MPL implantation optimization and real-time adjustment method and system based on genetic algorithm

Abstract

The invention provides an MPL implantation optimization and real-time adjustment method and system based on a genetic algorithm, and relates to the technical field of ophthalmology medical instruments. The method comprises the following steps: calculating an initial adaptation value IAS to evaluate the physical suitability of the implant; calculating an implantation position floating value IPF based on the dynamic eyeball movement, and monitoring the position stability; a modulation transfer function (MTF) is adopted to optimize visual definition, and transition performance of an optical area is analyzed; multi-objective optimization is realized by utilizing a genetic algorithm, a scheme is screened through a non-inferior solution sorting formula, and dynamic fitting characteristics are refined in combination with a visual offset compensation model; and dynamically monitoring and adjusting the iris pressure and the crystalline lens stability after implantation based on anterior aqueous fluid dynamics. According to the method, the accuracy, the stability and the postoperative visual performance of MPL implantation are improved, and a personalized implantation optimization scheme is provided for a patient.

Description

Technical Field

[0001] The present invention relates to the technical field of ophthalmic medical devices, and in particular to a method and system for optimizing and adjusting MPL implantation in real time based on a genetic algorithm. Background Art

[0002] Currently, as people age, ophthalmic diseases, especially cataracts and other lens-related vision problems, have become an important factor affecting the health of the global population. In order to restore patients' vision, intraocular lens (IOL) implantation surgery has become a common treatment method. However, despite the continuous advancement of intraocular lens implantation technology, existing treatment options still have some limitations.

[0003] First, existing intraocular lens implantation schemes usually rely on traditional physiological parameters (such as axial length, corneal curvature, etc.) to select the appropriate lens type and optical power. However, these parameters can only provide limited personalized references, ignoring the individual differences in patients' genetic information and ocular physiological characteristics, resulting in the inability to provide the most optimized treatment plan for each patient. Therefore, the existing technology has the problem of insufficient personalized treatment.

[0004] Secondly, existing implantation solutions usually rely only on static data before surgery to make treatment decisions during surgery, and lack real-time monitoring and adjustment of postoperative changes in the ocular environment. The ocular environment may change dynamically after surgery, such as changes in ocular biomarkers (such as blood flow, metabolism, etc.). Traditional methods cannot timely feedback these changes and adjust treatment plans, thus affecting the postoperative effect and the patient's recovery process.

[0005] In addition, although the application of genetics and biomarkers is increasing in many medical fields, the combined use of genetic information and biomarkers in ophthalmology is still in its early stages, and there is a lack of technology to integrate it with intraocular lens implantation programs. Analysis of genetic information, ocular genomes, and biomarkers can provide a more precise basis for personalized treatment, but current technology has not yet been able to effectively use this information to optimize treatment.

[0006] Therefore, the existing technology urgently needs a technology that can combine the patient's genetic information, eye physiological characteristics and real-time monitoring data to provide a personalized and flexibly adjusted artificial lens implantation plan. Summary of the invention

[0007] In order to solve the technical problems in the prior art of insufficient personalized treatment, inability to monitor and adjust postoperative ocular environment changes in real time, and failure to effectively combine genetic information with artificial lens implantation schemes, the present invention provides a method and system for MPL implantation optimization and real-time adjustment based on a genetic algorithm.

[0008] The technical solution provided by the present invention is as follows:

[0009] First aspect:

[0010] The present invention provides a method for optimizing and adjusting MPL implantation in real time based on a genetic algorithm, comprising:

[0011] S1. Obtaining the patient's eye structural parameters, wherein the structural parameters include corneal diameter, corneal thickness, anterior chamber depth and ciliary sulcus spacing, and generating multiple MPL initial implantation plans to form an initial plan set according to a preset data set, wherein the parameter set of each plan includes the total diameter of the lens, the diameter of the optical zone, the focal power range and the shape factor of the posterior surface of the lens;

[0012] S2. Calculate the initial adaptability of each solution to the patient's eye characteristics using the Initial Adaptation Score (IAS). The IAS is calculated based on the patient's eye dynamic model and the simulated stability after lens implantation, with specific reference to the ratio of the anterior chamber depth to the total diameter of the MPL lens and the width of the iris-lens gap after implantation.

