Smart-APP, VR headset, cloud and ai based method to detect field of vision problems

Abstract

Systems (100) and methods (300; 400) are provided that leverage a smartphone-based application (107) integrated with a low-cost VR headset (101) to conduct visual field testing (300) at home. The disclosed systems and methods deliver standardized perimetry tests, mimicking clinical-grade evaluations, by presenting a series of controlled light stimuli at predefined locations in the user's visual field. Unlike prior art solutions, this approach significantly reduces costs while increasing accessibility, making regular eye health monitoring feasible for individuals in remote or underprivileged areas.

Description

SMART-APP, VR HEADSET, CLOUD AND Al BASED METHOD TO DETECT FIELD OF VISION PROBLEMSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to, and the benefit of, U.S. Provisional Patent Application Serial No. 63 / 639,301, filed April 26, 2024, and titled "A SMART-APP, VR HEADSET, CLOUD AND Al BASED METHOD TO DETECT FIELD OF VISION PROBLEMS," the disclosure of which is hereby incorporated by reference in its entity.BACKGROUND

[0002] Glaucoma, a leading cause of irreversible blindness worldwide, affects an estimated 76 million people globally, with projections reaching 111.8 million by 2040, particularly impacting Africa and Asia. Traditional methods for glaucoma detection, such as the Humphrey Visual Field (HVF) test, require patients to visit specialized eye care centers equipped with costly perimetry devices. This makes detecting and treating glaucoma expensive and time consuming.SUMMARY

[0003] Systems and methods are provided that leverage a smartphone-based application integrated with a low-cost VR headset to conduct visual field testing at home. The disclosed systems and methods deliver standardized perimetry tests, mimicking clinical- grade evaluations, by presenting a series of controlled light stimuli at predefined locations in the user's visual field. Unlike prior art solutions, this approach significantly reduces costs while increasing accessibility, making regular eye health monitoring feasible for individuals in remote or underprivileged areas.

[0004] The proposed systems and methods also facilitate the longitudinal tracking of glaucoma progression. By recording and analyzing test results overtime, the smartphone-based application can identify subtle deterioration in the visual field, prompting timely medical intervention. Additionally, the home-based nature of the test encourages frequent self-assessments, improving diagnostic accuracy and adherence to treatment plans. The integration of a VR environment ensures an immersive experience, minimizing distractions and increasing patient focus, which is crucial for accurate perimetry testing.

[0005] In some aspects, the techniques described herein relate to a method including: detecting a resolution and a display size of a display of a computing device by a visual field-testing application executed by the computing device; receiving an indication to perform a visual field test by the visual field-testing application executed by the computing device from a user; in response to the indication, executing a visual field test for the user including: selecting a subset of pixels of the display based on the resolution and the display size, wherein the selected subset of pixels corresponds to a visual field grid; for each pixel of the selected subset of pixels of a plurality of pixels of the display: causing the pixel to activate with a varied intensity; recording a time stamp of the pixel activation and the varied intensity; receiving a response from the user; and recording a time stamp of the response; generating a visual field report based on the visual field test; and displaying a graphical representation of the visual field report to the user on the display of the computing device.

[0006] In some aspects, the techniques described herein relate to a method, further including placing the computing device into a virtual reality headset prior to receiving the indication.

[0007] In some aspects, the techniques described herein relate to a method, further including storing the visual field report in a cloud-based storage system.

[0008] In some aspects, the techniques described herein relate to a method, further including providing access to the stored visual field test to a physician or health professional associated with the user.

[0009] In some aspects, the techniques described herein relate to a method, wherein the visual field test further includes downloading one or more previous visual field reports of the user from a cloud-based storage system, and selecting the subset of pixels of the display based on the resolution and the display size and the one or more previous visual field reports.

[0010] In some aspects, the techniques described herein relate to a method, wherein the visual field test includes the Humphrey visual field test.

[0011] In some aspects, the techniques described herein relate to a method, wherein the visual field grid includes a 24-2 perimetry grid.

[0012] In some aspects, the techniques described herein relate to a method, wherein the visual field test further includes detecting one or more false responses from the received responses from the user based on the time stamps of the responses and the time stamps of the pixel activations, and removing the detected one or more false responses.

