# US 12,223,771 B2 · Determining digital markers indicative of a neurological condition > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,771 B2 - Document ID: US12223771B2 - Status: Granted - Kind: B2 - Application number: 18/734,323 - Filed: 2024-06-05 - Published: 2024-09-26 - Granted: 2025-02-11 - Earliest claimed: 2021-05-03 - Assignees: NeuraLight Ltd. - Applicants: NeuraLight Ltd. - Inventors: Edmund Ben-Ami; Micha Yochanan Breakstone; Rotem Zvi Bar-Or; Vladimir Anisimov - Web page: https://patentgrep.com/patent/US12223771B2 ## CPC - G06V 40/18: Eye characteristics, e.g. of the iris - A61B 3/0025: {characterised by electronic signal processing, e.g. eye models} - A61B 3/113: for determining or recording eye movement - A61B 5/163: {by tracking eye movement, gaze, or pupil change} - G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/09: Supervised learning - G06T 7/0012: {Biomedical image inspection} - G06T 7/0016: {involving temporal comparison} - G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments - G06V 10/82: using neural networks - G06N 3/084: Backpropagation, e.g. using gradient descent - G06T 2207/10016: Video; Image sequence - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30041: Eye; Retina; Ophthalmic - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Disclosed are system, method, and computer program product embodiments for determining a digital marker indicative of a neurological condition. An embodiment operates by detecting a region of interest in an image frame of a face of a user. The region of interest includes an eye of the user and the image frame is obtained from a video stream. The embodiment then generates a point spread function (PSF) based on acquired data and a portion of the image frame specified by the region of interest, performs deconvolution on the portion of the image frame specified by the region of interest using the PSF, determines a set of oculometric parameters of the eye of the user using the deconvolved image, and determines one or more digital markers of the user based on the set of oculometric parameters. The one or more digital markers are indicative of a neurological condition of the user. ## Claims ### Claim 1 A computer-implemented method for efficiently determining a digital marker indicative of a neurological condition or a mental health condition, comprising: detecting, using one or more processors, a region of interest in an image frame of a face of a user, wherein the region of interest includes an eye of the user and the image frame is obtained from a video stream; performing blind deconvolution on a portion of the image frame specified by the region of interest, wherein the portion of the image frame satisfies a signal to noise threshold; determining a set of oculometric parameters of the eye of the user using the blind deconvolved portion of the image frame; and determining one or more digital markers of the user based on the set of oculometric parameters, wherein the one or more digital markers are indicative of a neurological condition or a mental health condition of the user. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the signal to noise threshold comprises a minimum sclera brightness. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the oculometric parameters comprise a pupil center, iris data, and eyelid data. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the performing blind deconvolution further comprises: determining a point spread function based on stimulus data or device data. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the performing blind deconvolution further comprises: determining a spatial velocity based on a time series of a location of the eye of the user, wherein the time series is indicative of the location of the eye in a plurality of successive eye images obtained from the video stream; and determining a point spread function based on the spatial velocity. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, further comprising: adjusting a size of the region of interest to correct for a motion in a z-direction, wherein the z-direction corresponds to a direction perpendicular to an image sensor, and wherein the video stream is captured by the image sensor. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, further comprising: prior to the performing blind deconvolution on the portion of the image frame, determining a pre-set of oculometric parameters based on the portion of the image frame. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, further comprising: iteratively repeating the performing the blind deconvolution and the determining the set of oculometric parameters to improve an accuracy of the set of oculometric parameters. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein the determining the set of oculometric parameters comprises: detecting a plurality of boundaries in the blind deconvolved portion of the image frame based on a change in intensity between data points in the blind deconvolved portion of the image; and identifying, from a plurality of quadratic curves, a quadratic curve that fits an upper eyelid and a lower eyelid based on the plurality of boundaries. ### Claim 10 (depends on 9) The computer-implemented method of claim 9, wherein the identifying comprises: identifying the quadratic curve based on a maximal likelihood estimation. ### Claim 11 A system for efficiently determining a digital marker indicative of a neurological condition or a mental health condition, comprising: one or more memories; and at least one processor each coupled to at least one of the one or more memories and configured to perform operations comprising: detecting a region of interest in an image frame of a face of a user, wherein the region of interest includes an eye of the user and the image frame is obtained from a video stream; performing blind deconvolution on a portion of the image frame specified by the region of interest, wherein the portion of the image frame satisfies a signal to noise threshold; determining a set of oculometric parameters of the eye of the user using the blind deconvolved portion of the image frame; and determining one or more digital markers of the user based on the set of oculometric parameters, wherein the one or more digital markers are indicative of a neurological condition or a mental health condition of the user. ### Claim 12 (depends on 11) The system of claim 11, wherein the signal to noise threshold comprises a minimum sclera brightness. ### Claim 13 (depends on 11) The system of claim 11, wherein the oculometric parameters comprise a pupil center, iris data, and eyelid data. ### Claim 14 (depends on 11) The system of claim 11, wherein the performing blind deconvolution further comprises: determining a spatial velocity based on a time series of a location of the eye of the user, wherein the time series is indicative of the location of the eye in a plurality of successive eye images obtained from the video stream; and determining a point spread function based on the spatial velocity. ### Claim 15 (depends on 11) The system of claim 11, wherein the operations further comprise: adjusting a size of the region of interest to correct for a motion in a z-direction, wherein the z-direction corresponds to a direction perpendicular to an image sensor, and wherein the video stream is captured by the image sensor. ### Claim 16 (depends on 11) The system of claim 11, wherein the determining the set of oculometric parameters comprises: detecting a plurality of boundaries in the blind deconvolved portion of the image frame based on a change in intensity between data points in the blind deconvolved portion of the image; and identifying, from a plurality of quadratic curves, a quadratic curve that fits an upper eyelid and a lower eyelid based on the plurality of boundaries. ### Claim 17 A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising: detecting a region of interest in an image frame of a face of a user, wherein the region of interest includes an eye of the user and the image frame is obtained from a video stream; performing blind deconvolution on a portion of the image frame specified by the region of interest, wherein the portion of the image frame satisfies a signal to noise threshold; determining a set of oculometric parameters of the eye of the user using the blind deconvolved portion of the image frame; and determining one or more digital markers of the user based on the set of oculometric parameters, wherein the one or more digital markers are indicative of a neurological condition or a mental health condition of the user. ### Claim 18 (depends on 17) The non-transitory computer-readable medium of claim 17, wherein the signal to noise threshold comprises a minimum sclera brightness. ### Claim 19 (depends on 17) The non-transitory computer-readable medium of claim 17, wherein the performing blind deconvolution further comprises: determining a spatial velocity based on a time series of a location of the eye of the user, wherein the time series is indicative of the location of the eye in a plurality of successive eye images obtained from the video stream; and determining a point spread function based on the spatial velocity. ### Claim 20 (depends on 17) The non-transitory computer-readable medium of claim 17, the operations further comprising: adjusting a size of the region of interest to correct for a motion in a z-direction, wherein the z-direction corresponds to a direction perpendicular to an image sensor, and wherein the video stream is captured by the image sensor.