OCT Image Segmentation Using Sector IQC and Anchor Boundaries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current optical coherence tomography (OCT) systems struggle with variability in pediatric eye imaging due to uncooperative patients and varying eye sizes, lacking automated measurement software and age-stratified normative data, which impedes broad adoption in pediatric clinical practice.

Innovation Solution

A method for segmenting images into sectors, applying pre-defined labels, identifying anchor sectors, and using IQC for edge detection and smoothing, along with a system for managing and processing image data, including an image database, visualization module, and automated retinal segmentation algorithms, to create an age-stratified normative database.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual measurement tools are used in pediatric OCT imaging, then flexibility in handling uncooperative patients is maintained, but measurement precision and reliability deteriorate due to variability in eye size and image quality

Engineering Contradiction:

Improveflexibility in handling uncooperative patientsVSAvoidmeasurement precision

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs automated measurements and classifications without requiring manual intervention. The OCT device automatically segments retinal layers, identifies structures, and generates measurements, eliminating the need for manual calibration while maintaining reliability across varying pediatric eye sizes and image qualities.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system dynamically adjusts measurement parameters and classification thresholds based on detected image quality metrics and eye size variations. By changing parameters adaptively rather than using fixed manual settings, the system maintains measurement precision across diverse pediatric patients including uncooperative subjects.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If automated measurement software is implemented, then measurement precision and reliability improve, but device complexity increases

Engineering Contradiction:

Improvemeasurement precisionVSAvoiddevice complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The OCT device integrates multiple functions including imaging, automated segmentation, layer identification, and measurement into a single unified system. This multi-functionality achieves high measurement precision while avoiding the complexity of separate standalone devices by consolidating capabilities within the existing OCT platform.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system replaces manual mechanical measurement processes with automated computational algorithms. By substituting human operators and manual tools with software-based image processing and machine learning algorithms, the system achieves precise measurements without proportionally increasing physical device complexity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If comprehensive image processing and classification algorithms are applied, then quantification reliability improves, but processing time and computational resources increase

Engineering Contradiction:

Improvequantification reliabilityVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary image processing steps such as noise reduction, contrast enhancement, and preliminary segmentation during the image acquisition phase. By preparing images in advance with optimized preprocessing algorithms, the system reduces the computational burden of subsequent complex classification tasks, maintaining reliability while reducing overall processing time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The image processing pipeline is divided into multiple sequential stages including preprocessing, initial segmentation, refinement, and final classification. This segmented approach allows computationally intensive operations to be performed on progressively refined data, reducing total processing time while maintaining quantification reliability through cumulative refinement at each stage.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12530779B2Methods, systems and computer program products for classifying image data for future mining and training

Publication Date: 2026.01.20 TRANSLATIONAL IMAGING INNOVATIONS INC

AI summary

A method for segmenting images is provided including tessellating an image obtained from one of an image database and an imaging system into a plurality of sectors; classifying each of the plurality of sectors by applying one or more pre-defined labels to each of the plurality of sectors, wherein the pre-defined labels indicate at least one of an image quality metric (IQM) and a metric of structure; assigning each of the plurality of classified sectors an Image Quality Classification (IQC); identifying anchor sectors among the plurality of classified sectors, applying filtering and edge detection to identify target boundaries; applying contouring across contiguous sectors and using the assigned IQC as a guide to complete segmentation of an edge between any two identified anchor sectors; and smoothing across segmented regions to increase parametric second-order continuity.