[0013] In some aspects, the techniques described herein relate to a method, wherein detecting the one or more false responses includes detecting the one or more false responses using artificial intelligence.

[0014] In some aspects, the techniques described herein relate to a method, wherein receiving the response from the user includes receiving an input from a user input device associated with the computing device or receiving a voice input from the user.

[0015] In some aspects, the techniques described herein relate to a method, wherein the visual field test further includes causing the computing device to render a fixation cross on the display and instructing the user to look at the fixation cross during the test.

[0016] In some aspects, the techniques described herein relate to a method, further including detecting the user is not looking at the fixation cross by causing a pixel of the plurality of pixels associated with a blind spot of the user to activate and receiving a response to the activation from the user.

[0017] In some aspects, the techniques described herein relate to a method, further including dynamically adjusting the pixels of the subset of pixels that are activated and the varied intensity of each activation based on the user responses.

[0018] In some aspects, the techniques described herein relate to a method, further including dynamically adjusting the pixels of the subset of pixels that are activated and the varied intensity of each activation based on the user responses using artificial intelligence.

[0019] In some aspects, the techniques described herein relate to a method, further including dynamically translating instructions for the visual field test for the user based on a language selected by the user using a speech synthesis model trained for multilingual support.

[0020] In some aspects, the techniques described herein relate to a method, wherein generating the visual field report includes generating a grayscale visual field map.

[0021] In some aspects, the techniques described herein relate to a method, wherein generating the visual field report includes generating a grayscale visual field grid.

[0022] In some aspects, the techniques described herein relate to a method, further including comparing the generated visual field report to a previously generated visual field report to generate a metric that captures any changes to the visual field of the user.

[0023] In some aspects, the techniques described herein relate to a method, further including diagnosing the user with an eye condition based on the visual field report and one or more previously generated visual field reports.

[0024] In some aspects, the techniques described herein relate to a method, further including diagnosing the user with an eye condition using one or more of convolutional Neural Networks, recurrent neural networks, and Transformer-based models.

[0025] Other systems, methods, features and / or advantages will be or may become apparent to one with skill in the art upon examination of the following drawings and detailed description. It is intended that all such additional systems, methods, features and / or advantages be included within this description and be protected by the accompanying claims.BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The foregoing summary, as well as the following detailed description of illustrative embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the disclosed embodiments, there is shown in the drawings example constructions of the embodiments; however, the possible embodiments are not limited to the specific methods and instrumentalities disclosed. In the drawings:

[0027] FIG. 1 illustrates an example environment for implementing a visual field testing application;

[0028] FIG. 2 illustrates an example virtual reality headset and computing device for implementing a visual field testing application;

[0029] FIG. 3 is an illustration of an example method 300 for performing a visual field test and for generating a visual field report;

[0030] FIG. 4 is an illustration of an example method for performing a visual field test;

[0031] FIG. 5 is an illustration of an example visual field grid;

[0032] FIG. 6 is a schematic diagram of computer hardware that may be utilized to implement aspects of the disclosed systems and methods.DETAILED DESCRIPTION

[0033] FIG. 1 illustrates an example environment 100 for implementing a visual field testing application that performs one or more visual field tests for an associated user. As shown, the environment 100 includes virtual reality ("VR") goggles 101 adapted to hold a user computing device 105 and a visual test server 180 in communication through a network 160. The network 160 may be any combination of local and wide area networks (e.g., the internet). The user computing device 105 and the visual test server 180 may each be implemented using one or more general purpose computing devices such as the computing device 600 illustrated with respect to FIG. 6.

[0034] As used herein a visual field test is an eye test that is done while a user fixes their gaze on a central point. While the user looks at the central point, lights of varying intensity are displayed to the user at various locations in the field of view of the user. Based on which lights the user is able to see and at what intensities, the visual field test can help determine blind spots in the visual field of the user as well as areas where the user may bedeveloping blind spots. As described above, the Humphrey visual field test is an example of such a test that is used to diagnose eye diseases such as glaucoma.

[0035] While such tests are effective, they generally rely on specialized equipment that is expensive and must be operated by a health professional. Accordingly, many users may not have ready access to visual field tests due to poverty or location.

