Systems, methods, and devices for monitoring intraocular pressure

Abstract

Systems, methods, and devices for monitoring intraocular pressure are provided. A plurality of images is acquired using a camera, in which the plurality of images is associated with a blink by an eye of a subject. A corneal response is quantified using the plurality of images. An eye pressure of the subject is quantified using the corneal response. A risk of glaucoma is quantified for the subject using the eye pressure of the subject.

Description

SYSTEMS, METHODS, AND DEVICES FOR MONITORING INTRAOCULARPRESSURECROSS-REFERENCE TO RELATED APPLICATION

[0001] The present Application claims priority to United States Patent Application No.: 63 / 662,660, entitled “A Device and Method for Monitoring of Intraocular Pressure,” filed June 21, 2024, and also claims priority to United States Patent Application No.: 63 / 741,527, entitled “Device and Method for Monitoring Intraocular Pressure,” filed January 3, 2025, each of which is hereby incorporated by reference in its entirety for all purposes.TECHNICAL FIELD

[0002] The present disclosure relates to systems and methods for non-contact, real-time measurement and / or monitoring of intraocular pressure of a subject using optical techniques.BACKGROUND

[0003] Physiological control of fluid pressures within the eye is significant to maintenance of healthy vision. One of skill in the art will appreciate that a manifestation of chronic increase in fluid pressures within the eye is a condition called glaucoma. The most common type of glaucoma, open-angle glaucoma, results in slow loss of vision in a patient when left untreated. Open-angle glaucoma is the leading cause of irreversible blindness in the world.

[0004] Conventional solutions provide a diagnosis of glaucoma by mapping measurement of eye pressures, such as intraocular pressure (IOP) through a technique called tonometry.Tonometry usually requires a visit to an optometrist or an ophthalmologist who performs IOP measurement and examines the retina for changes related to elevated eye pressures. Once a patient is diagnosed with glaucoma, regular IOP monitoring, examination of the retina and timely medical or surgical treatment are necessary to assess progression of the disease and prevent irreversible changes to the retina and the optic nerve. Glaucoma is responsible for almost 10 million patient visits annually with consequent direct costs in excess of $2.5 billion. Therefore, identification of cost-reduction intervention points is a priority shared byphysicians as well as governmental agencies. Furthermore, medication non-compliance is estimated to be over 25% in patients who require medical treatment of elevated IOP.

[0005] Of the wide variety of techniques described for tonometry, one conventional solution is IOP measurement derived from application of mechanical force directly to the eye by direct contact (e.g., applanation). A less reliable technique utilizes pneumatic (e.g., air) pressure. The primary limitation of all these conventional techniques, including the applanation tonometry, is fluctuation of IOP outside the time of measurement. Time-based (e.g., temporal) measurements are limited by the number of visits to the physician, and hence are not practical to perform on a day-to-day basis. Tonometry and current non-invasive measurements using current commercially available devices, thus, only obtain spot measurements, and cannot monitor continuous changes in IOP.

[0006] There is a significant paucity of home-based methods to measure IOP and / or changes in the eye resulting from glaucoma. Yet, a further requirement is to continuously assess changes within the retina related to an elevated IOP. Conventional tonometry uses mechanical pressure on the eye using a probe to determine the eye pressure that resists the deformation. This is termed applanation tonometry and is considered the gold standard for measurement of IOP. IOP could also be measured by two other methods that serve as surrogates. Current commercial transducers need to be implanted and are therefore invasive. Others are limited by the need for dexterity to place the device and the measurement head in direct contact with the eye.

[0007] Currently available commercial devices such as are easy to use, but lack reliability and validation in a clinically relevant scenario. Moreover, other conventional techniques such as contact-lens sensing or implantable probes, are considered either commercially non- viable or invasive (requiring implantation and / or surgery) and therefore their wide-spread use has not been recommended.

[0008] For example, one conventional solution provides lens sensors with transducers custom molded to the shape of the patient’s cornea, or other physical characteristics of the patient. Thus, lens sensors are expensive and do not necessarily address the costs associated with regular measurements made by trained personnel. Still further, lens sensors demand additional dexterity from the patient at home. The lens sensor also requires additional washing, storage, replacement requirements at regular intervals. Therefore, constant monitoring of IOP remains a clinical challenge unsolved by currently available technologies.

[0009] Given the above background, what is needed in the art are improved systems and methods for determining IOP outside the physician's office, such as to monitor disease progression and / or to assess response to treatment for a patient.SUMMARY

[0010] The present disclosure addresses the shortcomings disclosed above by providing systems and methods for non-contact, real-time measurement and / or monitoring of intraocular pressure of a subject.

[0011] Provided are systems, methods, and devices configured to non-invasively monitor IOP. According to one embodiment, the systems, methods, and devices of the present disclosure are configured to assess changes within a retina and determine if a change is due to elevated IOP, including trends of IOP over time for a respective subject, such as over the course of minutes, hours, or days. In some embodiments, the systems, methods, and devices acquire data for longitudinal assessment of changes within the retina through a plurality of images. For instance, in some embodiments, the plurality of images is related to the light scattering characteristics of the retina and the optic nerve head in response to directed illumination of the macula (e.g., central portion of the visual field) using a coherent light source. In some embodiments, an imaging device for measurement and / or acquiring the images is mounted on typical a frame (e.g., a head-mounted display), such as a first frame with a power source coupled to the frame (e.g., a 3 Volt (V) battery). In some embodiments, to mitigate problems with monitoring intraocular pressure, the systems, methods, and devices utilized a microelectromechanical (MEMS) architecture for continuous, non-invasive monitoring of eye changes related to glaucoma, providing data on (i) trends in IOP and / or (ii) early changes within the retina in response to chronic elevation of eye pressures (e.g., i) trends in IOP and (ii) early changes within the retina in response to chronic elevation of eye pressures). Thus, there is a need for systems, methods, and devices integrates both (i) and (ii) within a portable diagnostic footprint. Furthermore, in some embodiments, the systems, methods, and devices determine trends over time by determining measurement (e.g., quantifying values) for long periods of time, such as at least 12 hours during a day. In some embodiments, the imaging device includes a sensor that monitors compliance and usage patterns, which allows for providing a report for visualization, such as by a medical practitioner associated with the subject.

[0012] In some embodiments, the systems and methods of the present disclosure enable an end-user, such as a clinician at a second computer system, which includes radiologists, pathologists, oncologists, or the like, to receive a similarly optimized subset of the encoded byte stream, such as for utilizing with high-throughput clinical decision making and diagnosis. Accordingly, in some embodiments, the systems and methods of the present disclosure match an optimal resolution for a plurality of graphical data of an encoded byte stream based on, for instance, a clinical use case and / or a form factor (e.g., hardware specifications) of a device including one or more feature extraction models configured to perform an evaluation on a respective modality of graphical data. As such, the systems and methods of the present disclosure yield higher throughput, without negatively impacting clinical decision making as well as performance when using a respective computational model with the encoded byte stream, resulting in faster turnaround times, and reduced overall cost of data storage and transmission in comparison to conventional progressive encoding and / or decoding techniques.

[0013] Turning to more specific aspects, one aspect of the present disclosure is directed to providing a method. The method includes acquiring a plurality of images associated with a blink by an eye of a subject.

[0014] In some such embodiments, the acquiring the plurality of images is performed using a camera proximate to an eye of the subject configured to capture an image in the plurality of images at a range between 200 frames per second and 700 frames per second.

[0015] In some such embodiments, the camera includes a field of view. In some embodiments, the field of view includes a profile or substantially profile view of the eye of the subject.

[0016] In some such embodiments, the plurality of images includes a range between 2 images and 60 images.

[0017] In some such embodiments, a frequency of the acquiring the plurality of images is a range between 1.5 milliseconds (ms) per image and 3.5 ms per image.

[0018] In some such embodiments, the plurality of images is associated with at least two blinks by the eye of the subject.

[0019] In some such embodiments, the plurality of images is associated with a range between two blinks and two thousand blinks.

[0020] In some such embodiments, each respective image in the plurality of images is a two- dimensional image having a size of at most 500 kilobytes.

[0021] In some such embodiments, the acquiring the plurality of images includes concurrently illuminating a portion of the field of view that includes the profile or substantially the profile view of the eye of the subject.

[0022] In some such embodiments, the illuminating is performed using a first light source set associated with a wavelength in a range between 380 nm and 750 nm.

[0023] In some such embodiments, the illuminating is performed using a first light source set associated with a wavelength in a range between 750 nm and 1,000 nm.

[0024] In some such embodiments, the acquiring the plurality of images includes acquiring, when the illuminating the portion of the field of view, a corresponding value for a set of plurality of boundary conditions based upon a plurality of measurements associated with a region of interest (ROI) of the eye of the subject exposed to the light during the acquiring the plurality of images. In some embodiments, the acquiring the plurality of images includes interrupting the acquiring in accordance with a determination a boundary condition in the set of boundary conditions satisfies a threshold dimension.

[0025] The method includes quantifying a corneal response using the plurality of images.

[0026] In some such embodiments, the quantifying the corneal response includes determining a blinking phase of a respective blink by the eye of the subject; determining a contour of the cornea of the eye in accordance with a determination a dimension of the eye satisfies a threshold dimension. In some embodiments, the quantifying the corneal response includes determining a centroid of the cornea using the contour of the cornea. In some embodiments, the quantifying the corneal response includes determining a displacement of the centroid during some or all of a respective blinking phase of a first eye blink by the eye of the subject. In some embodiments, the quantifying the corneal response includes quantifying the corneal response by comparing the displacement of the centroid against a baseline displacement.

[0027] In some such embodiments, the determining the displacement of the centroid includes determining a time constant value associated with a velocity of the eye during the respective blinking phase.

[0028] In some such embodiments, the quantifying the corneal response comprises inputting the plurality of images into a first model that iteratively compare sets of images in theplurality of images until a set of images satisfies a threshold contour of the cornea, and wherein each respective temporally adjacent set of images is associated with a corresponding blink of the eye by the subject.

[0029] In some such embodiments, the first model is trained to compare temporally adjacent sets of images.

[0030] In some such embodiments, the first model is trained to compare sequential sets of images.

[0031] In some such embodiments, the first model is trained to compare collective sets of images.

[0032] In some such embodiments, the first model is a neural network architecture includes a plurality of parameters. In some embodiments, the plurality of parameters comprises at least 1 x 106parameters. In some embodiments, the neural network architecture provides the categorization of each respective in the plurality of images by application of the at least 1 x 106parameters to each image in the plurality of images.

[0033] In some such embodiments, the quantifying the corneal response comprises inputting the plurality of images into a second model that categorizes one or more sets of images in the plurality of images into one of a set of eye blink states, wherein the set of eye blink states includes at least an eye state associated with an open or substantially open eye and a second eye state associated with a closed or substantially closed eye.

[0034] In some such embodiments, the set of eye blink states comprises an open state, a partially open state, and a closed state.

[0035] In some such embodiments, the second model is a neural network architecture that includes a plurality of parameters, in which the plurality of parameters comprises at least 1 x 106parameters, and the neural network architecture provides the categorization of each respective in the plurality of images by application of the at least 1 x 106parameters to each image in the plurality of images.

[0036] The method includes quantifying an eye pressure of the subject using the corneal response.

[0037] In some such embodiments, the quantifying the eye pressure comprises quantifying an intraocular pressure of the eye of the subject.

[0038] The method includes quantifying a risk of glaucoma for the subject using the eye pressure of the subject.

[0039] In some such embodiments, the quantifying the risk of glaucoma comprises generating a value defining a comparison of the eye pressure of the against a threshold baseline pressure.

[0040] In some such embodiments, the threshold baseline pressure is in a range between 18 millimeters of mercury (mmHg) and 25 mmHg.

[0041] In some embodiments, the acquiring, the quantifying the corneal response, the quantifying the eye pressure, and the quantifying the risk of glaucoma are performed in real time.

[0042] The systems, methods, devices, and non-transitory computer readable storage medium of the present invention have other features and advantages that will be apparent from, or are set forth in more detail in, the accompanying drawings, which are incorporated herein, and the following Detailed Description, which together serve to explain certain principles of exemplary embodiments of the present invention.BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 illustrates an exemplary system topology including a distributed computer system including a graphical data system and one or more imaging devices, in accordance with an exemplary embodiment of the present disclosure;

[0044] Figures 2A and 2B collectively illustrates a graphical data system for, at least, acquiring a plurality of images, quantifying a corneal response, quantifying an eye pressure of the subject using the corneal response, quantifying a risk of glaucoma for the subject using the eye pressure of the subject, or a combination thereof.

[0045] Figure 3 illustrates an imaging device, in accordance with an embodiment of the present disclosure;

[0046] Figures 4A, 4B, 4C, 4D, and 4E collectively illustrate exemplary methods for acquiring a plurality of images, quantifying a corneal response, quantifying an eye pressure of the subject using the corneal response, quantifying a risk of glaucoma for the subject using the eye pressure of the subject, or a combination thereof, in which optional embodiments are indicated by dashed boxes, in accordance with some embodiments of the present disclosure;

[0047] Figure 5 illustrates a view of an imaging device, in accordance with some embodiments of the present disclosure;

[0048] Figure 6A is a side view of an imaging device, in accordance with some embodiments of the present disclosure;

[0049] Figure 6B is a rear view of an imaging device, in accordance with some embodiments of the present disclosure;

[0050] Figure 7 illustrates a graphical user interface for visualizing an eye of a subject using an imaging device, in accordance with some embodiments of the present disclosure;

[0051] Figure 8A illustrates a plurality of images of an opening phase of a blink of an eye of a subject, in accordance with some embodiments of the present disclosure;

[0052] Figure 8B illustrates a chart depicting different quantification for corneal dynamics during blinking, including (1) whole globe translation; (2) corneal deformation; and (3) superposition of globe translation and corneal deformation, in accordance with some embodiments of the present disclosure;

[0053] Figure 8C illustrates a chart depicting an IOP as a function of corneal displacement and a baseline eye pressure, in accordance with some embodiments of the present disclosure;

[0054] Figures 9A, 9B, 9C, and 9D collectively illustrate a chart depicting an evaluation of corneal dynamics during a blink, in which sequential images of the blink visualize the transition from a slightly open-eye state to a fully open-eye state, with a predicted corneal masks from a model overlaid in blue (dark gray) color, and the green (light gray) dot indicates the centroid of the corneal profile, in accordance with some embodiments of the present disclosure;

[0055] Figure 10 illustrates a chart depicting corneal centroid displacement along the x-axis during the eye-opening phase, including raw data (blue (dark gray) circles) and the corresponding exponential fit (red (gray) line) based on key metrics (T and A), in accordance with some embodiments of the present disclosure;

[0056] Figure 11 illustrates a chart depicting an example of a classification method based on the mask area, in which the curve represents the segmented area over the sequence of frames during the eye-opening blink phase, each image is classified into four categories: closed eye (gray, area = 0), semi-closed eye (blue, area between 0% and 40% of the maximum), semiopen eye (green, area between 40% and 80% of the maximum), and open eye (red, area >network training, in accordance with some embodiments of the present disclosure;

[0057] Figure 12 illustrates a chart depicting a correlation coefficient signal when the adaptive template matching algorithm is employed, in which onsets represent the starting points of the opening phase, whereas offsets represent the ending points of the opening phase, in accordance with some embodiments of the present disclosure;

[0058] Figures 13, 14A, and 14B collectively illustrates a chart depicting corneal dynamics for a single participant in baseline and elevated IOP conditions, in which Figure 13 depicts normalized longitudinal centroid displacement during the blinks’ opening phase, the blue (dark gray) curves represent the displacement under baseline IOP condition, whereas the red (gray) curves correspond to the displacement under elevated IOP condition (Valsalva), in which normalization was applied only for visualization, as eye positions may vary across blinks recorded in different videos, Figure 14A depicts A of baseline versus elevated IOP conditions, and Figure 14B depicts T of baseline versus elevated IOP conditions, in accordance with some embodiments of the present disclosure;

[0059] Figures 15A and 15B collectively illustrate charts depicting the in vivo ability of the imaging device a) differentiate between the two responses, corneal applanation and eyeball translation; and b) have sufficient spatio-temporal resolution to characterize the corneal applanation and rebound post-blinking, in which the ability of the instrument to separate the two phenomena using different markers, e.g. cornea vertex for applanation and lashes or pupil displacement for eyeball translation and that the corneal displacement is tracked with sufficient spatio-temporal resolution to analyze the magnitude of applanation and speed of rebound, further that the behavior of the cornea is consistent with the ex vivo data thus validating the ability to infer IOP, in accordance with some embodiments of the present disclosure;

[0060] Figure 16 illustrates a chart depicting a comparison of centroid displacement between normal and Valsalva blinks, in accordance with some embodiments of the present disclosure;

[0061] Figure 17 illustrates a chart depicting a time constant, in accordance with some embodiments of the present disclosure;

[0062] Figure 18 illustrates a chart depicting a rise time of an eye lid during a blink, in accordance with some embodiments of the present disclosure;

[0063] Figure 19 illustrates a chart depicting a bilinear approximate, in accordance with some embodiments of the present disclosure;

[0064] Figure 20 illustrates a chart depicting a normalized centroid displacement for all the acquired blinks (normal and Valsalva), in accordance with some embodiments of the present disclosure;

[0065] Figures 21 and 22 collectively illustrates charts depicting a statistical analysis for 15 healthy subjects without ocular disease history, in which Figure 21 depicts T of normal and Valsalva IOP conditions across 15 samples (P<0.05), and Figure 22 depicts A of normal and Valsalva IOP conditions across 15 samples (no statistically significant difference), in accordance with some embodiments of the present disclosure;

[0066] Figure 23 illustrates a flow chart of an adaptive template matching algorithm to detect the opening phase of a blink, in accordance with some embodiments of the present disclosure;

[0067] Figure 24 illustrates exemplary logical functions that are used implemented in various embodiments of the present disclosure.

[0068] It should be understood that the appended drawings are not necessarily to scale, presenting a somewhat simplified representation of various features illustrative of the basic principles of the invention. The specific design features of the present invention as disclosed herein, including, for example, specific dimensions, orientations, locations, and shapes will be determined in part by the particular intended application and use environment.

[0069] In the figures, reference numbers refer to the same or equivalent parts of the present invention throughout the several figures of the drawing.DETAILED DESCRIPTION

[0070] The present disclosure provides systems and methods for monitoring intraocular pressure are provided. A plurality of images is acquired using a camera, in which the plurality of images is associated with a blink by an eye of a subject. In some embodiments, the plurality of images is associated with a plurality of blinks by the eye of the subject, such as a first blink during a first period of time and a second blink during the first period of time, which allows for capturing the eye during different points in time during the first period of time for a more accurate and precise data of the eye. However, the present disclosure is notlimited thereto. In some embodiments, a corneal response is quantified using the plurality of images, such as some or all of the plurality of images. For instance, in some embodiments, the corneal response is defined, at least in part, by an application of the cornea caused by the blink (e.g., by pressure exerted on the cornea by the eyelid of the subject, etc. . In this way, in some embodiments, the present disclosure provides for determining the corneal response using non-invasive techniques, which is advantageous to users lacking access to medical practitioners. In some embodiments, an eye pressure of the subject is quantified using the corneal response, such as by comparing the eye pressure to a predetermined baseline eye pressure or a threshold baseline eye pressure determined, at least in part, by a characteristic of the subject, such as a prior eye pressure value associated with the subject. However, the present disclosure is not limited thereto. In some embodiments, a risk of glaucoma is quantified for the subject using the eye pressure of the subject. In this way, the subject or a medical practitioner associated with the subject is provided the risked of glaucoma without having to utilize an invasive or resource extensive process. Moreover, in some embodiments, the risk of glaucoma is quantified using historic information (e.g., eye pressures) of the subject, which allows for individualizing the risk of glaucoma to the subject. However, the present disclosure is not limited thereto.