[0013] S3. Based on a genetic algorithm, the initial solution set is optimized through selection, crossover and mutation operations, with the objectives including post-implantation visual clarity and optical zone coverage. During the optimization process, an implantation position floating value (Insertion Position Float, IPF) is introduced to represent the floating stability of the actual implantation position of the MPL during dynamic eye movement, and the solution is adjusted in real time in combination with the patient's eye model;

[0014] S4. For each optimized solution, the implantation effect is simulated using a real-time optical simulation system, and the solution parameters are fine-tuned by comparing the deviation between the actual lens floating path and the theoretical expected path;

[0015] S5. Based on the optimized solution set, select the solution with the highest comprehensive IAS and IPF scores, generate the final implantation parameters, and monitor and adjust them in real time during the implementation process to ensure the stability and adaptability of the lens.

[0016] Second aspect:

[0017] The present invention provides a genetic algorithm-based MPL implantation optimization and real-time adjustment system, comprising:

[0018] processor;

[0019] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the MPL implantation optimization and real-time adjustment method based on genetic algorithm as described in the first aspect is implemented.

[0020] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0021] (1) In the present invention, by combining genetic algorithms with ocular genome analysis, a personalized ocular health profile can be provided for each patient, and the interaction between the ocular environment and MPL implantation can be accurately simulated, thereby achieving the optimal lens implantation plan, solving the problem of insufficient personalized treatment in the prior art;

[0022] (2) In the present invention, by real-time monitoring of ocular biomarker data and feeding back the monitoring results to the algorithm system, the treatment plan is dynamically adjusted to effectively respond to changes in the postoperative ocular environment, thus solving the problem of the inability to adjust the treatment plan in real time after surgery in the prior art;

[0023] (3) In the present invention, the combination of genetic algorithm and simulation optimization technology enables the optimization of parameters such as the lens implantation angle and optical focal length, thereby improving the implantation effect and reducing postoperative complications, and solving the problem of insufficient accuracy of lens implantation schemes in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A schematic diagram of a flow chart of a method for optimizing and adjusting MPL implantation in real time based on a genetic algorithm provided by an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of the structure of a genetic algorithm-based MPL implantation optimization and real-time adjustment system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0028] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0029] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0030] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0031] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0032] Reference Manual Attached Figure 1 , shows a flow chart of a method for optimizing and adjusting MPL implantation in real time based on a genetic algorithm provided in an embodiment of the present invention.

[0033] The embodiment of the present invention provides a method for optimizing and adjusting MPL implantation in real time based on a genetic algorithm. The method can be implemented by a device for optimizing and adjusting MPL implantation in real time based on a genetic algorithm. The device for optimizing and adjusting MPL implantation in real time based on a genetic algorithm can be a terminal or a server. The processing flow of the method for optimizing and adjusting MPL implantation in real time based on a genetic algorithm can include the following steps:

[0034] S1. Obtain the patient's eye structural parameters, which include corneal diameter, corneal thickness, anterior chamber depth and ciliary sulcus distance. Generate multiple MPL initial implantation plans to form an initial plan set based on a preset data set. The parameter set of each plan includes the total diameter of the lens, the diameter of the optical zone, the optical power range and the shape factor of the posterior surface of the lens.

[0035] It should be noted that the purpose of this step is to provide basic data for subsequent lens implantation plans by accurately obtaining the patient's eye structure parameters. Corneal diameter, corneal thickness, anterior chamber depth and ciliary sulcus spacing are key factors affecting eye morphology and lens adaptability. Therefore, accurate measurement of these parameters can provide sufficient basis for generating multiple initial implantation plans. The preset data set helps generate a set of preliminary plans that adapt to different eye structures, providing a variety of options for subsequent optimization, and ensuring the personalization and accuracy of the implantation plan.

[0036] S2. Use the initial adaptation score (IAS) to calculate the initial adaptability of each solution to the patient's eye characteristics. IAS is calculated through the patient's eye dynamic model and the simulated stability after lens implantation, with specific reference to the ratio of the anterior chamber depth to the total diameter of the MPL lens and the width of the iris-lens gap after implantation.

[0037] It should be noted that the purpose of this step is to evaluate the adaptability of each initial solution. The initial adaptation value (IAS) can screen out the most promising solution by considering the relationship between eye characteristics and post-implantation stability. By analyzing the ratio of anterior chamber depth to lens diameter and the width of the gap between the iris and the lens, IAS can effectively predict the adaptability of the lens in actual implantation. This step helps to eliminate unsuitable solutions and ensure that the subsequent optimization process can focus on more suitable implantation solutions.