[0036] Accordingly, to allow users to perform visual field tests at home using low- cost equipment, the visual test application 107 is provided that works on user computing devices 105 such as smart phones in combination with commonly available VR headsets 101. For example, FIG. 2 is an illustration of an example VR headset 101 that may be used with the user computing device 105 (e.g., a smartphone). As shown, the computing device 105 may be placed in the VR headset 101 such that the display of the device 105 is visible to the user when wearing the VR headset 101. The user may then cause the visual test application 107 to be downloaded to the device 105 through an "app store" or other repository of applications that may be executed on a device 105.

[0037] As will be described further below, the user may then use the visual test application 107 to perform one or more visual field tests while the user wears the VR headset 101. The results of the test, referred to herein as a visual field report 187, may then be displayed to the user by the visual test application 107, and / or may be provided to a health professional 150 associated with the user. The health professional 150 may then review the report 187, and may use the report 187 to diagnose the user with one or more eye diseases or conditions or to monitor the progression of such conditions or diseases.

[0038] Returning again to FIG. 1, the visual test application 107 may perform a visual field test, by first determining a resolution and / or size of the display associated with the device 105. As may be appreciated, because devices 105 may have a variety of displaysizes and resolutions, in order to perform the visual field test, the device 105 may first determine the display size and resolution of the device 105 so that the pixels that make up the display can be mapped or translated into corresponding regions or areas of the eyes of the user. Because a distance between the eyes of the user and the display of the device 105 is known or fixed, once the resolution and / or size of the display is determined, the application 107 may determine which pixels of the display of the device 105 correspond to which regions of the eyes of the user.

[0039] In some embodiments, the visual test application 107 may determine the size and / or resolution of the display of the device 105 through the operating system of the device 105. Alternatively, the device 105 may ask the user to identify their device 105, and the application 107 may use stored information about a variety of known devices 105 to determine the likely size and / or resolution of the display of the device 105. Other methods may be used. In some embodiments, the display size and resolution may be determined as part of a calibration process.

[0040] The visual test application 107 may perform a visual field test by first displaying a fixation cross on the display of the device 105. The fixation cross may be a graphic that the user is asked to focus on during the duration of the visual field test. Depending on the embodiment, the application 107 may ask the user to focus on the center of the fixation cross by displaying instructions to the user on the display or by audibly playing instructions to the user. Depending on the embodiment, the application 107 may store text and / or spoken instructions for the test in a variety of languages and may select a language based on user or preferences or settings on the device 105. Alternatively, the application 107 may include an Al component that can translate instructions into anylanguage preferred by the user on the fly. Any method fortranslating instructions may be used.

[0041] While the fixation cross is displayed to the user, the visual test application 107 may perform the visual field test by first selecting a subset of pixels of the display of the computing device 105 that correspond to regions of the eye to be tested. The visual field test may test specific regions of the eye depending on the test being performed. These regions of the eye may be mapped to what is referred to as a visual field grid. An example visual field grid is the Amsler grid or the 24-2 grids used for glaucoma testing.

[0042] The visual test application 107, for each region of a selected visual field grid, may determine the pixels of the display that correspond to the region. Depending on the embodiment, the visual test application 107 may make the determination based on the determined size and resolution of the display of the computing device 105, and a known distance between the display and the eyes of the user when the device 105 is placed in the VR headset 101.

[0043] Once the pixels are determined for each region of the visual field grid, the visual test application 107 may perform the visual field test by, for each of the regions of the visual field grid, causing the pixels of the display corresponding to the region to selectively activate at a selected intensity or brightness. Depending on the embodiment, there may be a set number of intensity levels that the pixels are activated at starting at a very low intensity and ending at a very high intensity level that may correspond to a highest intensity that is supported by the display. Each subsequent intensity level may be an increase of some percentage with respect to a previous intensity level, such as 5%. Other percentages may be supported. The total number of intensity levels may be set by an administrator and may be dependent on the particular visual field test being performed.

[0044] In some embodiments, the visual test application 107, after activating pixels corresponding to a region of the visual field grid, may record a time stamp of when the pixels of the region were activated and at what intensity. The visual field test application 107 may continue to activate the pixels for a duration of time such as 3 seconds, for example. The duration may be fixed or may be dynamic and may change based on user test performance.