[0071] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be apparent to one of ordinary skill in the art that the present disclosure may be practiced without these specific details. In other instances, well-known methods, procedures, and components have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0072] It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For instance, a first subject could be termed a second subject, and, similarly, a second subject could be termed a first subject, without departing from the scope of the present disclosure. The first subject and the second subject are both subjects, but they are not the same subject.

[0073] The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the description of the invention and the appended claims, the singular forms “a,” “an,” and“the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0074] The foregoing description included example systems, methods, techniques, instruction sequences, and computing machine program products that embody illustrative implementations. For purposes of explanation, numerous specific details are set forth in order to provide an understanding of various implementations of the inventive subject matter. It will be evident, however, to those skilled in the art that implementations of the inventive subject matter may be practiced without these specific details. In general, well-known instruction instances, protocols, structures, and techniques have not been shown in detail.

[0075] The foregoing description, for purpose of explanation, has been described with reference to specific implementations. However, the illustrative discussions below are not intended to be exhaustive or to limit the implementations to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The implementations are chosen and described in order to best explain the principles and their practical applications, to thereby enable others skilled in the art to best utilize the implementations and various implementations with various modifications as are suited to the particular use contemplated.

[0076] In the interest of clarity, not all of the routine features of the implementations described herein are shown and described. It will be appreciated that, in the development of any such actual implementation, numerous implementation-specific decisions are made in order to achieve the designer’s specific goals, such as compliance with use case- and business-related constraints, and that these specific goals will vary from one implementation to another and from one designer to another. Moreover, it will be appreciated that such a design effort might be complex and time-consuming, but nevertheless be a routine undertaking of engineering for those of ordering skill in the art having the benefit of the present disclosure.

[0077] As used herein, the term “if’ may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” may be construed to mean “upon determining” or “in response to determining” or “upon detecting [the stated condition or event]” or “in response to detecting [the stated condition or event],” depending on the context.

[0078] Furthermore, as used herein, the term “about” or “approximately” can mean within an acceptable error range for the particular value as determined by one of ordinary skill in the art, which can depend in part on how the value is measured or determined, e.g., the limitations of the measurement system. For example, “about” can mean within 1 or more than 1 standard deviation, per the practice in the art. “About” can mean a range of ± 20%, ± 10%, ± 5%, or ± 1% of a given value. Where particular values are described in the application and claims, unless otherwise stated, the term “about” means within an acceptable error range for the particular value. The term “about” can have the meaning as commonly understood by one of ordinary skill in the art. The term “about” can refer to ± 10%. The term “about” can refer to ± 5%.

[0079] Moreover, as used herein, the term “AxB,” denotes a resolution of two-dimensional graphical data in which “A” is a number of pixels in a horizontal direction and “B” is a number of pixels in a vertical direction.

[0080] As used interchangeably herein, the term “classifier” or “model” refers to a machine learning model or algorithm.

[0081] In some embodiments, a model includes an unsupervised learning algorithm. One example of an unsupervised learning algorithm is cluster analysis. In some embodiments, a model includes supervised machine learning. Nonlimiting examples of supervised learning algorithms include, but are not limited to, logistic regression, neural networks, support vector machines, Naive Bayes algorithms, nearest neighbor algorithms, random forest algorithms, decision tree algorithms, boosted trees algorithms, multinomial logistic regression algorithms, linear models, linear regression, Gradient Boosting, mixture models, hidden Markov models, Gaussian NB algorithms, linear discriminant analysis, or any combinations thereof. In some embodiments, a model is a multinomial classifier algorithm. In some embodiments, a model is a 2-stage stochastic gradient descent (SGD) model. In some embodiments, a model is a deep neural network (e.g., a deep-and-wide sample-level model).

[0082] Neural networks. In some embodiments, the model is a neural network (e.g., a convolutional neural network and / or a residual neural network). Neural network algorithms, also known as artificial neural networks (ANNs), include convolutional and / or residual neural network algorithms (deep learning algorithms). In some embodiments, neural networks are machine learning algorithms that are trained to map an input dataset to an output dataset, where the neural network includes an interconnected group of nodes organized into multiple layers of nodes. For example, in some embodiments, the neural network architecture includes at least an input layer, one or more hidden layers, and an output layer. In some embodiments, the neural network includes any total number of layers, and any number of hidden layers, where the hidden layers function as trainable feature extractors that allow mapping of a set of input data to an output value or set of output values. In some embodiments, a deep learning algorithm is a neural network including a plurality of hidden layers, e.g., two or more hidden layers. In some instances, each layer of the neural network includes a number of nodes (or “neurons”). In some embodiments, a node receives input that comes either directly from the input data or the output of nodes in previous layers, and performs a specific operation, e.g., a summation operation. In some embodiments, a connection from an input to a node is associated with a parameter (c.g, a weight and / or weighting factor). In some embodiments, the node sums up the products of all pairs of inputs, xi, and their associated parameters. In some embodiments, the weighted sum is offset with a bias, b. In some embodiments, the output of a node or neuron is gated using a threshold or activation function, f, which, in some instances, is a linear or non-linear function. In some embodiments, the activation function is, for example, a rectified linear unit (ReLU) activation function, a Leaky ReLU activation function, or other function such as a saturating hyperbolic tangent, identity, binary step, logistic, arcTan, softsign, parametric rectified linear unit, exponential linear unit, softPlus, bent identity, softExponential, Sinusoid, Sine, Gaussian, or sigmoid function, or any combination thereof.

[0083] In some implementations, the weighting factors, bias values, and threshold values, or other computational parameters of the neural network, are “taught” or “learned” in a training phase using one or more sets of training data. For example, in some implementations, the parameters are trained using the input data from a training dataset and a gradient descent or backward propagation method so that the output value(s) that the ANN computes are consistent with the examples included in the training dataset. In some embodiments, the parameters are obtained from a back propagation neural network training process.

[0084] Any of a variety of neural networks are suitable for use in accordance with the present disclosure. Examples include, but are not limited to, graph neural networks, feedforward neural networks, radial basis function networks, recurrent neural networks, residual neural networks, convolutional neural networks, residual convolutional neural networks, and the like, or any combination thereof. In some embodiments, the machine learning makes use of a pre-trained and / or transfer-learned ANN or deep learning architecture. In some implementations, convolutional and / or residual neural networks are used, in accordance with the present disclosure.

[0085] For instance, a deep neural network model includes an input layer, a plurality of individually parameterized (e.g., weighted) convolutional layers, and an output scorer. The parameters (e.g., weights) of each of the convolutional layers as well as the input layer contribute to the plurality of parameters (e.g., weights) associated with the deep neural network model. In some embodiments, at least 50 parameters, at least 100 parameters, at least 1,000 parameters, at least 2,000 parameters or at least 5,000 parameters are associated with the deep neural network model. As such, deep neural network models require a computer to be used because they cannot be mentally solved. In other words, given an input to the model, the model output needs to be determined using a computer rather than mentally in such embodiments. See, for example, Krizhevsky et al., 2012, “Imagenet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems 2, Pereira, Burges, Bottou, Weinberger, eds., pp. 1097-1105, Curran Associates, Inc.; Zeiler, 2012 “ADADELTA: an adaptive learning rate method,” CoRR, vol. abs / 1212.5701; and Rumelhart et al., 1988, “Neurocomputing: Foundations of research,” ch. Learning Representations by Back-propagating Errors, pp. 696-699, Cambridge, MA, USA: MIT Press, each of which is hereby incorporated by reference.

[0086] Neural network algorithms, including convolutional neural network algorithms, suitable for use as models are disclosed in, for example, Vincent et al., 2010, “Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion,” J Mach Learn Res 11, pp. 3371-3408; Larochelle et al., 2009, “Exploring strategies for training deep neural networks, ””dec J Mach Learn Res 10, pp. 1-40; and Hassoun, 1995, Fundamentals of Artificial Neural Networks, Massachusetts Institute of Technology, each of which is hereby incorporated by reference. Additional example neural networks suitable for use as models are disclosed in Duda et al., 2001, Pattern Classification, Second Edition, John Wiley & Sons, Inc., New York; and Hastie et al., 2001, The Elementsof Statistical Learning, Springer-Verlag, New York, each of which is hereby incorporated by reference in its entirety. Additional example neural networks suitable for use as models are also described in Draghici, 2003, Data Analysis Tools for DNA Microarrays, Chapman & Hall / CRC; and Mount, 2001, Bioinformatics: sequence and genome analysis, Cold Spring Harbor Laboratory Press, Cold Spring Harbor, New York, each of which is hereby incorporated by reference in its entirety.

[0087] Ensembles of models and boosting. In some embodiments, an ensemble (two or more) of models is used. In some embodiments, a boosting technique such as AdaBoost is used in conjunction with many other types of learning algorithms to improve the performance of the model. In this approach, the output of any of the models disclosed herein, or their equivalents, is combined into a weighted sum that represents the final output of the boosted model. In some embodiments, the plurality of outputs from the models is combined using any measure of central tendency known in the art, including but not limited to a mean, median, mode, a weighted mean, weighted median, weighted mode, etc. In some embodiments, the plurality of outputs is combined using a voting method. In some embodiments, a respective model in the ensemble of models is weighted or unweighted.

[0088] As used herein, the term “parameter” refers to any coefficient or, similarly, any value of an internal or external element (e.g., a weight and / or a hyperparameter) in an algorithm, model, regressor, and / or classifier that can affect (e.g., modify, tailor, and / or adjust) one or more inputs, outputs, and / or functions in the algorithm, model, regressor and / or classifier. For example, in some embodiments, a parameter refers to any coefficient, weight, and / or hyperparameter that can be used to control, modify, tailor, and / or adjust the behavior, learning, and / or performance of an algorithm, model, regressor, and / or classifier. In some instances, a parameter is used to increase or decrease the influence of an input (e.g., a feature) to an algorithm, model, regressor, and / or classifier. As a nonlimiting example, in some embodiments, a parameter is used to increase or decrease the influence of a node (e.g., of a neural network), where the node includes one or more activation functions. Assignment of parameters to specific inputs, outputs, and / or functions is not limited to any one paradigm for a given algorithm, model, regressor, and / or classifier but can be used in any suitable algorithm, model, regressor, and / or classifier architecture for a desired performance. In some embodiments, a parameter has a fixed value. In some embodiments, a value of a parameter is manually and / or automatically adjustable. In some embodiments, a value of a parameter is modified by a validation and / or training process for an algorithm, model, regressor, and / orclassifier (e.g., by error minimization and / or backpropagation methods). In some embodiments, an algorithm, model, regressor, and / or classifier of the present disclosure includes a plurality of parameters. In some embodiments, the plurality of parameters is n parameters, where: n > 2; n > 5; n > 10; n > 25; n > 40; n > 50; n > 75; n > 100; n > 125; n > 150; n > 200; n > 225; n > 250; n > 350; n > 500; n > 600; n > 750; n > 1,000; n > 2,000; n > 4,000; n > 5,000; n > 7,500; n > 10,000; n > 20,000; n > 40,000; n > 75,000; n > 100,000; n > 200,000; n > 500,000, n > 1 x 106, n > 5 x 106, or n > 1 x 107. As such, the algorithms, models, regressors, and / or classifiers of the present disclosure cannot be mentally performed. In some embodiments n is between 10,000 and 1 x 107, between 100,000 and 5 x 106, or between 500,000 and 1 x 106. In some embodiments, the algorithms, models, regressors, and / or classifier of the present disclosure operate in a k-dimensional space, where k is a positive integer of 5 or greater (e.g., 5, 6, 7, 8, 9, 10, etc.). As such, the algorithms, models, regressors, and / or classifiers of the present disclosure cannot be mentally performed.

[0089] As used herein, the term “untrained model” (e.g., “untrained classifier” and / or “untrained neural network”) refers to a machine learning model or algorithm, such as a classifier or a neural network, that has not been trained on a target dataset. In some embodiments, “training a model” (e.g., “training a neural network”) refers to the process of training an untrained or partially trained model (e.g., “an untrained or partially trained neural network”). Moreover, it will be appreciated that the term “untrained model” does not exclude the possibility that transfer learning techniques are used in such training of the untrained or partially trained model. For instance, Fernandes et al., 2017, “Transfer Learning with Partial Observability Applied to Cervical Cancer Screening,” Pattern Recognition and Image Analysis: 8thIberian Conference Proceedings, 243-250, which is hereby incorporated by reference, provides non-limiting examples of such transfer learning. In instances where transfer learning is used, the untrained model described above is provided with additional data over and beyond that of the primary training dataset. Typically, this additional data is in the form of parameters (e.g., coefficients, weights, and / or hyperparameters) that were learned from another, auxiliary training dataset. Moreover, while a description of a single auxiliary training dataset has been disclosed, it will be appreciated that there is no limit on the number of auxiliary training datasets that can be used to complement the primary training dataset in training the untrained model in the present disclosure. For instance, in some embodiments, two or more auxiliary training datasets, three or more auxiliary training datasets, four or more auxiliary training datasets or five or more auxiliary training datasets are used to complementthe primary training dataset through transfer learning, where each such auxiliary dataset is different than the primary training dataset. Any manner of transfer learning is used, in some such embodiments. For instance, consider the case where there is a first auxiliary training dataset and a second auxiliary training dataset in addition to the primary training dataset. In such a case, the parameters learned from the first auxiliary training dataset (by application of a first model to the first auxiliary training dataset) are applied to the second auxiliary training dataset using transfer learning techniques (e.g., a second model that is the same or different from the first model), which in turn results in a trained intermediate model whose parameters are then applied to the primary training dataset and this, in conjunction with the primary training dataset itself, is applied to the untrained model. Alternatively, in another example embodiment, a first set of parameters learned from the first auxiliary training dataset (by application of a first model to the first auxiliary training dataset) and a second set of parameters learned from the second auxiliary training dataset (by application of a second model that is the same or different from the first model to the second auxiliary training dataset) are each individually applied to a separate instance of the primary training dataset (e.g., by separate independent matrix multiplications) and both such applications of the parameters to separate instances of the primary training dataset in conjunction with the primary training dataset itself (or some reduced form of the primary training dataset such as principal components or regression coefficients learned from the primary training set) are then applied to the untrained model in order to train the untrained model.

[0090] Furthermore, when a reference number is given an “zth” denotation, the reference number refers to a generic component, set, or embodiment. For instance, a model termed “model z” refers to the zthmodel in a plurality of models (e.g., a model 118-z in a plurality of models 118). In the present disclosure, unless expressly stated otherwise, descriptions of devices and systems will include implementations of one or more computers.

[0091] In the present disclosure, unless expressly stated otherwise, descriptions of devices and systems will include implementations of one or more computers. For instance, and for purposes of illustration in Figure 1, 2A and 2B, a graphical data system 200 is represented as a single device that includes all the functionality of a computer system. Moreover, and for purposes of illustration in Figures 1, 3, 5, and 6A-6B, an imaging device 300 is represented as a single device that includes all the functionality of a computer system. However, the present disclosure is not limited thereto. For instance, in some embodiments, the functionality of the graphical data system 200 is spread across any number of networked computers and / or resideon each of several networked computers and / or by hosted on one or more virtual machines and / or containers at a remote location accessible across a communications network (c.g, communications network 186 of Figure 1) and / or the functionality of the imaging device 300 is spread across any number of networked computers and / or reside on each of several networked computers and / or by hosted on one or more virtual machines and / or containers. One of skill in the art will appreciate that a wide array of different computer topologies is possible for the graphical data system 200, the imaging device 300, and other devices and systems of the preset disclosure, and that all such topologies are within the scope of the present disclosure. Moreover, rather than relying on a physical communications network 186, the illustrated devices and systems may wirelessly transmit information between each other. As such, the exemplary topology shown in Figure 1 merely serves to describe the features of an embodiment of the present disclosure in a manner that will be readily understood to one of skill in the art.

[0092] Figures 2A and 2B collectively depicts a block diagram of a graphical data system 200 according to some embodiments of the present disclosure. In some embodiments, the graphical data system 200 at least facilitates quantifying a corneal response using aplurality of images (e.g., images captured using the imaging device 300 of Figure 5, etc.), quantifying an eye pressure of the subject using the corneal response, quantifying a risk of glaucoma for the subject using the eye pressure of the subject, or a combination thereof.

[0093] In some embodiments, the communication network 186 optionally includes the Internet, one or more local area networks (LANs), one or more wide area networks (WANs), other types of networks, or a combination of such networks.

[0094] Examples of communication networks 186 include the World Wide Web (WWW), an intranet and / or a wireless network, such as a cellular telephone network, a wireless local area network (LAN) and / or a metropolitan area network (MAN), and other devices by wireless communication. The wireless communication optionally uses any of a plurality of communications standards, protocols and technologies, including Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), high-speed downlink packet access (HSDPA), high-speed uplink packet access (HSUPA), Evolution, Data-Only (EV-DO), HSPA, HSPA+, Dual-Cell HSPA (DC-HSPDA), long term evolution (LTE), near field communication (NFC), wideband code division multiple access (W-CDMA), code division multiple access (CDMA), time division multiple access (TDMA), Bluetooth, Wireless Fidelity (Wi-Fi) (e.g., IEEE 802. I la, IEEE 802.1 lac, IEEE 802.1 lax, IEEE802.1 lb, IEEE 802.11g and / or IEEE 802.1 In), voice over Internet Protocol (VoIP), WiMAX, a protocol for e-mail (e.g., Internet message access protocol (IMAP) and / or post office protocol (POP)), instant messaging (e.g., extensible messaging and presence protocol (XMPP), Session Initiation Protocol for Instant Messaging and Presence Leveraging Extensions (SIMPLE), Instant Messaging and Presence Service (IMPS)), and / or Short Message Service (SMS), or any other suitable communication protocol, including communication protocols not yet developed as of the filing date of this document.

[0095] In various embodiments, the graphical data system 200 includes one or more processing units (CPUs) 172, a network or other communications interface 174, and memory 192.

[0096] In some embodiments, the graphical data system 200 includes a user interface 176. The user interface 176 typically includes a display 178 for presenting media, such as a result by a plurality of models (e.g., first model 118-1, second model 118-2, . . ., model X 118-X of Figure 2B), a graphical user interface of a client application (e.g., graphical user interface 700 of Figure 7), or a portion (e.g., some or all) of a plurality of images captured by an imaging device 300. In some embodiments, the display 178 is integrated within the graphical data system 200 (e.g., housed in the same chassis as the CPU 172 and the memory 192). In some embodiments, the graphical data system 200 includes one or more input device(s) 180, which allow a subject to interact with the graphical data system 200. In some embodiments, the input devices 180 include a keyboard, a mouse, and / or other input mechanisms.Alternatively, or in addition, in some embodiments, the display 178 includes a touch- sensitive surface (e.g., where display 178 is a touch-sensitive display or the graphical data system 200 includes a touch pad).

