Total-cycle management method for keratoconus and related devices

Abstract

This application discloses a method and related apparatus for full-cycle management of keratoconus. The method includes extracting corneal birefringence structural features from a region of interest based on acquired polarization parameters, including a phase retardation map and a fast axis orientation map. The corneal birefringence structural features include phase retardation statistical features, gradient energy features, and orientation consistency features. A corneal birefringence structure score is calculated based on these features. Full-cycle management of the user's keratoconus is then performed based on the corneal birefringence structure score. Using this application overcomes the limitations of single indicators, provides a standardized basis for full-cycle management, and improves the efficiency of full-cycle management.

Description

Technical Field

[0001] This invention relates to the field of ophthalmic optical testing and slit-lamp imaging technology, and in particular to a method and related device for the full-cycle management of keratoconus. Background Technology

[0002] The corneal stroma is composed of multiple layers of collagen fiber lamellae with varying orientations, and the integrity of its microstructure directly determines the mechanical stability and optical transparency of the cornea. Polarization-based measurement techniques can non-invasively characterize the arrangement of collagen fibers by acquiring phase retardation and fast-axis orientation, which has significant clinical value in the early diagnosis of keratoconus, refractive surgery risk assessment, and corneal disease monitoring.

[0003] Although polarization-based measurement techniques have shown great potential in keratoconus research, current applications are mostly focused on qualitative analysis of single parameters or observation of local areas, lacking a systematic quantitative evaluation system. This makes it difficult to quantitatively assess and dynamically monitor the risk, progression rate, and treatment effectiveness of keratoconus. Consequently, clinicians struggle to form intuitive and consistent judgment criteria when faced with complex polarization data, thus limiting the widespread application of this technology in large-scale screening and long-term follow-up. Summary of the Invention

[0004] This application provides a method and related device for full-cycle management of keratoconus, which helps to overcome the limitations of a single indicator, provides a standardized basis for full-cycle management, and can also improve the efficiency of full-cycle management.

[0005] The first aspect of this application provides a method for the full-cycle management of keratoconus, the method comprising: Based on the obtained polarization parameters, corneal birefringence structure features are extracted in the region of interest. The polarization parameters include a phase delay map and a fast axis orientation map. The corneal birefringence structure features include phase delay statistical features, gradient energy features, and orientation consistency features. Calculate the corneal birefringence structure score based on the corneal birefringence structure characteristics; The user's keratoconus is managed throughout its entire lifecycle based on the corneal birefringence structure score.

[0006] Optionally, the phase delay statistical characteristics include at least one of the following: phase delay mean, phase delay standard deviation, and phase delay quantile.

[0007] Optionally, the gradient energy feature is characterized by an energy gradient, and the formula for calculating the energy gradient is: , in, For energy gradient, This is a phase delay map, where ROI is the region of interest. For location, It is the square of the gradient magnitude.

[0008] Optionally, the directional consistency feature is characterized by directional consistency or directional variance. The directional consistency is obtained by statistical analysis using a double-angle circumferential method based on the π-periodicity of the fast-axis direction map. The formula for calculating the directional consistency is as follows: , in, For consistency of direction, The number of effective observation units selected. This is the fast axis direction map for the i-th valid unit. The imaginary unit is the direction of the fast axis. and equivalence; The formula for calculating the directional variance is: , in, Here is the directional variance.

[0009] Optionally, calculating the corneal birefringence structure score based on the corneal birefringence structure characteristics includes: The corneal birefringence structure features are mapped to a birefringence structure score according to a preset scorer, wherein the scorer is: , in, Scoring the corneal birefringence structure, The preset total score, For activation function, For the preset weight vector, The feature vector of the corneal birefringence structure. This is a bias term.

[0010] Optionally, the step of providing full-cycle management of the user's keratoconus based on the corneal birefringence structure score includes: A threshold table is used to map the corneal birefringence structure score into discrete levels; Full-cycle management of keratoconus is performed based on the discrete levels of users.

