state of the cornea, specifically as follows: Figure 1 As shown, it includes the following steps: S101. Obtain a sequence of cross-sectional images of the cornea before and after being subjected to mechanical load.
[0027] S102. Perform interlayer segmentation on the corneal stroma layer in the image sequence to distinguish the anterior stroma region and the posterior stroma region.
[0028] In this step, the image sequence is input into a pre-trained deep learning segmentation model, which automatically identifies and segments the boundaries between the anterior and posterior matrix regions. The deep learning segmentation model employs a U-Net encoder-decoder architecture.
[0029] In this step, the corneal stroma can be divided into layers with a thickness ratio of anterior:middle:posterior = 5:7:8.
[0030] First, the upper and lower boundaries of the corneal stroma are identified using a segmentation model, and the total thickness of the stroma is T.
[0031] Then, starting from the top boundary and moving downwards, divide the area into the following sections: Anterior matrix layer: thickness 5 / 20T = 0.25T; Intermediate matrix layer: thickness 7 / 20T = 0.35T; Post-matrix layer: thickness 8 / 20T = 0.40T; Three matrix regions—front, middle, and back—were obtained.
[0032] This ratio can be adjusted according to different groups of people or devices.
[0033] S103. Based on the segmentation results, track the displacement of the interlayer boundary between the front matrix region and the back matrix region during the loading process, and calculate the maximum strain value of the front matrix region and the maximum strain value of the back matrix region respectively.
[0034] In this step, the displacement components of the interlayer boundaries in the load direction are tracked using optical flow or digital image correlation techniques. Based on these displacement components, the strain of each region is calculated using the following formulas: The strain εa of the front matrix region is determined by the ratio of the relative displacement of the interlayer boundary of the front matrix region to the original thickness of the front matrix region, calculated as: εa = |ΔLa| / Ta, where Ta is the original thickness of the front matrix region and ΔLa is the relative displacement of the interlayer boundary of the front matrix region under load; The strain εp of the rear matrix region is determined by the ratio of the relative displacement of the interlayer boundary of the rear matrix region to the original thickness of the rear matrix region, calculated as: εp = |ΔLp| / Tp, where Tp is the original thickness of the rear matrix region and ΔLp is the relative displacement of the interlayer boundary of the rear matrix region under load; The maximum values of the strains of the front and rear matrix regions during the load process are extracted.
[0035] S104. Determine the ratio of the maximum strain value of the rear matrix region to the maximum strain value of the front matrix region, and define this ratio as the interlayer strain ratio.
[0036] The interlaminar strain ratio (LSR) reflects the corneal interlaminar layer's ability to resist excessive deformation, and its calculation formula is as follows: LSR = εp / εa; Where εp is the maximum strain value in the rear matrix region and εa is the maximum strain value in the front matrix region.
[0037] S105. Obtain multiple interlaminar strain ratios at different time points for the same subject; calculate the rate of change of the interlaminar strain ratio over time; and assess the dynamic evolution trend of the biomechanical state of the tested cornea based on the rate of change.
[0038] The risk level is determined according to the following rules: When the interlaminar strain ratio is within the normal reference range, it is considered that the corneal interlaminar mechanical balance is achieved, with a low risk level; when the interlaminar strain ratio is higher than the upper limit of the normal reference range, it is considered that the corneal interlaminar mechanical state is evolving towards homogenization, indicating disease progression, with a very high risk level; when the interlaminar strain ratio shows an increasing trend in multiple consecutive measurements, it is considered that the corneal interlaminar mechanical state is evolving towards progression, with a high risk level. The normal reference range is obtained through statistical analysis. This normal reference range is obtained by statistically analyzing the interlaminar strain ratio of healthy population samples, for example, by using the mean ± standard deviation or percentile method.
[0039] For example, the corneal interlaminar strain ratio can be measured in at least 30 healthy volunteers, and its mean and standard deviation can be calculated. The normal reference range is defined as the mean ± 1.96 times the standard deviation. When the interlaminar strain ratio of the tested individual is greater than 1.40, it is considered abnormal. It should be noted that those skilled in the art can adjust the above thresholds according to the actual measuring equipment and population characteristics, and all such adjustments are within the scope of protection of this invention.
