Dry Eye Classification via Corneal Reflection Blurriness Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for classifying dry eye syndrome are invasive and lack objectivity, often relying on staining with fluorescein and subjective interpretation, which can lead to inaccurate classification due to variability in staining methods and examiner interpretation.
Innovation Solution
An ophthalmic apparatus that projects a predetermined pattern onto the cornea, captures reflected images, and uses blurriness information to classify dry eye syndrome through a learning model trained with time-series blurriness data, allowing for non-invasive and objective classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If staining with fluorescein is performed to observe lacrimal fluid layer disruption pattern, then classification of dry eye syndrome can be performed, but the test becomes invasive and subjective interpretation varies by examiner
Solution Approach 1:
The patent replaces the mechanical/staining-based observation method with an optical reflection method. Instead of using fluorescein staining and subjective visual inspection, the system uses a light source to illuminate the corneal surface and captures reflected light patterns to objectively measure lacrimal fluid layer characteristics, eliminating the need for invasive staining while providing quantifiable data for classification
Solution Approach 2:
The patent creates an optical copy/reflection of the corneal surface instead of directly observing the stained cornea. By capturing the reflected light pattern from the corneal surface, the system creates a non-invasive representation of the lacrimal fluid layer state that can be analyzed objectively without altering or irritating the eye
2Object-affected harmful factors
If threshold value is set for destructive region in non-invasive apparatus, then measurement can be performed without staining, but information from regions smaller than threshold is lost and classification accuracy decreases
Solution Approach 1:
The patent changes the measurement parameter from binary threshold-based detection to continuous blurriness value measurement. Instead of using a fixed threshold that discards data below a certain value, the system measures the degree of blurriness at multiple points and uses these continuous values as input to a learning model, allowing detection of subtle changes and small-scale disruptions that would be lost with threshold-based methods
Solution Approach 2:
The patent adds a temporal dimension by repeatedly capturing images and creating time-series data. By measuring blurriness values at multiple time points and using this temporal information in the learning model, the system can detect dynamic changes in the lacrimal fluid layer that static threshold-based methods would miss, thereby improving classification accuracy without requiring invasive staining
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The apparatus enables accurate and objective classification of dry eye syndrome by applying blurriness information to a learning model, improving classification accuracy and providing severity information without the need for invasive staining, thus enhancing diagnostic reliability.
Implementation Method 1
a light-projecting unit (13) that projects a predetermined pattern onto a cornea surface, an image capturing unit (14) that repeatedly captures a reflected image of the pattern reflected off the cornea surface
Data Source
AI summary
Classifying dry eye syndrome using a measurement comprising a light-projecting unit projecting a predetermined pattern onto a cornea surface, an image capturing unit that repeatedly captures a reflected images of the pattern reflected off the cornea surface, an acquiring unit that acquires blurriness information according to a value indicating a blurriness level at a maximum portion of luminance values in a reflected image, for each of the captured multiple reflected images, and a classifying unit that acquires a classification result of a dry eye syndrome by applying multiple pieces of time-series blurriness information acquired by the acquiring unit to a learning model trained using multiple pairs of training input information. Providing a classification result of a dry eye syndrome corresponding to the training input information, and an output unit that outputs the classification result acquired by the classifying unit.