[0038] S3. Based on the genetic algorithm, the initial solution set is optimized through selection, crossover and mutation operations. The goals include visual clarity and optical zone coverage after implantation. During the optimization process, the implantation position floating value (Insertion Position Float, IPF) is introduced to represent the floating stability of the actual implantation position of the MPL during dynamic eye movement, and the solution is adjusted in real time in combination with the patient's eye model.

[0039] It should be noted that the application of genetic algorithms in this step is mainly to screen and optimize the initial solution set by simulating the mechanism of natural selection. Through selection, crossover and mutation operations, the optimal solution can be efficiently found in the solution space. The optimized solution can significantly improve the visual clarity and optical zone coverage after implantation. The introduction of the implant position floating value (IPF) further takes into account the impact of the dynamic movement of the eyeball on the position of the lens, ensuring the stability of the implant position. This process makes the optimization plan more personalized and maximizes the stability of the implant effect.

[0040] S4. For each optimized solution, the implantation effect is simulated using a real-time optical simulation system, and the solution parameters are fine-tuned by comparing the deviation between the actual lens floating path and the theoretical expected path.

[0041] It should be noted that the purpose of this step is to verify the actual effect of the optimization plan through the optical simulation system, and to ensure that the movement and floating path of the lens in the eye meet expectations by comparing the deviation between the simulation path and the theoretical expected path. Real-time simulation can provide feedback information for each optimization plan and make fine adjustments based on the deviation, thereby improving the adaptability and stability of the lens after implantation. This step further verifies the effectiveness of the optimization process and provides accurate data support for the final implantation.

[0042] S5. Based on the optimized solution set, select the solution with the highest comprehensive IAS and IPF scores, generate the final implantation parameters, and monitor and adjust them in real time during the implementation process to ensure the stability and adaptability of the lens.

[0043] It should be noted that in this step, the plan with the highest comprehensive score is selected as the final implant plan. The comprehensive score of IAS and IPF can comprehensively evaluate the adaptability and dynamic stability of the implant plan, ensuring that the selected plan can provide the best visual effect and stability. Through real-time monitoring and adjustment during the implementation process, the lens can be further optimized according to slight changes in the ocular environment to ensure its long-term stable adaptation. This step ensures the accuracy and durability of lens implantation, greatly improving the success rate of the operation and the patient's postoperative experience.

[0044] In a possible implementation, the calculation of the initial adaptation value IAS is based on the following steps:

[0045] Calculate the range of distance variation between the iris and the lens to determine whether the MPL may induce physical contact after implantation;

[0046] Combine the optical zone diameter with the patient's pupil diameter range to analyze the visual coverage area after implantation;

[0047] The dynamic fit characteristics are evaluated based on the matching degree between the patient's corneal curvature and the posterior surface of the lens, and the overall fit is corrected in combination with the dynamic intraocular pressure changes.

[0048] It should be noted that the change in the distance between the iris and the lens directly affects the risk of physical contact with the MPL after implantation, while the matching of the optical zone diameter and the patient's pupil diameter determines the range and effect of visual coverage. By combining the dynamic matching characteristics of the corneal curvature and the posterior surface of the lens, the fit of the implant can be optimized, and the correction of dynamic intraocular pressure changes can further improve the accuracy of the fit. If dynamic factors are ignored, the post-implantation fit performance may be reduced, ultimately affecting the patient's visual quality. Through the above steps, problems such as postoperative physical discomfort and blurred vision can be reduced.

[0049] In a possible implementation, the implantation position floating value IPF is calculated with reference to the following formula:

[0050]

[0051] Among them, Δd represents the linear offset value of the relative position of the lens during dynamic eye movement, Δθ represents the rotation angle offset value of the lens, and n is the total number of sampling points of the patient's eye movement. When calculating IPF, the lens material properties and the parameters of the optical zone design are corrected in real time. The lens material properties include the density of hydrophobic silicone, and the optical zone design includes the edge thickness.

[0052] It should be noted that the calculation of IPF is intended to quantify the impact of dynamic eye movement on the position of the implant, so as to evaluate and correct its dynamic stability. The linear offset value and the rotation angle offset value reflect the possible position changes during the implantation process, and the real-time correction of the lens material properties (such as density) and the optical zone design (such as edge thickness) can better adapt to the eye characteristics of different patients and improve the adaptation effect. Failure to consider these correction parameters may lead to insufficient implant stability or impaired optical performance.