[0097] In some embodiments, the graphical data system 200 presents media to a user through the display 178. Examples of media presented by the display 178 include one or more images, a video, audio (e.g., waveforms of an audio sample), or a combination thereof. In typical embodiments, the one or more images, the video, the audio, or the combination thereof is presented by the display 178 through a client application 130. In some embodiments, the audio is presented through an external device (e.g., speakers, headphones, input / output (I / O) subsystem, etc.) that receives audio information from the graphical data system 200 and presents audio data based on this audio information. In some embodiments, the user interface 176 also includes an audio output device, such as speakers or an audio output for connecting with speakers, earphones, or headphones.

[0098] The memory 192 includes high-speed random access memory, such as DRAM, SRAM, DDR RAM, or other random access solid state memory devices, and optionally also includes non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. The memory 192 may optionally include one or more storage devices remotely located from the CPU(s) 172. The memory 192, or alternatively the non-volatile memory device(s) within the memory 192, includes a non-transitory computer readable storage medium. Access to the memory 192 by other components of the graphical data system 200, such as the CPU(s) 172, is, optionally, controlled by a controller. In some embodiments, the memory 192 can include mass storage that is remotely located with respect to the CPU(s) 172. In other words, some data stored in memory 192 may in fact be hosted on devices that are external to the graphical data system 200, but that can be electronically accessed by the graphical data system 200 over an Internet, intranet, or other form of network 186 or electronic cable using communication interface 184.

[0099] In some embodiments, the memory 192 of the graphical data system 200 optimizing decoding of graphical data 108 stores:• optionally, an operating system 102 (e.g., ANDROID, iOS, DARWIN, RTXC, LINUX, UNIX, OS X, WINDOWS, or an embedded operating system such as VxWorks) that includes procedures for handling various basic system services;• optionally, an electronic address 104 associated with the graphical data system 200 that identifies graphical data system 200 (e.g., within the communication network 186);• optionally, a graphical data store 106 that stores a record of graphical data (e.g., first plurality of graphical data 108-1, second one or more graphical data 108-2, . . ., graphical data C 108-C of Figure 2A), each graphical data 108 is defined by a plurality of characteristics (e.g., first plurality of characteristics 110-1 of Figure 2A), that collectively characterize a corresponding graphical data 108 by one or more characteristics (e.g., value of first characteristic 112-1-1, value of second characteristic 112-2-1, . . ., value of characteristic P 112-1-P of first plurality of characteristics 110-1 of Figure 2A) that is utilized by one or more models 118, such as for obtaining a training data set, obtaining a trained feature extraction model 118, and, optionally, an encoded byte stream including a plurality of sequence scans associated with the corresponding graphical data 108;• a model library 116 that retains a plurality of models (e.g., first model 118-1, second model 118-2, . . ., model F 118-F of Figure 2B), in which, in some embodiments, a respective model 118 is configured for evaluating, at least in part, a plurality of images 710 and / or in accordance with one or more parameters of the model 118 (e.g., first parameter 120-1, second parameter 120-2, . . ., parameter D 120-D of first model 118-1 of Figure 2B);• a camera control model 122 that includes a light control module 124 for controlling illumination of a field of view associated with one or more cameras 504 and an image capture module 126 for facilitating capture of one or more images 710 using at least one camera 702 in the one or more cameras 504; and• optionally, a client application 130 for presenting information (e.g., media) using a display 178 of the graphical data system 200.

[0100] As indicated above, preferably, the graphical data system 200 includes an operating system 102 that includes procedures for handling various basic system services. The operating system 102 (e g., iOS, ANDROID, DARWIN, RTXC, LINUX, UNIX, OS X, WINDOWS, or an embedded operating system such as VxWorks) includes various software components and or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.) and facilitates communication between various hardware and software components.

[0101] In some embodiments, an optional electronic address 104 is associated with the graphical data system 200. The optional electronic address 104 is utilized to at least uniquely identify the graphical data system 200 from other devices and components of the distributed system 100, such as other client devices 300 having access to the communications network 186. For instance, in some embodiments, the electronic address 104 is utilized to receive a request from an imaging device 300 to communicate a one or more images 710 captured at the imaging device 30, such as in real-time or after deemed to have completed capture of each image 710 in the one or more images 710. However, the present disclosure is not limited thereto.

[0102] The graphical data system 200 includes a graphical data store 106 that stores a variety of image data 108, such as one or more sets of a respective plurality of images 702. For instance, in some embodiments, the graphical data store 106 is configured to retain between three and 20 sets of image data associated with one or more subjects, between 5 and 40 sets of images, between 15 and 100 sets of images, or between 25 and 150 sets of images.

[0103] Each respective image data 108 is defined by a corresponding plurality of characteristics (e.g., first plurality of characteristics 110-1 define first image data 108-1 of Figure 2A). For instance, in some embodiments, each respective plurality of images 710 is defined by between three and 20 characteristics 112, between 5 and 40 characteristics, between 15 and 100 characteristics, or between 25 and 150 characteristics. In some embodiments, each respective plurality of images 710 is defined by between three and 20 characteristics 112, between 5 and 40 characteristics, between 15 and 100 characteristics, or between 25 and 150 characteristics. In some embodiments, each respective plurality of images 710 is defined by at least 5 characteristics 112, at least 15 characteristics, at least 25 characteristics, at least 50 characteristics, at least 100 characteristics, or at least 150 characteristics. In some embodiments, each respective plurality of images 710 is defined by at most 5 characteristics 112, at most 15 characteristics, at most 25 characteristics, at most 50 characteristics, at most 100 characteristics, or at most 150 characteristics 112.

[0104] Collectively, the plurality of characteristics 110 characterize the corresponding image data 108 by one or more characteristics 112. The one or more characteristics provide information about one or more aspects of the corresponding graphical data 108. For instance, in some embodiments, the one or more characteristics 112 includes a first characteristic 112-1 associated with a corresponding modality of the plurality of images 710 (e.g., a first value of the first characteristic 112-1 is associated with a first modality, a second value of the first characteristic 112-1 is associated with a second modality different than the first modality, etc.), a second characteristic 112-2 associated with a sampling resolution of the plurality of images 710, a third characteristic 112-3 associated with a file format of the plurality of images 710 a, a fourth characteristic 112-4 associated with a subject matter (e.g., content) of the plurality of images 710, a fifth characteristic 112-5 associated with a capture setting (e.g., camera setting) associated with the plurality of images 710, or a combination thereof. However, the present disclosure is not limited thereto. For instance, in some embodiments, the third characteristic 112-3 associated with the file format allows for retaining images 710 in any electronic image file format, including but not limited to JPEG / JFIF, TIFF, Exif, PDF, EPS, GIF, BMP, PNG, PPM, PGM, PBM, PNM, WebP, HDR raster formats, HEIF, BAT, BPG, DEEP, DRW, ECW, FITS, FLIF, ICO, ILBM, IMG, PAM, PCX, PGF, JPEG XR, Layered Image File Format, PLBM, SGI, SID, CD5, CPT, PSD, PSP, XCF, PDN, CGM, SVG, PostScript, PCT, WMF, EMF, SWF, XAML, and / or RAW. Furthermore, in some such embodiments, the ability of the graphical data system 200 to retain a variety of electronicallows for compressing and reconstructing the plurality of images 710 for future user or training.

[0105] In some embodiments, the plurality of images 710 is obtained in any electronic color mode, including but not limited to grayscale, bitmap, indexed, RGB, CMYK, HSV, lab color, duotone, and / or multichannel. In some embodiments, the plurality of images 710 is manipulated (e.g., stitched, compressed and / or flattened).

[0106] In some embodiments, the plurality of images 710 includes between 1 million and 25 million pixels. In some embodiments, each resolution is represented by five or more, ten or more, 100 or more, 1,000 or more contiguous pixels in an image. In some embodiments, each resolution is represented by between 1,000 and 250,000 contiguous pixels in a native image 125.

[0107] In some embodiments, the plurality of images 710 is represented as an array (e.g., matrix) including a plurality of pixels, such that the location of each respective pixel in the plurality of pixels in the array (e.g., matrix) corresponds to its original location in the image. In some embodiments, the plurality of images 710 is represented as a vector including a plurality of pixels, such that each respective pixel in the plurality of pixels in the vector includes spatial information corresponding to its original location in an image 710 in the plurality of images 710.

[0108] In some embodiments, a pixel includes one or more pixel values (e.g., an intensity value). In some embodiments, each respective pixel in the plurality of pixels includes one pixel intensity value, such that the plurality of pixels represents a single-channel image including a one-dimensional integer vector including the respective pixel values for each respective pixel. For example, in some embodiments, an 8-bit single-channel image (e.g., grey-scale) includes 28or 256 different pixel values (e.g., 0-255). In some embodiments, each respective pixel in the plurality of pixels of an image includes a plurality of pixel values, such that the plurality of pixels represents a multi-channel image including a multidimensional integer vector, where each vector element represents a plurality of pixel values for each respective pixel. For example, in some embodiments, a 24-bit 3-channel image (e.g., RGB color) includes 224(e.g., 28x3) different pixel values, where each vector element includes 3 components, each between 0-255. In some embodiments, an / / -bit image of the plurality of graphical data includes up to 2" different pixel values, where n is any positive integer. See, Uchida, 2013, “Image processing and recognition for biological images,” Develop. GrowthDiffer., 55, pg. 523-549, doi: 10.1111 / dgd.12054, which is hereby incorporated herein by reference in its entirety for all purposes.

[0109] Referring to Figure 2B, the graphical data system 200 includes a model library 116 that stores a plurality of models 118 (e.g., classifiers, regressors, clustering, etc.). In some embodiments, the model library 116 stores two more models 118 (e.g., a first feature extraction model 118-1 and a second feature extraction model 118-2), three or more models (e.g., a first segmentation model 118-1, a second first classification model 118-2, a third second classification model 118-3), four or more models, ten or more models, 50 or more models, or 100 or more models. In some embodiments, a model 118 in the plurality of models 118 of the model library 116 is implemented as an artificial intelligence engine. For instance, in some embodiments, the model 118 includes one or more feature extraction models including one or more segmentation models 118, classification models 118, one or more gradient boosting models 118, one or more random forest models 118, one or more neural network (NN) models 118, one or more regression models, one or more Naive Bayes models 118, one or more machine learning algorithms (MLA) 118, or a combination thereof. In some embodiments, an MLA or a NN is trained from a training data set that includes one or more features identified from a data set. MLAs include supervised algorithms (such as algorithms where the features / classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naive Bayes, nearest neighbor clustering; unsupervised algorithms (such as algorithms where no features / classification in the data set are annotated a priori), such as means clustering, principal component analysis, random forest, adaptive boosting; and semi-supervised algorithms (such as algorithms where an incomplete number of features / classifications in the data set are annotated) using generative approach (such as a mixture of Gaussian distributions, mixture of multinomial distributions, hidden Markov models), low density separation, graph-based approaches (such as minimum cut, harmonic function, manifold regularization, etc.), heuristic approaches, or support vector machines.

[0110] Neural network models 118 include conditional random fields models 118, convolutional neural network (CNN) models 118, attention based neural network models 118, deep learning models 118, long short term memory network model 118, or other neural models 118.

[0111] While MLA and neural networks identify distinct approaches to machine learning, the terms may be used interchangeably herein. Thus, a reference to MLA may include acorresponding NN or a reference to NN may include a corresponding MLA unless explicitly stated otherwise. In some embodiments, the training of a respective model 118 includes providing one or more optimized data sets, such as a first plurality of graphical data 108-1, labeling features as they occur (e.g., as a characteristic 112 associated with the plurality of graphical data 108), and training the MLA to predict or classify based on new inputs. Artificial NNs are efficient computing models 118 which have shown their strengths in solving hard problems in artificial intelligence. For instance, artificial NNs have also been shown to be universal approximators, that is, they can represent a wide variety of functions when given appropriate parameters.

[0112] One of skill in the art will readily appreciate other models 118 that are applicable to the systems and methods of the present disclosure. In some embodiments, the systems and methods of the present disclosure utilize more than one model 118 to provide an evaluation (e.g., arrive at an evaluation given one or more inputs), such as quantifying a corneal response using the plurality of images, quantifying an eye pressure of the subject using the corneal response, quantifying a risk of glaucoma for the subject using the eye pressure of the subject, or a combination thereof with an increased accuracy and computational efficency. For instance, in some embodiments, each respective model 118 arrives at a corresponding evaluation when provided a respective data set. Accordingly, in some embodiments, each respective model 118 independently arrives at a result and then the result of each respective model 118 is collectively verified through a comparison or amalgamation of the models 118. From this, a cumulative result is provided by the models 118. However, the present disclosure is not limited thereto.

[0113] In some embodiments, a respective model 118 is tasked with performing a corresponding activity. As a non-limiting example, in some embodiments, the task performed by the respective model 118 includes, but is not limited to, acquiring a plurality of images associated with a blink by an eye of a subject, quantifying a corneal response using the plurality of images, quantifying an eye pressure of the subject using the corneal response, quantifying a risk of glaucoma for the subject using the eye pressure of the subject, any combination thereof.

[0114] In some embodiments, each respective model 118 of the present disclosure makes use of 10 or more parameters, 100 or more parameters, 1000 or more parameters, 10,000 or more parameters, or 100,000 or more parameters. In some embodiments, each respective model 118 of the present disclosure cannot be mentally performed.

[0115] In some embodiments, a client application 130 is a group of instructions that, when executed by the processor 174, generates content for presentation to the user (e.g., graphical data 108-1 of Figure 11, etc.), such as a result provided by one or more models 118. In some embodiments, the client application 130 generates content in response to one or more inputs received from the user through the imaging device 300 and / or the inputs 180 of the graphical data system 200.

[0116] Each of the above identified modules and applications correspond to a set of executable instructions for performing one or more functions described above and the methods described in the present disclosure (e.g., the computer-implemented methods and other information processing methods described herein). These modules (e.g., sets of instructions) need not be implemented as separate software programs, procedures or modules, and thus various subsets of these modules are, optionally, combined or otherwise re-arranged in various embodiments of the present disclosure. In some embodiments, the memory 192 optionally stores a subset of the modules and data structures identified above. Furthermore, in some embodiments, the memory 192 stores additional modules and data structures not described above.

[0117] It should be appreciated that the graphical data system of Figures 2A and 2B is only one example of a graphical data system, and that the graphical data system 200 optionally has more or fewer components than shown, optionally combines two or more components, or optionally has a different configuration or arrangement of the components. The various components shown in Figures 2A and 2B are implemented in hardware, software, firmware, or a combination thereof, including one or more signal processing and / or application specific integrated circuits.

[0118] Referring to Figure 3, a description of an exemplary imaging device 300 that can be used with the present disclosure is provided. In some embodiments, an imaging device 300 includes a smart phone (e.g., an iPhone, an Android device, etc.), a laptop computer, a tablet computer, a desktop computer, a wearable device (e.g., a smart watch, a heads-up display (HUD) device, imaging device of Figure 5, imaging device 300 of Figure 6A, imaging device 300 of Figure 6B, etc.), a television (e.g., a smart television), or another form of electronic device such as a gaming console, a stand-alone device, and the like. However, the present disclosure is not limited thereto

[0119] The imaging device 300 illustrated in Figure 3 has one or more processing units (CPU’s) 272, a network or other communications interface 274, a memory 292 (e.g., random access memory), a user interface 276, the user interface 276 including a display 278 and input 280 (e.g., keyboard, keypad, touch screen, etc.), optional audio circuitry, an optional speaker, an optional microphone, an optional input / output (I / O) subsystem, one or more communication busses 270 for interconnecting the aforementioned components, and a power system (e.g., power supply) for powering the aforementioned components.

[0120] In some embodiments, the input 280 is a touch-sensitive display, such as a touch- sensitive surface. In some embodiments, the user interface 276 includes one or more soft keyboard embodiments. In some embodiments, the soft keyboard embodiments include standard (QWERTY) and or non-standard configurations of symbols on the displayed icons. The input 280 and / or the user interface 276 is utilized by an end-user of the respective imaging device 300 (e.g., a respective subject) to input various information (e.g., a text object within a message) to the respective imaging device.

[0121] In some embodiments, the imaging device 300 illustrated in Figure 3 optionally includes, in addition to accelerometer(s), a magnetometer, and a global positioning system (GPS or GLONASS or other global navigation system) receiver for obtaining information concerning a current location (e.g., a latitude, a longitude, an elevation, etc.) and / or an orientation (e.g., a portrait or a landscape orientation of the device) of the imaging device 300.

[0122] It should be appreciated that the imaging device 300 illustrated in Figure 3 is only one example of a multifunctional device that may be used for acquiring a plurality of images associated with a blink by an eye of a subject, quantifying a corneal response using the plurality of images, quantifying an eye pressure of the subject using the corneal response, quantifying a risk of glaucoma for the subject using the eye pressure of the subject, or a combination thereof. Thus, the imaging device 300 optionally has more or fewer components than shown, optionally combines two or more components, or optionally has a different configuration or arrangement of the components. The various components shown in Figure 3 are implemented in hardware, software, firmware, or a combination thereof, including one or more signal processing and / or application specific integrated circuits. In some embodiments imaging device 300 is a desktop or laptop computer.

[0123] The memory 292 of the imaging device 300 illustrated in Figure 3 optionally includes high-speed random access memory and optionally also includes non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. Access to the memory 292 by other components of the imaging device 300, such as CPU(s) 272 is, optionally, controlled by the memory controller.

[0124] In some embodiments, the one or more CPU(s) 272 run or execute various software programs and / or sets of instructions stored in the memory 292, such as the client application 230, to perform various functions for the imaging device 300 and process data.

[0125] In some embodiments, the CPU(s) 272 and the memory controller are implemented on a single chip. In some other embodiments, the CPU(s) 272 and the memory controller are implemented on separate chips.

[0126] In some embodiments, the audio circuitry, the optional speaker, and the optional microphone provide an audio interface between the respective subject and the imaging device 300, enabling the imaging device to provide a message that include audio data provided through the audio circuitry, the optional speaker, and / or the optional microphone. The audio circuitry receives audio data from the peripherals interface, converts the audio data to electrical signals, and transmits the electrical signals to the speaker. The speaker converts the electrical signals to human-audible sound waves. The audio circuitry also receives electrical signals converted by the microphone from sound waves. The audio circuitry converts the electrical signal to audio data and transmits the audio data to peripherals interface for processing. Audio data is, optionally, retrieved from and or transmitted to the memory 292 and or the RF circuitry by the peripherals interface.

[0127] In some embodiments, the imaging device 300 optionally also includes one or more optical sensors. The optical sensor(s) optionally include charge-coupled device (CCD) or complementary metal-oxide semiconductor (CMOS) phototransistors. The optical sensor(s) receive light from the environment, projected through one or more lens, and converts the light to data representing an image. The optical sensor(s) optionally capture still images and or video. In some embodiments, an optical sensor is disposed on a back end portion of the imaging device 300 (e.g., opposite the display 278 on a front end portion of the imaging device 300) so that the input 280 is enabled for use as a viewfinder for still (e.g., digital image, etc. and or video graphical data acquisition.