[0040] In addition, the present invention can also obtain the values of at least one other corneal biomechanical parameter at the same or different time points, including the corneal interlaminar stiffness ratio, stress-strain index, and anisotropic stress-strain index; calculate the rate of change of the other corneal biomechanical parameter over time; and evaluate the dynamic evolution trend and intervention effect of the tested corneal biomechanical state based on the combination of the rate of change of the interlaminar strain ratio and the rate of change of the other parameter.
[0041] For example, the calculated rate of change of interlaminar strain ratio and other parameter rates of change can be input into a pre-constructed progression risk assessment model. This progression risk assessment model can be one of the following: a Cox proportional hazards model, a time-dependent covariate Cox model, a logistic regression model, a random survival forest model, or a deep learning survival model. This model is built based on historical cohort data, using the rate of change of interlaminar strain ratio and other parameter rates of change as primary predictors, and outputs individualized corneal biomechanical status, its corresponding risk level, and intervention effect. Alternatively, the interlaminar strain ratio can be input alone into this progression risk assessment model as a primary predictor to output individualized corneal biomechanical status, its corresponding risk level, and intervention effect.
[0042] Taking the stress-strain index as another corneal biomechanical parameter, for example, the interlaminar strain ratio (LSR) and stress-strain index (SSI) of the subject are measured simultaneously. The rates of change of both over time (ΔLSR and ΔSSI) are calculated separately. Referring to existing clinical studies, the annual decrease in SSI in patients with progressive keratoconus is approximately 0.02 (ΔSSI is negative). According to the theoretical deduction of this invention, as the cornea progresses from intermediate to posterior stromal softening to full-thickness softening, the LSR continuously increases (ΔLSR is positive). Therefore, the combined judgment rule is as follows:
[0043] If ΔLSR > 0 (LSR continues to rise) and ΔSSI < -0.02 (SSI decreases significantly), it is considered a high-risk progression. This combination suggests increased interlaminar mechanical imbalance (continued deterioration of relative excessive deformation of the matrix) and synchronous loss of overall stiffness, leading to enhanced disease activity.
[0044] If ΔLSR>0 and ΔSSI ≥ -0.02, it indicates early interlayer mechanical imbalance but the overall stiffness has not yet decreased significantly, and is judged as moderate risk. It is recommended to shorten the follow-up interval.
[0045] If ΔLSR ≤ 0 and ΔSSI < -0.02, it indicates that LSR has reached a plateau or is declining (possibly a compensatory period after full-layer softening), but the overall stiffness is still deteriorating, and further progress needs to be monitored, thus it is classified as a moderate risk.
[0046] If neither of the two changes is significant, the condition is considered stable, and routine follow-up should be maintained.
[0047] It should be noted that the threshold for determining the positive or negative value of ΔLSR can be adjusted based on large-sample follow-up data in actual clinical applications. This combined assessment method utilizes the sensitivity of LSR to interlaminar mechanical imbalance and the representativeness of SSI to overall stiffness changes, providing multi-dimensional reference information for clinical practice.
[0048] Using the above method, a sequence of cross-sectional images of the cornea under mechanical load is acquired. The corneal stroma in the images is segmented to distinguish between the anterior and posterior stromal regions. The displacement of the interlaminar boundary is then tracked, and the maximum strain values of the two regions are calculated separately. The ratio of these two values is used as the interlaminar strain ratio to assess the corneal biomechanical reserve state and output a risk assessment result. This directly extracts key parameters that can quantitatively characterize the degree of interlaminar mechanical coupling from a single measurement. This method breaks through the obscuring of anisotropy and depth-dependent features by traditional macroscopic parameters, revealing the deformation differences between the anterior and posterior stromal layers under the same external force. It can sensitively capture early local mechanical imbalance signals that cannot be reflected by overall mechanical parameters. Simultaneously, the longitudinal assessment pathway based on the interlaminar strain ratio gives the predictive information a clear mechanical meaning, significantly improving the interpretability of risk assessment. Furthermore, the calculation process does not rely on complex finite element modeling assumptions and is easily deployed on existing biomechanical measurement equipment. This provides clinicians with a corneal change trend assessment tool that balances automation, objectivity, and the reliability of mechanical principles.
