Systems and methods for ocular finite element modeling and machine learning

Abstract

The hardware and software system solution provides a real-time, interactive and predictive simulation of the eye (e.g., human eye and animal eye). The predictive simulation of the human eye can be created using a Finite Element Model (FEM) of the ocular structures involved in the optical biomechanics, including accommodation.

Description

[Technical field]

[0001] The subject matter described herein relates to ocular finite element modeling (FEM) and machine learning, and more particularly to a virtual ecosystem configured to provide a real-time, dynamic, interactive virtual eye image reproduction of a biological eye in a plurality of condition states in virtual reality using a plurality of associated predictive simulation algorithms. The interactive virtual eye image can represent individual-specific mechanical, material, and physical properties and can represent or mimic the behavior of a biological eye (regardless of species) under various conditions and demands, i.e., surgical interventions, therapeutic interventions, progression of representative disease processes. Furthermore, the present invention can communicate the numerical simulations and results of these various interventions, including interventions and reversal of disease processes. Furthermore, the present invention is configured to apply numerical methods and calculations to any data source to predict a plurality of expected and unexpected states and events in the biological eye.

[0002] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims priority to U.S. Patent Application No. 63 / 334,107, filed April 23, 2022, entitled "SYSTEMS AND METHODS FOR OCULAR FINITE ELEMENT MODELING AND MACHINE LEARNING," the contents of which are incorporated herein by reference in their entirety. [Background technology]

[0003] The eye is a biomechanical structure that contains complex muscular, excretory, and fluid mechanisms responsible for visual function and intraocular biological transport. The accommodative system is the main motor system of the ocular apparatus and facilitates many physiological and visual functions of the eye. The physiological role of the accommodative system is to transport aqueous humor, vitreous humor, blood, nutrients, oxygen, carbon dioxide, large and small molecule drugs, and other cells within the ocular apparatus.

[0004] In general, the decline in accommodative ability in presbyopia is related to many factors related to the lens that are affected by aging, factors outside the lens, and physiological factors. AGEs (Advanced Glycation End Products) = When AGEs accumulate, harmful chemical bonds are formed, which increases the biomechanical stiffness of the connective tissues in the body, including the eyeball.

[0005] The age-related increase in eye rigidity may put stress and strain on these ocular structures, affecting their ability to accommodate. This may affect the eye in the form of reduced biomechanical dysfunction in physiological processes such as visual accommodation, aqueous and vitreous fluid dynamics, and ocular pulsatile blood flow. Current surgeries only manipulate the optics by some artificial means, such as refractive laser surgery, adaptive optics, and corneal or intraocular implants, and ignore the importance of altering the refractive power of one optic of the eye and preserving the other optic nerve and the physiological function of the accommodation mechanism.

[0006] Furthermore, current devices implanted in the sclera have a mechanical effect on accommodation. These methods do not take into account the effect of pores (e.g., micropores) or the creation of a matrix array of pores in a three-dimensional tissue. Therefore, current procedures and devices are unable to restore normal ocular physiology. Summary of the Invention [Problem to be solved by the invention]

[0007] Therefore, there is a need for improved systems and methods for restoring normal ocular physiology. [Means for solving the problem]

[0008] Generally, presented herein are hardware and software system solutions that provide real-time, interactive, predictive simulation of an eye (e.g., a human eye or an animal eye). As described in more detail below, the predictive simulation of the human eye can be created using a finite element model (FEM) of ocular structures involved in optical biomechanics, including accommodation.

[0009] In one aspect, a system for the reproduction, manipulation and intervention of a human eye in virtual reality is disclosed, comprising a 3D modeling component consisting of at least one data processor, an imaging system, a bio-thermal system, an interactive user interface, an input program for receiving and manipulating physical, biometric, biomechanical, material and mechanical information and data, and at least one memory for storing instructions, which when executed by the at least one data processor performs operations including: generating a first individualized simulation in which the Bruch's membrane choroid is activated to determine a first contribution of energy required for deformation of the lens of the eye; generating a second individualized simulation in which an origin of a ciliary muscle fiber section of the individual's eye is activated to determine a first contribution of the first ciliary muscle fiber section to deformation of the lens of the eye; and generating a second individualized simulation in which a second ciliary muscle fiber section of the individual's eye is activated to determine a second contribution of the second ciliary muscle fiber section to deformation of the lens of the eye; generating a third individual-specific simulation in which a third ciliary muscle fiber section of the individual's eye is activated to determine a third contribution of the second ciliary muscle fiber section to deformation of the eye's lens; and determining one or more parameters of a treatment for the individual based on at least the first Bruch's membrane-choroid complex (BMCC) apparatus, the first contribution of the first ciliary muscle fiber section, the second contribution of the second ciliary muscle fiber section, and the third contribution of the third ciliary muscle fiber section. All simulations can be performed sequentially, alone, or in parallel with other parameter manipulations. The system can further generate a fluid-structure interaction of the aqueous humor flow of the eye with three outflow pathways activated. The system includes one or more parameters of the Bruch's choroid apparatus, the first ciliary muscle fiber section, and / or the second ciliary muscle fiber section, and / or the third ciliary muscle fiber section of the individual's eye. In one embodiment, one or more micropores are created by a laser in the scleral tissue of the eye over the Bruch's choroid apparatus, the first ciliary muscle fiber portion and / or the second ciliary muscle fiber portion and / or the third ciliary muscle fiber portion of the individual's eye.The one or more parameters of the treatment may include an amount of matrix containing one or more pores, an arrangement of the matrices, an overall shape of each matrix, an overall dimension of each matrix, an amount of pores in each matrix, a distribution of pores in each matrix, and / or a depth of pores in each matrix. In an embodiment, the one or more treatment parameters for the individual are determined by applying a machine learning model, such as a regression model or algorithm, an age progression model or algorithm, etc. The machine learning model can be trained based on various combinations of treatment parameters and treatment outcomes. The machine learning model is further trained based on individual demographic data associated with various combinations of treatment parameters and treatment outcomes. A user interface can be generated that displays the one or more parameters of the treatment for the individual. The system can further include receiving at least one user input via the user interface related to the one or more parameters of the treatment for the individual, and updating the machine learning model based at least on the user input.

[0010] Operations further include a system and method for assessing tissue biomechanical properties, including a simulated generator incorporating various optical, biomechanical, and physical properties of a given human eye into a simulated VR phantom of a living eye, and / or a parameter calculation component calculating values ​​of the biomechanical properties at a subset of a number of eye positions (Hoop stress maps) where the virtual eye is interactive, and / or an eye physics calculation. The evaluation toolbox component is configured to calculate at least one parameter related to various possible outcomes of a given therapeutic intervention in the human eye from the extracted features. The system output is configured to provide the calculated at least one parameter to one of a therapeutic system and a user. One or more optical, biometric, biomechanical, physical, and geometric parameters are incorporated into the computational prediction. The VESA calculator toolbox can adjust the equations to provide the most optimal therapeutic or surgical intervention for the user.

[0011] In another aspect, a system for evaluating a patient's eye is disclosed, the system comprising: a modeling component configured to determine a representation of the entire eye from a three-dimensional structural image of the entire eye and at least one biomechanical property of the eye, a feature extractor configured to extract a plurality of features from the model of the entire eye, and a user interface configured to accept input from a clinician defining an objective function as a function of at least one parameter of the eye after a therapeutic procedure; a condition or disease assessment component configured to calculate at least one parameter related to a risk of disease of the eye from the extracted plurality of features and the objective function, the calculated at least one parameter including variables in the surgical process representing therapeutic procedures, therapeutic interventions, and / or surgical parameters that can be changed by the clinician in the therapeutic procedure; and a system output configured to provide the calculated at least one parameter to one of a treatment system and a user.

[0012] The details of one or more variations of the subject matter described herein are set forth in the accompanying drawings and the description below. Other features and advantages of the subject matter described herein will become apparent from the description and drawings, and from the claims. [Brief description of the drawings]