[0128] In some embodiments, the memory 292 of the imaging device 300 stores:• an operating system 202 that includes procedures for handling various basic system services;• an electronic address 204 associated with the imaging device 300;• a model library 216 that retains a plurality of models (e.g., first model 118-1, second model 118-2, . . ., model F 118-X of Figure 2B), in which, in some embodiments, a respective model 118 is configured for evaluating, at least in part, images 710 in accordance with one or more parameters of the model 118 (e.g., first parameter 120-1, second parameter 120-2, . . ., parameter D 120-D of first model 118-1 of Figure 2B);• a camera control model 222 that includes a light control module 224 for controlling illumination of a field of view associated with one or more cameras 504 and an image capture module 226 for facilitating capture of one or more images 710 using at least one camera 702 in the one or more cameras 504; and• optionally, a client application 130 for presenting information (e.g., media) using a display 278.

[0129] As illustrated in Figure 3, the imaging device 300 preferably includes an operating system 202 that includes procedures for handling various basic system services. The operating system 202 (e g., iOS, ANDROID, DARWIN, RTXC, LINUX, UNIX, OS X, WINDOWS, or an embedded operating system such as VxWorks) includes various software components and or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.) and facilitates communication between various hardware and software components.

[0130] An electronic address 204 is associated with each imaging device 300, which is utilized to at least uniquely identify the imaging device from other devices and components of the system 100. In some embodiments, the electronic address 204 of the imaging device 300 has the same functionality as the electronic address 104 of the graphical data system 200. However, the present disclosure is not limited thereto.

[0131] In some embodiments, the imaging device includes a model library 216 that stores a plurality of models 118 (e.g., classifiers, regressors, clustering, etc.). In some embodiments, the model library 216 of the imaging device 300 has the same functionality as the modellibrary 116 of the graphical data system 200. However, the present disclosure is not limited thereto.

[0132] In some embodiments, the client application 230 is a group of instructions that, when executed by the processor 272, generates content for presentation to the respective subject (e.g., image 710 of Figure 8, etc.), such as a result of a corresponding output generated by one or more models 118. In some embodiments, the client application 230 generates content in response to one or more inputs received from the respective subject through the imaging device 300, such as the inputs 280 of the imaging device 300. In some embodiments, the client application 230 of the imaging device 300 has the same functionality as the client application 130 of the graphical data system 200. However, the present disclosure is not limited thereto.

[0133] In some embodiments, the imaging device 300 has any or all of the circuitry, hardware components, and software components found in the system depicted in Figure 3. In the interest of brevity and clarity, only a few of the possible components of the client device 300 are shown to better emphasize the additional software modules that are installed on the client device.

[0134] Referring to Figure 5, provided is an imaging device 300 configured to non- invasively monitor IOP in accordance with some embodiments of the present disclosure. Accordingly, in some embodiments, the imaging device 300 is configured to quantify one or more changes associated with an eye of a subject, such as a retina change due to elevated IOP, including trends of IOP over a period of time for the subject. However, the present disclosure is not limited thereto.

[0135] In some embodiments, the imaging device 300 is an electro-optical device configured for measuring (e.g., quantifying) the intraocular pressure of the eye 702 without physical excitation or external forces, such as an air puff provided by another device. In some embodiments, the imaging device 300 includes one or more cameras 702 configured to acquire a plurality of images 710 having a field of view of a close-up of the eye 702, such as from the side (e.g., the profile view of substantially profile view). In some embodiments, the imaging device 300 is configured to compile the plurality of images 710 into a video (e.g., video of Figure 7, etc.). However, the present disclosure is not limited thereto.

[0136] In some embodiments, the imaging device 300 includes one or more light sources 506 configured to illuminate a region of interest (ROI), such as a field of view of one or morecameras 504 of the imaging device 300. For instance, in some embodiments, a first light source 506-s is configured to provide coherent light (e.g., first light source 506-2 includes a laser light source), which causes coherent light to reflect off a surface of the cornea and is received by a first camera 504-1 configured to receive the coherent light of a different light. For instance, in some embodiments, the imaging device 300 includes a front facing laser light source 506 configured to illuminate the cornea of the eye, and a camera 504 configured to receive infrared (IR) light is utilized, at least in part, quantify an angle of reflected light from the cornea (e.g., quantify a beam wander, etc.). In some embodiments, such as in order to keep an exposure time of one or more cameras 504 at or below a threshold exposure time, and, thus, improve a boundary contrast of the cornea, the one or more light sources illuminate the eye to be bright in the image 701. However, the present disclosure is not limited thereto.

[0137] In some embodiments, one or more cameras 504 of the imaging device 300 is disposed or configured to view a side of the eye. In some embodiments, the one or more cameras 504 include a first camera 504-1 configured to view a first side of a first eye (e.g., a right hand side of a right eye of the subject) and a second camera 504-2 is configured to view a second side of a second eye (e.g., a left hand side of a left eye of the subject), which allows for selecting acquiring images of either eye of the subject or both eyes of the subject.

[0138] Each of the above identified modules and applications correspond to a set of executable instructions for performing one or more functions described above and the methods described in the present disclosure. These modules (e.g., sets of instructions) need not be implemented as separate software programs, procedures or modules, and thus various subsets of these modules are, optionally, combined or otherwise re-arranged in various embodiments of the present disclosure. In some embodiments, the memory 292 optionally stores a subset of the modules and data structures identified above. Furthermore, in some embodiments, the memory 292 stores additional modules and data structures not described above.

[0139] It should be appreciated that Figures 3 and 5 illustrates only an example of the imaging device 300, and that the imaging device 300 optionally has more or fewer components than shown, optionally combines two or more components, or optionally has a different configuration or arrangement of the components. The various components shown in Figure 3 are implemented in hardware, software, firmware, or a combination thereof, including one or more signal processing and / or application specific integrated circuits. Moreover, the imaging device 300 can be a single device that includes all the functionality ofthe imaging device 300. The imaging device 300 can also be a combination of multiple devices. For instance, the functionality of the imaging device 300 may be spread across any number of networked computers and / or reside on each of several networked computers and / or by hosted on one or more virtual machines and / or containers at a remote location accessible across a communications network (e.g, communications network 186, network interface 284, or both). One of skill in the art will appreciate that a wide array of different computer topologies is possible for the imaging device 300, and other devices and systems of the preset disclosure, and that all such topologies are within the scope of the present disclosure.

[0140] Now that a general topology of the distributed system 100 has been described in accordance with various embodiments of the present disclosures, details regarding some processes in accordance with Figures 4A through 4D will be described.

[0141] Various modules in a memory 192 of a graphical data system 200 (e.g., graphical data store 106 of Figure 2A, model library 116 of Figure 2B, camera control module 122, etc.) and / or a memory 292 of an imaging device 300 (e.g., model library 216 of Figure 3, camera control module 222 of Figure 3, etc.) perform certain processes of the methods of the present disclosure, unless expressly stated otherwise. Furthermore, it will be appreciated that the processes of a method of the present disclosure can be encoded in a single module or any combination of modules.

[0142] Referring now to Figures 4A through 4D, there is depicted a flowchart illustrating an exemplary method 400 in accordance with some embodiments of the present disclosure. In the flowchart, the preferred parts of the method are shown in solid line boxes, whereas additional, optional, or alterative parts of the method are shown in dashed line boxes.

[0143] In some embodiments, the method 400 allows for

[0144] Block 402. Referring to block 402 of Figure 4 A, in various embodiments, the method 400 is provided at a computer system (e.g., graphical data system 200 of Figures 2A and 2B, imaging device 300 of Figure 3, imaging device 300 of Figure 6, imaging device 300 of Figure 6A, imaging device 300 of Figure 6B, etc.). The computer system 200 includes one or more processors (e.g., CPU 172 of Figure 2A, CPU 272 of Figure 3, etc.) and a memory (e.g., memory 192 of Figures 2A and 2B, memory 392 of Figure 3, etc.), such a first memory coupled to the one or more processors. In some embodiments, the memory includes one or more programs configured to be executed by the one or more processors (e.g, graphical datastore 106 of Figure 2A, model library 116 of Figure 2B, control module 122 of Figure 2B, model library 216 of Figure 3, control module 222 of Figure 3, etc.). Accordingly, in some such embodiments, the method 400 requires utilization of a computer system, such as in order to evaluate the image data 710 and communicate the image data 710 via the communication network 186, and, therefore, cannot be mentally performed.

[0145] Block 4002. Referring to block 4002, in some embodiments, the method 400 includes acquiring a plurality of images 710 associated with a blink by an eye 702 of a subject. For instance, in some embodiments, the plurality of images 710 is acquired as a stream of graphical data, captured at an imaging device 300, of an eye of the subject during a period of time, in which the subject blinks at least one during the period of time, such that the blink is visualized through some or all of the plurality of images 710. However, the present disclosure is not limited thereto.

[0146] In some embodiments, the acquiring is performed for a continuous period of time, such as for 30 seconds (s), a minute (min), an hour (hr), etc., which allows for capturing two or more blinks in the plurality of images 710. However, the present disclosure is not limited thereto.

[0147] In some embodiments, the continuous period of time of the acquiring is at least 5 s, at least 350 s, at least 695 s, at least 1040 s, at least 1385 s, at least 1730 s, at least 2075 s, at least 2420 s, at least 2760 s, at least 3105 s, at least 3600 s, at least 3795 s, at least 4140 s, at least 4485 s, at least 4830 s, at least 5175 s, at least 5520 s, at least 5865 s, at least 6210 s, at least 6555 s, at least 6900 s, at least 7200 s, at least 7585 s, at least 7930 s, at least 8275 s, at least 8620 s, at least 8965 s, at least 9310 s, at least 9655 s, or at least 10000 s.

[0148] In some embodiments, the continuous period of time of the acquiring is at most 5 s, at most 350 s, at most 695 s, at most 1040 s, at most 1385 s, at most 1730 s, at most 2075 s, at most 2420 s, at most 2760 s, at most 3105 s, at most 3600 s, at most 3795 s, at most 4140 s, at most 4485 s, at most 4830 s, at most 5175 s, at most 5520 s, at most 5865 s, at most 6210 s, at most 6555 s, at most 6900 s, at most 7200 s, at most 7585 s, at most 7930 s, at most 8275 s, at most 8620 s, at most 8965 s, at most 9310 s, at most 9655 s, or at most 10000 s.

[0149] In some embodiments, the continuous period of time of the acquiring contains between 5 s and 350 s, between 5 s and 2760 s, between 5 s and 5175 s, between 5 s and 7200 s, between 5 s and 9655 s, between 5 s and 10000 s, between 350 s and 2760 s, between 350 s and 4830 s, between 350 s and 7200 s, between 350 s and 9655 s, between 350 s and 10000 s,between 695 s and 3105 s, between 695 s and 5520 s, between 695 s and 7585 s, between 695 s and 10000 s, between 1040 s and 1385 s, between 1040 s and 3795 s, between 1040 s and 5865 s, between 1040 s and 8275 s, between 1040 s and 10000 s, between 1385 s and 2420 s, between 1385 s and 4830 s, between 1385 s and 7200 s, between 1385 s and 9310 s, between 1385 s and 10000 s, between 1730 s and 3795 s, between 1730 s and 6210 s, between 1730 s and 8275 s, between 1730 s and 10000 s, between 2075 s and 3105 s, between 2075 s and 5520 s, between 2075 s and 7930 s, between 2075 s and 10000 s, between 2420 s and 3105 s, between 2420 s and 5175 s, between 2420 s and 7585 s, between 2420 s and 10000 s, between 2760 s and 3105 s, between 2760 s and 5175 s, between 2760 s and 7585 s, between 2760 s and 10000 s, between 3105 s and 3600 s, between 3105 s and 5865 s, between 3105 s and 8275 s, between 3105 s and 10000 s, between 3600 s and 4140 s, between 3600 s and 6555 s, between 3600 s and 8965 s, between 3600 s and 10000 s, between 3795 s and 5175 s, between 3795 s and 7585 s, between 3795 s and 10000 s, between 4140 s and 4485 s, between 4140 s and 6900 s, between 4140 s and 9310 s, between 4140 s and 10000 s, between 4485 s and 6210 s, between 4485 s and 8620 s, between 4485 s and 10000 s, between 4830 s and 6210 s, between 4830 s and 8275 s, between 4830 s and 10000 s, between 5175 s and 6210 s, between 5175 s and 8620 s, between 5175 s and 10000 s, between 5520 s and 6900 s, between 5520 s and 9310 s, between 5520 s and 10000 s, between 5865 s and 7585 s, between 5865 s and 10000 s, between 6210 s and 6555 s, between 6210 s and 8965 s, between 6210 s and 10000 s, between 6555 s and 7930 s, between 6555 s and 10000 s, between 6900 s and 7585 s, between 6900 s and 10000 s, between 7200 s and 7585 s, between 7200 s and 10000 s, between 7585 s and 7930 s, between 7585 s and 10000 s, between 7930 s and 8620 s, between 7930 s and 10000 s, between 8275 s and 9310 s, between 8275 s and 10000 s, between 8620 s and 10000 s, between 8965 s and 10000 s, between 9310 s and 9655 s, between 9310 s and 10000 s, or between 9655 s and 10000 s, inclusive.

[0150] Block 4004. Referring to block 4004, in some embodiments, the acquiring the plurality of images 710 is performed using a camera 504. In some embodiments, the camera 504 is proximate to an eye 702 of the subject, such that the camera 504 is configured to capture an image 710 at a range between 200 frames per second and 700 frames per second (fps) (e.g., between 200 images per second and 700 images per second).

[0151] In some embodiments, in some embodiments, the acquiring the plurality of images 710 is performed by the camera 605 at least 200 fps, at least 225 fps, at least 250 fps, at least280 fps, at least 305 fps, at least 330 fps, at least 360 fps, at least 385 fps, at least 410 fps, at least 435 fps, at least 465 fps, at least 490 fps, at least 515 fps, at least 540 fps, at least 570 fps, at least 595 fps, at least 620 fps, at least 645 fps, at least 675 fps, or at least 700 fps.

[0152] In In some embodiments, in some embodiments, the acquiring the plurality of images 710 is performed by the camera 605 at most 200 fps, at most 225 fps, at most 250 fps, at most 280 fps, at most 305 fps, at most 330 fps, at most 360 fps, at most 385 fps, at most 410 fps, at most 435 fps, at most 465 fps, at most 490 fps, at most 515 fps, at most 540 fps, at most 570 fps, at most 595 fps, at most 620 fps, at most 645 fps, at most 675 fps, or at most 700 fps.

[0153] In some embodiments, in some embodiments, the acquiring the plurality of images 710 is performed by the camera 605 at a range that contains between 200 fps and 225 fps, between 200 fps and 330 fps, between 200 fps and 435 fps, between 200 fps and 570 fps, between 200 fps and 675 fps, between 200 fps and 700 fps, between 225 fps and 330 fps, between 225 fps and 465 fps, between 225 fps and 570 fps, between 225 fps and 675 fps, between 225 fps and 700 fps, between 250 fps and 360 fps, between 250 fps and 465 fps, between 250 fps and 595 fps, between 250 fps and 700 fps, between 280 fps and 305 fps, between 280 fps and 410 fps, between 280 fps and 540 fps, between 280 fps and 645 fps, between 280 fps and 700 fps, between 305 fps and 385 fps, between 305 fps and 490 fps, between 305 fps and 595 fps, between 305 fps and 700 fps, between 330 fps and 385 fps, between 330 fps and 490 fps, between 330 fps and 595 fps, between 330 fps and 700 fps, between 360 fps and 410 fps, between 360 fps and 515 fps, between 360 fps and 620 fps, between 360 fps and 700 fps, between 385 fps and 435 fps, between 385 fps and 540 fps, between 385 fps and 675 fps, between 385 fps and 700 fps, between 410 fps and 515 fps, between 410 fps and 620 fps, between 410 fps and 700 fps, between 435 fps and 515 fps, between 435 fps and 620 fps, between 435 fps and 700 fps, between 465 fps and 515 fps, between 465 fps and 620 fps, between 465 fps and 700 fps, between 490 fps and 540 fps, between 490 fps and 675 fps, between 490 fps and 700 fps, between 515 fps and 620 fps, between 515 fps and 700 fps, between 540 fps and 595 fps, between 540 fps and 700 fps, between 570 fps and 620 fps, between 570 fps and 700 fps, between 595 fps and 645 fps, between 595 fps and 700 fps, between 620 fps and 700 fps, between 645 fps and 675 fps, between 645 fps and 700 fps, or between 675 fps and 700 fps, inclusive.

[0154] Block 4006. Referring to block 4006, in some embodiments, the camera 504 includes a field of view that further includes a profile or substantially profile view of the eye702 of the subject. For instance, in some embodiments, the camera 504 includes an objective lens having a surface facing the face of the subject and a mirror 508 directs the field of view of the camera towards the side of the face of the subject. However, the present disclosure is not limited thereto. In some embodiments, by viewing the profile or substantially profile view of the eye 702 of the subject, the camera 504 is able to have a direct or substantially direct view of one or more dimensions of the eye, such as a curvature of the cornea of the eye 702, an axial length of the eye, an overall shape of the eye, or the like.

[0155] In some embodiments, the camera 504 is disposed proximate to an eye 702 of the subject, such that the camera configured to capture an image 710 in the plurality of images of the eye 702. For instance, in some embodiments, the camera 504 is coupled on a frame and disposed orthogonally or substantially orthogonally to the line of sight of the eye of the subject, which allows for the plurality of images 710 to with a limited or low resolution (e.g., one or more images in the plurality of images has a 510 pixels by 636 pixels resolution) with the eye consuming a substantial (e.g., major or substantially major) portion of the field of view. However, the present disclosure is not limited thereto.

[0156] Block 4008. Referring to block 4008, in some embodiments, the plurality of images 710 includes between 2 images and 60 images 710.

[0157] In some embodiments, the plurality of images 710 includes at least 2 images, at least 6 images, at least 8 images, at least 12 images, at least 14 images, at least 18 images, at least 20 images, at least 24 images, at least 26 images, at least 30 images, at least 32 images, at least 36 images, at least 38 images, at least 42 images, at least 44 images, at least 48 images, at least 50 images, at least 54 images, at least 56 images, or at least 60 images.

[0158] In some embodiments, the plurality of images 710 includes at most 2 images, at most 6 images, at most 8 images, at most 12 images, at most 14 images, at most 18 images, at most 20 images, at most 24 images, at most 26 images, at most 30 images, at most 32 images, at most 36 images, at most 38 images, at most 42 images, at most 44 images, at most 48 images, at most 50 images, at most 54 images, at most 56 images, or at most 60 images.