[0053] In a possible implementation, an optical system analytical model for visual clarity evaluation is introduced into the optimization process:

[0054]

[0055] Among them, MTF(v) represents the variation of modulation transfer function with spatial frequency v, D represents the aperture diameter of the lens, and λ represents the wavelength of light. By calculating the MTF distribution of different schemes, the visual performance of MPL at night and under strong light conditions is optimized to ensure the visual stability of the transition areas of different optical zones.

[0056] It should be noted that the reason for introducing the modulation transfer function (MTF) model is that the aperture diameter of the lens and the wavelength of light jointly determine the physical limit of visual clarity. By calculating the MTF distribution under different schemes, the visual performance of the implant under various lighting conditions can be predicted, especially at night or in strong light conditions, to optimize the stability of the visual zone transition. The lack of this model may cause the implant to perform poorly in extreme lighting environments.

[0057] In a possible implementation, the optimization process adopts a multi-objective distribution optimization model in a genetic algorithm, specifically including:

[0058] Initialize the population and generate multiple randomization schemes;

[0059] According to the following non-inferior solution sorting formula, select the appropriate solution for crossover and mutation:

[0060]

[0061] Among them, R i is the sort value in the i-th direction, represents the performance of solution i on the jth objective, z j is the reference value of target j, σ j represents the standard deviation of target j, and m is the total number of optimization targets;

[0062] According to the final generated set of non-inferior solutions, the solution with the highest fitness is selected as the output result.

[0063] It should be noted that the multi-objective optimization model using genetic algorithms is designed to take into account multiple performance indicators (such as adaptability, visual clarity, and dynamic stability) at the same time, and to achieve rapid search for the global optimal solution. The non-inferior solution sorting formula can effectively screen out solutions with higher fitness, and further improve the optimization efficiency in subsequent crossover mutation. If single-objective optimization is directly used, some performance indicators may not be adequately weighed.

[0064] In a possible implementation manner, the calculation formula of the initial adaptation value IAS is:

[0065]

[0066] Among them, A d represents the corneal diameter, T c Indicates the depth of the anterior chamber, E s Indicates the thickness of the lens edge, L i Representing the minimum distance from the iris to the lens, IAS is used to preliminarily evaluate the physical fit of the MPL and to verify the reliability of the parameters in combination with the dynamic simulation results.

[0067] It should be noted that the IAS formula preliminarily evaluates the physical fit of the implant by integrating key parameters such as corneal diameter, anterior chamber depth, lens edge thickness, and iris-lens minimum distance. Its role is to provide a reliable reference basis for subsequent dynamic simulation and verify the rationality of the parameters. If these basic parameters are ignored, it may lead to deviations in the fit assessment at the initial stage of implantation.

[0068] In a possible implementation, the calculation formula of the implantation position floating value IPF is:

[0069]

[0070] Among them, x k and k The horizontal and vertical coordinates representing the position of the lens during dynamic eye movements, and represents the average coordinate value, n represents the total number of sampling points, and by calculating IPF, the dynamic implantation effect is monitored in real time, and the scheme generated in the genetic algorithm is fed back and corrected.

[0071] It should be noted that the above formula quantifies the horizontal and vertical position changes of the implant during dynamic eye movement, and provides a real-time monitoring basis for dynamic stability based on the average coordinate value. The stability of the generated solution in the genetic algorithm can be improved through feedback correction. If the dynamic feedback of IPF is not considered, the solution optimization results may perform poorly during actual implantation.

[0072] In a possible implementation, the dynamic fitting characteristics of the lens during the simulation process may be further refined, and the visual offset compensation value may be calculated using the following model:

[0073]

[0074] Among them, ΔV represents the visual deviation compensation value, k is the optical deviation coefficient in the simulation, which is dynamically calculated according to the patient's eye model, Δd represents the deviation value between the MPL lens position and the ideal position, and T represents the lens stabilization time.

[0075] It should be noted that by calculating the visual offset compensation value ΔV, the dynamic fit characteristic evaluation can be further refined, especially the relationship between the offset value and the stabilization time can be dynamically corrected. The purpose of this method is to ensure that the visual effect of the implant in a dynamic state is close to the ideal value, thereby improving the patient's postoperative experience. If the visual offset compensation is ignored, poor visual effects in a dynamic environment may result.