[0013] [Figure 1A] Figure 1A shows the VESA, 3D-ID AI, MP tool, and regression database and their interrelationships. [Figure 1B] FIG. 1B shows an exemplary process flow chart. [Figure 2A] FIG. 2A illustrates the VESA ecosystem with various hardware / software systems that reside in the procedure room, in the cloud, and / or in a database. [Figure 2B] Figure 2B shows the various technologies and tools that make up the backend services of the VESA ecosystem. [Figure 2C] Figure 2C shows multiple subsystems of the VESA ecosystem, including standalone diagnostic tools, clinical trial tools, lasers, imaging devices, AI engines, and more. [Figure 2D] FIG. 2D shows two of many disease application modules. [Diagram 3] Figure 3 shows the contribution of VESA at various stages of major medical procedures. [Figure 4] FIG. 4 shows the structure, various measurable variables, and boundary conditions that can be used to generate a finite element model of the eye. [Diagram 5] 5 shows an exemplary zone definition that can be used to generate a finite element model. The zone definition can be applied to any region of the eye, including the posterior segment, anterior segment, and other regions. [Figure 6] FIG. 6 shows examples of each of the zone descriptions or anatomical locations for one or more regions of the eye. [Figure 7] Figure 7 shows an example of a 3D model generated by VESA. [Figure 8] Figure 8 shows the FEM created with more fibers and elements. [Figure 9] Figure 9 shows an example of a mesh network for a 3D model of an eyeball. [Figure 10] FIG. 10 shows an example of an anatomical model that VESA uses to generate the trabecular meshwork and other aspects of the eye, including the ciliary body zonules, the lens, and other ocular anatomical structures. [Figure 11] FIG. 11 shows an example of an anatomical model that VESA uses to generate the trabecular meshwork and other aspects of the eye, including the ciliary body zonules, the lens, and other ocular anatomical structures. [Figure 12] FIG. 12 shows an example of an anatomical model that VESA uses to generate the trabecular meshwork and other aspects of the eye, including the ciliary body zonules, the lens, and other ocular anatomical structures. [Figure 13A]FIG. 13A shows the first step where the raw data is read in and converted into a pseudo 2D mesh array. [Figure 13B] FIG. 13B shows the image before and after the smoothing process. [Figure 14] FIG. 14 shows a micropore analysis tool consisting of OCT (optical coherence tomography). [Figure 15] FIG. 15 shows a screenshot of the pre-planning mode. [Figure 16] FIG. 16 shows a micro-hole tool including registration features. [Figure 17] Figures 17 and 18 show an example of the steps and workflow of the pre-scan visit process. [Figure 18] Figures 17 and 18 show an example of the steps and workflow of the pre-scan visit process. [Figure 19] Figure 19 is an example screenshot. [Figure 20] FIG. 20 is a block diagram illustrating an example of a computing system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] The systems and methods described herein include many aspects that may be usefully employed in combination or separately, and may be advantageously used to treat a variety of medical conditions, both ocular and elsewhere in the body. At least some of the particularly detailed examples focus on treating ocular conditions, such as age-related glaucoma, cataract formation, treating presbyopia, and treating other age-related eye diseases, such as age-related macular degeneration.

[0015] Generally, hardware and software system solutions are presented herein that provide a real-time, interactive, predictive simulation of the eye (e.g., human eye and animal eye). As described in more detail below, the predictive simulation of the human eye can be created using a finite element model (FEM) of the ocular structures involved in optical biomechanics, including accommodation. Unlike previous eye models, the present FEM described herein is a three-dimensional (3D) FEM of the accommodative mechanisms, including but not limited to the human anterior segment, that simulates the action of ciliary muscle fiber contraction to predict the dynamic deformation of the crystalline lens required for the change in optical power due to accommodation, described herein as "central optical power" (COP). The present FEM further describes the mechanisms of aqueous / vitreous outflow and fluid flow, described herein as "fluid mechanics". The virtual FEM further describes the biomechanics of the posterior segment, simulating the action of Bruch's membrane, retina, vitreous, and lamina cribrosa in the pre-stretch, accommodative relaxation, and accommodative movements of the eye.

[0016] More specifically, the disclosed system and method includes a Virtual Eye Simulation Analyzer (VESA). VESA utilizes a virtual eye model to create an accurate and realistic virtual interactive model of a human eye, and then provides a 3D FEM based on such model to develop treatment options, predict the future state of the eye based on the individual's age, material properties, optical properties, and other physical parameters, and to enable predicting the effects of various operations such as surgery, therapeutic interventions, and disease states. Thus, the virtual model of the human eye holds among its components bio-information, mechanical information, optical information, and physical information as the unique 3D-ID of the human eye. Furthermore, the resulting virtual 3D FEM model, and thus the VESA, allows a user (e.g., user, consumer) to examine the biomechanical properties and various physical, optical, and physiological conditions (e.g., accommodation, accommodation laxity, glaucomatous, etc.) of the virtual 3D model, so that, for example, the user can more accurately simulate various treatments and determine the therapeutic effects on the individual's real eye. In other words, VESA provides an in silico (in-computer) virtual method to perform multiple treatments and operations on an individual's virtual eye model and determine in real time output information (e.g., scleral notch, ciliary muscle fiber movement, lens movement and shape) that can inform the user of the current and future treatment effects, outcomes, and probability of success on the human eye.

[0017] An exemplary chart showing VESA, 3D-ID AI, MP Tools, and Regression Database and their interrelationships is shown in Figure 1A. While this diagram shows VESA in isolation from the 3D-ID AI, MP Tools, and Regression Database components, these components are essentially part of the VESA ecosystem. As shown in Figure 1A, VESA contains various elements, which are described in more detail below.

[0018] Regression Database: A cloud database configured to store pre-run and manual personalized Finite Element Analysis (FEA) models, whether from structural analysis, fluid analysis, or micropore tools (i.e., captured from pre- and post-operative clinical trials). For example, inputs can include individual specific treatment or treatment data results and specific ocular geometric variables, and the data and regression output are entered into the database. Rather than running computationally intensive FEA simulations in real-time during the procedure, this database allows VESA to reference and retrieve pre-run FEA results in a cloud library database that can be assigned to the individual subject, thereby proposing possible pore matrix laser firing solutions to achieve the desired results.

[0019] Laser scleral microporation (LSM) is a type of treatment applied to the human eye, aiming to uncrosslink microfibrils underlying human scleral tissue. Here we describe a numerical analysis package called the Micropore Tool (MPTool), based on the stiffness of the eye and Newtonian mechanics. Using OCT images as the main input data, the MPTool creates a data structure that represents the internal and external shape of the eye, the geometric parameters of all individual pores, and the geometry of the pore matrix for all treatment areas of both eyes, for a specific individual's eye characteristics. The MPTool further allows the medical engineer to experiment in virtual reality to adjust the depth, diameter, and spacing of the pores, decreasing their biomechanical stiffness or increasing their flexibility, so that VESA can run numerous simulations to suggest the optimal pattern, depth, and placement of the holes. The MPTool receives mathematical and physical input from the Ligament Efficiency Tool (LET), which is able to calculate and predict the strength, flexibility, and tissue differences between each pore (i.e., ligament). Numerous simulations are performed so that the LEC can suggest an improved or most ideal pore placement. The MP tool can create a regression equation database for VESA, and VESA's FEM can be derived from literature images as well as from personal post-procedure analysis that can be used to train VESA's neural network. Hyperelastic image registration is image restoration within 3D FEM including registration of non-linear deformations and shape changes (e.g. during clinical trials). Micropore tools contain various parts. VESA can be equipped with multiple customizable toolboxes for various surgical and / or therapeutic virtual reality interactions and interventions. Some preferred embodiments currently being developed are: Micropore Tools Artificial Intelligence and Machine Learning Module (AI_ML): AI_ML is a set of routines that pre-process OCT images and prepare the data for further analysis. Tasks performed by the AI_ML routines include: -Read proprietary binary OCT format, -Pre-process the data and create multiple data structures to represent all quadrants, eyes, and patients of the treatment session. These data structures may include, but are not limited to: --Mesh-like micropore tool pore matrix squares based on OCT analysis. --Image color division --Dividing organizational boundaries --Thickness from top to bottom --Individual pore geometry: including, but not limited to, the three-dimensional coordinates of the pore centroid, pore volume, depth, diameter, volume fraction, and density. --Detection of characteristic edges. --RGB real-time biofeedback color recognition depth control function 3 - Perform several color smoothing and interpolation routines. -Perform feature recognition to distinguish between upper and lower scleral thickness and air gaps. -Perform an automatic tissue segmentation routine to distinguish the layers of the sclera-conjunctiva-choroid geometric complex. -Perform edge detection post-processing on the outer border of the episcleral layer and the underlying layer. -Saving the results of pre-processing in a second set of data structures (PVF, NSI, COP, IOP, etc.) for reading by various downstream tools. -Prepare data for use with Micropore Tools, PVF Calculators and NSI Calculators, Micropore Tools Physics Package 1. Pore volume fraction display tool: A graphical user interface (GUI) evaluation and validation tool to measure the pore volume fraction over a specified 1D, 2D, or 3D area. The pore volume fraction varies with scleral thickness depending on the zone, pore shape, pore density, and pore size. The pore volume fraction display tool can provide information on the removed tissue, except for the location information. 2. Intraocular Pressure Prediction: The Intraocular Pressure Calculation Prediction tool is a tool that can predict and measure the changes in intraocular pressure within the eye and evaluate the current or future effects that will occur based on the primary condition of a person's eye and / or the selected intervention through the release and change of hydrostatic pressure and hydrodynamics. 3. Elastic Modulus Calculator: Processes biomechanical and physical data input from the biometer and takes into account the material properties, biomechanics, geometry and bioshape of the ocular tissues. It has three applications: pre-treatment planning, pre- and post-treatment evaluation, validation and post-treatment validation. 4. Negative stiffness index (NSI) / quotient calculator (NSQ) / prediction (NSP): Real-time Material Properties & Biomechanical Property Calculator showing the Negative Stiffness Modulus of change in biomechanical properties / physical outcome of ocular tissues during and after treatment. One preferred embodiment shows the properties and biomechanical properties of scleral tissue before and after LSM treatment. In this example, there are four quadrants (Q1-Q4) of the eye that are treated with the LSM technique and are treated until the desired NSQ is met for the given tissue. Inputs are from a biometer, a Ligament Efficiency Calculator (LEC) and an Elastic Modulus Calculator (EMC). 5. Ligament Efficiency Tool (LET): A physics package of the MicroPore Tool (MPTool) that determines various factors including (but not limited to) hole placement and appropriate surgical decisions. MPTool - Eyeball stiffness post-processing tool - Hyperelastic Image Restoration (HIR): HIR is a highly robust numerical simulation of hyperelastic as a regularization, introducing a new stable numerical implementation of highly nonlinear deformations. -OCT tissue / color segmentation: Depth sensing tool AI automatic segmentation software Visible on OCT scan Creating an augmented reality view of the biometric tissue layers of the eye. The overlay shows key tissues such as the cornea, sclera, conjunctiva, zonules, ciliary muscle fibers, and Tenon's capsule, correlating colors from an RGB database with real-time interactive tissue identification. Micropore Tools Simulation Package: The simulation package consists of a toolset that allows the same pore matrix analysis tools to be used on simulated pores, pore matrices, and human eyes, rather than on real pores, pore matrices, and human eyes. The toolset includes: -Multiple sets of FEA runs to fully depict individual patient eyes and possible LSM outcomes -Database: Run an FEA and then run a regression algorithm on that data. -Live finite element analysis performed simultaneously with LSM processing -Empirically derived numerical methods such as moment of inertia