[0045] As part of the visual field test application, the visual test application 107 may further receive user responses 109 from the user during the visual field test. In some embodiments, the user may use a mouse, or other input device, to provide a user response 109 to the activated pixels that indicates that the user was able to see the activated pixels. The user response 109 may further include audible responses such as the user speaking certain keywords such as "I see it" or "yes." Other user responses 109 may be supported.

[0046] When the visual test application 107 receives a user response 109, the visual test application 107 may store a time stamp of when the user response 109 was received. As will be described further below, the time stamp of each response 109 may be cross referenced with the time stamps of the pixel activations to determine which regions and with which intensities the user was able to see, and which regions and which intensities the user was unable to see.

[0047] During the visual field test, the visual test application may select a region of the grid to display and an intensity. In some embodiments, the visual test application 107 may randomly select a region of grid from among the regions that have not yet been displayed, or may select regions in a predetermined order. The predetermined order may be set by a user or administrator. The intensity or brightness of the pixels that are used for the display may be based on a previous intensity that was used for the same region. Forexample, for a first activation of the pixels corresponding to a display region, the visual test application 107 may select a lowest intensity for the pixels. For the second activation of the pixels, the visual test application 107 may select a slightly higher intensity for the pixels. The visual test application 107 may continue until a highest intensity has been used for the pixel region. Alternatively, rather than start at the lowest intensity, the visual test application 107 may start at the highest intensity and decrease the intensity of a pixel region for each subsequent activation.

[0048] In some embodiments, the visual test application may dynamically select and adjust some or all of the regions that are selected for pixel activation, the intensity of the activations, and the duration of the activation based on the user responses 109. For example, if the user responses 109 indicate that the user is frequently recognizing pixel activations at a low intensity for most regions, the visual test application 107 may skip higher intensity activations and start at lower intensity for subsequent regions of the grid. As another example, if the user is quickly providing user responses 109, the visual test application 107 may decrease the duration of each activation.

[0049] After completing the visual field test, the visual test application 107 may send the time stamps of each pixel activation and received user responses 109 to the visual test server 180 for processing by the visual test engine 185. Alternatively or additionally, the visual test application 107 may process the time stamps on the user computing device 105. As may be appreciated, the visual test server 180 may be a cloud-based server and may have more available computing resources than the user computing device 105. The data may be transmitted to the visual test server 180 using encryption protocols such as AES-256 for storage and TLS for data transmission protect patient privacy while ensuring compliance with HIPAA and GDPR.

[0050] In embodiments where the processing is performed by the visual test application 107 on the user computing device 105, the application 107 may use lightweight Al models optimized for edge computing on mobile devices. These may include quantized neural networks, support vector machines, random forest classifiers, and few shot learning. Other methods for optimized processing may be used.

[0051] In some embodiments, the Al models of the visual test application 107 may, based on user response 109 patterns received during the test, adjust stimulus presentation based on prior accuracy, and may flag potential issues with the test in realtime. These flags may be used by the application 107 to alert the users to retake sections of the test if needed.

[0052] In some embodiments, the visual test application and / or the visual test engine 185 may correlate the time stamps of the user responses 109 to the time stamps of the pixel activations to determine which regions of the visual field grid that the user was able to perceive and at which intensities. In some embodiments, a pixel activation is determined to have been seen by the user when the activation has a user response 109 with a time stamp that is within some threshold duration of the time stamp of the activation. The threshold may be set by a user or administrator.

[0053] After determining which regions of the visual field grid that the user was able to perceive and at which intensities, the visual test engine 185 and / or the visual test application 107 may use the determined regions to generate a report 187. The report 187 may include a graphical representation of the determined regions with color or shading representing the lowest intensity that the user was able to perceive. An example graphical representation is shown in the visual field grid 500 of FIG. 5. Here the darker shaded regions indicate regions that responded only to high intensity light or did not respond at all,and lighter shaded regions indicate regions that responded to low intensity light. The report 187 may be displayed to the user on the device 105, and may be provided to a health professional 150 associated with the user.