[0049] Based on the above method, the present invention also provides an embodiment.
[0050] Step A: Corneal image acquisition.
[0051] High-resolution cross-sectional image sequences of the cornea are acquired before and after the application of controlled mechanical load using biomechanical measurement equipment.
[0052] Step B: Deep learning-assisted inter-layer segmentation.
[0053] The acquired images are input into a pre-trained deep learning segmentation model, which automatically identifies and segments the corneal stroma. In a preferred embodiment, the model can divide the corneal stroma into at least a first sublayer and a second sublayer.
[0054] Step C: Calculation of interlayer strain.
[0055] Based on the segmented layer boundaries, image sequences are continuously acquired during the loading process. Optical flow or digital image correlation (DIC) techniques are used to track the interlayer boundary displacements, extract the displacement components in the load direction, and calculate the strain of each layer accordingly. Fore-matrix layer: original thickness Ta, interlayer boundary relative displacement ΔLa, strain εa=|ΔLa| / Ta.
[0056] Post-matrix layer: original thickness Tp, interlayer boundary relative displacement ΔLp, strain εp=|ΔLp| / Tp.
[0057] Extract the maximum strain value of each region during the loading process.
[0058] Step D: Calculation of interlaminar strain ratio (LSR).
[0059] Define and calculate the strain ratio before and after strain: LSR = εp / εa; in, εa=∣ΔLa∣ / Ta; εa is the strain of the forematrix region; Ta is the original thickness of the forematrix region (unit: μm); ΔLa is the relative displacement of the interlayer boundary of the forematrix region under load (unit: μm). ΔLa = La(front) - La(back).
[0060] εp=∣ΔLp∣ / Tp; εp is the strain of the back matrix region; Tp is the original thickness of the back matrix region (unit: μm); ΔLp: the relative displacement of the interlayer boundary of the back matrix region under load (unit: μm). ΔLp = Lp(front) - Lp(back).
[0061] This ratio quantifies the difference in deformation between the front and rear matrix regions under the same external force, directly reflecting the interlayer mechanical coupling state.
[0062] Step E: Biomechanical reserve assessment and progress trend assessment.
[0063] The calculated LSR is combined with a pre-established progress risk assessment model: ① The interlaminar strain ratio (LSR) reflects the corneal interlaminar layer's ability to resist excessive deformation, i.e., biomechanical reserve.
[0064] like Figure 2 As shown, when the LSR is within the normal reference range (e.g., 1.1–1.2), it indicates that the anterior and posterior stroma are well mechanically coupled, the biomechanical reserve is sufficient, and the cornea can effectively resist physiological loads.
[0065] When the LSR is significantly higher than the upper limit of the normal reference range (e.g., 1.2), it indicates that the posterior matrix is excessively deformed relative to the anterior matrix, interlaminar mechanical imbalance has appeared early, biomechanical reserves have begun to be depleted, and the risk of future progression has increased.
[0066] When the interlaminar strain ratio (LSR) gradually decreases from the upper limit of the normal reference range, and the rate of change of two or more consecutive measurements is negative, it is judged as an evolution of the corneal interlaminar mechanical state towards homogenization, indicating disease progression and a very high risk level. Furthermore, when the LSR gradually decreases from a high value to near 1 or less than 1, it indicates an increase in anterior stromal compensatory load or loss of stiffness, an inverted interlaminar mechanical gradient, a significant reduction in biomechanical reserve, and the cornea is prone to abnormal deformation under physiological load.
[0067] When LSR shows an increasing trend in multiple consecutive measurements, it is determined that the interlaminar mechanical state of the cornea is evolving in a progressive direction, and the risk level is high risk.
[0068] In addition, the values of at least one other corneal biomechanical parameter can be obtained and the corresponding rate of change can be calculated. Combined with LSR, this allows for the assessment of biomechanical reserve and progress trend.