[0011] Optionally, the step of providing full-cycle management of the user's keratoconus based on the corneal birefringence structure score includes: At least one of the following trend analysis methods is used to calculate the user's keratoconus trend index based on the corneal birefringence structure score: sliding window interpolation method, regression slope method, and CUSUM method. When the keratoconus trend index exceeds the preset keratoconus trend index threshold, it is recommended that the user retest or verify it in conjunction with the topography index. The topography index is a corneal topography or thickness-related index that is cross-validated with the polarization birefringence results.

[0012] Optionally, the terrain indices include the crossover ratio and / or the Dice coefficient, and the method further includes: Import multimodal data, which includes terrain data and thickness data; Weakness mask is calculated based on the terrain data and thickness data, and polarization enhancement mask is calculated based on the phase delay map and / or fast axis orientation map; Calculate the cross-union ratio and / or Dice coefficient based on the weak region mask and the polarization enhancement region mask.

[0013] Optionally, the combined terrain index verification includes: The risk quantification result is calculated based on the keratoconus trend index and its corresponding weight, the topography index and its corresponding weight, and the confidence level of the risk quantification result is output.

[0014] A second aspect of this application provides a keratoconus full-cycle management device, the device comprising: The feature extraction unit is used to extract corneal birefringence structure features in the region of interest based on the acquired polarization parameters, the polarization parameters including a phase delay map and a fast axis orientation map, and the corneal birefringence structure features including phase delay statistical features, gradient energy features, and orientation consistency features. A structural scoring unit is used to calculate a corneal birefringence structure score based on the corneal birefringence structure characteristics. The cycle management unit is used to perform full-cycle management of the user's keratoconus based on the corneal birefringence structure score.

[0015] A third aspect of this application provides an electronic device, including: a processor and a memory; The processor is connected to a memory, wherein the memory is used to store computer programs and the processor is used to invoke the computer programs to execute the methods as described in the first aspect of the embodiments of this application.

[0016] A fourth aspect of this application provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor, perform the method as described in the first aspect of this application.

[0017] This application has at least the following beneficial effects: (1) By acquiring phase delay maps and fast axis orientation maps, the microscopic arrangement and integrity of collagen fibers in the corneal stroma can be directly detected. Since the disorder of collagen fiber structure usually precedes changes in macroscopic morphology, this method can capture subtle birefringence abnormalities in the early stage of the disease, thereby significantly advancing the detection window of keratoconus and achieving true early detection; (2) Innovatively, phase delay statistical features, gradient energy features, and directional consistency features were extracted. This multi-dimensional feature fusion can comprehensively and three-dimensionally characterize the abnormal patterns of corneal biomechanical properties, effectively avoiding misjudgments caused by fluctuations in a single indicator, and improving the robustness and specificity of the assessment results; (3) Transforming complex polarization data into intuitive and comparable numerical indicators can not only be used for risk grading during initial screening, but also as a core monitoring indicator in longitudinal follow-up, thereby facilitating doctors to judge the trend of disease changes based on the score and formulate personalized intervention strategies.

[0018] (4) By automating feature extraction and scoring calculation, the excessive reliance on human subjective experience is reduced, the threshold for film viewing and time costs are lowered, and the efficiency of full-cycle management is improved. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art 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.

[0020] Figure 1 A schematic diagram of a slit-cutting band polarization measurement system provided in one embodiment of this application is shown; Figure 2 A schematic flowchart of a full-cycle management method for keratoconus provided in one embodiment of this application is shown; Figure 3 A schematic diagram of the structure of a keratoconus full-cycle management device provided in one embodiment of this application is shown; Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of this application is shown. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0022] Please refer to Figure 1 This diagram illustrates a slit-cutting band polarization measurement system according to an embodiment of this application. Wherein: The slit lamp body (100) provides stable mechanical support, an illumination channel, and an observation channel; the observation path (101) is used to collect corneal reflected light and direct it to subsequent analysis components.

[0023] The illumination path (110) is used to project a preset polarized illumination onto the corneal surface, and the scission band (111) is used to define the width, direction and incident geometry of the illumination beam, thereby forming different scission band configuration parameters.