[0054] In some embodiments, the visual test application 107 and / or the visual test engine 185 may further generate a diagnosis of one mor more eye conditions or diseases based on the report 187. For example, report 187 may include indications of possible eye conditions such as glaucoma or retinal degeneration. Other conditions may be supported. Depending on the embodiment, the application 107 and / or engine 185 may use one or more artificial intelligence-based models to process the report 187 and identify any possible eye conditions. The models may have been trained using reports 187 and / or visual field grids known to be associated with patients afflicted with certain eye conditions or diseases. The models may include convolutional neural networks, recurrent neural networks, and transformer-based models.

[0055] In some embodiments, the report 187, and some or all of the time stamp and response 109 data that was used to generate the report 187, may be stored by the visual test engine 185 as user visual test data 205 for the user. The user visual test data 205 for the user may include some or all of the visual field tests that were performed for the user by the visual test application 107. The visual test server 180 may provide a portal or other interface through which an associated health professional 150 may download and / or view the reports 187.

[0056] In some embodiments, the visual test server 180 may anonymize and aggregate the reports 187 for each user and the user visual test data 205. This anonymized and aggregated data can be used for research purposes with respect to one or more eyeconditions and diseases. Depending on the implementation, each user may consent to the use of their data before their data is included in the anonymized and aggregated data.

[0057] In some embodiments, the report 187 may include a score or metric that indicates the progression or severity of the particular eye disease or condition being measured. Depending on the embodiment, the visual test engine 185 and / or the visual test application 107 may generate the metric based in part on a sum of the minimum intensities that were visible to the user for each of the regions of the visual field grid. Other methods for computing a metric may be used. The metric may allow the user to easily compare reports 187 and to quickly determine if a monitored eye condition or disease is progressing.

[0058] In some embodiments, prior to generating the report 187, the visual test engine 185 may identify and remove one or more "false" user responses from the user responses 109 received during the vision field test. A response 109 may be considered false when evidence suggests that the user did not provide the user response 109 because they saw a particular pixel activation. For example, a user may have accidentally provided the user response 109 in response to some other stimulation, or may be trying to cheat. The visual test engine 185 may identify and remove false responses using various heuristics such as removing responses 109 with time stamps that are too close to the time stamp of the closest pixel activation, or that are outliers with respect to the average response time for the user or other users.

[0059] In some embodiments, the visual test engine 185 may remove false positives using one or more artificial intelligence-based models. The models may have been trained to recognize false positives based on a history of previously performed vision field tests and identified false positives.

[0060] As described above, the user visual test data 205 recorded for a user may allow the user to view their history of vision field tests and to monitor the progression of one or more eye conditions by comparing current and past reports 187 including metrics. In some embodiments, as another feature, the visual test application 107 may reduce the length of the visual field test by using previous visual field tests for a user to reduce the overall number of pixel activations that are displayed for the user.

[0061] As described above, the visual test application 107 may activate pixels for each region of the visual test grid starting at a minimum intensity and gradually increasing the intensity with subsequent activations of the pixels for the region. The visual test application 107 may reduce the number of pixel activations for a visual field test by, for each region of the grid, determining the minimum intensity that was visible for the user in a previous visual field test as indicated by the user vision data 205. After determining the minimum intensity for each region, the visual test application 107 may then use that minimum intensity as the starting intensity for that region in the current visual field test to reduce the overall number of activations for the pixels corresponding to the region.

[0062] For example, a previous visual field test for a region may have showed that the user detected the region when the corresponding pixels were activated at 50% brightness. For a subsequent visual field test, the visual test application 107 may activate the pixels for the region starting at around the 50% brightness level, rather than the minimum brightness level usually used. To allow for improvements to the user's vision, the visual test application 107 may start slightly below the previous minimum. As may be appreciated, by starting the current visual field test at or around the previous test minimum intensities, the amount of time and number of pixel activations may be greatly reducedwhen compared to a full visual field test. Depending on the embodiments, a user or health professional 150 may disable this feature to force a complete visual field test if desired.