[0076] In one possible implementation, the final implantation plan can be dynamically monitored in real time, and a model based on the fluid dynamics of the aqueous humor can be used to jointly optimize the iris pressure and lens stability to maximize long-term stability and visual outcomes after surgery.

[0077] It should be noted that real-time dynamic monitoring combined with the anterior chamber aqueous fluid dynamics model can jointly optimize iris pressure and lens stability, thereby maximizing long-term stability and visual effects after surgery. Its role is to provide early warning and timely adjustments for potential postoperative problems (such as implant position drift or iris pressure) to ensure that the patient's postoperative effects are long-lasting and reliable. Without this dynamic monitoring mechanism, unexpected complications or deterioration of visual effects may occur after surgery.

[0078] In the embodiment of the present invention, it is assumed that a patient suffers from cataracts and vision deterioration and needs to implant MPL to achieve vision correction and multifocal vision restoration. This method optimizes the lens implantation scheme through genetic algorithm, combined with real-time dynamic monitoring, to ensure the stability and visual adaptability of the lens after implantation. The specific implementation steps are described below:

[0079] Patient eye parameter collection: Use ophthalmic imaging equipment to measure and record the patient's key eye parameters, including corneal diameter A d =12.5mm, corneal thickness C t =0.55mm, anterior chamber depth T c =3.2mm and ciliary sulcus distance S i=11.8mm. Combined with the patient parameters and the preset database, an initial solution set is generated, each of which includes the total lens diameter D, the optical zone diameter O z , focal range P r and the rear surface shape factor S f For example, an initial solution is D = 13.0 mm, O z =6.0mm, P r =[+3.0,-2.5]D,S f =1.5.

[0080] The initial adaptation value IAS of the initial solution is calculated using the formula:

[0081]

[0082] Among them, E s =0.4mm (lens edge thickness), L i =0.5mm (the minimum distance from the iris to the lens), calculated as:

[0083]

[0084] Preliminary screening: Set the threshold IAS>10 to screen out suitable implantation options.

[0085] In the genetic algorithm optimization part, 30 solutions are randomly selected from the initially screened solutions to form a population. Each individual code includes D, O z , P r and S f The visual clarity, optical zone coverage and dynamic implant stability were taken as optimization targets, and the comprehensive score was used as fitness. The dynamic implant stability was calculated using the following formula to calculate the implant position float value (IPF):

[0086]

[0087] Among them, the dynamic eye movement sampling point n = 1000, the position offset value Δd = 0.2mm, the rotation angle offset value Δθ = 0.05°, and the calculation results are:

[0088]

[0089] Genetic operations include selection, crossover and mutation, where selection can be to use the roulette wheel selection method to prioritize individuals with higher fitness, crossover can be to generate new individuals through single-point crossover, and mutation can be to modify the optical diameter O of individuals. z Random adjustment ±0.1mm.

[0090] The visual effects of the optimization schemes were simulated using a real-time optical simulation system, and the visual clarity of each scheme was evaluated using the modulation transfer function (MTF):

[0091]

[0092] Where, the wavelength of light λ = 550nm, the spatial frequency v = 30 cycles / mm, and the calculation is:

[0093]

[0094] For solutions that perform poorly in optical simulation, adjust the focal power range P r And recalculate the fitness.

[0095] Finally, according to the optimal solution output by the genetic algorithm (for example, D = 13.2 mm, O z =6.2mm, P r =[+3.5,-2.0]D,S f =1.6), prepare the lens and implant it into the patient's eye. During the operation, a real-time monitoring system is used to record the lens position deviation and calculate the visual deviation compensation value:

[0096]

[0097] Where k = 1.2, Δd = 0.2 mm, stabilization time T = 2.5 s, the calculation is:

[0098]

[0099] The lens position is adjusted according to the compensation value to ensure stable postoperative visual effects. The anterior chamber hydrodynamic model is used regularly after surgery to evaluate iris pressure and lens stability, and the implantation parameters are adjusted through simulation analysis to extend the service life of the lens.

[0100] After surgery, the patient's vision was judged to be improved and to what extent based on the patient's vision clarity at far, medium and near distances, the dynamic implant stability index IPF and night vision. For example, the patient's vision was significantly improved after surgery, with vision clarity at far, medium and near distances reaching 95%, 90% and 85% respectively. The dynamic implant stability index IPF < 0.01, and the night vision was good.