[0020] FEM Geometry and Mesh: A commercial FEM biomechanical simulation software was used to generate the geometry and mesh of a complex human eye model. Inputs are geometric data obtained, for example, from published literature (e.g., literature images, hyperelastic image restoration (HIR)) and / or regression equation databases, ultrasound biomicroscopy (UBM), optical coherence tomography (OCT), scanning electron microscopy (SEM), and histology. For this FEM geometry and mesh analysis, the geometry is created in SpaceClaim and the mesh is created in ANSYS. Boundary conditions, loads, elastic supports, Neo-Hooken material properties, stresses, tensions, forces, moments, displacements, etc. are applied within ANSYS. Zones: As will be described in more detail below, the eye FEM geometry and mesh are constructed with zones that are constructed of distinct pore matrix firing regions selected based on the geometric locations of specific anatomical landmarks found in the literature and / or regression databases.

[0021] VESA Structural FEM: Accommodative eye model built in ANSYS. Inputs include, but are not limited to, FEM geometry and meshes. Outputs include, but are not limited to, simulation of accommodative models for multiple age eyes, and improved accommodation based on diopter value changes in an individual's visual acuity captured from Central Optical Power (COP) calculations. Laser scleral microporation: See above. Central Optical Power Calculator: This calculator concerns the COP of the crystalline lens. Given that deformation of the crystalline lens changes its optical power in diopters (D), this calculator is designed to calculate the free body forces of the crystalline lens. The input can include, for example, data from accommodation simulations before and after an LSM procedure. An alternative and extended formula for this calculation is presented, using measurements calculated with ray tracing as direct input to the COP. This is why the invention is novel. An example embodiment is a lens equation derived by ray tracing, where the lens shape is determined by finite element analysis. The shape is then exported to, e.g., a software process that traces the paths of rays in both accommodated and unaccommodated states. The COP is then determined as follows:

number

[0022] VESA Fluid Simulation: Computational Fluid Dynamics (CFD) and Fluid / Solid Interaction (FSI): Similar to the VESA structural FEM, but here an eye model of accommodation concept built within ANSYS captures dynamic fluid, inflow and outflow as well. Thus, inputs include, but are not limited to, the same geometry / mesh data as the FEM geometry and mesh. For example, geometric fluid paths are added that are assigned for the movement of specified fluids based on clinical studies and literature. Similar to the VESA structural FEM, outputs here include, but are not limited to, simulation of the accommodation model of the eye at multiple ages, and improved accommodation based on the change in diopter value of the individual's visual acuity captured from the central optical power (COP) calculation. Furthermore, by incorporating fluids in the FSI model, the VESA FEM is more accurate to the reality of how the human eye functions. This is because the VESA structural FEM includes assumptions that account for the lack of dynamic fluids in the FEM. For example, it can be assumed that fluids are present and incompressible. That is, in this case, the volume inside the car remains constant during the stay.

[0023] 3D-ID: The input can include an individually specified VESA structural / fluid model (FSI) that is analyzed by accommodation simulation before and after the LSM procedure. The result is an accommodation improvement based on the change in the individual's visual acuity in diopters obtained from the central optical power calculation. In this way, the VESA can be used as a virtual platform to import individual-specific eye-related data, so that every person's eye becomes his or her own VESA structural and / or fluid model. The 3D-ID also includes the individual's concrete shape stored in a CAD file or similar database. The 3D-ID includes all the individual-specific metadata collected during the treatment process, such as name, age, sex, ethnicity, etc.

[0024] 3D-ID AI: The 3D-ID AI is a machine learning based analytical engine communicatively coupled with the VESA, MP tools and regression equation database. The 3D-ID is further derived from an "age progression" equation that accounts for standard gradual changes in material properties and changes in biological geometry that occur with age. The 3D-ID AI can apply deep learning or regression of one or more off-the-shelf machine learning or custom regression models trained to determine one or more individual specific treatment parameters based on real-time FEA simulations performed by the VESA and / or existing individual specific FEA models from the regression equation database. The machine learning models associated with the 3D-ID AI can include regression models (and other machine learning models) trained based on simulation data and / or clinical data of various treatment parameters, conditions, treatment outcomes (e.g., improvement in accommodation based on change in diopter value of an individual's visual acuity derived from central optical power calculations). Through this training, the 3D-ID AI machine learning model learns the relationship between the combination of different eye conditions, the treatment parameters and corresponding treatment outcomes, and the progressive trends of response to treatment, such as age-related changes in material properties over time. Additionally, in some cases, the 3D-ID AI machine learning model may be trained to take into account additional personal data, such as demographic information. Thus, the 3D-ID AI can determine in silico (in computer) the precise treatment parameters appropriate for each individual prior to performing the in vivo treatment. For example, in some exemplary embodiments, the output of the 3D-ID AI may be a dosage for a particular individual, including one or more of the pore matrix configurations, such as the amount of matrix, the arrangement of the matrices, the overall shape of each matrix, the overall dimensions of each matrix, the amount of pores in each matrix, the distribution of pores in each matrix, and the depth of the pores in each matrix. For example, another output of the 3D-ID is a prediction of the amount of treatment over time, as well as the number of treatments required over a period of time. For example, another output of the 3D-ID may be a suggestion of a type of intraocular lens that is more appropriate or desirable for a particular outcome in a human eye, taking into account the conditions of the human eye, with respect to its ability to achieve a COP at various focal positions.For example, another output of 3D-ID is a suggestion of a type of Minimally Invasive Glaucoma Surgery (MIGS) implant that may be more appropriate or desirable for a particular outcome in a person's eye, taking into account the conditions of that individual's disease state. Via the 3D-ID plugin, VESA can be presented with multiple virtual treatment options to solve a particular individual's eye.

[0025] It should be understood that the 3D-ID AI machine learning model may undergo additional, and possibly ongoing, training. For example, for a set of treatment parameters output by the 3D-ID AI, the 3D-ID AI may receive feedback from the user performing the treatment, including real-time adjustments made to one or more treatment parameters. The 3D-ID AI machine learning model may be updated based on these additional data points, such that the 3D-ID AI machine learning model can learn additional and / or more nuanced relationships between treatment parameters, treatment outcomes, and other individual-specific data (e.g., demographics).

[0026] VESA may include additional elements such as, but not limited to: · Registration Tools: Micropore Registration Tool (MIRT): Uses the Matrix Registration Tool (MART) and provides information on the pattern as well as the dynamic position of the pores and spots. · Microporation · Biometer Elastic Modulus Calculator (EMC) and individual biomechanical / physical inputs into 3D-ID VESA components: age-related mpa, depth, PVF, bulk density (aka part stiffness), density, pore size, pore shape (square). Treatment Progress Meter: A progress meter for treatment progress, synchronized with a time clock for each quadrant countdown. This is done for each quadrant that incorporates a countdown. Treatment Countdown Clock: GUI treatment countdown clock. · Hyperelastic Image Registration (HIR) for UBM analysis: Converting inverse imaging of dynamic biomotion into 3D FEM. Artificial Intelligence / Neural Networks Statistical and / or heuristic approaches to implement the decision-making engine of the VESA system. ·Hoop Stress Coordinate Map: Real-time physics / depth calculations Global Positioning System (GPS). Hoop stress is the stress that occurs along the circumference of a pipe when pressure is applied. Hoop stress acts perpendicular to the axial direction. Hoop stress is a tensile stress and occurs to resist the bursting effect caused by the application of pressure. HSCM shows the various periphery diagrams present on a sphere that fit the hoop structure theory. Used to construct the hoop strain constitutive equation. HSCM is further useful in developing infinite treatment patterns, for example, forming pores for specific purposes based on the nodes and node arrangements that can be aligned using LSM to perform ideal treatment. 4D Hypersphere Coordinate Scanning & Whole-area Mapping (3D ID: Global Positioning System (GPS) post-processing tool for VESA FEM: Virtual OCT post-processing scanner. 4D HCSPM can be used as a training database for VESA. Resultant Force Calculator: Calculates free body forces and moments acting on the lens capsule of the eye. Used to determine the response speed and direction of the lens during accommodation. Spherical Stiffness Indicators: Shows the calculated stiffness of a 3D shell attached to a spherical coordinate system. Hoop stresses and strains are emphasized. Ocular stiffness coefficient: A mathematical formula predicting a constant as a macroscopic parameter characterizing the relationship between pressure and volume change in the human eye. Medication Adjustment Device: A medication adjustment device to control, predict, administer, calculate and report dosages of surgical, chemical, biochemical, therapeutic, physical, fluid, geometric, biological and / or biomechanical interventions in virtual reality.