[0063] As may be appreciated, for the visual field test to correctly test the visual field of the user, the user must remain focused on the fixation cross during the visual field test. In some embodiments, to determine whether the user is in fact focused on the fixation cross, the visual test application 107 may periodically activate pixels of the display that are known to correspond to a blind spot of the user if the user were in fact focused on the fixation cross. These blind spots are located where the optic nerve is connected to the retina and may be located at approximately the same location for all users. The pixels corresponding to the blind spots of the user may be determined based on the size and resolution of the display of the user computing device 105 and the distance between the eyes of the user and display in the VR headset 101. Alternatively, the pixels corresponding to the blind spot of the user may be determined through the calibration process that is performed by the user prior to performing the visual field test.

[0064] After activating the pixels corresponding to the blind spot of the user, if the user provides a user response 109, indicating that the user saw the pixels and is therefore not looking at the fixation cross, the visual test application 107 may display or speak a reminder to the user to look at the fixation cross. Depending on the embodiment, if the user continues to fail the test by providing user responses 109 to blind spot pixel activations, the visual test application 107 may either redo portions of the visual field test, may restart the visual field test, or may ask the user to recalibrate the visual test application 107.

[0065] As described above, the visual test application 107 may support voice recognition for purposes of receiving user responses 109 and for general user control. Thevoice recognition may include machine-learning based voice recognition and may incorporate features such as mel-frequency cepstral coefficients (MFCCs) for converting speech into numerical features for recognition, small-footprint neural networks (e.g., convolutional recurrent neural networks, TinyBERT for speech, or MobileNet-based classifiers) for on-device keyword spotting, noise suppression algorithms to filter out background sounds and prevent false triggers, and user-specific voice model training. Other voice recognition features may be supported.

[0066] As an additional feature, in some embodiments, the visual test application 107 may provide for the selective occlusion of an eye of the user without the use of an eye patch. Traditional perimetry tests require the patient to wear an eye patch to block the vision of the non-tested eye, ensuring monocular testing. However, this approach introduces multiple challenges, including discomfort, slippage, and improper fixation stability due to the pressure or movement of the eye patch. Many patients, particularly elderly individuals, find eye patches cumbersome and uncomfortable, leading to test inaccuracies or non-compliance.

[0067] Accordingly, in some embodiments, the visual test application 107 may perform a perimetry test. When testing the left eye, the right side of the display in the VR headset 101 remains completely black, preventing the right eye from perceiving any stimuli. Similarly, when testing the right eye, the left side of the display in the VR headset 101 is blacked out. This ensures that only the target eye is actively engaged in the test, replicating traditional occlusion methods without requiring any additional hardware.

[0068] FIG. 3 illustrates an example flow diagram of a method 300 for performing a visual field test and for generating a visual field report. The method 300 may be implemented by one or both of the visual test server 180 and the visual test application 107.

[0069] At 301, a computing device is placed in VR headset. The computing device 105 may be a smartphone and may be placed in the VR headset 101 by a user who wished to perform a visual field test. The user may have also installed a visual test application 107 on the computing device 105. The device 105 may have a display size and resolution.

[0070] At 310, the resolution and display size are detected. The resolution and display size of the device 105 may be detected by the application 107 or selected by the user, for example.

[0071] At 320, an indication to perform a visual field test is received. The indication may be received by the visual test application 107 from the user. For example, the user may speak a word such as "begin" or may provide the indication using a mouse or other input device associated or paired with the device 105. Any method for providing an indication may be used.

[0072] At 330, the visual field test is performed. The visual field test may be performed according to the method 400 of FIG. 4. Depending on the embodiment, the visual field test may be similar to the Humphrey visual field test and may detect the presence or signs of glaucoma.

[0073] At 340, a report is generated. The report 187 may be generated by one or more of the visual test application 107 or the visual test server 180. In some embodiments, the report 187 may include a greyscale visual field grid that represents the sensitivity of different regions of the eye to light. The report 187 may also include a metric that represents the health of the eye. If a previous visual field test was performed, the report 187 may include any changes to the metric with respect to the previous visual field test.

[0074] At 350, the report is displayed. The report 187 may be displayed to the user by the visual test application 107.

[0075] At 360, the report is stored. The report 187 may be stored by the visual test server 180 as part of the user visual test data 205 associated with the user. In some embodiments, the report 187 may also be provided to a health professional 150 associated with the user such as a physician. The report 187 may be provided directly to the health professional 150 or the health professional may use a portal or other application to access the report 187 on the visual test server 180.