[0069] ② Assessment Model: Establish a regression model (such as Cox proportional hazards model or Logistic regression) based on historical cohort data, using LSR as the main predictor, and output individualized progression risk probability or risk level (low / medium / high).
[0070] Step F: Output the results.
[0071] The output includes: ① the LSR value of this measurement; ② the probability of progress risk based on the model; ③ risk level recommendations.
[0072] Secondly, the present invention also provides a corneal biomechanical state assessment device, such as... Figure 3 As shown, it includes: The acquisition module 201 is used to acquire a sequence of cross-sectional images of the cornea before and after being subjected to mechanical load.
[0073] The segmentation module 202 is used to perform interlayer segmentation of the corneal stroma in the image sequence, distinguishing the anterior stroma region and the posterior stroma region.
[0074] The calculation module 203 is used to track the displacement of the interlayer boundary between the front matrix region and the rear matrix region during the loading process based on the segmentation results, and to determine the maximum strain value of the front matrix region and the maximum strain value of the rear matrix region, respectively.
[0075] The determination module 204 is used to determine the ratio of the maximum strain value of the posterior stromal region to the maximum strain value of the anterior stromal region, and defines the ratio as the interlaminar strain ratio, which reflects the corneal interlaminar layer's ability to resist excessive deformation.
[0076] The evaluation module 205 is used to obtain multiple interlayer strain ratio values at different time points for the same subject; calculate the rate of change of the interlayer strain ratio value over time; and evaluate the dynamic evolution trend of the biomechanical state of the tested cornea based on the rate of change.
[0077] The present invention also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The steps of a method for assessing corneal biomechanical status are provided.
[0078] This invention also provides a computer device. At the hardware level, the computer device includes a processor, an internal bus, a network interface, memory, and non-volatile memory, and may also include other hardware required for various operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then executes it to achieve the above-mentioned functions. Figure 1 The steps of a method for assessing corneal biomechanical status are provided.
[0079] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.
[0080] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), 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, as well as 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 data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0081] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing 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.
[0082] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment 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.
[0083] It should be noted that the specific embodiments described above enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although the present invention has been described in detail in this specification, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the present invention; and all technical solutions and improvements that do not depart from the spirit and scope of the present invention are covered within the protection scope of the patent of the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.
Claims
1. A method for assessing the biomechanical state of the cornea, characterized in that, The method includes: Obtain a sequence of cross-sectional images of the cornea before and after being subjected to mechanical load; The corneal stroma in the image sequence is segmented to distinguish between the anterior and posterior stroma regions; Based on the segmentation results, the displacement of the interlayer boundary between the front matrix region and the rear matrix region during the loading process is tracked, and the maximum strain value of the front matrix region and the maximum strain value of the rear matrix region are determined respectively. The ratio of the maximum strain value in the posterior stromal region to the maximum strain value in the anterior stromal region is determined, and this ratio is defined as the interlaminar strain ratio, which reflects the corneal interlaminar layer's ability to resist excessive deformation. Multiple interlaminar strain ratios at different time points are obtained for the same subject; the rate of change of the interlaminar strain ratios over time is calculated; and the dynamic evolution trend of the biomechanical state of the tested cornea is evaluated based on the rate of change.
2. The method according to claim 1, characterized in that, Determining the maximum strain value of the front matrix region and the maximum strain value of the rear matrix region respectively includes: The displacement components of the interlayer boundary in the direction of load application are tracked using optical flow or digital image correlation techniques. Based on the displacement components, the strain of each region is calculated according to the following formula: The strain εa of the forematrix region is determined by the ratio of the relative displacement of the interlayer boundary of the forematrix region to the original thickness of the forematrix region. The calculation formula is: εa = |ΔLa| / Ta. Where Ta is the original thickness of the pre-matrix region, and ΔLa is the relative displacement of the interlayer boundary of the pre-matrix region under load. The strain εp in the back matrix region is determined by the ratio of the relative displacement of the interlayer boundary in the back matrix region to the original thickness of the back matrix region. The calculation formula is: εp = |ΔLp| / Tp. Where Tp is the original thickness of the back matrix region, and ΔLp is the relative displacement of the interlayer boundary of the back matrix region under load; Extract the maximum values of the strain in the front matrix region and the strain in the rear matrix region during the loading process.