[0024] An optional polarization state generator (PSG) (130) is used to switch the incident polarization state on the input side; an input state switch (131) is used to switch between multiple linear polarization states or other preset polarization states to facilitate subsequent polarization measurements.

[0025] A pluggable module (120) is set on the output side of the observation path (101) to complete polarization analysis and imaging; wherein, the metasurface polarization state analyzer (PSA) (121) is used to decompose the returned light into multiple polarization analysis channels, the imaging lens group (122) is used to image the light field corresponding to the analysis channel onto the camera (123), and the camera (123) is used to acquire images of each channel.

[0026] The eye (200) represents the object being measured, and the scattering / reflecting medium (210) represents the scattering, reflection, and birefringence modulation of incident polarized light by the anterior surface and superficial stroma of the cornea.

[0027] The data link (310) is used to transmit the image data and corresponding configuration parameters acquired by the camera (123) to the processing unit (300); the processing unit (300) is used to perform parameter acquisition control, Stokes parameter or Mueller matrix solving, phase delay and fast axis direction reconstruction, layer fusion, quality gating, report export and other processing.

[0028] When the system is working, the illumination path (110) emits tangential illumination to the cornea under given incident angle, tangential width, observation angle and exposure settings; the corneal modulated return light enters the pluggable module (120) through the observation path (101), polarization analysis is completed by the metasurface PSA (121), and multi-channel imaging is completed by the imaging lens group (122) and the camera (123); the processing unit (300) reconstructs and fuseds the data under multiple tangential configurations, thereby outputting a phase delay map and fast axis orientation map dominated by the anterior corneal surface structure.

[0029] Please refer to Figure 2 This illustration shows a flowchart of a method for full-cycle management of keratoconus provided in one embodiment of this application. This method can be applied to computer devices, which refer to electronic devices with data computing and processing capabilities. The method may include the following steps: Step 201: Extract corneal birefringence structure features from the region of interest based on the obtained polarization parameters. The polarization parameters include a phase delay map and a fast axis orientation map. The corneal birefringence structure features include phase delay statistical features, gradient energy features, and orientation consistency features.

[0030] Among them, phase delay map Phase delay parameter Depending on location The change in phase retardation represents the cumulative phase difference between two orthogonally polarized components after a light wave passes through the corneal tissue. The corneal stroma is mainly composed of neatly arranged collagen fibers and exhibits birefringence. The magnitude of the phase retardation directly reflects the density, orderliness, and thickness of the corneal tissue. In the early stages of keratoconus, disordered or broken collagen fibers can lead to a decrease in local birefringence, which manifests on the corneal map as an abnormally low or uneven distribution of the phase retardation value.

[0031] Among them, the fast axis direction map Fast axis direction parameter Depending on location The change in the fast axis indicates the angle of polarization direction at a point on the cornea where light waves propagate fastest. The fast axis direction is usually perpendicular or parallel to the main alignment direction of local collagen fibers. In normal corneas, the fast axis direction exhibits a highly consistent radial or circumferential arrangement pattern. Keratoconus causes distortion of the fiber arrangement, resulting in a chaotic, abrupt, or vortex-like fast axis pattern.

[0032] The Region of Interest (ROI) refers to a specific region of analysis selected from the entire corneal image.

[0033] The phase delay statistical features are characteristics obtained by statistical analysis of the phase delay parameters within the ROI, including at least one of the following: mean phase delay, standard deviation of phase delay, and phase delay quantiles, wherein the phase delay quantiles can be, for example, [missing information - likely related to a specific feature or characteristic]. , i.e., variables The 95th percentile, or any other percentile, is not limited here. The overall birefringence of the cornea in patients with keratoconus is often lower than in normal individuals, and due to the mixture of diseased and normal areas, the value fluctuates more significantly. This characteristic is used to assess the overall integrity of the corneal stroma.

[0034] The gradient energy feature calculates the rate of change of the phase delay map or fast axis direction map in position and obtains the gradient energy, which is characterized by the energy gradient. In keratoconus lesion boundaries or stress concentration areas, the birefringence parameters change drastically. A high gradient energy indicates a dramatic structural transition or anomaly within that region. The gradient energy feature helps identify minute, localized structural collapse points that might be masked by simple statistical averages. This feature reflects the local instability and stress concentration of the corneal structure.

