Eye Disease Probability Assessment Using Weighted Feature Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing diseases using eye imaging, such as iridology, are not efficient enough for early detection and often require expensive equipment, limiting their accessibility and accuracy.
Innovation Solution
A computer-implemented method that identifies multiple eye features and their associated elements in images, using machine learning models to determine a quantitative value for each element's significance and position, calculating a weighted sum to assess the probability of disease presence, which can be done without contact and using low-cost devices like smartphones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional iridology methods are used for disease diagnosis, then equipment cost is reduced, but measurement precision and reliability are insufficient
Solution Approach 1:
The patent replaces traditional mechanical/optical imaging equipment with a digital image processing system that uses standard cameras or smartphones. The mechanical system for capturing and analyzing eye images is substituted with a computational system that processes digital images through machine learning algorithms, achieving high precision without complex specialized equipment.
Solution Approach 2:
The patent transforms the diagnosis approach by changing from qualitative visual assessment to quantitative analysis. Multiple features are assigned numerical values and weights, and the final disease probability is calculated through mathematical computation of these weighted features, enabling precise measurement without complex equipment.
2Measurement precision
If multiple features and elements are analyzed, then measurement precision improves, but computational complexity increases
Solution Approach 1:
The patent segments the eye image analysis into multiple independent features (color, texture, shape, position) and further divides each feature into specific elements. This segmentation allows the complex analysis task to be broken down into manageable components, each processed separately and then combined through weighted summation, improving precision while keeping computational complexity manageable.
Solution Approach 2:
The patent analyzes more features and elements than traditionally required (excessive action), assigning weights to multiple eye features including color, texture, shape, and position. This comprehensive analysis improves measurement precision by considering more diagnostic indicators, while the weighted scoring system efficiently manages the computational complexity.
3Reliability
If early disease detection is prioritized, then reliability improves, but false positives increase
Solution Approach 1:
The patent implements a feedback mechanism through the weighted feature analysis system. Multiple eye features are evaluated and combined, with the system able to adjust weights based on the significance of different features for specific diseases. This feedback loop allows the system to distinguish between early disease signs and normal variations, improving reliability while reducing false positives through iterative refinement of the diagnostic criteria.
Data Source
AI summary
The present disclosure relates to a computer implemented method (400) for determining a probability of a disease in at least one image representative of an eye. The method (400) comprising: identifying (S102) two or more eye features in the at least one image, for each identified feature, identifying (S104) at least one element associated with the identified feature, for the at least one element of each identified feature, determining (S106) a quantitative value indicative of the at least one elements significance for the disease, determining (S108) a position of the at least one element of each identified feature, determining (S110) the probability of the disease based on the quantitative values and position of the at least one element for each identified feature.