[0076] FIG. 4 is an illustration of an example method 400 for performing a visual field test. The method 400 may be implemented by one or both of the visual test server 180 and the visual test application 107.

[0077] At 401, a subset of pixels of the display are selected based on the determined resolution and display size. The subset of pixels may be pixels that correspond to regions of the eye of the user when the user is looking at the fixation cross. The regions may be regions of a visual field grid corresponding to the particular eye condition or disease being tested.

[0078] At 410, a fixation cross is generated and displayed. The fixation cross may be displayed by the visual test application 107.

[0079] At 420, pixels are selectively activated at varied intensities. The pixels may be selectively activated by the visual test application. The pixels in each activation may correspond to a particular region of the visual field grid that is being tested. The intensity may be selected from a plurality of intensities supported by the display. Each region of the visual field grid may be tested during the visual field test.

[0080] At 430, a time stamp and intensity are recorded for each activation. The time stamp and intensity may be recorded by the visual test application 107.

[0081] At 440, user responses are received. The user responses 109 may be received by the visual test application 107. The user responses 109 may be received from a mouse or may be spoken by the user being tested. Each response 109 may be received after a corresponding pixel activation.

[0082] At 450, a time stamp is recorded for each response. The time stamp and intensity may be recorded by the visual test application 107.

[0083] At 460, false responses are removed. The false responses 109 may be removed by the visual test application 107 using one or more Al models

[0084] At 470, the report is generated. The report 187 may be generated by the visual test application 107 by correlating the user responses with the pixel activations based on the time stamps. The report 187 may be stored with the user visual test data 205, displayed to the user by the visual test application 107, and / or provide to a health professional 150.

[0085] FIG. 6 shows an exemplary computing environment in which example embodiments and aspects may be implemented. The computing device environment is only one example of a suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality.

[0086] N umerous other general purpose or special purpose computing devices environments or configurations may be used. Examples of well-known computing devices, environments, and / or configurations that may be suitable for use include, but are not limited to, personal computers, server computers, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, network personal computers (PCs), minicomputers, mainframe computers, embedded systems, distributed computing environments that include any of the above systems or devices, and the like.

[0087] Computer-executable instructions, such as program modules, being executed by a computer may be used. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Distributed computing environments may be used where tasks are performed by remote processing devices that are linked through a communications network or other data transmission medium. In a distributed computing environment, program modules and other data may be located in both local and remote computer storage media including memory storage devices.

[0088] With reference to FIG. 6, an exemplary system for implementing aspects described herein includes a computing device, such as computing device 600. In its most basic configuration, computing device 600 typically includes at least one processing unit 602 and memory 604. Depending on the exact configuration and type of computing device, memory 604 may be volatile (such as random-access memory (RAM)), non-volatile (such as read-only memory (ROM), flash memory, etc.), or some combination of the two. This most basic configuration is illustrated in FIG. 6 by dashed line 606.

[0089] Computing device 600 may have additional features / functionality. For example, computing device 600 may include additional storage (removable and / or nonremovable) including, but not limited to, magnetic or optical disks or tape. Such additional storage is illustrated in FIG. 6 by removable storage 608 and non-removable storage 610.

[0090] Computing device 600 typically includes a variety of computer readable media. Computer readable media can be any available media that can be accessed by the device 600 and includes both volatile and non-volatile media, removable and non-removable media.

[0091] Computer storage media include volatile and non-volatile, and removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Memory 604, removable storage 608, and non-removable storage 610 are all examples of computer storage media. Computer storage media include, but are not limited to, RAM, ROM, electrically erasable program read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by computing device 600. Any such computer storage media may be part of computing device 600.

[0092] Computing device 600 may contain communication connection(s) 612 that allow the device to communicate with other devices. Computing device 600 may also have input device(s) 614 such as a keyboard, mouse, pen, voice input device, touch input device, etc. Output device(s) 616 such as a display, speakers, printer, etc. may also be included. All these devices are well known in the art and need not be discussed at length here.