[0035] For example, the formula for calculating the energy gradient of the phase delay map is as follows: , in, For energy gradient, This is a phase delay map, where ROI is the region of interest. For location, It is the square of the gradient magnitude.

[0036] Similarly, the energy gradient of the map along the fast axis direction will be expressed in the above equation. Change to That's all.

[0037] The directional consistency feature is characterized by directional consistency or directional variance, and is used to analyze the similarity of the directional vectors of effective observation units in the fast-axis directional map. Effective observation units can be, for example, effective pixels, superpixel units, or sector units within a Region of Interest (ROI).

[0038] For example, the directional consistency is obtained by statistically analyzing the π-periodity of the fast axis direction map using a double-angle circumferential method. The formula for calculating the directional consistency is as follows: , in, For consistency of direction, The number of effective observation units selected. This is the fast axis direction map for the i-th valid unit. The imaginary unit is the direction of the fast axis. and equivalence; The formula for calculating the directional variance is: , in, Here is the directional variance.

[0039] Step 202: Calculate the corneal birefringence structure score based on the corneal birefringence structure characteristics.

[0040] Specifically, the step of calculating the corneal birefringence structure score based on the corneal birefringence structure characteristics includes: The corneal birefringence structure features are mapped to a birefringence structure score according to a preset scorer, wherein the scorer is: , in, Scoring the corneal birefringence structure, The preset total score, For activation function, For the preset weight vector, The feature vector of the corneal birefringence structure. This is a bias term.

[0041] The total score is a configurable normalization constant and is not limited to a specific scoring system. In practice, a 100-point system, a 10-point system, or a 1-point system can be used before linear mapping. For example, if a 100-point system is used, the output Score ∈ [0, 100]; if a 10-point system is used, Score_10 = Score_100 / 10 can be directly set. The corneal birefringence structure feature vector can be obtained by arranging multiple corneal birefringence structure features in a preset order.

[0042] Step 203: Perform full-cycle management of the user's keratoconus based on the corneal birefringence structure score.

[0043] Specifically, the full-cycle management of the user's keratoconus based on the corneal birefringence structure score includes: A threshold table is used to map the corneal birefringence structure score into discrete levels; Full-cycle management of keratoconus is performed based on the discrete levels of users.

[0044] For example, the threshold table is as follows: in, This indicates that when the score is less than the first threshold At that time, the rating was G0, which usually represents "normal", "no risk" or "lowest level". This means when the score is greater than or equal to and less than At that time, the level was rated as G1, which means that it has entered the first abnormal or risky zone. This means when the score is greater than or equal to and less than At that time, the level was rated as G2, which means that the risk or severity has increased further. This means when the score is greater than or equal to At that time, the level was rated as G3, which typically represents "severe," "high risk," or "highest level." This threshold table is an example of a 4-level threshold table; of course, more or fewer discrete levels can be added depending on the actual situation, which is not limited here.

[0045] Specifically, the full-cycle management of the user's keratoconus based on the corneal birefringence structure score includes: At least one of the following trend analysis methods is used to calculate the user's keratoconus trend index based on the corneal birefringence structure score: sliding window interpolation method, regression slope method, and CUSUM method. When the keratoconus trend index exceeds the preset keratoconus trend index threshold, it is recommended that the user retest or verify it in conjunction with the topography index. The topography index is a corneal topography or thickness-related index that is cross-validated with the polarization birefringence results.

[0046] The sliding window interpolation method arranges data along a timeline. By setting a fixed-length time window, it slides forward along the timeline, discarding the oldest data and incorporating the newest. It then calculates the difference between the latest and earliest values ​​within the window, or the change in the average value within the window. In the sliding window interpolation method, the difference between the latest and earliest values ​​within the window, or the change in the average value within the window, can serve as an indicator of keratoconus trends. For example, the interpolation value can be defined as... For the current moment Corneal birefringence structure score Compared to a certain reference time point Corneal birefringence structure score difference .