[0159] In some embodiments, the plurality of images 710 contains between 2 images and 6 images, between 2 images and 18 images, between 2 images and 30 images, between 2 images and 44 images, between 2 images and 56 images, between 2 images and 60 images, between 6 images and 18 images, between 6 images and 32 images, between 6 images and 44 images, between 6 images and 56 images, between 6 images and 60 images, between 8images and 20 images, between 8 images and 32 images, between 8 images and 48 images, between 8 images and 60 images, between 12 images and 14 images, between 12 images and 26 images, between 12 images and 42 images, between 12 images and 54 images, between 12 images and 60 images, between 14 images and 24 images, between 14 images and 36 images, between 14 images and 48 images, between 14 images and 60 images, between 18 images and 24 images, between 18 images and 36 images, between 18 images and 48 images, between 18 images and 60 images, between 20 images and 26 images, between 20 images and 38 images, between 20 images and 50 images, between 20 images and 60 images, between 24 images and 30 images, between 24 images and 42 images, between 24 images and 56 images, between 24 images and 60 images, between 26 images and 38 images, between 26 images and 50 images, between 26 images and 60 images, between 30 images and 38 images, between 30 images and 50 images, between 30 images and 60 images, between 32 images and 38 images, between 32 images and 50 images, between 32 images and 60 images, between 36 images and 42 images, between 36 images and 56 images, between 36 images and 60 images, between 38 images and 50 images, between 38 images and 60 images, between 42 images and 48 images, between 42 images and 60 images, between 44 images and 50 images, between 44 images and 60 images, between 48 images and 54 images, between 48 images and 60 images, between 50 images and 60 images, between 54 images and 56 images, between 54 images and 60 images, or between 56 images and 60 images, inclusive. However, the present disclosure is not limited thereto. In some embodiments, the plurality of images includes hundreds or thousands of images (e.g., 10,000 images, 100,000 images, etc.).

[0160] Block 4010. Referring to block 4010, in some embodiments, a frequency of the acquiring the plurality of images is a range between 1.5 milliseconds (ms) per image and 3.5 ms per image.

[0161] In some embodiments, the plurality of images 710 is acquired at frequency of at least 1.5 ms per image, at least 1.6 ms per image, at least 1.7 ms per image, at least 1.8 ms per image, at least 1.9 ms per image, at least 2.0 ms per image, at least 2.1 ms per image, at least 2.2 ms per image, at least 2.3 ms per image, at least 2.4 ms per image, at least 2.5 ms per image, at least 2.6 ms per image, at least 2.7 ms per image, at least 2.8 ms per image, at least 2.9 ms per image, at least 3.0 ms per image, at least 3.1 ms per image, at least 3.2 ms per image, at least 3.3 ms per image, at least 3.4 ms per image, or at least 3.5 ms per image.

[0162] In some embodiments, the plurality of images 710 is acquired at frequency of at most 1.5 ms per image, at most 1.6 ms per image, at most 1.7 ms per image, at most 1.8 ms per image, at most 1.9 ms per image, at most 2.0 ms per image, at most 2.1 ms per image, at most 2.2 ms per image, at most 2.3 ms per image, at most 2.4 ms per image, at most 2.5 ms per image, at most 2.6 ms per image, at most 2.7 ms per image, at most 2.8 ms per image, at most 2.9 ms per image, at most 3.0 ms per image, at most 3.1 ms per image, at most 3.2 ms per image, at most 3.3 ms per image, at most 3.4 ms per image, or at most 3.5 ms per image.

[0163] Block 4012. Referring to block 4012, in some embodiments, the plurality of images is associated with at least two blinks by the eye of the subject. For instance, in some embodiments, a first blink in the at least two blinks (e.g., a first set of images 710 in the plurality of images 710 associated with the first blink) is utilized to determine a baseline characteristic associated with the eye of the subject, such as a baseline curvature of the cornea of the eye and / or a baseline cycle of a blinking phase of the eye of the subject. In some such embodiments, a second blink in the at least two blinks (e.g., a second set of images 710 in the plurality of images 710 associated with the second blink) is utilized to evaluate a characteristic of the eye during the second blink in comparison to the first blink, such as to quantify a change in corneal response between the first blink and the second blink, quantify a change in an eye pressure of the subject between the first blink and the second blink, quantify a change in a risk of glaucoma for the subject between the first blink and the second blink, or a combination thereof. However, the present disclosure is not limited thereto. By way of example, in some embodiments, one or more blinks in the at least two blinks is discarded, such as in accordance with a determination of an incomplete blinking phase or the like.However, the present disclosure is not limited thereto.

[0164] Block 4014. Referring to block 4014, in some embodiments, the plurality of images 710 is associated with a range between two blinks and two thousand blinks.

[0165] In some embodiments, the range is at least 2 blinks, at least 68 blinks, at least 138 blinks, at least 206 blinks, at least 276 blinks, at least 344 blinks, at least 414 blinks, at least 482 blinks, at least 552 blinks, at least 620 blinks, at least 690 blinks, at least 758 blinks, at least 828 blinks, at least 896 blinks, at least 966 blinks, at least 1034 blinks, at least 1104 blinks, at least 1172 blinks, at least 1242 blinks, at least 1310 blinks, at least 1380 blinks, at least 1448 blinks, at least 1518 blinks, at least 1586 blinks, at least 1656 blinks, at least 1724 blinks, at least 1794 blinks, at least 1862 blinks, at least 1932 blinks, or at least 2000 blinks.

[0166] In some embodiments, the range is at most 2 blinks, at most 68 blinks, at most 138 blinks, at most 206 blinks, at most 276 blinks, at most 344 blinks, at most 414 blinks, at most 482 blinks, at most 552 blinks, at most 620 blinks, at most 690 blinks, at most 758 blinks, at most 828 blinks, at most 896 blinks, at most 966 blinks, at most 1034 blinks, at most 1104 blinks, at most 1172 blinks, at most 1242 blinks, at most 1310 blinks, at most 1380 blinks, at most 1448 blinks, at most 1518 blinks, at most 1586 blinks, at most 1656 blinks, at most 1724 blinks, at most 1794 blinks, at most 1862 blinks, at most 1932 blinks, or at most 2000 blinks.

[0167] In some embodiments, the range contains between 2 blinks and 68 blinks, between 2 blinks and 552 blinks, between 2 blinks and 1034 blinks, between 2 blinks and 1448 blinks, between 2 blinks and 1932 blinks, between 2 blinks and 2000 blinks, between 68 blinks and 552 blinks, between 68 blinks and 966 blinks, between 68 blinks and 1448 blinks, between 68 blinks and 1932 blinks, between 68 blinks and 2000 blinks, between 138 blinks and 620 blinks, between 138 blinks and 1104 blinks, between 138 blinks and 1518 blinks, between 138 blinks and 2000 blinks, between 206 blinks and 276 blinks, between 206 blinks and 758 blinks, between 206 blinks and 1172 blinks, between 206 blinks and 1656 blinks, between 206 blinks and 2000 blinks, between 276 blinks and 482 blinks, between 276 blinks and 966 blinks, between 276 blinks and 1448 blinks, between 276 blinks and 1862 blinks, between 276 blinks and 2000 blinks, between 344 blinks and 758 blinks, between 344 blinks and 1242 blinks, between 344 blinks and 1656 blinks, between 344 blinks and 2000 blinks, between 414 blinks and 620 blinks, between 414 blinks and 1104 blinks, between 414 blinks and 1586 blinks, between 414 blinks and 2000 blinks, between 482 blinks and 620 blinks, between 482 blinks and 1034 blinks, between 482 blinks and 1518 blinks, between 482 blinks and 2000 blinks, between 552 blinks and 620 blinks, between 552 blinks and 1034 blinks, between 552 blinks and 1518 blinks, between 552 blinks and 2000 blinks, between 620 blinks and 690 blinks, between 620 blinks and 1172 blinks, between 620 blinks and 1656 blinks, between 620 blinks and 2000 blinks, between 690 blinks and 828 blinks, between 690 blinks and 1310 blinks, between 690 blinks and 1794 blinks, between 690 blinks and 2000 blinks, between 758 blinks and 1034 blinks, between 758 blinks and 1518 blinks, between 758 blinks and 2000 blinks, between 828 blinks and 896 blinks, between 828 blinks and 1380 blinks, between 828 blinks and 1862 blinks, between 828 blinks and 2000 blinks, between 896 blinks and 1242 blinks, between 896 blinks and 1724 blinks, between 896 blinks and 2000 blinks, between 966 blinks and 1242 blinks, between 966 blinks and 1656 blinks, between 966 blinksand 2000 blinks, between 1034 blinks and 1242 blinks, between 1034 blinks and 1724 blinks, between 1034 blinks and 2000 blinks, between 1104 blinks and 1380 blinks, between 1104 blinks and 1862 blinks, between 1104 blinks and 2000 blinks, between 1172 blinks and 1518 blinks, between 1172 blinks and 2000 blinks, between 1242 blinks and 1310 blinks, between 1242 blinks and 1794 blinks, between 1242 blinks and 2000 blinks, between 1310 blinks and 1586 blinks, between 1310 blinks and 2000 blinks, between 1380 blinks and 1518 blinks, between 1380 blinks and 2000 blinks, between 1448 blinks and 1518 blinks, between 1448 blinks and 2000 blinks, between 1518 blinks and 1586 blinks, between 1518 blinks and 2000 blinks, between 1586 blinks and 1724 blinks, between 1586 blinks and 2000 blinks, between 1656 blinks and 1862 blinks, between 1656 blinks and 2000 blinks, between 1724 blinks and 2000 blinks, between 1794 blinks and 2000 blinks, between 1862 blinks and 1932 blinks, between 1862 blinks and 2000 blinks, or between 1932 blinks and 2000 blinks, inclusive.

[0168] Block 4016. Referring to block 4016, in some embodiments, each respective image in the plurality of images is a two-dimensional image having a size of at most 500 kilobytes. For instance, in some embodiments, the camera 504 is configured to capture each respective image 710 at a low resolution e.g., at most 600 pixels by 600 pixels, at most 550 pixels by 600 pixels, at most 500 pixels by 500 pixels, etc.), which allows for evaluating (e.g., quantifying an aspect of the respective image 710) in a computationally efficient manner using the processor 272 of the imaging device 300 and / or the graphical data system 200. However, the present disclosure is not limited thereto.

[0169] In some embodiments, the respective image 710 in the plurality of images is at least 2 kb, at least 55 kb, at least 105 kb, at least 160 kb, at least 210 kb, at least 265 kb, at least 315 kb, at least 370 kb, at least 420 kb, at least 500 kb, at least 525 kb, at least 580 kb, at least 630 kb, at least 685 kb, at least 735 kb, at least 790 kb, at least 840 kb, at least 895 kb, at least 945 kb, or at least 1000 kb.

[0170] In some embodiments, the respective image 710 in the plurality of images is at most 2 kb, at most 55 kb, at most 105 kb, at most 160 kb, at most 210 kb, at most 265 kb, at most 315 kb, at most 370 kb, at most 420 kb, at most 500 kb, at most 525 kb, at most 580 kb, at most 630 kb, at most 685 kb, at most 735 kb, at most 790 kb, at most 840 kb, at most 895 kb, at most 945 kb, or at most 1000 kb.

[0171] In some embodiments, the respective image 710 in the plurality of images is a size in a range that contains between 2 kb and 55 kb, between 2 kb and 265 kb, between 2 kb and500 kb, between 2 kb and 735 kb, between 2 kb and 945 kb, between 2 kb and 1000 kb, between 55 kb and 265 kb, between 55 kb and 525 kb, between 55 kb and 735 kb, between 55 kb and 945 kb, between 55 kb and 1000 kb, between 105 kb and 315 kb, between 105 kb and 525 kb, between 105 kb and 790 kb, between 105 kb and 1000 kb, between 160 kb and 210 kb, between 160 kb and 420 kb, between 160 kb and 685 kb, between 160 kb and 895 kb, between 160 kb and 1000 kb, between 210 kb and 370 kb, between 210 kb and 580 kb, between 210 kb and 790 kb, between 210 kb and 1000 kb, between 265 kb and 370 kb, between 265 kb and 580 kb, between 265 kb and 790 kb, between 265 kb and 1000 kb, between 315 kb and 420 kb, between 315 kb and 630 kb, between 315 kb and 840 kb, between 315 kb and 1000 kb, between 370 kb and 500 kb, between 370 kb and 685 kb, between 370 kb and 945 kb, between 370 kb and 1000 kb, between 420 kb and 630 kb, between 420 kb and 840 kb, between 420 kb and 1000 kb, between 500 kb and 630 kb, between 500 kb and 840 kb, between 500 kb and 1000 kb, between 525 kb and 630 kb, between 525 kb and 840 kb, between 525 kb and 1000 kb, between 580 kb and 685 kb, between 580 kb and 945 kb, between 580 kb and 1000 kb, between 630 kb and 840 kb, between 630 kb and 1000 kb, between 685 kb and 790 kb, between 685 kb and 1000 kb, between 735 kb and 840 kb, between 735 kb and 1000 kb, between 790 kb and 895 kb, between 790 kb and 1000 kb, between 840 kb and 1000 kb, between 895 kb and 945 kb, between 895 kb and 1000 kb, or between 945 kb and 1000 kb, inclusive.

[0172] Block 4018. Referring to block 4018, in some embodiments, the acquiring the plurality of images includes concurrently illuminating a portion of the field of view that includes the profile or substantially the profile view of the eye 702 of the subject. For instance, in some embodiments, the imaging device 300 includes one more light sources 506 coupled to a frame 502 of the imaging device, which allows for illuminating the face of the subject, particularly the eye(s) of the subject, allowing for improved quality of the image 710 captured by the camera 504. By way of non-limiting example, in some embodiments, the camera 504 is configured to capture a respective image 710 in the plurality of images at a rate 510 fps, resulting in a low, or short, exposure time, such that an array of light sources 506 (e.g., a circular or concentric array of light sources 506) aligned concentrically with the objective lens of the camera illuminates the eye of the subject, allowing a broader dynamic range [e.g., a range between 0 and 255 grayscale values, etc.) of for improved image quality.

[0173] Block 4020. Referring to block 4020, in some embodiments, the illuminating is performed using a first light source set 506 associated with a wavelength in a range between380 nm and 750 nm, which allows for illuminating the subject using visible light, such as white light. However, the present disclosure is not limited thereto.

[0174] In some embodiments, the range of the illuminating performed using the first light source set is at least 380 nm, at least 400 nm, at least 420 nm, at least 440 nm, at least 460 nm, at least 475 nm, at least 500 nm, at least 515 nm, at least 535 nm, at least 555 nm, at least 575 nm, at least 595 nm, at least 615 nm, at least 635 nm, at least 655 nm, at least 670 nm, at least 690 nm, at least 710 nm, at least 730 nm, or at least 750 nm.

[0175] In some embodiments, the range of the illuminating performed using the first light source set is at most 380 nm, at most 400 nm, at most 420 nm, at most 440 nm, at most 460 nm, at most 475 nm, at most 500 nm, at most 515 nm, at most 535 nm, at most 555 nm, at most 575 nm, at most 595 nm, at most 615 nm, at most 635 nm, at most 655 nm, at most 670 nm, at most 690 nm, at most 710 nm, at most 730 nm, or at most 750 nm.

[0176] In some embodiments, the range of the illuminating performed using the first light source set contains between 380 nm and 400 nm, between 380 nm and 475 nm, between 380 nm and 555 nm, between 380 nm and 655 nm, between 380 nm and 730 nm, between 380 nm and 750 nm, between 400 nm and 475 nm, between 400 nm and 575 nm, between 400 nm and 655 nm, between 400 nm and 730 nm, between 400 nm and 750 nm, between 420 nm and 500 nm, between 420 nm and 575 nm, between 420 nm and 670 nm, between 420 nm and 750 nm, between 440 nm and 460 nm, between 440 nm and 535 nm, between 440 nm and 635 nm, between 440 nm and 710 nm, between 440 nm and 750 nm, between 460 nm and 515 nm, between 460 nm and 595 nm, between 460 nm and 670 nm, between 460 nm and 750 nm, between 475 nm and 515 nm, between 475 nm and 595 nm, between 475 nm and 670 nm, between 475 nm and 750 nm, between 500 nm and 535 nm, between 500 nm and 615 nm, between 500 nm and 690 nm, between 500 nm and 750 nm, between 515 nm and 555 nm, between 515 nm and 635 nm, between 515 nm and 730 nm, between 515 nm and 750 nm, between 535 nm and 615 nm, between 535 nm and 690 nm, between 535 nm and 750 nm, between 555 nm and 615 nm, between 555 nm and 690 nm, between 555 nm and 750 nm, between 575 nm and 615 nm, between 575 nm and 690 nm, between 575 nm and 750 nm, between 595 nm and 635 nm, between 595 nm and 730 nm, between 595 nm and 750 nm, between 615 nm and 690 nm, between 615 nm and 750 nm, between 635 nm and 670 nm, between 635 nm and 750 nm, between 655 nm and 690 nm, between 655 nm and 750 nm, between 670 nm and 710 nm, between 670 nm and 750 nm, between 690 nmand 750 nm, between 710 nm and 730 nm, between 710 nm and 750 nm, or between 730 nm and 750 nm, inclusive.

[0177] Block 4022. Referring to block 4022, in some embodiments, the illuminating is performed using a first light source set 506 associated with a wavelength in a range between 750 nm and 1,000 nm, which allows for illuminating some or all of the face of the subject with infrared light.

[0178] In some embodiments, the range of the illuminating performed using the first light source set is at least 750 nm, at least 765 nm, at least 775 nm, at least 790 nm, at least 805 nm, at least 815 nm, at least 830 nm, at least 840 nm, at least 855 nm, at least 870 nm, at least 880 nm, at least 900 nm, at least 910 nm, at least 920 nm, at least 935 nm, at least 945 nm, at least 960 nm, at least 975 nm, at least 985 nm, or at least 1000 nm.

[0179] In some embodiments, the range of the illuminating performed using the first light source set is at most 750 nm, at most 765 nm, at most 775 nm, at most 790 nm, at most 805 nm, at most 815 nm, at most 830 nm, at most 840 nm, at most 855 nm, at most 870 nm, at most 880 nm, at most 900 nm, at most 910 nm, at most 920 nm, at most 935 nm, at most 945 nm, at most 960 nm, at most 975 nm, at most 985 nm, or at most 1000 nm.

[0180] In some embodiments, the range of the illuminating performed using the first light source set contains between 750 nm and 765 nm, between 750 nm and 815 nm, between 750 nm and 870 nm, between 750 nm and 935 nm, between 750 nm and 985 nm, between 750 nm and 1000 nm, between 765 nm and 815 nm, between 765 nm and 880 nm, between 765 nm and 935 nm, between 765 nm and 985 nm, between 765 nm and 1000 nm, between 775 nm and 830 nm, between 775 nm and 880 nm, between 775 nm and 945 nm, between 775 nm and 1000 nm, between 790 nm and 805 nm, between 790 nm and 855 nm, between 790 nm and 920 nm, between 790 nm and 975 nm, between 790 nm and 1000 nm, between 805 nm and 840 nm, between 805 nm and 900 nm, between 805 nm and 945 nm, between 805 nm and 1000 nm, between 815 nm and 840 nm, between 815 nm and 900 nm, between 815 nm and 945 nm, between 815 nm and 1000 nm, between 830 nm and 855 nm, between 830 nm and 910 nm, between 830 nm and 960 nm, between 830 nm and 1000 nm, between 840 nm and 870 nm, between 840 nm and 920 nm, between 840 nm and 985 nm, between 840 nm and 1000 nm, between 855 nm and 910 nm, between 855 nm and 960 nm, between 855 nm and 1000 nm, between 870 nm and 910 nm, between 870 nm and 960 nm, between 870 nm and 1000 nm, between 880 nm and 910 nm, between 880 nm and 960 nm, between 880 nmand 1000 nm, between 900 nm and 920 nm, between 900 nm and 985 nm, between 900 nm and 1000 nm, between 910 nm and 960 nm, between 910 nm and 1000 nm, between 920 nm and 945 nm, between 920 nm and 1000 nm, between 935 nm and 960 nm, between 935 nm and 1000 nm, between 945 nm and 975 nm, between 945 nm and 1000 nm, between 960 nm and 1000 nm, between 975 nm and 985 nm, between 975 nm and 1000 nm, or between 985 nm and 1000 nm, inclusive.

