Objective Visual Photosensitivity Threshold Measurement Using Pupil Responses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for measuring visual photosensitivity discomfort threshold (VPT) are subjective and lack repeatability due to variations in refractive error, pupil response, and blinking, leading to inconsistent results.
Innovation Solution
A deep learning system that utilizes neural networks to analyze pupil and palpebral fissure contours in response to varying light stimuli, expressing VPT in terms of retinal illuminance and incorporating facial expression detection to improve measurement accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional subjective VPT measurement methods are used, then the measurement can be performed with simple equipment, but the measurement lacks repeatability and objectivity
Solution Approach 1:
The patent replaces subjective mechanical measurement methods with an automated image processing system that uses neural networks to analyze pupil responses and facial expressions. This substitution of manual/subjective evaluation with automated computational analysis directly improves measurement repeatability while managing system complexity through algorithmic automation.
Solution Approach 2:
The system uses the subject's own physiological responses (pupil dilation, facial expressions) as the measurement criterion, eliminating the need for external subjective reporting. The subject's biological responses automatically provide the measurement data, improving objectivity and repeatability without requiring complex external evaluation mechanisms.
2Measurement precision
If VPT is measured based on stimulus illuminance, then the measurement is simple to implement, but it fails to account for individual variations in refractive error and pupil response
Solution Approach 1:
The patent transforms the measurement parameter from stimulus illuminance to retinal illuminance by incorporating pupil diameter and facial expression data. This parameter transformation allows the system to account for individual variations in refractive error and pupil response, improving measurement precision while managing complexity through computational modeling.
Solution Approach 2:
The system introduces pupil diameter and facial expression as intermediary parameters that mediate between stimulus illuminance and actual retinal illuminance. These intermediary measurements allow the system to compensate for individual variations in eye optics and response, improving accuracy without requiring direct measurement of retinal illuminance.
3Reliability
If facial expression detection is added to improve measurement repeatability, then measurement objectivity improves, but the system complexity increases
Solution Approach 1:
The neural network system performs multiple functions simultaneously: it detects pupil contours, measures pupil diameter, identifies facial expressions, and calculates retinal illuminance. This multi-functionality approach improves measurement repeatability through comprehensive data collection while managing complexity by consolidating multiple processing tasks into a single integrated system.
Data Source
AI summary
Method to measure a visual photosensitivity discomfort threshold or presence of a condition associated therewith within a subject, includes obtaining, by one or more processors, a plurality of images of the subject captured while the at least one pupil and corresponding palpebral fissure contour was being subjected to a light stimuli; determining, by the one or more processors, executing instructions for a neural network having been trained using a plurality of images of a plurality of subjects captured at a plurality of different illumination levels, an output value corresponding to a measure of visual photosensitivity discomfort threshold in which the visual photosensitivity discomfort threshold is defined by an estimated illuminance of the retina of the subject, and outputting, by the one or more processors, the output value in a report.