[0101] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0102] (1) In the present invention, by combining genetic algorithms with ocular genome analysis, a personalized ocular health profile can be provided for each patient, and the interaction between the ocular environment and MPL implantation can be accurately simulated, thereby achieving the optimal lens implantation plan, solving the problem of insufficient personalized treatment in the prior art;

[0103] (2) In the present invention, by real-time monitoring of ocular biomarker data and feeding back the monitoring results to the algorithm system, the treatment plan is dynamically adjusted to effectively respond to changes in the postoperative ocular environment, thus solving the problem of the inability to adjust the treatment plan in real time after surgery in the prior art;

[0104] (3) In the present invention, the combination of genetic algorithm and simulation optimization technology enables the optimization of parameters such as the lens implantation angle and optical focal length, thereby improving the implantation effect and reducing postoperative complications, and solving the problem of insufficient accuracy of lens implantation schemes in the prior art.

[0105] Reference Manual Attached Figure 2 , shows a structural schematic diagram of a MPL implantation optimization and real-time adjustment system based on a genetic algorithm provided in an embodiment of the present invention.

[0106] The present invention also provides a genetic algorithm-based MPL implantation optimization and real-time adjustment system, which is applied to the genetic algorithm-based MPL implantation optimization and real-time adjustment method, comprising:

[0107] Processor 201.

[0108] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the MPL implantation optimization and real-time adjustment method based on genetic algorithm as in the method embodiment is implemented.

[0109] The MPL implantation optimization and real-time adjustment system based on genetic algorithm provided by the present invention can execute the MPL implantation optimization and real-time adjustment method based on genetic algorithm and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0110] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0111] (1) In the present invention, by combining genetic algorithms with ocular genome analysis, a personalized ocular health profile can be provided for each patient, and the interaction between the ocular environment and MPL implantation can be accurately simulated, thereby achieving the optimal lens implantation plan, solving the problem of insufficient personalized treatment in the prior art;

[0112] (2) In the present invention, by real-time monitoring of ocular biomarker data and feeding back the monitoring results to the algorithm system, the treatment plan is dynamically adjusted to effectively respond to changes in the postoperative ocular environment, thus solving the problem of the inability to adjust the treatment plan in real time after surgery in the prior art;

[0113] (3) In the present invention, the combination of genetic algorithm and simulation optimization technology enables the optimization of parameters such as the lens implantation angle and optical focal length, thereby improving the implantation effect and reducing postoperative complications, and solving the problem of insufficient accuracy of lens implantation schemes in the prior art.

[0114] The above contents are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0115] There are a few points to note:

[0116] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0117] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0118] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0119] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for optimizing and adjusting MPL implantation in real time based on genetic algorithm, characterized in that: include: S1. Obtaining the patient's eye structural parameters, wherein the structural parameters include corneal diameter, corneal thickness, anterior chamber depth and ciliary sulcus spacing, and generating multiple MPL initial implantation plans to form an initial plan set according to a preset data set, wherein the parameter set of each plan includes the total diameter of the lens, the diameter of the optical zone, the focal power range and the shape factor of the posterior surface of the lens; S2. Calculate the initial adaptability of each solution to the patient's eye characteristics using the Initial Adaptation Score (IAS). The IAS is calculated based on the patient's eye dynamic model and the simulated stability after lens implantation, with specific reference to the ratio of the anterior chamber depth to the total diameter of the MPL lens and the width of the iris-lens gap after implantation. S3. Based on a genetic algorithm, the initial solution set is optimized through selection, crossover and mutation operations, with the objectives including post-implantation visual clarity and optical zone coverage. During the optimization process, an implantation position floating value (Insertion Position Float, IPF) is introduced to represent the floating stability of the actual implantation position of the MPL during dynamic eye movement, and the solution is adjusted in real time in combination with the patient's eye model; S4. For each optimized solution, the implantation effect is simulated using a real-time optical simulation system, and the solution parameters are fine-tuned by comparing the deviation between the actual lens floating path and the theoretical expected path; S5. Based on the optimized solution set, select the solution with the highest comprehensive IAS and IPF scores, generate the final implantation parameters, and monitor and adjust them in real time during the implementation process to ensure the stability and adaptability of the lens.

