Spectrally adjustable ocular photosensitivity analyzer
Inventors
PAREL, Jean Marie • ROWAAN, Cornelis • Gonzalez, Alex • SILGADO, Juan • AGUILAR, Mariela C. • CHANG, Yu-Cherng Channing
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Assignees
MemberUniversity of MiamiUniversity of MiamiThe University of Miami, established in 1925 and based in Coral Gables, Florida, is a private research university recognized for its comprehensive academic offerings, robust research infrastructure, and strong interdisciplinary focus. Home to more than 19,000 students and with more than 400 acres of campuses across the Miami region, its mission encompasses education, research, innovation, and community service. The institution supports clinical, biomedical, marine, and atmospheric research initiatives, delivers diverse undergraduate and graduate programs, and maintains numerous research centers and institutes dedicated to scientific, medical, and societal advancements.
The University of Miami, established in 1925 and based in Coral Gables, Florida, is a private research university recognized for its comprehensive academic offerings, robust research infrastructure, and strong interdisciplinary focus. Home to more than 19,000 students and with more than 400 acres of campuses across the Miami region, its mission encompasses education, research, innovation, and community service. The institution supports clinical, biomedical, marine, and atmospheric research initiatives, delivers diverse undergraduate and graduate programs, and maintains numerous research centers and institutes dedicated to scientific, medical, and societal advancements.
Publication Number
US-12484774-B2
Publication Date
2025-12-02
Expiration Date
Abstract
Ocular photosensitivity analyzer. In an embodiment, a programmable light source, comprising a plurality of multi-spectra light modules, is configured to emit light according to a lighting condition. For one or a plurality of iterations, the programmable light source is activated to emit the light according to the lighting condition, and collect a response, by a subject, to the emitted light via a sensing system comprising one or more sensors. Between iterations, the programmable light source may be reconfigured based on the response to determine a visual photosensitivity threshold of the subject.
Core Innovation
The invention provides an ocular photosensitivity analyzer that includes at least one hardware processor, a programmable light source with a plurality of multi-spectra light modules configured to emit light at a range of wavelengths, and a sensing system with one or more sensors. The software modules receive an indication of a lighting condition comprising one or more wavelengths of light and configure the programmable light source to emit light according to the lighting condition. For each of one or more iterations, the analyzer activates the programmable light source to emit the light according to the lighting condition and collects a response, by a subject, to the emitted light via the sensing system.
After collecting the response, the analyzer analyzes the response to determine whether or not the response represents discomfort or pain. The analyzing comprises applying a machine-learning algorithm that is trained to classify responses according to a plurality of classes, where the plurality of classes comprises one or both of a class representing discomfort or a class representing pain. In related implementations, the analyzer further analyzes and uses a stimuli algorithm to reconfigure the programmable light source based on the analysis while iteratively activating the light source and collecting responses.
The analyzer can determine a visual photosensitivity threshold based on the analysis in at least a last one of the plurality of iterations. The stimuli algorithm can implement a staircase in which reconfiguring the programmable light source comprises adjusting an intensity of the light to be emitted by a step size from the intensity of the light most recently emitted by the programmable light source. The stimuli algorithm can further adjust the step size based on the collected responses, and additional implementations include reconfiguring the programmable light source to emit light at a higher intensity and adding a new iteration when the response does not represent discomfort or pain.
Claims Coverage
The partial content provides multiple independent claims: clm-00001, clm-00006, clm-00010, clm-00013, clm-00015, clm-00016, and clm-00018. Across these independent claims, the core inventive coverage repeatedly includes a programmable multi-spectra light source configured by a received lighting condition, iterative activation with sensor-based response collection, and analysis of responses for discomfort and/or pain using a trained machine-learning classifier, with additional independent claims adding specific sensing, positioning, environmental control, and stimuli algorithms for determining visual photosensitivity threshold.