3. The method according to claim 1, characterized in that, Interlayer segmentation of the corneal stroma in the image sequence includes: The image sequence is input into a pre-trained deep learning segmentation model, which automatically identifies and segments the boundaries between the anterior and posterior matrix regions.
4. The method according to claim 1, characterized in that, The formula for calculating the interlaminar strain ratio (LSR) is as follows: LSR = εp / εa Where εp is the maximum strain value in the rear matrix region and εa is the maximum strain value in the front matrix region.
5. The method according to claim 1, characterized in that, The dynamic evolution trend of the biomechanical state of the examined cornea, based on the rate of change, includes: When the interlaminar strain ratio is within the normal reference range, it is determined that the corneal interlaminar mechanical balance is achieved, and the risk level is low. When the interlaminar strain ratio is higher than the upper limit of the normal reference range, it is determined to be an early corneal interlaminar mechanical imbalance with excessive stromal deformation, and the risk level is moderate. When the interlaminar strain ratio gradually decreases from the upper limit of the normal reference range, and the rate of change of two or more consecutive measurements is negative, it is determined that the interlaminar mechanical state of the cornea is evolving towards homogenization, indicating disease progression, and the risk level is extremely high. When the interlaminar strain ratio shows an increasing trend in multiple consecutive measurements, it is determined that the corneal interlaminar mechanical state is evolving in the direction of progression, and the risk level is high risk; wherein, the normal reference value range is obtained through statistical analysis.
6. The method according to claim 1, characterized in that, The method further includes: Obtain the value of at least one other corneal biomechanical parameter, said other corneal biomechanical parameter including corneal interlaminar stiffness ratio, stress-strain index and anisotropic stress-strain index; Calculate the rate of change of the other corneal biomechanical parameters over time; Based on the rate of change of the interlaminar strain ratio combined with the rate of change of other parameters, the dynamic evolution trend of the biomechanical state of the examined cornea and the intervention effect are evaluated.
7. The method according to claim 6, characterized in that, The dynamic evolution trend and intervention effect of the examined corneal biomechanical state are evaluated by combining the rate of change of the interlaminar strain ratio with the rate of change of other parameters, including: The calculated rate of change of the interlayer strain ratio and the rate of change of other parameters are input into a pre-constructed progress risk assessment model; wherein, the progress risk assessment model is one of the following: Cox proportional hazards model, time-dependent covariate Cox model, Logistic regression model, random survival forest, and deep learning survival model; The progress risk assessment model is built based on historical cohort data. It uses the rate of change of interlaminar strain ratio and the rate of change of other parameters as the main predictors, and outputs individualized corneal biomechanical status and its corresponding risk level and intervention effect.
8. A device for assessing corneal biomechanical status, characterized in that, The device includes: The acquisition module is used to acquire cross-sectional image sequences of the cornea before and after being subjected to mechanical load; The segmentation module is used to perform interlayer segmentation of the corneal stroma layer in the image sequence, distinguishing the anterior stroma region and the posterior stroma region; The calculation module is used to track the displacement of the interlayer boundary between the front matrix region and the rear matrix region during the loading process based on the segmentation results, and to determine the maximum strain value of the front matrix region and the maximum strain value of the rear matrix region, respectively. The determination module is used to determine the ratio of the maximum strain value of the posterior stromal region to the maximum strain value of the anterior stromal region, and defines this ratio as the interlaminar strain ratio, which reflects the corneal interlaminar layer's ability to resist excessive deformation. The evaluation module is used to obtain multiple interlaminar strain ratio values at different time points for the same subject; calculate the rate of change of the interlaminar strain ratio values over time; and evaluate the dynamic evolution trend of the biomechanical state of the examined cornea based on the rate of change.
9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 7.
10. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in any one of claims 1 to 7.