[0047] The regression slope method uses a linear regression model to fit a trend line for all data points over a period of time, and the slope of this trend line is used as an indicator of keratoconus trend. Compared to single-point difference, the regression slope is better able to resist the influence of single measurement errors or outliers, reflecting the long-term overall trend.

[0048] The Cumulative Sum Control Chart (CUSUM) method calculates the cumulative sum of the differences between observed values ​​and target values ​​(or historical mean), using this cumulative sum as an indicator of keratoconus trend. In the very early stages of keratoconus, parameter changes may be very small, which conventional methods might consider within error limits. However, the CUSUM chart will show a clear unidirectional deviation trend, thus issuing an early warning. For example, the cumulative sum can be defined as follows: , in, For the current moment The accumulation of, For the previous moment The accumulation of, For the current moment Corneal birefringence structure score, For the previous moment The target value or expected mean. To allow for deviation.

[0049] Furthermore, the terrain indices include the cross-union ratio and / or the Dice coefficient, and the method further includes: Import multimodal data, which includes terrain data and thickness data; Weakness mask is calculated based on the terrain data and thickness data, and polarization enhancement mask is calculated based on the phase delay map and / or fast axis orientation map; Calculate the cross-union ratio and / or Dice coefficient based on the weak region mask and the polarization enhancement region mask.

[0050] Intersection over Union (IoU) and Dice Coefficient are two core metrics used in image segmentation, computer vision, and medical image analysis to quantify the similarity or overlap between two regions (or sets). Their values ​​range from [0,1], where 0 indicates no overlap and 1 indicates complete overlap. IoU represents the proportion of the overlapping area between two regions (A and B, or in this application, the weak region mask and the polarization enhancement region mask) to the total coverage area. The specific calculation formula is as follows: , The Dice coefficient is used to represent the average proportion of overlap between two regions, and the specific calculation formula is as follows: .

[0051] In addition to these, topographic indicators may also include maximum keratometry (Kmax), posterior surface elevation, thinnest point thickness, thickness asymmetry, and other topographic / tomographic scanning indicators. Kmax is the value of the point on the corneal surface with the strongest refractive power (steepest point). Posterior surface elevation represents the height difference of the posterior surface of the cornea relative to a reference sphere or ellipsoid; a positive value indicates posterior bulging. Thinnest point thickness represents the value of the point with the smallest thickness within the entire corneal measurement area. Thickness asymmetry index is used to describe the non-uniformity of corneal thickness distribution.

[0052] Multimodal data refers to data from imaging devices based on different physical principles. For example, this application may include topographic data and thickness data. Topographic data reflects the curvature and height distribution of the corneal surface and is the gold standard morphological indicator for diagnosing keratoconus. Thickness data refers to the thickness distribution map of various points on the cornea. A typical feature of keratoconus is localized thinning. Topographic maps may miss subclinical diagnoses, while polarization maps may be affected by noise. Multimodal complementarity can overcome the limitations of single-modality data.

[0053] Specifically, based on topographic and thickness data, and using traditional diagnostic criteria for keratoconus, a binary image can be obtained, marking areas where anatomical deformation or thinning has occurred—the thin area mask. Based on phase retardation maps and / or fast axis orientation maps, algorithms identify areas with birefringence anomalies or disordered fiber arrangement, resulting in a binary image that marks areas with biomechanical or microstructural anomalies—the polarization enhancement area mask.

[0054] Specifically, the review incorporating terrain indicators includes: The risk quantification result is calculated based on the keratoconus trend index and its corresponding weight, the topography index and its corresponding weight, and the confidence level of the risk quantification result is output.

[0055] For example, the formula for calculating the risk quantification result is as follows: , in, To quantify the results of risk, The score corresponding to the keratoconus trend index. The weights corresponding to the keratoconus trend index, The scores corresponding to the terrain indicators. The weights corresponding to the terrain indicators.