2. The MPL implantation optimization and real-time adjustment method based on genetic algorithm according to claim 1, characterized in that: The initial adaptation value IAS specifically includes: The calculation of the initial adaptation value IAS is based on the following steps: Calculate the range of distance variation between the iris and the lens to determine whether the MPL may induce physical contact after implantation; Combine the optical zone diameter with the patient's pupil diameter range to analyze the visual coverage area after implantation; The dynamic fit characteristics are evaluated based on the matching degree between the patient's corneal curvature and the posterior surface of the lens, and the overall fit is corrected in combination with the dynamic intraocular pressure changes.

3. The MPL implantation optimization and real-time adjustment method based on genetic algorithm according to claim 1 is characterized in that: The implantation position floating value IPF specifically includes: The implantation position floating value IPF is calculated with reference to the following formula: Among them, Δd represents the linear offset value of the relative position of the lens in dynamic eye movement, Δθ represents the rotation angle offset value of the lens, and n is the total number of the patient's eye movement sampling points. When calculating IPF, the lens material properties and the parameters of the optical zone design are simultaneously corrected in real time. The lens material properties include the density of hydrophobic silicone, and the optical zone design includes the edge thickness.

4. The MPL implantation optimization and real-time adjustment method based on genetic algorithm according to claim 1 is characterized in that: The optimization process specifically includes: An analytical model of the optical system for visual clarity evaluation is introduced during the optimization process: Among them, MTF(v) represents the change of modulation transfer function (Modulation Transfer Function) with spatial frequency v, D represents the aperture diameter of the lens, and λ represents the wavelength of light. By calculating the MTF distribution of different schemes, the visual performance of MPL at night and under strong light conditions is optimized to ensure the visual stability of the transition area of ​​different optical zones.

5. The MPL implantation optimization and real-time adjustment method based on genetic algorithm according to claim 4 is characterized in that: The optimization process further comprises: The optimization process adopts a multi-objective distribution optimization model in a genetic algorithm, which specifically includes: Initialize the population and generate multiple randomization schemes; According to the following non-inferior solution sorting formula, select the appropriate solution for crossover and mutation: Among them, R i is the sort value in the i-th direction, represents the performance of solution i on the jth objective, z j is the reference value of target j, σ j represents the standard deviation of target j, and m is the total number of optimization targets; According to the final generated set of non-inferior solutions, the solution with the highest fitness is selected as the output result.

6. The MPL implantation optimization and real-time adjustment method based on genetic algorithm according to claim 2 is characterized in that: The initial adaptation value IAS further includes: The calculation formula of the initial adaptation value IAS is: Among them, A d represents the corneal diameter, T c Indicates the depth of the anterior chamber, E s Indicates the thickness of the lens edge, L i Representing the minimum distance from the iris to the lens, IAS is used to preliminarily evaluate the physical fit of the MPL and to verify the reliability of the parameters in combination with the dynamic simulation results.

7. The MPL implantation optimization and real-time adjustment method based on genetic algorithm according to claim 3 is characterized in that: The implantation position floating value IPF further includes: The calculation formula of the implantation position floating value IPF is: Among them, x k and k The horizontal and vertical coordinates representing the position of the lens during dynamic eye movements, and represents the average coordinate value, n represents the total number of sampling points, and by calculating IPF, the dynamic implantation effect is monitored in real time, and the scheme generated in the genetic algorithm is fed back and corrected.

8. The method for optimizing and adjusting MPL implantation in real time based on genetic algorithm according to claim 7, characterized in that: The dynamic fit further comprises: The dynamic fitting characteristics of the lens during the simulation are refined, and the visual offset compensation value is calculated using the following model: Among them, ΔV represents the visual deviation compensation value, k is the optical deviation coefficient in the simulation, which is dynamically calculated according to the patient's eye model, Δd represents the deviation value between the MPL lens position and the ideal position, and T represents the lens stabilization time.

9. The method for optimizing and adjusting MPL implantation in real time based on genetic algorithm according to claim 1, characterized in that: Further including: Real-time dynamic monitoring of the final implantation plan and the use of a model based on the anterior chamber aqueous fluid dynamics to jointly optimize iris pressure and lens stability to maximize long-term stability and visual outcomes after surgery.

10. A MPL implantation optimization and real-time adjustment system based on genetic algorithm, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the MPL implantation optimization and real-time adjustment method based on a genetic algorithm as described in any one of claims 1 to 9 is implemented.

Images