[0027] Additionally, additional information regarding certain elements of the VESA can be found in U.S. Pat. No. 1,071,450 and U.S. Patent Publication No. 2020 / 0185106, each of which is incorporated by reference in its entirety into this specification.

[0028] VESA is configured to enable applications that were not possible with previous ocular modeling systems and methods. For example, such applications include identifying and visualizing the cause and effect relationships of accommodation intuition from the interrelated observation of ocular geometry, material properties, physical forces, and dynamic shape changes. Identification is achieved by VESA using FEM to predict the ciliary muscle fiber movements and force displacements (dynamic 3D shape changes) and model all stages of focal movement from far to near and near to far, or from pre-extension to accommodative relaxation to accommodation, or from maximum accommodation to accommodative relaxation to pre-extension. These stages, movements, and forces are the result of a combination of elastic energy stored in the BMCC, the specified ciliary muscle fiber structure, the specified ciliary zonules shape and structure, and their respective predetermined activations. The deformation (dynamic 3D shape change) of the crystalline lens from a pre-stretched state to an accommodative to accommodative relaxed state is due to a combination of a specified ciliary zonular geometry, a distortion of the capsule, and a predetermined tension, and / or a deformation of the crystalline lens during accommodation due to a stretching of the ciliary muscle fibers. The modeling component is configured to determine a three-dimensional finite element model of the entire eye from the three-dimensional structural image and at least one biomechanical property of the eye. The modeling component is configured to provide a three-dimensional finite element model representative of the entire eye after the therapeutic treatment, and the system further comprises a user interface configured to accept input from a clinician defining at least a type and a location of the therapeutic treatment. The feature extraction unit is configured to extract at least one feature of the plurality of features from the three-dimensional finite element model representative of the entire eye after the therapeutic treatment, and the ectasia evaluation component is configured to calculate a parameter representative of a predicted risk of ectasia for a patient given a therapeutic treatment having an associated type and location. The ectasia evaluation component is configured to perform a sensitivity analysis on the at least one feature such that a magnitude of an effect of a value of the at least one feature on the at least one parameter can be determined. The at least one extracted feature represents either a geometric or a biomechanical feature of the eye.The modeling component is configured to provide a three-dimensional finite element model representative of the entire eye under load, the system further comprising a user interface configured to accept input from a clinician defining at least a magnitude and a location of the load. The modeling component is configured to determine a finite element model of the entire eye from the three-dimensional structural image and the at least one biomechanical property of the eye. The objective function can be a function of at least one of a strain value and a stress value of the eye. The objective function can be a function of at least one measure of a refractive outcome. The modeling component can determine a representation of the entire eye as a virtual model consisting of a set of parameters extracted from evaluating the statistical model according to the three-dimensional structural image and the at least one biomechanical property of the eye.

[0029] Another application example could be the estimation of aspects of accommodative function that are currently not measurable experimentally. As an example, this estimation could be performed via the FEM of the VESA by analyzing the biomechanical effects of ciliary muscle fiber sections, activating each ciliary muscle fiber section in isolation and performing simulations to quantify its unique contribution to the lens deformation, and / or tensioning each zonula division in isolation and performing simulations to quantify its unique contribution to the lens deformation. Anatomical components of the accommodative system could be run individually to determine their unique contribution to the lens shape change output in virtual reality that cannot be investigated in vivo or ex vivo. VESA allows for infinite manipulation of geometry, activation, physical properties, material properties, biomechanical relationships and interactions that are not possible in vivo.

[0030] In addition, as described above, VESA provides an in silico experimentation function that allows users (e.g., physicians and surgeons) to understand the pathophysiology of accommodative dysfunction and determine effective treatment methods by running various simulations and "what if" scenarios. For example, in elderly people with age-related accommodative dysfunction (senile accommodative dysfunction), a simulation can be performed that reflects changes in activation of the ciliary muscle fiber site due to measured atrophy or connective tissue infiltration and compares the predicted accommodative response of the lens, or a simulation can be performed that changes the material properties of passive structures such as lens components and sclera sites alone and reflects measured stiffness changes in elderly people and compares the predicted accommodative lens response / COP, or a simulation can be performed that compares measured stiffness changes due to therapeutic interventions (e.g., intraocular lens replacement, scleral microperforation) and compares the predicted accommodative response of the lens.

[0031] In one exemplary VESA embodiment, the FEM identifies for each individual the exact ciliary muscle fiber sections where one or more holes need to be placed in different sections of the eye (e.g., scleral zones). This VESA FEM allows for in silico isolation of individual ciliary muscle fiber sections. For example, each simulation can isolate at least one ciliary muscle fiber section (or some combination of muscle fiber sections), so that at the end of x simulations, the user can determine the location and number of holes that need to be added to the eye. In other words, the VESA is configured to model not only the human eye as a whole, but also in discrete cross sections to help determine the desired location of one or more holes to be formed in the eye via, for example, laser scleral microporation (LSM). Furthermore, the VESA FEM allows for in silico isolation of individual ciliary muscle fiber sections. VESA can perform such isolation analysis for any component of the ocular anatomical system, such as the elastic motion of a BMCC device.

[0032] 1B illustrates an exemplary process flow chart 9300 that generally includes generating a first personalized simulation 9302, generating a second personalized simulation 9304, and determining one or more parameters of a treatment 9306 based on at least the first personalized simulation and the second personalized simulation. In an exemplary embodiment, the first personalized simulation 9302 can include activating a first ciliary muscle fiber section of the human eye to determine a first contribution of the first ciliary muscle fiber section to a deformation of a lens of the human eye, the second personalized simulation 9304 can include activating a second ciliary muscle fiber section of the human eye to determine a second contribution of the second ciliary muscle fiber section to a deformation of the lens, and the one or more parameters of the treatment 9306 can include an arrangement of one or more holes in the first ciliary muscle fiber section and / or the second ciliary muscle fiber section. In some exemplary embodiments, the one or more parameters of the treatment 9306 can be determined by applying machine learning-based analysis of the 3D-ID AI. Examples of treatment parameters that are precisely determined to be optimal for each individual may include the amount of matrix, the arrangement of the matrix, the overall shape of each matrix, the overall dimensions of each matrix, the amount of holes in each matrix, the distribution of holes in each matrix, the depth of holes in each matrix, etc. Other anatomical structures other than ciliary muscle fibers are also within the scope of this disclosure. For example, a specific stimulus, such as the first, second and / or third specific stimulus, may consist of activation of one or more ciliary zonules or of any of the fiber bundles that form the fibrous ring connecting the ciliary body to the crystalline lens. Collectively, such fibers may be referred to as the suspensory ligament of the lens. The system may consider, model, or otherwise take into account the forces and anatomical response of the ciliary zonules, which may be divided into separate regions or groups based on anatomical location, forces exerted by the ciliary zonules, or other factors.

[0033] More specifically, the identification of the desired location of the one or more holes by FEM is based on the components and capabilities of the VESA, including, but not limited to, a detailed representation of the structure and contractile behavior of the ciliary muscle fibers, consideration of the pretension applied to the lens via the ciliary zonular structures, and a discrete 3D geometric representation and independent material specifications of the passive structures of the eye that mechanically interact during the contractile function. These passive structures may include, but are not limited to, the lens-like structures (e.g., lens capsule, lens cortex, lens nucleus), scleral zones (e.g., zone 0, zone 1, zone 2, zone 3, zone 4, and beyond), posterior sclera, and / or extralenticular structures (e.g., cornea, scleral spur, ciliary zonule, lamella layer, choroid, Bruch's membrane, vitreous membrane).

[0034] By way of example, and not limitation, a detailed representation of the structure and contractile behavior of the ciliary muscle fibers is generated based on a discretized 3D geometry of three sections of muscle fibers, a muscle geometry with fiber orientations assigned to represent the structure of each section, a constitutive law prescribing material behavior defined such that stress in the fiber direction is proportional to activation level, and instructions for time-varying activation levels resulting in dynamic contraction in each section. Similarly, a pretension applied to the lens through the ciliary zonule structure is generated based on a discretized 3D geometry of the ciliary zonule divided into seven segments. The ciliary zonule is represented as a 3D sheet, and based on fiber orientations assigned to the zonule geometry to represent the fibers within each sheet, a constitutive law prescribing material behavior defined such that stress in the fiber direction is proportional to tension level, and instructions for time-varying tension levels resulting in dynamic tension in each segment.