[0056] The confidence level indicates the reliability of the risk result itself. It can be calculated based on factors such as data integrity, quality control compliance, intermodal consistency, and historical stability. For example, it can be calculated using the following formula: , in, For confidence level, The activation function is Sigmoid. , , , These are weight coefficients learned from training data. Indicates the basic bias term. This indicates a penalty for missing data. This represents the fitting residual / noise penalty term. This indicates a consistency reward item.

[0057] Furthermore, the method also includes: The output report includes explanatory fields, which include at least one of orientation consistency, weak region overlap, and local correlation. The weak region overlap is used to measure the degree of spatial overlap between the polarization enhancement region and the terrain / thickness weak region, and can be expressed using IoU or Dice coefficient. The local correlation is used to measure the degree of correlation between local phase delay or fast axis orientation anomaly and local terrain or thickness anomaly, and can be expressed using local correlation coefficient or local mutual information.

[0058] Furthermore, the method also includes: The output package includes at least one of the following: the corneal birefringence structure score, the discrete level, the version of the threshold table, the corneal birefringence structure feature vector, the weak region overlap, and the local correlation.

[0059] In summary, it can be seen that this application has at least the following beneficial effects: (1) By acquiring phase delay maps and fast axis orientation maps, the microscopic arrangement and integrity of collagen fibers in the corneal stroma can be directly detected. Since the disorder of collagen fiber structure usually precedes changes in macroscopic morphology, this method can capture subtle birefringence abnormalities in the early stage of the disease, thereby significantly advancing the detection window of keratoconus and achieving true early detection; (2) Innovatively, phase delay statistical features, gradient energy features, and directional consistency features were extracted. This multi-dimensional feature fusion can comprehensively and three-dimensionally characterize the abnormal patterns of corneal biomechanical properties, effectively avoiding misjudgments caused by fluctuations in a single indicator, and improving the robustness and specificity of the assessment results; (3) Transforming complex polarization data into intuitive and comparable numerical indicators can not only be used for risk grading during initial screening, but also as a core monitoring indicator in longitudinal follow-up, thereby facilitating doctors to judge the trend of disease changes based on the score and formulate personalized intervention strategies.

[0060] (4) By automating feature extraction and scoring calculation, the excessive reliance on human subjective experience is reduced, the threshold for film viewing and time costs are lowered, and the efficiency of full-cycle management is improved.

[0061] Figure 3 A schematic diagram of a keratoconus full-cycle management device according to an embodiment of this application is shown. The device includes: The feature extraction unit 301 is used to extract corneal birefringence structure features in the region of interest based on the acquired polarization parameters. The polarization parameters include a phase delay map and a fast axis orientation map. The corneal birefringence structure features include phase delay statistical features, gradient energy features, and orientation consistency features. The structural scoring unit 302 is used to calculate the corneal birefringence structure score based on the corneal birefringence structure characteristics. The cycle management unit 303 is used to perform full-cycle management of the user's keratoconus based on the corneal birefringence structure score.

[0062] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of this application is shown, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the functions of the computer system of the full-cycle management method for keratoconus in any of the above embodiments.

[0063] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer, causes the computer to perform the functions of the computer system of the keratoconus full-cycle management method in any of the above embodiments.

[0064] This application also provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the functions of the computer system of the keratoconus full-cycle management method in any of the above embodiments.

[0065] It is understood that the specific examples in this application are only intended to help those skilled in the art better understand the implementation methods of this application, and are not intended to limit the scope of the invention.

[0066] It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not limit the implementation process of the embodiments of this application in any way.

[0067] It is understood that the various implementation methods described in this application can be implemented individually or in combination, and the implementation methods in this application are not limited in this respect.