[0181] Furthermore, in some embodiments, one or more polycarbonate lenses 510 is coupled the frame 502, which allows for increased safety and accuracy of measurements. In some embodiments, the first light source set 506-1 is or includes a monochromatic light source, such as one or more tunable laser or one or more light emitting diodes (LED). However, the present disclosure is not limited thereto.

[0182] Block 4024. Referring to block 4024, in some embodiments, the acquiring the plurality of images includes acquiring a corresponding value for a set of plurality of boundary conditions when the illuminating the portion of the field of view. For instance, in some embodiments, the set of boundary conditions is associated with a position of the pupil of the eye, an orientation of the frame 502 of the imaging device 300, a position of the frame 502 of the imaging device 300, or the like, such as based upon a plurality of measurements associated with a region of interest (ROI) of the eye of the subject when exposed to the light during the acquiring of the plurality of images.

[0183] In some embodiments, the method 400 further includes interrupting the acquiring of the plurality of images 710 in accordance with a determination a boundary condition in the set of boundary conditions satisfies a threshold dimension.

[0184] Block 4026. Referring to block 4026, in some embodiments, quantifying a corneal response using the plurality of images. For instance, in some embodiments, a set of at least two images 710 is utilized to determine the corneal response of the cornea of the eye 702 based on an applanation of the cornea caused by a blink of the eye, such as an inward applanation caused by a closing phase of the blink, an inward applanation caused by an opening phase of the blink, or both the inward and outward applanation caused by some or all of the blinking phase. By way of example, in some embodiments, the quantifying the corneal responses uses a first set of images 710 associated with the eyelid deforming the corneal surface during the blink, resulting in a rebound response of the cornea. In this way, in some embodiments, the method 400 provides a non-contact quantification of the corneal responseduring the natural blinking by the subject and since the corneal response is dependent on IOP (e.g., chart 830 Figure 8C).

[0185] Block 4028. Referring to block 4028, in some embodiments, the quantifying the corneal response includes determining a blinking phase of a respective blink by the eye of the subject. In some embodiments, the quantifying the corneal response includes determining a contour of the cornea of the eye in accordance with a determination a dimension of the eye satisfies a threshold dimension. In some embodiments, in some embodiments, the quantifying the corneal response includes determining a centroid of the cornea using the contour of the cornea. In some embodiments, in some embodiments, the quantifying the corneal response includes determining a displacement of the centroid during some or all of a respective blinking phase of a first eye blink by the eye of the subject. In some embodiments, the quantifying the corneal response includes quantifying the corneal response by comparing the displacement of the centroid against a baseline displacement.

[0186] For instance, in some embodiments, the determining the blinking phase of the respective blink by the eye of the subject allows for, before applying the plurality of images to a first model, filtering potential outliers in a centroid displacement from the plurality of images to form a filtered set of images. By way of example, in some embodiments, an initial predetermined number of images (e.g., a first five images, a first ten images, etc. of each blink’s opening phase were filtered, as these images present challenges for the model in accurately predicting a shape of the eye (e.g., eye mask), due to partial obstruction of the corneal profile by eyelashes. In some embodiments, a filtering step is applied to the fitted curves based on their fitted parameters as the root mean square error (RMSE) and R2. In some embodiments, R2values below gR2 — 3<JR2 and RMSE values exceeding gRMSE + 3<JRMSRare considered outliers. In some embodiments, this determining the blinking phase and forming of the filtered image set allows the method to filter images associated with blinks with poorly fitted curves, resulting from segmentation errors, non-natural blinks, head movements during the image acquisition process, and the like. In some embodiments, to evaluate differences in the dynamics of the corneal profile, the two parameters of the fitted curves, T and A, are considered by the model.

[0187] In some embodiments, the method 400 performs second filtering process to obtain estimates of T for each condition and participant. As such, the method 400 allows for determine that the cornea rebounds faster due to the higher internal pressure exerting anincreased restoring force. In some embodiments, a lower T is expected for the Valsalva condition, reflecting faster corneal dynamics than the baseline IOP condition.

[0188] Block 4030. Referring to block 4030, in some embodiments, the determining the displacement of the centroid comprises determining a time constant value associated with a velocity of the eye during the respective blinking phase. For instance, in some embodiments, the determining the displacement of the centroid includes determining the time constant value, or time constant, T, which is associated with a rebound speed of the cornea, and a displacement amplitude A, measuring an extent of corneal displacement of the cornea caused by the blink of the eye. By way of non-limiting example, referring to Figure 10, in some embodiments, the method 400 determines the time constant that quantifies the velocity at which the cornea rebounds during a natural, complete blink by the subject captured by the plurality of images 710, and the displacement amplitude that represents the extent of translation of the corneal profile. However, the present disclosure is not limited thereto. In some embodiments, the method 400 determines the time constant that quantifies the velocity at which the cornea rebounds during a natural, complete blink by the subject captured by the plurality of images 710. In some embodiments, the method 400 determines the displacement amplitude that represents the extent of translation of the corneal profile

[0189] Block 4032. Referring to block 4032, in some embodiments, the quantifying the corneal response comprises inputting the plurality of images into a first model that iteratively compare sets of images in the plurality of images until a set of images satisfies a threshold contour of the cornea, and wherein each respective temporally adjacent set of images is associated with a corresponding blink of the eye by the subject.

[0190] Block 4034. Referring to block 4034, in some embodiments, the first model is trained to compare temporally adjacent sets of images. For instance, in some embodiments, the first model 118-1 is trained to evaluate pairs of one or more images 710 that have contiguous temporal time periods (e.g., a first time at time t and a second at time t+1, etc.), such as for comparing short-term changes or fine-tune temporal changes.

[0191] Block 4036. Referring to block 4036, in some embodiments, the first model is trained to compare sequential sets of images. For instance, in some embodiments, the first model is trained to compare sequential sets of images associated with a corresponding eye state, such as sequential sets of open state images, sequential sets of partially open state images, sequential sets of closed state images, and / or the like.

[0192] Block 4038. Referring to block 4038, in some embodiments, the first model is trained to compare collective sets of images.

[0193] Block 4040. Referring to block 4040, in some embodiments, the first model is a neural network architecture includes a plurality of parameters. In some embodiments, the plurality of parameters comprises at least 1 x 106parameters. In some embodiments, the neural network architecture provides the categorization of each respective in the plurality of images by application of the at least 1 x 106parameters to each image in the plurality of images.

[0194] For instance, in some embodiments, at least two eye-blinking images were acquired and identified as a first image associated with a baseline IOP and a second image associated with an elevated IOP, resulting in a set of labeled images per subject e.g., at least 400 images per subject). In some embodiments, these labeled images are inputted to a first model neural network for segmenting the ocular region. In some embodiments, the first model neural network is initialized and trained individually for the subject, using only their respective eye images, ensuring that the model is optimized for the respective subject. In some embodiments, the model includes convolutional layers with filters ranging from 64 to 512, with a bottleneck having 1024 filters. In some embodiments, batch normalization layers were included after each convolution to improve the convergence rate and stability of the training process. In some embodiments, the images inputted to the model were resized to a predetermined resolution (e.g., a first resolution of 256 x 256 pixels and normalized in the range [0, 1]) prior to inputting into the model.

[0195] In some embodiments, the model classified images related to the opening phase of blinking into four different classifications: closed eye, semi-closed eye, semi-open eye, and open eye. In some embodiments, a resampling process based on the mask area is performed by the model to address a potential class imbalance. Referring to Figure 11, in some embodiments, the model categorizes masks into one of: (i) closed eye: masks with zero area, (ii) semi-closed eye: masks with an area between 0% and 40% of the maximum observed area, (iii) semi-open eye: masks with an area between 40% and 80% of the maximum observed area, (iv) open eye: masks with an area greater than 80% of the maximum observed area.

[0196] In some embodiments, after classification, the method 400 utilizes a random resampling approach to increase the number of images 710 in underrepresented classes.Specifically, in some embodiments, the method 400 resamples images and masks to match the number of samples in the majority class, ensuring a balanced distribution. In some embodiments, data augmentation techniques are then utilized to enhance the diversity of the training dataset. In some embodiments, the method 400 utilizes one or more transformations to facilitate model generalization for various eye positions: (i) flip: images were horizontally flipped; (ii) rotation: images were randomly rotated within a range of ±10 degrees to account for slight variations in head pose; (iii) zoom: images were randomly scaled up or down within ±10% of their dimensions; and (iv) translation: images were randomly translated up to ±10% of the frame dimensions in both vertical and horizontal directions to simulate slight head movements. In some embodiments, the method 400 utilizes one or more transformations to facilitate model generalization for various eye positions including: (i) flip: images were horizontally flipped; (ii) rotation: images were randomly rotated within a range of ±10 degrees to account for slight variations in head pose; (iii) zoom: images were randomly scaled up or down within ±10% of their dimensions; (iv) translation: images were randomly translated up to ±10% of the frame dimensions in both vertical and horizontal directions to simulate slight head movements; or (v) a combination thereof.

[0197] In some embodiments, the dataset is filtered into a first portion for training and a second portion for validation, such as a split into 80% for training and 20% for validation. In some embodiments, early stopping based on validation loss and a reduced learning rate on plateau strategy are implemented during training to prevent overfitting and enhance generalization. In some embodiments, the loss function for training is the combo loss, a weighted sum of Binary Crossentropy (BCE) and Dice Loss. In some embodiments, the BCE component effectively penalizes incorrect predictions for each pixel, handling output imbalance, whereas on the other hand, the Dice Loss is particularly effective in addressing input imbalance by emphasizing the overlap between predicted and ground truth masks. In some embodiments, this combination leverages the strengths of both loss functions, improving the ability of the model to learn from imbalanced data while maintaining segmentation accuracy. In some embodiments, the model is particularly suitable for our application since semi-closed eye frames are heavily imbalanced in terms of foreground and background pixels.

[0198] In some embodiments, the performance of the trained model is evaluated using the Intersection over Union (loU) metric, which measures the overlap between the predicted and ground-truth masks. In some embodiments, for each participant, the trained model achievesan loU score greater than 90% on the test dataset. In some embodiments, the trained network predicts eye masks for all other blinks of the same participant, significantly accelerating the manual labeling processes. Referring to Figures 9A-9D, a predict eye maks generated by the model for four distinct image of a blink by the subject is overlaid on the original images, showing the progression from a slight to a fully open eye collectively.

[0199] Block 4042. Referring to block 4042, in some embodiments, the quantifying the corneal response includes inputting the plurality of images into a second model different from the first model. For instance, in some embodiments, the second model is configured to categorizes one or more sets of images in the plurality of images into one of a set of eye blink states, in which the set of eye blink states includes at least an eye state associated with an open or substantially open eye and a second eye state associated with a closed or substantially closed eye. In this way, in some embodiments, the method 400 utilizes two different models to arrive an independent conclusions that are evaluated to quantify the corneal response. However, the present disclosure is not limited thereto. In some embodiments, the method 400 utilizes the second model but not the first model.

[0200] Block 4044. Referring to block 4044, in some embodiments, the set of eye blink states includes an open state, a partially open state, and a closed state. For instance, in some embodiments, two or more blinks were captured using the plurality of images 710 at utilized to determine an initial terminal image in a set of images and a final terminal image in the set of images associated with an eye-opening phase, which is traversing from a fully closed eye to a fully open eye. In some embodiments, during this manual eye blinking detection process, one or more sets of images associated with one or more blinks identified and filtered based on the following criteria: (i) multiple blinks, such as two or more consecutive blinks occur in rapid succession during a respective set of images, making isolating a single eyeopening phase difficult, such as identifying by the absence of a stable, fully open eye state between two consecutive closures of the eye; (ii) incomplete blinks, when the eye does not fully close before reopening; and (iii) excessive facial muscle activation, when significant movement of the eyebrows, forehead, or cheeks was observed, suggesting facial contractions that could interfere with the natural corneal response. In this way, in some embodiments, only natural and complete blinks were further analyzed. However, the present disclosure is not limited thereto.

[0201] Block 4046. Referring to block 4046, in some embodiments, the second model is a neural network architecture comprising a plurality of parameters, wherein the plurality ofparameters comprises at least 1 x 106parameters, and wherein the neural network architecture provides the categorization of each respective in the plurality of images by application of the at least 1 x 106parameters to each image in the plurality of images.

[0202] Block 4048-4050. Referring to blocks 4048 and 4050, in some embodiments, the quantifying an eye pressure of the subject using the corneal response. Moreover, in some embodiments, the quantifying the eye pressure includes quantifying an intraocular pressure of the eye of the subject. For instance, in some embodiments, the method 400 utilizes the corneal response associated with natural blinking by the subject and using a quantifies the correlation with IOP. By way of example, in some embodiments, the method 400 utilizes the natural eyelid pressure (ELP) exerted on the corneal surface during a blink to analyze IOP- related corneal deformation, allowing for non-contact, remote, continuous IOP monitoring for the subject.

[0203] Block 4052. Referring to block 4052, in some embodiments, the quantifying a risk of glaucoma for the subject using the eye pressure of the subject. For instance, in some embodiments, the risk for glaucoma is based on a change of the eye pressure of the subject during a predetermined period of time (e.g., during a 30 second period of time, during a minute period of time, during a rolling hour period, during a rolling day period, during a one week rolling period, during a one month rolling period, etc.).

[0204] In some embodiments, by providing continuous data on IOP patterns of the subject, this method 400 allows for more precise treatment optimization, improve medication adherence, and reduces the risk of vision loss for the subject, providing a valuable tool for glaucoma management. For instance, in some embodiments, in accordance with a determination the risk of glaucoma for the subject satisfies a threshold risk value e.g., is deemed to meet or exceeds a predetermined risk value), the method 400 generates a report for visualization by a medical practitioner associated with the subject, which allows the medical practitioner to modify a dosage of a pharmaceutical compound or treatment administered to the subject, such as increasing the dosage in accordance with a determination the risk of glaucoma satisfies a first risk value, decreasing the dosage in accordance with a determination the risk of glaucoma satisfies the second risk value, maintaining the dosage in accordance with a determination the risk of glaucoma satisfies the third risk value, or a combination thereof. However, the present disclosure is not limited thereto. In some embodiments, the report provides a recommended modification to the dosage of the pharmaceutical compound or treatment administered to the subject through the report.

[0205] Block 4054. Referring to block 4054, in some embodiments, the quantifying the risk of glaucoma includes generating a value defining a comparison of the eye pressure of the against a threshold baseline pressure. For instance, in some embodiments, the method 400 includes, prior to quantifying the risk of glaucoma, quantifying an initial IOP value of the subject at a first time period, storing the initial IOP value at a user profile associated with the subject, and, comparing a current IOP value quantified during a second time period, after the first time period, against the initial IOP value in real time. By way of non-limiting example, in some embodiments, to determine the threshold baseline pressure, a plurality of images 710 totaling one minute in duration were acquired, during which the subject performed natural blinks captured through the plurality of images 710, which were utilized to quantify the threshold baseline pressure.

[0206] Block 4056. Referring to block 4056, in some embodiments, the threshold baseline pressure is in a range between 18 millimeters of mercury (mmHg) and 25 mmHg.

[0207] In some embodiments, the threshold baseline pressure is at least 18 mmHg, at least 19 mmHg, at least 20 mmHg, at least 21 mmHg, at least 22 mmHg, at least 23 mmHg, at least 24 mmHg, or at least 25 mmHg.

[0208] In some embodiments, the threshold baseline pressure is at most 18 mmHg, at most 19 mmHg, at most 20 mmHg, at most 21 mmHg, at most 22 mmHg, at most 23 mmHg, at most 24 mmHg, or at most 25 mmHg.

[0209] In some embodiments, the range contains between 18 mmHg and 18 mmHg, between 18 mmHg and 20 mmHg, between 18 mmHg and 22 mmHg, between 18 mmHg and24 mmHg, between 18 mmHg and 25 mmHg, between 18 mmHg and 25 mmHg, between 18 mmHg and 20 mmHg, between 18 mmHg and 22 mmHg, between 18 mmHg and 24 mmHg, between 18 mmHg and 25 mmHg, between 18 mmHg and 25 mmHg, between 20 mmHg and 22 mmHg, between 20 mmHg and 24 mmHg, between 20 mmHg and 24 mmHg, between 20 mmHg and 25 mmHg, between 20 mmHg and 22 mmHg, between 20 mmHg and 24 mmHg, between 20 mmHg and 24 mmHg, between 20 mmHg and 25 mmHg, between 22 mmHg and 22 mmHg, between 22 mmHg and 24 mmHg, between 22 mmHg and 25 mmHg, between 22 mmHg and 24 mmHg, between 22 mmHg and 25 mmHg, between 22 mmHg and 25 mmHg, between 24 mmHg and 24 mmHg, between 24 mmHg and 25 mmHg, between 24 mmHg and25 mmHg, between 24 mmHg and 25 mmHg, or between 25 mmHg and 25 mmHg, inclusive.

[0210] Block 4058. Referring to block 4058, in some embodiments, the acquiring, the quantifying the corneal response, the quantifying the eye pressure, and the quantifying the risk of glaucoma are performed in real time.

[0211] Example 1

[0212] Materials and Methods

[0213] Imaging System

[0214] The imaging system developed to track the corneal profile during eye blinking is depicted in 6A. The setup comprises a modified ophthalmology slit lamp and an imaging lens (focal length of 50 mm, numerical aperture of 0.18; Thorlabs, Newton, NJ). This system is integrated with a high-frame-rate (510 FPS) camera (Allied Vision, Edmund Optics, Barrington, NJ) placed lateral to the participant’s eye to capture the corneal profile during each blink. The videos were acquired in 8-bit grayscale format with a spatial resolution of 800x600 pixels. Since the camera operates at 510 FPS, resulting in a low exposure time, a visible LED ring light aligned concentrically with the camera lens was employed as the illumination source, allowing a broader dynamic range [0-255] of grayscale values for improved image quality. An example lateral eye image is shown in 6B.

[0215] Participants and Experimental Protocol

[0216] This Example included healthy volunteers aged 18-50 without history of ocular or systemic conditions that could influence IOP. All participants provided written informed consent. This Example was conducted in compliance with the Declaration of Helsinki and approved by the Institutional Review Board (IRB) of the University of Maryland Baltimore. Each participant was assessed under two experimental conditions to examine corneal dynamics during a natural, complete blink (baseline) and during a Valsalva maneuver. For each participant, data were acquired only from the left eye.

[0217] The experimental protocol included four steps. First, baseline IOP was measured using a portable tonometer (iCare IC200, Icare USA, Inc., Raleigh, NC, USA) an FDA- approved medical device comparable to the Goldmann Applanation Tonometer (GAT).