[0035] Figure 2A illustrates the VESA ecosystem with various hardware / software systems that reside in the procedure room, in the cloud, and / or in a database. Figure 2B illustrates the various technologies and tools that make up the back-end services of the VESA ecosystem. The back-end services can reside on one or more computing systems, such as an AVG PC unit, or on the cloud. As shown in Figure 2B, VESA includes applications of AI, neural networks, machine learning, signal processing, mathematics, neurobiology, physics, image processing, and robotics.

[0036] FIG. 2C shows multiple subsystems of the VESA ecosystem, including standalone diagnostic tools, clinical trial tools, lasers, imaging devices, AI engines, etc. FIG. 2D shows two of many disease application modules. Module 1 is for treating presbyopia, and module 2 is for treating glaucoma. For module 1, modeling of lens deformation, zonular tension, choroidal spring properties, scleral motion, and ciliary force is important. For module 2, tools such as FEA and / or computational fluid dynamics (CFD) can be used to model at least the following characteristics of the eye: aqueous outflow pathways, trabecular meshwork hydrodynamics, flow velocity changes, and fluid dynamics. In some embodiments, the VESA can measure the intraocular pressure (IOP) of the eye using CFD and / or constitutive calculations. The VESA can employ FEA to calculate or simulate the deflection shape of the IRIS.

[0037] VESA can also perform simulations of pipe flow to predict flow rates within the eye using CFD. In some embodiments, the CFD model can simulate / model pump efficiency, constricted outflow, and ambient pressure. The CFD can also show in VESA the fluid-structure interaction (FSI) of particles and liquid in the water-based outflow system, and the outflow path under both normal and perturbed conditions. The geometry can be modeled from the SIMSCALE forum. A produced water flow rate of 3.6 mL / day can be used as input for the CFD model. Porous media can also be used in the model. ANSYS Fluent was used to develop the model. Other modeling software can also be used. One or more of the following can be assumed when modeling the flow rate: Modified Goldmann Equation: P0=(FU) / C+Pv Below is a summary of many of these factors and their relationship to intraocular pressure (IOP) in the undisturbed eye. where P0 is the intraocular pressure (mmHg). F is the aqueous production rate in microliters per minute (μL / min). U is the pressure-independent aqueous humor drainage rate through the uveoscleral pathway in microliters per minute (μL / min). C is the outflow capacity through the pressure-sensitive trabecular pathway, expressed in microliters per minute per mmHg (μL / min / mmHg). Pv is the episcleral venous pressure (mmHg). Outflow resistance (R) is the reciprocal of outflow capacity (C).

[0038] Figure 3 shows how VESA can contribute at various stages of a critical medical procedure. Thus, VESA can add many benefits at every stage of a medical procedure by providing powerful AI-based predictive analytics (e.g., predictive software), improving processes and enhancing knowledge.

[0039] As previously mentioned, the VESA includes one or more finite element models of the human eye. There may be one or more assumptions about the overall eye model. For example, a portion of the sclera may be divided and modeled into five different zones. Each zone may be further defined by its material and biomechanical properties. FIG. 4 illustrates the structure, various measurable variables, and boundary conditions that may be used to generate a finite element model of the eye. As previously mentioned, the cerebellum of the eye is within the scope of this disclosure.

[0040] 5 shows an example zone definition that can be used to generate a finite element model. In some embodiments, the zone assumptions are as follows: · There is no literature indicating specific dimensions due to the intermingling of different parts of the ciliary muscle fibers. The zones are perpendicular to the outer scleral surface, i.e. zone 0 is the area between a line starting from a point medial to the spur and another line starting from a point medial to the limbus. The model is composed of distinct regions whose boundaries were chosen to replicate descriptions in each section of the literature. The boundaries of each zone are based on the geometric location of specific anatomical landmarks in a 30-year-old eye model. · Descriptions of boundaries with respect to specific anatomical landmarks vary slightly from subject to subject.

[0041] FIG. 6 shows examples of each of the zone descriptions or anatomical locations for one or more regions of the eye.

[0042] VESA may take into account one or more of the following non-limiting factors: ·Coreoscleral junction Cornea (License) Crystalline details Crystalline capsule details Weigert's ligament -Front corner structure ·retina ·Choroid Bruch's membrane - Vitreous membrane Aqueous fluid Vitreous body ·Eyeball shape ·Axial length Ciliary body, all muscle fiber directions Ciliary body apex Eye chart ·Iris (pupil) Biomechanical elastic properties of the sclera ·Sclera-twin ring junction - Muscle attachments of all ciliary muscle fibers ·Bone layer -Details of all ciliary zonular attachments Crystalline capsule ·Scleral beat Schlemm's canal ·Subchoroidal space ·Subchoroidal layer Trabecular meshwork

[0043] In some embodiments, the fluid-solid interaction solver can model the trabecular meshwork using software such as, but not limited to, Ansys Fluent. The trabecular meshwork has the following anatomical features: Cornea - consists of thin, flat, porous sheets arranged in layers, containing large amounts of elastin. Periductal Tissue - Periductal tissue (also called cribriform meshwork) - lies adjacent to Schlemm's canal and is composed of connective tissue ground substance rich in glycoaminoglycans and glycoproteins. This thin band of tissue is covered by a single layer of endothelial cells. Schlemm's canal is a round, lymphatic-like vessel in the eye that collects aqueous humor from the anterior chamber and delivers it to the episcleral vessels via the aqueous veins. The ducts are essentially endothelial lined vessels, similar to lymphatic vessels. The inner side of the lumen closest to the aqueous humor is lined by the trabecular meshwork. This area is the largest contributor to the resistance of aqueous humor to outflow. Traditionally, Schlemm's canal has been thought of as a blood vessel, but a study published in 2014 showed that its molecular identity is very similar to the lymphatic system. Iris aorta - a vascular ring located in front of the ciliary body, near the base of the iris. It is formed by anastomosis of two long posterior ciliary arteries and seven anterior ciliary arteries. It supplies the iris, ciliary process, and anterior choroid. · Ciliary capillaries- These capillaries supply blood to the surrounding tissues. · Tributaries of the eye: the anterior and posterior ciliary veins. Two vortex veins from the upper half of the eye. Episcleral veins from the eyelid and conjunctiva. The central retinal vein. Lacrimal veins. Collector Channel

[0044] In some embodiments, the network can be divided into several portions, each with a characteristically different structure, including but not limited to: · The inner uveal plexus - closest to the anterior chamber angle, contains thin, cord-like trabeculae, is primarily radially oriented, and encloses a larger trabecular space than the corneoscleral plexus. Corneoscleral meshwork - consists of thin, flat, porous sheets that are rich in elastin and arranged in layers. Peritubular tissue (also called cribriform reticular tissue) - adjacent to Schlemm's canal, consists of connective tissue ground substance rich in glycoaminoglycans and glycoproteins. This thin band of tissue is covered by a single layer of endothelial cells. - The trabecular meshwork provides a small amount of drainage of aqueous humor through a second outflow pathway, the uveoscleral pathway (5-10% of outflow occurs through this pathway), which is increased by the use of glaucoma medications such as prostaglandins. -The trabecular meshwork was previously thought to arise from a point (the apex) corresponding to the end of the DM (Schwalbe's line) but is now thought to extend into the cornea and form the Duar layer. Schwalbe lines are anatomical lines found on the inner surface of the cornea of ​​the eye that mark the outer limit of the endothelial layer of the cornea. Specifically, they represent the end of Descemet's membrane. They can often be seen on gonioscopy. - There is also evidence to suggest that the corneal endothelium does in fact contain, albeit on a limited scale, stem cells that produce endothelial cells, especially after injury. -Collector channels are endothelium-lined openings originating from the outer wall of Schlemm's canal that function as conduits for aqueous humor to intra- and extrascleral vessels that connect to the venous system. The number of collector channels varies among individuals but generally ranges from 24 to 35 per eye, with 8 to 10 randomly distributed around the circumference of the outer wall of Schlemm's canal. Episcleral veins - Aqueous fluid leaves the eyeball through the trabecular meshwork into Schlemm's canal (a groove at the edge of the eye, where the cornea joins the sclera). -Iris-aortic circle - A vascular ring located in front of the ciliary body, near the base of the iris. It is formed by anastomoses of two long posterior ciliary arteries and seven anterior ciliary arteries. It supplies the iris, ciliary processes, and anterior choroid. The conjunctiva is located inside the eyelid and covers the sclera (the white of the eye). It is made up of stratified squamous epithelium with goblet cells and stratified columnar epithelium that is non-keratinized.

[0045] Figure 7 shows an example of a 3D model generated by VESA. The 3D model is a FEM with 703 fibers and 42,000 elements. It should be noted that more or less fibers and mesh elements can be used. For example, Figure 8 shows a FEM created with more fibers and elements, which would increase the computation time.

[0046] Figure 9 shows an example of a mesh network for a 3D model of the eye. Additionally, Figure 9 shows the simulated accommodation of the zonules and muscles within the eye, further illustrating the approximation of the zonules as springs for the purpose of generating the FEM. Once the mesh model is generated, it can be imported into FEBio.

[0047] Figures 10-12 show an example of an anatomical model that VESA uses to generate the trabecular meshwork. For example, the material properties of each feature (e.g., Schlemm's canal, episcleral vein, conjunctiva) can be assigned to one or more mesh elements associated with the respective feature.