[0068] Unless otherwise stated, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The term "and / or" as used in this application includes any and all combinations of one or more of the associated listed items. The singular forms "a," "the," and "the" as used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0069] It is understood that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by the integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0070] It is understood that the memory in the embodiments of this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Specifically, non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM). It should be noted that the memory in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0071] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0072] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the aforementioned method implementations, and will not be repeated here.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0074] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0075] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0076] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0077] The above are merely specific embodiments of this application, but the scope of protection of this invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A method for full-cycle management of keratoconus, characterized in that, The method includes: Based on the obtained polarization parameters, corneal birefringence structure features are extracted in the region of interest. The polarization parameters include a phase delay map and a fast axis orientation map. The corneal birefringence structure features include phase delay statistical features, gradient energy features, and orientation consistency features. Calculate the corneal birefringence structure score based on the corneal birefringence structure characteristics; The user's keratoconus is managed throughout its entire lifecycle based on the corneal birefringence structure score.

2. The method according to claim 1, characterized in that, The phase delay statistical characteristics include at least one of the following: phase delay mean, phase delay standard deviation, and phase delay quantile.

3. The method according to claim 1, characterized in that, The gradient energy feature is characterized by an energy gradient, and the formula for calculating the energy gradient is: ， in, For energy gradient, This is a phase delay map, where ROI is the region of interest. For location, It is the square of the gradient magnitude.

4. The method according to claim 1, characterized in that, The directional consistency feature is characterized by directional consistency or directional variance. The directional consistency is obtained by statistical analysis using a double-angle circumferential method based on the π-periodicity of the fast-axis direction map. The formula for calculating the directional consistency is as follows: ， in, For consistency of direction, The number of effective observation units selected. This is the fast axis direction map for the i-th valid unit. The imaginary unit is the direction of the fast axis. and equivalence; The formula for calculating the directional variance is: ， in, Here is the directional variance.

5. The method according to claim 1, characterized in that, The calculation of the corneal birefringence structure score based on the corneal birefringence structure characteristics includes: The corneal birefringence structure features are mapped to a birefringence structure score according to a preset scorer, wherein the scorer is: ， in, Scoring the corneal birefringence structure, The preset total score, For activation function, For the preset weight vector, The feature vector of the corneal birefringence structure. This is a bias term.

6. The method according to claim 5, characterized in that, The process of providing full-cycle management of the user's keratoconus based on the corneal birefringence structure score includes: A threshold table is used to map the corneal birefringence structure score into discrete levels; Full-cycle management of keratoconus is performed based on the discrete levels of users.

7. The method according to claim 5, characterized in that, The process of providing full-cycle management of the user's keratoconus based on the corneal birefringence structure score includes: At least one of the following trend analysis methods is used to calculate the user's keratoconus trend index based on the corneal birefringence structure score: sliding window interpolation method, regression slope method, and CUSUM method. When the keratoconus trend index exceeds the preset keratoconus trend index threshold, it is recommended that the user retest or verify it in conjunction with the topography index. The topography index is a corneal topography or thickness-related index that is cross-validated with the polarization birefringence results.

8. The method according to claim 7, characterized in that, The terrain indices include the cross-union ratio and / or the Dice coefficient, and the method further includes: Import multimodal data, which includes terrain data and thickness data; Weakness mask is calculated based on the terrain data and thickness data, and polarization enhancement mask is calculated based on the phase delay map and / or fast axis orientation map; Calculate the cross-union ratio and / or Dice coefficient based on the weak region mask and the polarization enhancement region mask.

9. The method according to claim 8, characterized in that, The combined topographic index verification includes: The risk quantification result is calculated based on the keratoconus trend index and its corresponding weight, the topography index and its corresponding weight, and the confidence level of the risk quantification result is output.

10. A keratoconus full-cycle management device, characterized in that, The device includes: The feature extraction unit is used to extract corneal birefringence structure features in the region of interest based on the acquired polarization parameters, the polarization parameters including a phase delay map and a fast axis orientation map, and the corneal birefringence structure features including phase delay statistical features, gradient energy features, and orientation consistency features. A structural scoring unit is used to calculate a corneal birefringence structure score based on the corneal birefringence structure characteristics. The cycle management unit is used to perform full-cycle management of the user's keratoconus based on the corneal birefringence structure score.

11. An electronic device, characterized in that, include: Processor and memory; The processor is connected to a memory, wherein the memory is used to store a computer program, and the processor is used to invoke the computer program to perform the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, perform the method as described in any one of claims 1-9.

Images