Multi-spectra programmable light source with machine-learning discomfort/pain classification
The analyzer receives an indication of a lighting condition comprising one or more wavelengths of light, configures the programmable light source to emit light according to the lighting condition, activates the programmable light source for each of one or more iterations, collects a response via the sensing system, and after collecting the response analyzes the response to determine whether or not the response represents discomfort or pain by applying a machine-learning algorithm trained to classify responses into a plurality of classes comprising one or both of a class representing discomfort or a class representing pain.
Three-camera sensing of face, right eye, and left eye
The sensing system comprises at least three high-definition cameras including a first high-definition camera configured to capture images of a face of a subject, a second high-definition camera configured to capture images of a right eye of the subject, and a third high-definition camera configured to capture images of a left eye of the subject; for each of one or more iterations the analyzer activates the programmable light source and collects a response by receiving the images captured by the at least three high-definition cameras during a time period that includes or follows a time at which the programmable light source was activated.
Escalation by reconfiguring to higher intensity when response is not discomfort or pain
For each of one or more iterations the analyzer activates the programmable light source to emit the light and collects a response via the sensing system, and when determining that the response does not represent discomfort or pain it reconfigures the programmable light source to emit the light at a higher intensity and adds a new iteration to the one or more iterations.
Staircase stimuli algorithm with step size adjustment and determination of visual photosensitivity threshold
After collecting the response, the analyzer analyzes the response and reconfigures the programmable light source based on the analysis and a stimuli algorithm implementing a staircase such that in each of the plurality of iterations reconfiguring comprises adjusting an intensity of the light to be emitted by a step size from the intensity of the light most recently emitted, wherein the stimuli algorithm comprises adjusting the step size based on the collected responses, and determining a visual photosensitivity threshold of the subject based on the analysis in at least a last one of the plurality of iterations.
Motorized chin/forehead positioning with real-time region-of-interest centering
A positioning system comprising one or both of a chin rest and a forehead rest is positioned relative to the programmable light source to seat a head of a subject such that each eye of the subject is positioned at a focal point of the programmable light source, and wherein the positioning system is motorized; the analyzer in real time analyzes images captured by at least one camera to detect a region of interest of the subject and controls one or more motors of the positioning system to center the region of interest within the images, and then receives an indication of a lighting condition to configure and activate the programmable light source for one or more iterations and collect a response via the sensing system.
Graphical user interface controlling ambient illumination within an indicated illumination range
The analyzer includes an interface with an environmental system comprising one or more ambient light sources, wherein the software receives an indication of one of a plurality of illumination ranges via a graphical user interface, controls the one or more ambient light sources via the interface to maintain ambient illumination from the one or more ambient light sources within the indicated illumination range, and receives an indication of a lighting condition comprising one or more wavelengths of light to configure and activate the programmable light source for each of one or more iterations and collect a response via the sensing system.
Method: iterative activation, response collection, and machine-learning discomfort/pain classification
In a method, the analyzer receives an indication of a lighting condition comprising one or more wavelengths of light, configures the programmable light source to emit light according to the lighting condition, for each of one or more iterations activates the programmable light source and collects a response via the sensing system, and after collecting the response analyzes the response to determine whether or not the response represents discomfort or pain by applying a machine-learning algorithm trained to classify responses into a plurality of classes comprising one or both of a class representing discomfort or a class representing pain.
The claim coverage centers on an ocular photosensitivity analyzer that uses a programmable multi-spectra light source configured by a received wavelength lighting condition, iteratively activates the light source and collects subject responses via sensors, and analyzes responses for discomfort and/or pain using a trained machine-learning classifier. Additional independent claims further specify camera-based sensing for face/right eye/left eye, escalation to higher intensity by adding iterations when responses are not discomfort or pain, a staircase stimuli algorithm with step-size adjustment and determination of a visual photosensitivity threshold, motorized chin/forehead positioning with real-time region-of-interest centering, graphical user interface control of ambient illumination within an indicated illumination range, and a corresponding method implementation.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?