[0048] In some embodiments, the VESA can include a micropore analysis tool configured to analyze and determine properties of the micropore array fringed by the human eye. Features of the micropore analysis tool include the following, the list of which is not exhaustive:

[0049] Micropore Tool (MPTool)The Micropore Analysis Tool (or simply "Tool") can arrange xyz data in a grid or mesh configuration and display the data color-coded according to Z-value, which is the height coordinate, a conversion of the grayscale value of the image.

[0050] The tool can employ a cell smoothing routine. The tool can implement an edge detection algorithm to find the edges of each hole. Examples and criteria for finding edges are provided in this document. Using the edge detection algorithm, a second copy of the grid can be created discarding values ​​that are determined not to be within the holes. A box can be drawn around each hole and its dimensions reported. This box can be drawn using the edges found in the previous step. The height values ​​within this box can be used to report one characteristic height for each hole.

[0051] A process is described for using a micropore analysis tool to characterize, quantify, and qualify micropore arrays, including, but not limited to, ligament efficiency, pore thickness, and pore height. Using characteristic height data from a pore grid, the tool employs ASME ligament efficiency principles and can evaluate the change in bulk pore value across a patch imparted by a pore patch.

[0052] Figure 13A shows the first step where the raw data is read in and converted into a pseudo 2D mesh array. In step 2 (not shown), the tool is configured to determine the width of the hole block. This can be manually entered by the user. The width of the hole block can be the average width of the pores in the array. Alternatively, the width of the hole block can be determined programmatically using various algorithms and / or computer vision analysis tools.

[0053] Then, a color grid for each hole is determined, which finally results in a color grid that is representative of a matrix with multiple holes, for example a 5x5 matrix.

[0054] Next, a smoothing of the grid is performed, smoothing the color of the most likely erroneous outliers, which should have green hues rather than orange or red hues, as indicated by the arrows. Smoothing the outliers can aid the edge detection process. Figure 13B shows the effect before and after the smoothing process.

[0055] Next, the tool cleans the whitespace. This step involves determining the linear mean (non-zero value) of the entire pore block, zeroing out all cells that are less than 105% of the linear mean of the pore block (Note: the 105% modifier is an engineering judgment; it may need to be adjusted based on available data), and re-coloring the data.

[0056] Then the following actions occur: · Assume remaining non-zero cells are contiguous and approximately square (engineering judgment). Determine the linear average of the remaining non-zero cells. The reported depth of the void cylinder will be 80%-90% of this value. This is the characteristic height of the pore.

[0057] Finally, the characteristics of each hole were tabulated and recorded and registered.

[0058] The micropore analysis tool can be an OCT (optical coherence tomography) viewer configured to generate images of the micropores in various views (e.g., X-slice, Y-slice, Z-slice) to measure specific properties of the micropores such as depth, width, edges, size, shape, coordinates, diameter, distance to neighboring pores, etc., as shown in Figure 14. The micropore analysis tool can include multiple AI (e.g., neural network) engines trained to perform edge detection, diameter measurement, depth measurement, layering (e.g., tissue segmentation), etc.

[0059] Once the FEM or virtual eye model has been created, it can be used for additional modeling (sub-modeling, predictive modeling, etc.). The purpose of sub-modeling is to determine the new biomechanical properties of the sclera after surgery. The assumptions for this model are: · Early sclera is a homogeneous or heterogeneous substance. Sclera properties can be obtained from experimental and / or adjusted FEM data from previous modeling work (e.g. Young's modulus = 1.62Mpa, Poisson's ratio = 0.48) · Hole stiffness is zero to negative.

[0060] In pore geometry modeling, the following variables or conditions are observed: Each hole is modeled separately. The cross section of each hole is square, 433 μm in this example. The distance between the centers of each hole varies, in this example it is 722 μm. Pore ​​depth was obtained from micropore OCT review. Scleral thickness is the average thickness measured on the same scale.

[0061] Micropore Tools As a non-limiting example, a micropore tool can have three different modes (though there could be more). There are four modes: · Pre-planning mode: Pre-processing step - Calculate the PVF and accept it as input. Perform image recognition of the surgical field to check for obstacles (vessels, foreign bodies, etc.) that may obscure the hole position. Treatment mode: Peri-treatment step – PVF and EMC are updated in real time and displayed to the user as a color map. Post-processing mode: Post-processing step - the Micropore Tool (with embedded EMC calculator) calculates relevant quantities and generates reports for the current pore matrix, each of the four pore matrices, and the four pore matrices as a system. Micropore matrices can be independent, continuous and arranged in multiple patterns. Micropores can also be reduced to nanopores with similar composition, shape, size and density.

[0062] Figure 15 shows a screenshot of the pre-planning mode, which includes but is not limited to: A snapshot of an individual's anatomical features (e.g., eyes). -Red outline of the matrix. -Has anatomical avoidance buttons. -Memo button. Edit / Markup / Font / Arrow / Draw toolbar. ·EMC teaches the biomechanical properties of tissues. · PVFI tells you what tissue was removed but not where. Bulk density reading (BDR) indicates the hardness of the part. · The Micropore Registration Tool (MIRT) teaches pore locations, not patterns. · Matrix Registration Tool (MART) teaches about patterns.

[0063] The GUI may include one or more of the following tools: Micropore Tools: Ligament Efficiency Tool (LET) A 3D touch-enabled GUI simulation tool that accepts user inputs to define ASME parameters. A tool that generates intermediate results for the simulation solution. · Ligament Efficiency Tooling (LET) (ASME): The physics package that supports the micropore tool. Registration tool: (MPR)-(MAR) location tracker to communicate and register the position and orientation of micropores and matrix. Elasticity Calculator: processes the following biomechanical and physical data input from the biometer: -Three uses: Pre-op planning, Peri-op evaluation and validation, Post-op validation. Real-time GUI solver. Microporation Biometer (MBM): Separate biomechanical / physical inputs to EMC and 3D-ID VESA. The following inputs and / or measurements are possible: -component: -Age-related MPA -Depth -PVF -Bulk density (aka local stiffness) -density -Pore size -Hole shape (square) [coding language: diameter] -Hole pattern -Pore array

[0064] The MicroPore Tool GUI may also display one or more of the following characteristics / values: Negative Stiffness Index (NSI): A progress bar showing the Negative Stiffness Index of biomechanical property / physical outcome changes of scleral tissue during and after LSM (Laser Scleral Microporation). For more details on the LSM process, see the description below and Figures 65-70. - Measured by progression through quadrants Q1-Q4 until NSQ is met in all eyes. - Input from biometer + EMC Treatment Progress Meter: - A progress completion meter for treatment progress is also connected to a time clock for countdown of each quadrant. -This should be done for each quadrant that incorporates a countdown. Treatment countdown clock. OCT Tools: AI and OCT auto-segmentation integration -Depth-sensing tools to identify tissue layers -3D image processing and image presentation. -3D depth analysis Custom Micropore Tools: - Micro-pore pattern trays to customize your treatment platform by selection or AI recommendation. ·COP (Central Optical Power) Calculator: -Uses standard formulas with a unique method that utilizes ray tracing to calculate the COP of crystalline lenses. -Calculate the free body forces on the crystal. - COP calculation formula and chart (see Figures 54 to 57) Depth sensor tool: InnoMinds

[0065] In some embodiments, the micropore tool is configured to determine the material properties of the tissue between the pores. Once the pores, depth, spacing, and diameter are determined, the overall ocular structure can be simulated with the effect of the micropore procedure. The accommodative response can be determined to determine the velocity. Furthermore, by placing a new micropore matrix, a new intraocular dynamic pressure after treatment can be obtained. This pressure can be compared to the preoperative dynamic pressure.

[0066] The micropore tool is configured to determine: · Coefficient of Ocular Stiffness (COR): A mathematical formula that predicts a constant intraocular pressure. Pore ​​Volume Fraction Index (PVFI): A mathematical formula that predicts the bulk density of pores and the percentage of removed tissue relative to the percentage of remaining tissue. - GUI evaluation and validation tool to measure PVF across the treatment area -PVF is related to zonal scleral thickness, scleral material properties, pore geometry, pore density, and pore size. -It tells us what tissue was removed, but nothing about its location. Elastic Modulus Calculator (EMC): Related to viscoelastic and elastic properties of tissue. Displays the output of physical meters with negative stiffness changer and performs 3D simulation of biometers. The physical meter reading is the NSI. The NSI is related to the negative Poisson equation in the tissue. · NSI triggers recommendations.

[0067] The Micropore Tool (MPTool) can also include registration functionality as shown in Figure 16. The Micropore Registration Tool (MIRT) is configured to determine the dynamic location of the micropores, not the pattern. The Matrix Registration Tool (MART) informs the pattern of the micropores. The MART and MIRT give continuous biofeedback to the data stack regarding the center of gravity of the ocular ecosystem related to NSI and biomechanical strain in the periphery stress coordinate map. The periphery stress coordinate map (HSCM) gives locality, density, and registration information to the database and continuously biofeedback to the daa stack regarding these and other assigned information.