[0093] It should be understood that the various techniques described herein may be implemented in connection with hardware components or software components or, where appropriate, with a combination of both. Illustrative types of hardware components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc. The methods and apparatus of the presently disclosed subject matter, or certain aspects or portions thereof, may take the form of program code (i.e., instructions) embodied in tangible media, such asfloppy diskettes, CD-ROMs, hard drives, or any other machine-readable storage medium where, when the program code is loaded into and executed by a machine, such as a computer, the machine becomes an apparatus for practicing the presently disclosed subject matter.

[0094] Although exemplary implementations may refer to utilizing aspects of the presently disclosed subject matter in the context of one or more stand-alone computer systems, the subject matter is not so limited, but rather may be implemented in connection with any computing environment, such as a network or distributed computing environment. Still further, aspects of the presently disclosed subject matter may be implemented in or across a plurality of processing chips or devices, and storage may similarly be effected across a plurality of devices. Such devices might include personal computers, network servers, and handheld devices, for example.

[0095] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

WHAT IS CLAIMED:

1. A method comprising: detecting a resolution and a display size of a display of a computing device by a visual field-testing application executed by the computing device; receiving an indication to perform a visual field test by the visual field-testing application executed by the computing device from a user; in response to the indication, executing a visual field test for the user comprising: selecting a subset of pixels of the display based on the resolution and the display size, wherein the selected subset of pixels corresponds to a visual field grid; for each pixel of the selected subset of pixels of a plurality of pixels of the display: causing the pixel to activate with a varied intensity; recording a time stamp of the pixel activation and the varied intensity; receiving a response from the user; and recording a time stamp of the response; generating a visual field report based on the visual field test; and displaying a graphical representation of the visual field report to the user on the display of the computing device.

2. The method of claim 1, further comprising placing the computing device into a virtual reality headset prior to receiving the indication.

3. The method of claim 1, further comprising storing the visual field report in a cloudbased storage system.

4. The method of claim 3, further comprising providing access to the stored visual field test to a physician or health professional associated with the user.

5. The method of claim 1, wherein the visual field test further comprises downloading one or more previous visual field reports of the user from a cloud-based storage system, and selecting the subset of pixels of the display based on the resolution and the display size and the one or more previous visual field reports.

6. The method of claim 1, wherein the visual field test comprises the Humphrey visual field test.

7. The method of claim 1, wherein the visual field grid comprises a 24-2 perimetry grid.

8. The method of claim 1, wherein the visual field test further comprises detecting one or more false responses from the received responses from the user based on the time stamps of the responses and the time stamps of the pixel activations, and removing the detected one or more false responses.

9. The method of claim 8, wherein detecting the one or more false responses comprises detecting the one or more false responses using artificial intelligence.

10. The method of claim 1, wherein receiving the response from the user comprises receiving an input from a user input device associated with the computing device or receiving a voice input from the user.

11. The method of claim 1, wherein the visual field test further comprises causing the computing device to render a fixation cross on the display and instructing the user to look at the fixation cross during the test.

12. The method of claim 1, further comprising detecting the user is not looking at the fixation cross by causing a pixel of the plurality of pixels associated with a blind spot of the user to activate and receiving a response to the activation from the user.

13. The method of claim 1, further comprising dynamically adjusting the pixels of the subset of pixels that are activated and the varied intensity of each activation based on the user responses.

14. The method of claim 13, further comprising dynamically adjusting the pixels of the subset of pixels that are activated and the varied intensity of each activation based on the user responses using artificial intelligence.

15. The method of claim 1, further comprising dynamically translating instructions for the visual field test for the user based on a language selected by the user using a speech synthesis model trained for multilingual support.

16. The method of claim 1, wherein generating the visual field report comprises generating a grayscale visual field map.

17. The method of claim 1, wherein generating the visual field report comprises generating a grayscale visual field grid.

18. The method of claim 17, further comprising comparing the generated visual field report to a previously generated visual field report to generate a metric that captures any changes to the visual field of the user.

19. The method of claim 1, further comprising diagnosing the user with an eye condition based on the visual field report and one or more previously generated visual field reports.

20. The method of claim 19, further comprising diagnosing the user with an eye condition using one or more of convolutional Neural Networks, recurrent neural networks, and Transformer-based models.

Images