[0218] Next, participants were asked to blink naturally while their eye movements were recorded using the high-speed imaging system. Then, participants were instructed to perform the Valsalva maneuver, which is known to raise IOP. This technique required them to exhale forcefully against a closed glottis into an air tube connected to an analog manometer,maintaining a pressure of at least 40 mmHg for 15 seconds. The elevation of IOP during the Valsalva maneuver was confirmed with the portable tonometer. The maneuver was successful only if the IOP increased by more than 1 mmHg. If participants failed to maintain the required pressure or the IOP increase did not meet this threshold, they were asked to repeat the experiment. Finally, additional blinks and associated corneal dynamics were recorded while participants performed the Valsalva maneuver. Participants were excluded if their eyelashes obstructed the corneal profile, preventing measurement of corneal dynamics.

[0219] Data Acquisition and Analysis

[0220] A software program (StreamPix, NorPix Inc., Montreal, CA) was used to record blinks under two conditions: baseline and Valsalva. For the baseline condition, single or multiple videos totaling one minute in duration were recorded, during which participants were asked to perform natural blinks. For the Valsalva condition, multiple videos were recorded as each maneuver lasted approximately 15 seconds. A minimum of five blinks was considered acceptable for each condition.

[0221] Using a built-in MATLAB application (Video Viewer; MathWorks Inc., Natick, MA, USA), the blinks in the recorded videos were manually identified, determining the start and end frames of the eye-opening phase, from a fully closed eye to a fully open eye. During this manual eye blinking detection process, certain blinks were discarded based on the following criteria: (i) multiple blinks, when two or more consecutive blinks occur in rapid succession, making it difficult to isolate a single eye-opening phase. These were identified by the absence of a stable, fully open eye state between two consecutive closures, (ii) incomplete blinks, when the eye does not fully close before reopening, and (iii) excessive facial muscle activation, when significant movement of the eyebrows, forehead, or cheeks was observed, suggesting facial contractions that could interfere with the natural corneal response. Only natural and complete blinks were further analyzed.

[0222] A custom Python script was used to train a neural network specifically designed to predict eye masks during the eye-opening phase of each blink. The predicted ocular masks were subsequently assessed for the dynamics of the corneal profile during each blink. An exponential-like curve was produced for all the blinks by evaluating the longitudinal corneal displacement over time. The following parameters were computed: (i) the time constant, which quantifies the velocity at which the cornea rebounds during a natural, complete blink,and (ii) the displacement amplitude, which represents the extent of translation of the corneal profile (Figure 10).

[0223] Neural Network Training

[0224] For each participant, at least two eye-blinking frames were manually labeled, one from the baseline and one from elevated IOP conditions, resulting in approximately 400 labeled images per participant. These manually labeled images were then used to train a modified U-Net neural network for segmenting the ocular region. The network was initialized and trained individually for each participant, using only their respective eye images, ensuring that the model was optimized for each participant. The architecture consisted of convolutional layers with filters ranging from 64 to 512, with a bottleneck containing 1024 filters. Batch normalization layers were included after each convolution to improve the convergence rate and stability of the training process. The input images were resized to [256, 256] pixels and normalized in the range [0, 1] before being fed into the neural network.

[0225] Frames related to the opening phase of blinking were classified into four different classes: closed eye, semi-closed eye, semi-open eye, and open eye. A resampling method based on the mask area was applied to address the potential class imbalance. Masks were categorized as follows: (i) closed eye: masks with zero area, (ii) semi-closed eye: masks with an area between 0% and 40% of the maximum observed area, (iii) semi-open eye: masks with an area between 40% and 80% of the maximum observed area, (iv) open eye: masks with an area greater than 80% of the maximum observed area. An example of the classification of these images based on the mask area is shown in Figure 11.

[0226] Before applying exponential fitting, potential outliers in the centroid displacement data were removed. Specifically, the first five frames of each blink’s opening phase were excluded, as these frames often present challenges for the neural network in accurately predicting the eye’s mask due to partial obstruction of the corneal profile by eyelashes.

[0227] A filtering step was applied to the fitted curves based on their fitted parameters as the root mean square error (RMSE) and R2. Specifically, R2values below / J.R2 — 3<JR2 and RMSE values exceeding / J.RMSE + ORMSE were considered outliers.

[0228] This filtering process allows us to exclude blinks with poorly fitted curves, resulting from segmentation errors, non-natural blinks, or head movements during the blink acquisition process. To evaluate differences in the dynamics of the corneal profile under baseline andduring the Valsalva maneuver, the two parameters of the fitted curves, T and A, were analyzed.

[0229] A second filtering process was applied to the curves to obtain the most accurate estimate of T for each condition and participant. Specifically, only curves with a z-score within 1 were included for the baseline and Valsalva IOP conditions. This approach was validated by confirming that this metric satisfied the Kolmogorov- Smirnov test for normality, ensuring the distribution aligned with the assumptions required for this statistical filtering method. Although the limited number of analyzed blinks per participant does not allow us to conclude that T follows a normal distribution, the Kolmogorov- Smirnov test indicated no significant deviations from normality in the analyzed dataset. Therefore, the assumption of normality for T appears reasonable. Finally, the average T and amplitude were calculated for the remaining baseline and Valsalva IOP trajectories after this filtering process.

[0230] Under elevated IOP conditions, induced by the Valsalva maneuver, this Example hypothesize that the cornea rebounds faster due to the higher internal pressure exerting an increased restoring force. Consequently, a lower T is expected for the Valsalva condition, reflecting faster corneal dynamics than the baseline IOP condition.

[0231] Results

[0232] Fifteen healthy participants (28.3 ± 6.02 years; 10 males, 5 females) were enrolled in the study and included in the final analysis. Each participant successfully performed the Valsalva maneuver, which was well tolerated without any adverse events during or after the procedure.

[0233] Corneal Displacement for a Single Sample

[0234] Initially, nine blinks were recorded under baseline IOP conditions and ten under elevated IOP (Valsalva) conditions. After applying the filtering process, six blinks from each condition were selected for further analysis. Figure 13 shows the corneal centroid displacement along the x-axis during the blink’s opening phase for a single participant. In both conditions, the trajectory of the corneal centroid exhibits an exponential trend, stabilizing as the eye reaches its fully open state.

[0235] This Example measured T and A of the cornea during the blink’s opening phase for both conditions. The results showed that T was lower in the Valsalva condition (37.44 ±0.64 ms) compared to the baseline (61.17 ± 2.44 ms), and this difference was statistically significant (t = 9.42, P < 0.001, Figure 14B).

[0236] Regarding A, the average for the baseline IOP condition was 45.56 ± 1.47 px, and for the Valsalva condition, it was 41.86 ± 1.81 px, and this difference was not statistically significant (Figure 9B).

[0237] Statistical Analysis

[0238] To assess the effectiveness of the Valsalva maneuver in increasing IOP, we compared IOP values measured before and after the maneuver across all participants using the portable tonometer. The mean baseline IOP was 18.55 ± 0.72 mmHg, while the mean IOP during the Valsalva condition increased to 23.73 ± 1.01 mmHg. This increase was statistically significant (t = 6.78, P < 0.001), confirming that the Valsalva maneuver induced a consistent and measurable elevation in IOP, with IOP difference ranging from 1.7 mHg to 13 mmHg between the two conditions.

[0239] To determine whether the lOP-dependent behavior observed in a single subject was consistent among participants, we performed a statistical analysis on all enrolled samples.

[0240] Figure 21 illustrates the variation of T for each participant who underwent the experiment. Out of 15 samples, 11 exhibit the expected trend, showing a lower T under the elevated IOP condition compared to the baseline IOP condition.

[0241] The average T was 46.23 ± 2.48 ms for the baseline IOP condition and 39.73 ± 1.31 ms for the elevated IOP condition (t = —2.56, P < 0.05, Figure 22), which indicates a faster comeal rebound when the Valsalva maneuver is performed. Figure 14A depicts the changes in A for each participant across the two IOP conditions, with the color scale indicating the change in the amplitude A between baseline and elevated IOP conditions. The average amplitude was 35.25 ± 2.73 px for the baseline IOP and 34.81 ± 2.64 px for the elevated IOP condition. Unlike T, A does not exhibit a clear or consistent pattern across participants, with changes appearing more variable and without a statistically significant difference.

[0242] Discussion

[0243] This study presents a novel imaging system that provides information on the corneal dynamics during a natural, complete blink and its correlation with IOP changes. Thus, thecorneal dynamics were analyzed under two conditions: baseline IOP and elevated IOP, obtained during the Valsalva maneuver.

[0244] The deformation of the cornea by the eyelid during a blink provides an opportunity to assess lOP-dependence of this phenomenon. However, the corneal deformation depends on its topography and biomechanics, leading to observable changes in corneal dynamics. As a result, various structural and pathological conditions may be potential modifiers of the observed corneal response. For instance, keratoconus leads to localized thinning and steepening of the cornea, altering its curvature and mechanical stiffness, which can modify the corneal response to ELP. Moreover, post-surgical eyes typically exhibit a lower corneal hysteresis, which reflects the viscoelastic damping response of the corneal tissue to the applied force and corneal resistance factor, which is related to the time-independent corneal response to the applied force. These biomechanical changes can result in a slower rebound of the corneal profile and an altered displacement amplitude induced by ELP.

[0245] One of skill in the art will appreciate that ELP causes a flattening effect on the cornea, with biomechanical IOP correlating with eyelid pressure and corneal deformation during a blink. The results demonstrate that the velocity of the corneal rebound is sensitive to IOP changes: the observed decrease of T under elevated IOP conditions suggests that the cornea rebounds more rapidly after eyelid-induced deformation. This Example hypothesized that this is due to the increased internal pressure exerting a greater restoring force, leading to faster recovery of the corneal profile. On the other hand, A did not significantly differ between conditions, indicating that the extent of corneal deformation is consistent across the two conditions. The absence of a statistically significant difference in the amplitude suggests that the faster rebound of the corneal profile under Valsalva conditions cannot be attributed to an increase in the magnitude of eye movement. Indeed, elevated IOP predominantly influences the corneal rebound velocity without affecting the displacement amplitude.

[0246] Compared to conventional tonometry or recent innovations (e.g. contact lenses, implantable sensors), which require contact with the eye or surgical implants and can only be performed during office visits with professional assistance, the systems, methods, and devices of the present disclosure provide continuous non-contact IOP monitoring without requiring significant patient expertise. A more accessible and frequent monitoring solution like this can lead to a better understanding of IOP patterns and their relationship to glaucoma progression. For instance, a study of IOP monitoring conducted outside of regular office hours found that peak 24-hour IOP was greater than the peak IOP observed during prior office visits in 62% ofthe patients. Notably, the results of 24-hour IOP monitoring led to an immediate treatment change in 36% of patients. Indeed, this technology could also promote more precise patientbased treatment strategies and mitigate the impact of untreated glaucoma.

[0247] Several types of glaucoma exist, the most common being primary open-angle glaucoma which is characterized by elevated IOP values beyond the normal range and progressive optic nerve damage. However, not all forms of glaucoma are associated with increased IOP. In normal-tension glaucoma, IOP values remain within the clinically normal range, yet progressive optic nerve damage can still occur. In such cases, analyzing IOP fluctuations throughout the day could be beneficial for the early detection of the disease, as patients with normal-tension glaucoma often exhibit greater diurnal IOP variability, even if additional lOP-independent factors have gained increasing relevance in detecting this ocular disease. The proposed method can potentially assess these variations through frequent, non- invasive, home-based measurements. Conversely, ocular hypertension is characterized by IOP levels above the normal threshold despite the absence of optic nerve damage. For these patients, the absolute IOP value remains the primary diagnostic metric. Although, in some embodiments, a calibration step is performed before conducting absolute IOP monitoring.

[0248] In some embodiments, the variability of IOP elevation induced by the Valsalva maneuver presented challenges in achieving consistent IOP increments across trials. Additionally, IOP measurements during the Valsalva maneuver are taken before the acquisition of natural blinks, as it was not feasible to measure IOP using a portable tonometer and simultaneously record natural blinks during the application of the maneuver. This sequential process may introduce variability in the exact elevated IOP level during blink acquisition.

[0249] Furthermore, while the systems, methods, and devices of the present disclosure focused on longitudinal corneal displacement, it is known that the eye can retract during blinking due to ELP and subsequently move forward upon eyelid release, contributing to the observed dynamics. Three different models proposed are depicted in Figure 8B. Their results have shown that the longitudinal movement of the corneal profile during a blink is the superposition of eye movement and corneal deformation (Figure 8(3)). Indeed, the inability to separate these effects in this Example is another limitation. However, the results suggest that the Valsalva maneuver does not necessarily lead to greater globe movement. If it were true that this maneuver causes greater forward movement of the eye during the opening phase of a blink, one would expect A to consistently be higher than in the baseline IOP condition, with astatistically significant difference. The fact that a statistically significant difference is observed only for T suggests that the Valsalva maneuver primarily results in a different response speed of the corneal rebound, which could be related to the IOP.

[0250] Finally, another concern is the potential influence of physiological changes unrelated to IOP during the Valsalva maneuver. While it is well-documented that the maneuver induces an increase in IOP, the exact mechanisms behind this increase remain unclear. Therefore, the observed differences between the baseline IOP condition and the Valsalva condition may not be attributed only to an IOP increase but could also be influenced by other phenomena induced by the Valsalva maneuver, such as changes in ocular blood flow, venous pressure, or biomechanical properties of the anterior segment.

[0251] Future research should address key limitations. Specifically, separating the effects of corneal deformation and globe movement during blinking would provide a clearer understanding of the corneal dynamics. Moreover, assessing corneal deformation dynamics in glaucoma patients before and after administering lOP-lowering medication could overcome the limitations of the Valsalva maneuver and provide deeper insight into the relationship between corneal dynamics and IOP. Additionally, system illumination should be optimized to properly work under ambient lighting conditions typically found in a real-world scenario.

[0252] In conclusion, we have presented a novel, non-contact imaging system capable of tracking the corneal profile during a natural, complete blink and analyzing its dynamics as an indicator of IOP.

[0253] Before translating this method into a clinical setting, a clinical trial is required to validate the blink-induced corneal rebound metrics against the gold standard of applanation tonometry. Indeed, a population of glaucoma patients will be enrolled and IOP will be measured during follow-up visits using both the proposed method and standard tonometry to evaluate the ability of this method to predict IOP variations. Once validated, this method would allow continuous tracking of IOP variations over time without repeated in-office measurements.

[0254] By providing continuous data on IOP patterns, this technology could support more precise treatment optimization, improve medication adherence, and reduce the risk of vision loss, making it a valuable tool for glaucoma management.

[0255] Example 2: An Imaging Device

[0256] An imaging device 300 was further configured to determine deformation of a cornea. In one embodiment, the imaging device 300 detects a blink, detects an edge of a cornea, determines a reference point of the cornea, and determines displacement of the reference point. For example, the reference point was an arbitrary point on a cornea or pertain to a physical or geometric property of the cornea, such as a centroid of the cornea. For example, displacement of the reference point was the difference in location, such as at the reference point or other points on the cornea, from a first time and a second time. As a further example, the first time is a time preceding the blink and the second time is a time following the blink. In a further example, the difference in location is measured from a point on curve configured to a model (e.g., such as a first-order system or a second-order system) a cornea.

[0257] Because IOP can vary widely throughout the course of the day, the imaging device 300 is configured to be a take-home or easily accessible platform for patients to keep track of their IOP, which will then help make more informed and accurate treatment decisions.

[0258] The first method of measuring IOP with the imaging device 300 is using a laser reflectance configuration. In this setup, an eye-safe IR laser is directed from in front of the eye onto the center of the cornea. A front facing high-speed IR camera then measures the reflected laser spot coming off the eye. As the eye moves and deforms, the angle of the reflected beam changes, which is indicated by vertical and lateral shifts of the spot as seen by the camera’s image sensor. Analysis of how this spot moves over time can tell how much the cornea is deforming, and thereby measure the IOP.