[0068] The MicroPore Tool can also simultaneously display one or more raw OCT images, such as (but not limited to) depth sensing images, y-slice, z-slice, x-slice, etc., in 1D, 2D, 3D, 4D viewer capacity. The MPTool also has zoom capabilities for macro and micro viewing and evaluation. The MicroPore Tool GUI is also configured to overlay key tissues on the images. Key tissues that can be overlaid include, but are not limited to, cornea, sclera, conjunctiva, ciliary muscle fibers, Tenon's capsule, etc. This facilitates diagnosis.

[0069] The Micropore Tool has five main modes of operation: · Pre-processing plan (snapshot) Treatment (dynamic, real-time) Immediately after treatment (simulation) Post-treatment: Pore ​​matrix evaluation and reporting (simulation)

[0070] In all modes, it is necessary to simulate the matrix from the (PVF / BD / EM / COR) point of view. This is useful for medical professionals: · Plan your matrix in advance. -Evaluates each of the four pore matrices while performing the laser treatment, allowing for re-lease of areas that do not meet the guidelines and informing the user of suggested corrections. - Dynamic changes in eye tissue caused by LSM treatment can be observed in real time. · Report the results of any intervention or racing procedure to the responsible person to determine the success of the procedure.

[0071] For the peri-treatment step, this needs to be done in real time, so FEA simulation is not suitable. Therefore, pre-operative VESA simulation is performed using various 3D-ID TM -This will be done using a DOE approach (Design of Experiments). Further iterations of the VESA FEA will be available via a cloud application.

[0072] The micropore tool can include an EMC calculator based on first-principles stress calculations (ASME Ligament Efficiency) that allows stress calculations to be solved in real time.

[0073] Pre-scan visit process The pre-scan visit process may include steps and processes as shown in Figure 17, and both the pre-planning and post-OCT scan workflow is shown in Figure 18. An application with multiple GUIs and functions configured to facilitate the individual intake process is shown in Figure 19.

[0074] From the screen shown in Figure 19, the user can: -Register position using eye tracker. Calibrate the laser. Step 1. Decide on a position. · Step 2. Run the simulation on the estimated value of NSI (Negative Stiffness Index value) after matrix Q1 treatment. · Step 3. Check your position. · Step 4: Go to the Edit screen, Treatment screen or various sub-screens.

[0075] With the micropore array, users can: Select / deselect / add holes. Run the simulation. -Do live calculation of PVF. · View and rate. · Do live calculations of LET, NSI, EMC. Live elasticity based hole placement assumptions. ·Receive real-time AI-driven recommendations based on BioMeter / EMC / NSI.

[0076] The screen of FIG. 19 can also include a physical dynamic progress meter that measures: ·PVF Bulk density ·Negative stiffness index (NSI) Elastic modulus Depth

[0077] The micropore tool can include a treatment mode screen, which can include a real-time OCT signal chart.

[0078] The MicroPore tool runs the simulation and can include a sub-screen. The VESA simulation can be used to predict results and set GO, NO GO parameters. The VESA simulation in MPT runs simulations in the following scenarios: · Pre-planning - if an edit has been performed, VESA controls the stop of the edit / VESA allows to proceed to the next quadrant with subtracted holes as long as the embedded EMC code reaches the desired NSI to successfully generate the individual matrix. Progressive matrices run in the background, allowing the surgeon to bypass the transition to MPT if the series of matrices still meets the full-eye requirement for VESA-predicted NSI values ​​at the end of treatment. · When using MRT, if the OPF ratio is not met in each quadrant, it will be forced to retry and return to the registered hole. If matrix editing requires replacement of micropore arrays, force additional pore arrays once a threshold is met. · Act as a medical administration control center to prevent undesirable treatment parameters and interventions. · To be an informing agent regarding parameters and status of biomechanical, therapeutic and surgical interventions. · Acts as a stop system mechanism or abort mechanism.

[0079] The micropore tool can include a post-treatment screen (FIGS. 53A-53B). The post-treatment NSI should have the following thresholds: (1) GO, (2) allow for regression, and (3) no GO.

[0080] Hyperelastic Image Registration ANSYS hyperelastic modeling can track critical points in the numerical model during accommodation simulations, and these critical points can also be tracked with in vivo imaging, allowing multiple data points to confirm the accuracy of the model.

[0081] Hyperelastic modeling allows inverse imaging of dynamic biological motion into 3D FEM, and also allows the calculation of stresses within the deforming body.

[0082] Eye Tracking Augmented Reality VESA can include an augmented reality eye-tracking system.

[0083] 20 is a block diagram illustrating an example of a computing system 500 consistent with embodiments of the present subject matter. The computing system 500 may implement VESA, 3D-ID AI, MP tools, and / or any components thereof. The system may include or be coupled to imaging systems, biothermal thermal systems, interactive user interfaces, and / or input programs for receiving and manipulating physical, biometric, biomechanical, material, and mechanical information and data.

[0084] As shown in FIG. 20, the computing system 500 may include a processor 510, a memory 520, a storage device 530, and an input / output device 540. The processor 510, the memory 520, the storage device 530, and the input / output device 540 may be interconnected via a system bus 550. The processor 510 may process instructions to execute within the computing system 500. Such executing instructions may implement, for example, one or more components of VESA, 3D-ID AI, and / or MP tools. In some embodiments of the present subject matter, the processor 510 may be a single-threaded processor. Alternatively, the processor 510 may be a multi-threaded processor. The processor 510 may process instructions stored in the memory 520 and / or the storage device 530 to display graphical information of a user interface provided via the input / output device 540.

[0085] The memory 520 is a computer-readable medium, such as volatile or non-volatile, that stores information within the computing system 500. The memory 520 can store, for example, a data structure representing a configuration object database. The storage device 530 can provide persistent storage for the computing system 500. The storage device 530 can be a floppy disk drive, a digital cloud, a hard disk drive, an optical disk drive, a tape drive, or other suitable persistent storage means. The input / output device 540 provides input / output operations to the computing system 500. In some implementations of the current subject matter, the input / output device 540 includes a keyboard and / or a pointing device. In various embodiments, the input / output device 540 includes a display device for displaying a graphical user interface.

[0086] According to some implementations of the current subject matter, I / O device 540 can provide input / output operations to network devices. For example, I / O device 540 can include Ethernet ports or other network ports for communicating with one or more wired and / or wireless networks, Bluetooth, or digital cloud systems (e.g., a local area network (LAN), a wide area network (WAN), the Internet).

[0087] In some embodiments of the current subject matter, the computing system 500 can be used to execute various interactive computer software applications that can be used for organizing, analyzing, and / or storing data in various (e.g., tabular) formats (e.g., Microsoft Excel®, and / or any other type of software). Alternatively, the computing system 500 can be used to execute any type of software application. These applications can be used to perform various functionalities, such as planning functionality (e.g., creating, managing, editing spreadsheet documents, word processing documents, and / or other objects, etc.), computing functionality, communication functionality, etc. Applications can include various add-in functions, plug-ins, or can be standalone computing products and / or functions. When launched within an application, the functionality can be used to generate a user interface that is provided via the input / output devices 540. The user interface can be generated by the computing system 500 and presented to a user (e.g., on a computer screen monitor, etc.). The user interface can be integrated with other devices and virtual ecosystems.

[0088] One or more aspects or features of the subject matter described herein may be implemented in digital electronic circuitry, integrated circuits, specially designed ASICs, field programmable gate array (FPGA) computer hardware, firmware, software, and / or combinations thereof. These various aspects or features may include implementation in one or more computer programs executable and / or interpretable on a programmable system including at least one programmable processor, which may be special purpose or general purpose, coupled to receive data and instructions from a storage system, at least one input device, and at least one output device, and to transmit data and instructions to the storage system, at least one input device, and at least one output device. The programmable system or computing system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communications network. The relationship of client and server arises by virtue of computer programs running on the respective computers having a client-server relationship to each other.

[0089] These computer programs, which may also be referred to as programs, software, software applications, applications, components, or codes, include machine instructions for a programmable processor and may be implemented in a high-level procedural and / or object-oriented programming language, and / or assembly / machine language. As used herein, the term "machine-readable medium" refers to any computer program product, apparatus, and / or device used to provide machine instructions and / or data to a programmable processor, such as, for example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), and includes a machine-readable medium that receives machine instructions as a machine-readable signal. A "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor. A machine-readable medium may store such machine instructions non-transiently, such as, for example, a non-transient solid-state memory, a magnetic hard drive, or an equivalent storage medium. A machine-readable medium may alternatively or additionally store such machine instructions in a transitory manner, such as, for example, a processor cache or other random access memory associated with one or more physical processor cores.

[0090] To provide for user interaction, one or more aspects or features of the subject matter described herein can be implemented on a computer having a display device, such as, for example, a cathode ray tube (CRT) or liquid crystal display (LCD) or light emitting diode (LED) monitor, for displaying information to a user, and a keyboard and pointing device, such as, for example, a mouse or trackball, by which the user can provide input to the computer. Other types of devices can also be used to provide user interaction. For example, feedback provided to the user can be any form of sensory feedback, such as, for example, visual feedback, auditory feedback, tactile feedback, and input from the user can be received in any form, such as acoustic input, voice input, tactile input, and the like. Other possible input devices include touch screens and other touch-sensitive devices, such as single or multi-point resistive or capacitive trackpads, joysticks, voice recognition hardware and software, optical scanners, optical pointers, digital image capture devices and associated interpretation software, and the like.

