Multimodal Ocular Imaging for AMD Progression Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current imaging technologies are inadequate for accurately diagnosing, staging, and predicting the progression of blinding eye diseases like Age Related Macular Degeneration (AMD), as they fail to characterize disease features using image-based biomarkers, leading to limitations in clinical trial design and treatment efficacy assessment.

Innovation Solution

A computing system that integrates multiple ocular imaging modalities, including DNIRA, IR, and functional tests, for comprehensive image analysis and processing, enabling quantitative and qualitative classification of disease features and predicting disease progression through pattern recognition and machine learning algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple imaging modalities are integrated for comprehensive disease characterization, then diagnostic accuracy and disease prediction capability are improved, but system complexity and computational requirements increase

Engineering Contradiction:
Improvedisease characterization accuracyVSAvoidimaging system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the comprehensive imaging analysis into distinct functional modules: image acquisition for multiple modalities, image processing for normalization and registration, feature extraction for quantitative and qualitative characteristics, and classification/prediction using machine learning models. This modular segmentation allows each component to be optimized independently while working together to achieve comprehensive disease characterization.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The computing system is designed as a universal platform that can process multiple imaging modalities (fundus photography, OCT, FAF, FLA, etc.) through a single integrated architecture. The system performs multiple functions including diagnostic classification, disease progression prediction, and biomarker identification using the same core processing pipeline, eliminating the need for separate specialized systems for each imaging type.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If image-based biomarkers are used for early disease detection and prediction, then clinical trial design and treatment evaluation are improved, but current imaging technologies fail to adequately characterize disease features

Engineering Contradiction:
Improvedisease prediction reliabilityVSAvoiddisease feature characterization
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The system transitions from traditional 2D image analysis to multi-dimensional characterization by extracting quantitative features (area, volume, density), qualitative phenotypic characteristics (texture, pattern recognition), and temporal dynamics (progression rates). This dimensional expansion enables comprehensive disease feature characterization that captures both structural and functional aspects, improving prediction reliability for early disease detection.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system introduces computational algorithms and machine learning models as intermediaries between raw imaging data and clinical interpretation. These intermediaries process multiple imaging modalities, extract meaningful biomarkers, and generate predictions that bridge the gap between imaging capabilities and clinical needs, enabling reliable disease characterization that current technologies cannot achieve alone.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If functional imaging methods relying on normal tissue physiology are developed, then biomarker reliability is improved, but functional tests are time-consuming and unreliable due to variable effort and cognitive capacity

Engineering Contradiction:
Improvebiomarker reliabilityVSAvoidtesting time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system replaces manual functional testing with automated image processing and analysis. Instead of relying on patient-performed functional tests that vary with cognitive capacity and effort, the system uses computational algorithms to automatically extract biomarkers from imaging data, eliminating human performance variability and reducing testing time while improving biomarker reliability.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3956813B1Detection, prediction, and classification for ocular disease
Publication Date: 2025.11.26 TRACERY OPHTHALMICS INC
  • EP3956813B1 patent drawingFigure 1
  • EP3956813B1 patent drawingFigure 2
  • EP3956813B1 patent drawingFigure 3

AI summary

Computer systems and computer-implemented methods for performing classification, detection, and/or prediction based on processing of ocular images obtained from various imaging modalities are disclosed. Use of delayed near-infrared analysis (DNIRA) as one of the imaging modality is also disclosed.