[0259] Additional details and information regarding method 400, and Examples 1-2 is found at Thylefors B, Negrel AD. The global impact of glaucoma. Bull World Health Organ. 1994; 72: 323-326; Kang JM, Tanna AP. Glaucoma. Medical Clinics of North America. 2021; 105: 493-510; McMonnies CW. The clinical and experimental significance of blinking behavior. Journal of Optometry. 2020; 13: 74-80; Cruz AAV, Garcia DM, Pinto CT, Cechetti SP. Spontaneous Eyeblink Activity. The Ocular Surface. 2011; 9: 29-41; Kotecha A, White E, Schlottmann PG, Garway-Heath DF. Intraocular Pressure Measurement Precision with the Goldmann Applanation, Dynamic Contour, and Ocular Response Analyzer Tonometers. Ophthalmology. 2010; 117: 730-737; Chen G-Z, Chan I-S, Leung LKK, Lam DCC. Soft wearable contact lens sensor for continuous intraocular pressure monitoring. Medical Engineering & Physics. 2014; 36: 1134-1139; De Moraes CG, Jasien JV, Simon-Zoula S, Liebmann JM, Ritch R. Visual Field Change and 24-Hour IOP -Related Profile with a Contact Lens Sensor in Treated Glaucoma Patients. Ophthalmology. 2016; 123: 744-753; Xu J, CuiT, Hirtz T, Qiao Y, Li X, Zhong F, et al. Highly Transparent and Sensitive Graphene Sensors for Continuous and Non-invasive Intraocular Pressure Monitoring. ACS Appl Mater Interfaces. 2020; 12: 18375-18384; Kim KH, Lee JO, Du J, Sretavan D, Choo H. Real-Time In Vivo Intraocular Pressure Monitoring Using an Optomechanical Implant and an Artificial Neural Network. IEEE Sensors J. 2017; 17: 7394-7404; Yang C, Huang X, Li X, Yang C, Zhang T, Wu Q, et al. Wearable and Implantable Intraocular Pressure Biosensors: Recent Progress and Future Prospects. Advanced Science. 2021; 8: 2002971; Raveendran R, Prabakaran L, Senthil R, Yesudhason BV, Dharmalingam S, Sathyaraj WV, et al. Current Innovations in Intraocular Pressure Monitoring Biosensors for Diagnosis and Treatment of Glaucoma — Novel Strategies and Future Perspectives, Biosensors. 2023; 13: 663; Shaw AJ, Collins MJ, Davis BA, Carney LG. Eyelid Pressure and Contact with the Ocular Surface. Invest Ophthalmol Vis Sci. 2010; 51 : 1911-1917; Yoshioka E, Yamaguchi M, Shiraishi A, Kono T, Ohta K, Ohashi Y. Influence of Eyelid Pressure on Fluorescein Staining of Ocular Surface in Dry Eyes. American Journal of Ophthalmology. 2015; 160: 685-692; Feng X, Li J, Hua Z, Zhang F. Low-light image enhancement based on multi-illumination estimation. Appl Intell. 2021; 51 : 5111-5131; Di Nisio A, D’ Alessandro VI, Scarcelli G, Lanzolla AML, Attivissimo F. Noise robustness evaluation of image processing algorithms for eye blinking detection. Measurement. 2025; 239: 115508; Icare IC200 Instruction Manual, materialbank.icare-world.com / wp- content / uploads / 2023 / 06 / iCare_IC200_instruction_manual_TA031-046-EN- 5.0.pdf?mtime=1687243513 (2023); Nakakura S, Asaoka R, Terao E, Nagata Y, Fukuma Y, Oogi S, et al. Evaluation of rebound tonometer iCare IC200 as compared with IcarePRO and Goldmann applanation tonometer in patients with glaucoma. Eye and Vis. 2021; 8: 25; Badakere SV, Chary R, Choudhari NS, Rao HL, Garudadri C, Senthil S. Agreement of Intraocular Pressure Measurement of Icare ic200 with Goldmann Applanation Tonometer in Adult Eyes with Normal Cornea. Ophthalmology Glaucoma. 2021; 4: 238-243; Brody S, Erb C, Veit R, Rau H. Intraocular pressure changes: the influence of psychological stress and the Valsalva maneuver. Biological Psychology. 1999; 51 : 43-57; Aykan U, Erdurmus M, Yilmaz B, Bilge AH. Intraocular pressure and ocular pulse amplitude variations during the Valsalva maneuver. Graefes Arch Clin Exp Ophthalmol. 2010; 248: 1183-1186; Liu W-C, Lee S-M, Graham AD, Lin MC. Effects of Eye Rubbing and Breath Holding on Corneal Biomechanical Properties and Intraocular Pressure. Cornea. 2011; 30: 855-860; Sun L, Chen W, Chen Z, Xiang Y, Guo J, Hu T, et al. Dual effect of the Valsalva maneuver on autonomic nervous system activity, intraocular pressure, Schl emm’s canal, and iridocorneal angle morphology.BMC Ophthalmol. 2020; 20: 5; Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds) Medical Image Computing and Computer- Assisted Intervention - MICCAI 2015. Cham: Springer International Publishing, pp. 234-241; Mumuni A, Mumuni F. Data augmentation: A comprehensive survey of modern approaches. Array. 2022; 16: 100258; Badrinarayanan V, Kendall A, Cipolla R. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Trans Pattern Anal Mach Intell. 2017; 39: 2481- 2495; Sudre CH, Li W, Vercauteren T, Ourselin S, Jorge Cardoso M. Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations. In: Cardoso MJ, Arbel T, Carneiro G, Syeda-Mahmood T, Tavares JMRS, Moradi M, et al. (eds) Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer International Publishing, pp. 240-248; Taghanaki SA, Zheng Y, Kevin Zhou S, Georgescu B, Sharma P, Xu D, et al. Combo loss: Handling input and output imbalance in multi-organ segmentation. Computerized Medical Imaging and Graphics. 2019; 75: 24-33; Shaw AJ, Collins MJ, Davis BA, Carney LG. Eyelid Pressure and Contact with the Ocular Surface. Invest Ophthalmol Vis Sci. 2010; 51 : 1911; Sakai E, Shiraishi A, Yamaguchi M, Ohta K, Ohashi Y. Blepharo-tensiometer: new eyelid pressure measurement system using tactile pressure sensor. Eye Contact Lens. 2012; 38: 326-330; Pult H, Tosatti SGP, Spencer ND, Asfour J-M, Ebenhoch M, Murphy PJ. Spontaneous Blinking from a Tribological Viewpoint. The Ocular Surface. 2015; 13: 236-249; Wang J, Bao J, Song W, Li S, Hao Y, Tian L, et al. Assessment of Eyelid Pressure Using a Novel Pressure Measurement Device in Patients With Moderate-to- Severe Dry Eye Disease. Front Med (Lausanne). 2022; 9: 833576; Buehren T, Collins MJ, Carney L. Corneal aberrations and reading. Optom Vis Sci. 2003; 80: 159-166; Collins MJ, Buehren T, Trevor T, Statham M, Hansen J, Cavanagh DA. Factors influencing lid pressure on the cornea. Eye Contact Lens. 2006; 32: 168-173; Shaw AJ, Collins MJ, Davis BA, Carney LG. Corneal refractive changes due to short-term eyelid pressure in downward gaze. J Cataract Refract Surg. 2008; 34: 1546-1553; Shaw AJ, Collins MJ, Davis BA, Carney LG. Eyelid pressure: inferences from corneal topographic changes. Cornea. 2009; 28: 181-188; Martinez -Abad A, Pinero DP. New perspectives on the detection and progression of keratoconus. Journal of Cataract and Refractive Surgery. 2017; 43: 1213-1227; Pniakowska Z, Jurowski P, Wierzbowska J. Clinical Evaluation of Corneal Biomechanics following Laser Refractive Surgery in Myopic Eyes: A Review of the Literature. J Clin Med. 2022; 12: 243; Lin M, Zhao J, Shao X, Ma H, Huang Y, Fang Z, et al. Effects of eyelid pressure on corneal tomography and biomechanics: Quantitative analysisusing a novel blepharo-tensiometer. Cont Lens Anterior Eye. 2024; 47: 102313; Barkana Y. Clinical Utility of Intraocular Pressure Monitoring Outside of Normal Office Hours in Patients With Glaucoma. Arch Ophthalmol. 2006; 124: 793; Sharts-Hopko NC, Glynn-Milley C. PRIMARY OPEN-ANGLE GLAUCOMA. AJN, American Journal of Nursing. 2009; 109: 40-4; Leung DYL, Tham CC. Normal-tension glaucoma: Current concepts and approaches-A review. Clinical Exper Ophthalmology. 2022; 50: 247-259; Lee BL, Bathija R, Weinreb RN. The definition of normal-tension glaucoma. J Glaucoma. 1998; 7: 366-371; Song B, Caprioli J. New directions in the treatment of normal tension glaucoma. Indian J Ophthalmol. 2014; 62: 529; Gramer E, Leydhecker W. Glaukom ohne Hochdruck. Eine klinische Studie*. Klin Monatsbl Augenheilkd. 1985; 186: 262-267; Mallick J, Devi L, Malik PK, Mallick J. Update on Normal Tension Glaucoma. J Ophthalmic Vis Res. 2016; 11 : 204-208; Shields MB. Normal-tension glaucoma: is it different from primary open-angle glaucoma?: Current Opinion in Ophthalmology. 2008; 19: 85-88; Jonas JB, Wang N, Wang YX, You QS, Yang D, Xu L. Ocular hypertension: general characteristics and estimated cerebrospinal fluid pressure. The Beijing Eye Study 2011. PLoS One. 2014; 9: el00533; Evinger C, Shaw MD, Peck CK, Manning KA, Baker R. Blinking and associated eye movements in humans, guinea pigs, and rabbits. J Neurophysiol. 1984; 52: 323-339; Bour LJ, Aramideh M, Ongerboer De Visser BW. Neurophysiological Aspects of Eye and Eyelid Movements During Blinking in Humans. Journal of Neurophysiology. 2000; 83: 166-176; Mas D, Domenech B, Espinosa J, Perez J, Hernandez C, Illueca C. Noninvasive measurement of eye retraction during blinking. Opt Lett. 2010; 35: 1884-1886; Perez J, Espinosa J, Domenech B, Mas D, Illueca C. Blinking kinematics description through non-invasive measurement. Journal of Modern Optics. 2011; 58: 1857-1863; Robert Iskander D, Kasprzak HT. Dynamics in longitudinal eye movements and corneal shape. Ophthalmic Physiol Opt. 2006; 26: 572-579; V S, Bhansali S, Kosti R, Balananda P, L N. Intraocular pressure changes during Valsalva maneuver. Natl J Physiol Pharm Pharmacol. 2023; 13: 1887-1892; Stodtmeister R, Heyde M, Georgii S, Matthe E, Spoerl E, Pillunat LE. Retinal venous pressure is higher than the airway pressure and the intraocular pressure during the Valsalva manoeuvre. Acta Ophthalmol. 2018; 96: e68-e73; and Kara N, Kenan S. Effect of refractive status on Valsalva-induced anterior segment changes. Int Ophthalmol. 2018; 38: 1205-1210, each of which is hereby incorporated by reference in its entirety for all purposes.REFERENCES CITED AND ALTERNATIVE EMBODIMENTS

[0260] All references cited herein are incorporated herein by reference in their entirety and for all purposes to the same extent as if each individual publication or patent or patent application was specifically and individually indicated to be incorporated by reference in its entirety for all purposes.

[0261] The present invention can be implemented as a computer program product that includes a computer program mechanism embedded in a non-transitory computer-readable storage medium. For instance, the computer program product could contain instructions for operating the user interfaces disclosed herein. These program modules can be stored on a CD-ROM, DVD, magnetic disk storage product, USB key, or any other non-transitory computer readable data or program storage product.

[0262] Many modifications and variations of this invention can be made without departing from its spirit and scope, as will be apparent to those skilled in the art. The specific embodiments described herein are offered by way of example only. The embodiments were chosen and described in order to best explain the principles of the invention and its practical applications, to thereby enable others skilled in the art to best utilize the invention and various embodiments with various modifications as are suited to the particular use contemplated. The invention is to be limited only by the terms of the appended claims, along with the full scope of equivalents to which such claims are entitled.

Claims

WHAT IS CLAIMED IS:

1. A method comprising: acquiring a plurality of images associated with a blink by an eye of a subject; quantifying a corneal response using the plurality of images; quantifying an eye pressure of the subject using the corneal response; and quantifying a risk of glaucoma for the subject using the eye pressure of the subject.

2. The method of claim 1, wherein the acquiring the plurality of images is performed using a camera proximate to an eye of the subject configured to capture an image in the plurality of images at a range between 200 frames per second and 700 frames per second.

3. The method of either of claim 1 or 2, wherein the plurality of images comprises a range between 2 images and 60 images.

4. The method of either of claim 2 or 3, wherein the camera comprises a field of view comprising a profile or substantially profile view of the eye of the subject.

5. The method of any preceding claim, wherein a frequency of the acquiring the plurality of images is a range between 1.5 milliseconds (ms) per image and 3.5 ms per image.

6. The method of any preceding claim, wherein the plurality of images is associated with at least two blinks by the eye of the subject.

7. The method of any preceding claim, wherein the plurality of images is associated with a range between two blinks and two thousand blinks.

8. The method of any preceding claim, wherein each respective image in the plurality of images is a two-dimensional image having a size of at most 500 kilobytes.

9. The method of any preceding claim, wherein the acquiring the plurality of images comprise concurrently illuminating a portion of the field of view comprising the profile or substantially the profile view of the eye of the subject.

10. The method of claim 9, wherein the illuminating is performed using a first light source set associated with a wavelength in a range between 380 nanometers (nm) and 750 nm.

11. The method of either of claim 9 or 10, wherein the illuminating is performed using a first light source set associated with a wavelength in a range between 750 nm and 1,000 nm.

12. The method of any preceding claim, wherein the acquiring the plurality of images comprises: acquiring, when the illuminating the portion of the field of view, a corresponding value for a set of plurality of boundary conditions based upon a plurality of measurements associated with a region of interest (ROI) of the eye of the subject exposed to the light during the acquiring; and interrupting the acquiring in accordance with a determination a boundary condition in the set of boundary conditions satisfies a threshold dimension.

13. The method of any preceding claim, wherein the quantifying the corneal response comprises: determining a blinking phase of a respective blink by the eye of the subject; determining a contour of the cornea of the eye in accordance with a determination a dimension of the eye satisfies a threshold dimension; determining a centroid of the cornea using the contour of the cornea; determining a displacement of the centroid during some or all of a respective blinking phase of a first eye blink by the eye of the subject; and quantifying the corneal response by comparing the displacement of the centroid against a baseline displacement.

14. The method of any preceding claim, wherein the determining the displacement of the centroid comprises determining a time constant value associated with a velocity of the eye during the respective blinking phase.

15. The method of any preceding claim, wherein the quantifying the corneal response comprises inputting the plurality of images into a first model that iteratively compare sets of images in the plurality of images until a set of images satisfies a threshold contour of the cornea, and wherein each respective temporally adjacent set of images is associated with a corresponding blink of the eye by the subject.

16. The method of claim 15, wherein the first model is trained to compare temporally adjacent sets of images.

17. The method of either of claim 15 or 16, wherein the first model is trained to compare sequential sets of images.

18. The method of any one of claims 15-17, wherein the first model is trained to compare collective sets of images.

19. The method of any preceding claim, wherein the quantifying the corneal response comprises inputting the plurality of images into a second model that categorizes one or more sets of images in the plurality of images into one of a set of eye blink states, wherein the set of eye blink states includes at least an eye state associated with an open or substantially open eye and a second eye state associated with a closed or substantially closed eye.

20. The method of any one of clams 1-19, wherein the set of eye blink states comprises an open state, a partially open state, and a closed state.

21. The method of any one of claims 15-20, the first model is a neural network architecture comprising a plurality of parameters, wherein the plurality of parameters comprises at least 1 x 106parameters, and wherein the neural network architecture provides the categorization of each respective in the plurality of images by application of the at least 1 x 106parameters to each image in the plurality of images.

22. The method of any one of claims 15-20, the second model is a neural network architecture comprising a plurality of parameters, wherein the plurality of parameters comprises at least 1 x 106parameters, and wherein the neural network architecture provides the categorization of each respective in the plurality of images by application of the at least 1 x 106parameters to each image in the plurality of images.

23. The method of any preceding claim, wherein the quantifying the eye pressure comprises quantifying an intraocular pressure of the eye of the subject.

24. The method of any preceding claim, wherein the quantifying the risk of glaucoma comprises generating a value defining a comparison of the eye pressure of the against a threshold baseline pressure.

25. The method of claim 24, wherein the threshold baseline pressure is in a range between 18 millimeters of mercury (mmHg) and 25 mmHg.

26. The method of any preceding claim, wherein the acquiring, the quantifying the corneal response, the quantifying the eye pressure, and the quantifying the risk of glaucoma are performed in real time.

27. A method of treating a subject, the method comprising: acquiring a plurality of images associated with a blink by an eye of a subject; quantifying a corneal response using the plurality of images; quantifying an eye pressure of the subject using the corneal response; and quantifying a risk of glaucoma for the subject using the eye pressure of the subject.

28. The method of claim 27, wherein the acquiring the plurality of images is performed using a camera proximate to an eye of the subject configured to capture an image in the plurality of images at a range between 200 frames per second and 700 frames per second.

29. The method of either of claim 27 or 28, wherein the plurality of images comprises a range between 2 images and 60 images.

30. The method of either of claim 28 or 29, wherein the camera comprises a field of view comprising a profile or substantially profile view of the eye of the subject.

31. The method of any one of claims 27-30, wherein a frequency of the acquiring the plurality of images is a range between 1.5 milliseconds (ms) per image and 3.5 ms per image.

32. The method of any one of claims 27-31, wherein the plurality of images is associated with at least two blinks by the eye of the subject.

33. The method of any one of claims 27-32, wherein the plurality of images is associated with a range between two blinks and two thousand blinks.

34. The method of any one of claims 27-33, wherein each respective image in the plurality of images is a two-dimensional image having a size of at most 500 kilobytes.

35. The method of any one of claims 27-34, wherein the acquiring the plurality of images comprise concurrently illuminating a portion of the field of view comprising the profile or substantially the profile view of the eye of the subject.

36. The method of claim 35, wherein the illuminating is performed using a first light source set associated with a wavelength in a range between 380 nanometers (nm) and 750 nm.

37. The method of either of claim 35 or 36, wherein the illuminating is performed using a first light source set associated with a wavelength in a range between 750 nm and 1,000 nm.

38. The method of any preceding claim, wherein the acquiring the plurality of images comprises: acquiring, when the illuminating the portion of the field of view, a corresponding value for a set of plurality of boundary conditions based upon a plurality of measurements associated with a region of interest (ROI) of the eye of the subject exposed to the light during the acquiring; and interrupting the acquiring in accordance with a determination a boundary condition in the set of boundary conditions satisfies a threshold dimension.

39. The method of any one of claims 27-38, wherein the quantifying the corneal response comprises: determining a blinking phase of a respective blink by the eye of the subject; determining a contour of the cornea of the eye in accordance with a determination a dimension of the eye satisfies a threshold dimension; determining a centroid of the cornea using the contour of the cornea; determining a displacement of the centroid during some or all of a respective blinking phase of a first eye blink by the eye of the subject; and quantifying the corneal response by comparing the displacement of the centroid against a baseline displacement.

40. The method of any one of claims 27-49, wherein the determining the displacement of the centroid comprises determining a time constant value associated with a velocity of the eye during the respective blinking phase.

41. The method of any one of claims 27-40, wherein the quantifying the corneal response comprises inputting the plurality of images into a first model that iteratively compare sets of images in the plurality of images until a set of images satisfies a threshold contour of the cornea, and wherein each respective temporally adjacent set of images is associated with a corresponding blink of the eye by the subject.

42. The method of claim 41, wherein the first model is trained to compare temporally adjacent sets of images.

43. The method of either of claim 41 or 42, wherein the first model is trained to compare sequential sets of images.

44. The method of any one of claims 41-43, wherein the first model is trained to compare collective sets of images.

45. The method of any one of claims 27-44, wherein the quantifying the corneal response comprises inputting the plurality of images into a second model that categorizes one or more sets of images in the plurality of images into one of a set of eye blink states, wherein the set of eye blink states includes at least an eye state associated with an open or substantially open eye and a second eye state associated with a closed or substantially closed eye.

46. The method of any one of clams 27-45, wherein the set of eye blink states comprises an open state, a partially open state, and a closed state.

47. The method of any one of claims 41-26, the first model is a neural network architecture comprising a plurality of parameters, wherein the plurality of parameters comprises at least 1 x 106parameters, and wherein the neural network architecture provides the categorization of each respective in the plurality of images by application of the at least 1 x 106parameters to each image in the plurality of images.

48. The method of any one of claims 41-26, the second model is a neural network architecture comprising a plurality of parameters, wherein the plurality of parameters comprises at least 1 x 106parameters, and wherein the neural network architecture provides the categorization of each respective in the plurality of images by application of the at least 1 x 106parameters to each image in the plurality of images.

49. The method of any one of claims 27-48, wherein the quantifying the eye pressure comprises quantifying an intraocular pressure of the eye of the subject.

50. The method of any one of claims 27-49, wherein the quantifying the risk of glaucoma comprises generating a value defining a comparison of the eye pressure of the against a threshold baseline pressure.

51. The method of claim 50, wherein the threshold baseline pressure is in a range between 18 millimeters of mercury (mmHg) and 25 mmHg.

52. The method of any one of claims 27-51, wherein the acquiring, the quantifying the corneal response, the quantifying the eye pressure, and the quantifying the risk of glaucoma are performed in real time.

53. A method of treating a subject afflicted with an ocular disorder, the method comprising: conducting a therapy session at computing system comprising one or more processors, a camera, a memory, wherein one or more programs are stored in the memory and are configured to be executed by the one or more processors, the one or more programs including instructions for conducting the therapy session comprising a plurality of trials, conducted sequentially, wherein each respective trial is for a respective period of time and comprises: acquiring a plurality of images associated with a blink by an eye of a subject; quantifying a corneal response using the plurality of images; quantifying an eye pressure of the subject using the corneal response; and quantifying a risk of glaucoma for the subject using the eye pressure of the subject.

54. A non-transitory computer readable storage medium storing one or more programs configured for execution by a computing device having one or more processors, memory, a display, a camera, and an input device, the one or more programs comprising instructions for performing a method of any one of claims 1-53.

55. An imaging device comprising: a frame configured to removably accommodate a subject; a camera coupled to the frame and configured to have a field of view of a profile view or substantially profile view of the subject; one or more processors; memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors to perform a method of any one of claims 1-53.

Images