[0091] In the above description and in the claims, phrases such as "at least one" or "one or more" may appear following a conjunctive list of elements or features. The term "and / or" may also appear in a list of more than one element or feature. Unless otherwise stated, implicitly or explicitly by the context of use, such phrases are intended to mean any of the listed elements or features individually, or any of the listed elements or features in combination with any of the other listed elements or features. For example, the phrases "at least one of A and B," "one or more of A and B," and "A and / or B" are intended to mean "A alone, B alone, or A and B," respectively. A similar interpretation is intended for lists containing more than two items. For example, the phrases "at least one of A, B, and C," "one or more of A, B, and C," and "A, B, and / or C" are intended to mean "A alone, B alone, C alone, A and B, A and C, B and C, or A, B and C," respectively. Use of the term "based on" above and in the claims is intended to mean "based at least in part on" and in that sense allows for unrecited features or elements.

[0092] The subject matter described herein may be embodied in systems, devices, methods, and / or articles, depending on the desired configuration. The embodiments described in the foregoing description do not represent all embodiments consistent with the subject matter described herein. Instead, they are merely some examples consistent with aspects related to the subject matter described. Although several variations have been detailed above, other modifications and additions are possible. In particular, further features and / or variations may be provided in addition to those described herein. For example, the embodiments described above may be directed to various combinations and subcombinations of the disclosed features, and / or combinations and subcombinations of some further features disclosed above. In addition, the logic flow depicted in the accompanying figures and / or described herein does not necessarily require the particular order shown, or sequential order, to achieve desirable results. Other embodiments are within the scope of the claims.

Claims

1. A system for replicating, manipulating and intervening in a virtual reality environment, comprising: at least one data processor; An imaging system; Bio-thermal system, An interactive user interface, an input program for receiving and manipulating physical, biometric, biomechanical, material, and mechanical information and data; at least one memory for storing instructions; a 3D modeling component having When the instructions are executed by the at least one data processor, the instructions generating a first specific simulation of operating the Bruch membrane-choroidal device to determine a first contribution of energy required to deform the crystalline lens; generating a second individualized simulation in which an origin section of a ciliary muscle fiber section of the human eye is activated to determine a first contribution of a first ciliary muscle fiber section to deformation of a lens of the eye; generating a second individualized simulation in which a second ciliary muscle fiber section of the human eye is activated to determine a second contribution of the second ciliary muscle fiber section to deformation of a lens of the eye; generating a third individualized simulation in which a third ciliary muscle fiber section of the human eye is activated to determine a third contribution of the second ciliary muscle fiber section to deformation of a lens of the eye; determining one or more parameters of a treatment for the person based on at least a first Bruch choroid apparatus, the first contribution of the first ciliary muscle fiber section, the second contribution of the second ciliary muscle fiber section, and the third contribution of the third ciliary muscle fiber section; Including, causing an action to be performed, system.

2. The system of claim 1 , wherein all simulations can be run in series, alone, and / or in parallel with other parameter manipulations.

3. The operation, generating a fluid-structure interaction for the aqueous humor flow of the eye, in which three outflow pathways are activated; The system of claim 1 , comprising:

4. one or more parameters of the Bruch choroid apparatus, the first ciliary muscle fiber section, the second ciliary muscle fiber section, and the third ciliary muscle fiber section of the eye of the person. The system of claim 1 .

5. one or more micropores are created by a laser in scleral tissue of the eye over the Bruch's choroid apparatus, the first ciliary muscle fiber section, and / or the second ciliary muscle fiber section, and / or the third ciliary muscle fiber section of the eye of the person; The system of claim 4.

6. 5. The system of claim 4, wherein the one or more parameters of the treatment include the amount of matrix containing one or more pores, the arrangement of the matrices, the overall shape of each matrix, the overall dimensions of each matrix, the amount of pores in each matrix, the distribution of pores in each matrix, and / or the depth of pores in each matrix.

7. The system of claim 1 , wherein one or more parameters of the treatment for the person are determined by applying a machine learning model.

8. The system of claim 7 , wherein the machine learning models include regression models and algorithms.

9. The system of claim 7 , wherein the machine learning models include age progression models and algorithms.

10. The system of claim 7 , wherein the machine learning model is trained based on various combinations of treatment parameters and treatment outcomes.

11. 10. The system of claim 9, wherein the machine learning model is further trained based on individual demographic data associated with various combinations of treatment parameters and treatment outcomes.

12. The operation further comprises: generating a user interface that displays one or more parameters of a treatment for the person. The system of claim 7 .

13. The operation further comprises: receiving at least one user input via a user interface related to one or more parameters of a treatment for the person; updating the machine learning model based at least on the user input; Including, The system of claim 11.

14. The operation further comprises: Systems and methods are provided for assessing biomechanical properties of tissue, including: The system of claim 1 .

15. an assessment toolbox component configured to calculate from the extracted features at least one parameter related to different possible outcomes of a given therapeutic intervention in the human eye; a system output configured to provide the calculated at least one parameter to one of a treatment system and a user; One or more optical, biometric, biomechanical, physical and geometric parameters are incorporated into the calculated prediction; The system and method of claim 1 .

16. 10. The system and method of claim 1, wherein the VESA computer toolbox allows for adjustment of equations that result in a therapeutic or surgical intervention that is most suitable for the user.

17. 1. A system for evaluating an eye of a patient, comprising: a modeling component configured to determine a representation of the entire eye from a three-dimensional structural image of the entire eye and at least one biomechanical property of the eye; a feature extractor configured to extract a plurality of features from the whole eye model; a user interface configured to receive input from a clinician defining an objective function as a function of at least one parameter of the eye after a therapeutic treatment; a condition or disease assessment component configured to calculate at least one parameter related to a risk of a disease of the eye from the extracted features and the objective function, the calculated at least one parameter including variables in a treatment procedure, the variables representing surgical parameters that can be varied by a clinician in the treatment procedure; and a system output configured to provide the calculated at least one parameter to one of a processing system and a user; The system has:

18. The system of claim 16 , wherein the modeling component is configured to determine a three-dimensional finite element model of the entire eye from the three-dimensional structural image and at least one biomechanical property of the eye.

19. the modeling component is configured to provide a three-dimensional finite element model representative of the entire eye after a therapeutic treatment; The system further comprises:

20. The system of claim 17, comprising a user interface configured to receive input from a clinician defining at least a type and location of a therapeutic procedure.

20. the feature extractor is configured to extract at least one feature of a plurality of features from a three-dimensional finite element model representative of the entire eye after a therapeutic treatment; The ectasia assessment component is configured to calculate a parameter representative of a predicted risk of ectasia in a patient given a therapeutic treatment having an associated type and location; 20. The system of claim 18.

21. The ectasia assessment component includes: configured to perform a sensitivity analysis on the at least one feature so as to be able to determine a magnitude of an influence of a value of the at least one feature on the at least one parameter.

20. The system of claim 19.

22. 20. The system of claim 19, wherein the at least one extracted feature represents either a geometric or a biomechanical feature of the eye.

23. the modeling component is configured to provide a three-dimensional finite element model representative of the entire eye under an applied load; The system further comprises: a user interface configured to receive input from a clinician defining at least a magnitude and location of the load; 20. The system of claim 17.

24. The system of claim 16 , wherein the modeling component is configured to determine a finite element model of the entire eye from a three-dimensional structural image and at least one biomechanical property of the eye.

25. The system of claim 16 , wherein the objective function is a function of at least one of the ocular strain values ​​and the ocular stress values.

26. The system of claim 16 , wherein the objective function is a function of at least one measure of refractive result.

27. The system of claim 16 , wherein the modeling component determines a representation of the entire eye as a virtual model consisting of a set of parameters extracted from evaluating a statistical model according to the three-dimensional structural image and at least one biomechanical property of the eye.

28. A system for replicating, manipulating and intervening in a human eye in virtual reality, comprising: at least one data processor; An imaging system, a bio-thermal system, an interactive user interface, an input program for receiving and manipulating physical, biometric, biomechanical, material, and mechanical information and data; at least one memory for storing instructions; a 3D modeling component having When the instructions are executed by the at least one data processor, the instructions generating a first specific simulation in which the Bruch's membrane-choroid complex device is operated to determine a first contribution of energy required to deform the crystalline lens; generating a second person-specific simulation in which an origin section of a zonular section of the eye of the person is activated to determine a first contribution of a first zonular section to deformation of the lens of the eye; generating a second individual-specific simulation in which a second zonular section of the eye of the person is activated to determine a second contribution of the second zonular section to deformation of the lens of the eye; generating a third individual-specific simulation in which a third zonular section of the eye of the person is activated to determine a third contribution of the third zonular section to deformation of the lens of the eye; determining one or more parameters of a treatment for the person based on at least the first Bruch choroid device, the first contribution of the first ciliary body zonule section, the second contribution of the second ciliary body zonule section, and the third contribution of the third ciliary body zonule section; Including, causing an action to be performed, system.

Images