Automated Retinal Vessel Segmentation for AVR Measurement

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual determination of the arteriolar-to-venular diameter ratio (AVR) in retinal blood vessels is time-consuming and imprecise, limiting its use in predicting cardiovascular events and other medical conditions.

Innovation Solution

An automated method for determining AVR by detecting the optic disc, segmenting vessels, classifying them as arteries or veins, and calculating the ratio using a combination of image processing techniques such as skeletonization, feature extraction, and iterative algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual determination of AVR is performed by experts, then measurement precision is improved, but productivity deteriorates due to time-consuming process

Engineering Contradiction:

ImproveAVR measurement precisionVSAvoidAVR determination speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the manual mechanical measurement process with an automated image processing system using computer algorithms. The system applies skeletonization to reduce vessels to centerlines, uses iterative algorithms to match artery-vein pairs, and automatically calculates AVR ratios, eliminating the need for manual expert measurement while maintaining accuracy through computational methods.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing automated AVR determination without requiring expert intervention. The algorithm independently performs vessel segmentation, classification, pairing, and ratio calculation, making the measurement process autonomous and eliminating dependency on manual expert analysis.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If manual AVR determination is performed, then measurement precision is improved, but loss of time increases due to expert requirement

Engineering Contradiction:

ImproveAVR measurement precisionVSAvoidTime for AVR determination

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces time-consuming manual expert measurement with automated computational algorithms that process images rapidly. The system uses computer-based skeletonization, iterative matching algorithms, and automated calculation to determine AVR ratios in minutes rather than hours, dramatically reducing time loss while preserving measurement precision through systematic computational approaches.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs preliminary actions by pre-processing images through skeletonization and vessel segmentation before the actual measurement. These preparatory computational steps organize the data structure in advance, enabling rapid subsequent pairing and ratio calculation, thereby reducing overall time loss while ensuring precise measurements.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If automated method is used for AVR determination, then productivity is improved, but measurement precision may deteriorate

Engineering Contradiction:

ImproveAVR determination speedVSAvoidAVR measurement precision

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent employs sophisticated computational algorithms including skeletonization to extract vessel centerlines, iterative algorithms to match artery-vein pairs based on anatomical relationships, and automated width measurements. These computational methods maintain measurement precision by systematically analyzing image data with consistent mathematical operations, eliminating human variability while preserving accuracy through algorithmic rigor.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system incorporates feedback mechanisms through iterative algorithms that continuously refine artery-vein pairings based on measured characteristics. The algorithm adjusts and re-evaluates pairings to ensure anatomical correctness, providing self-correction that maintains measurement precision while enabling rapid automated processing of multiple images.

Inventive Principle:

Principle #23Feedback

4Ease of operation

If automated vessel segmentation and classification is performed, then ease of operation is improved, but device complexity increases

Engineering Contradiction:

ImproveAVR determination easeVSAvoidImage processing system complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing the complex image processing task into distinct modules: skeletonization to extract centerlines, iterative algorithms for vessel pairing, width measurement functions, and ratio calculation. This modular segmentation simplifies operation by automating each step while managing system complexity through organized functional decomposition, making the overall system easier to operate despite the sophisticated processing required.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250318726A1Automated determination of arteriovenous ratio in images of blood vessels

Publication Date: 2025.10.16 THE UNIVERSITY OF IOWA RESEARCH

AI summary

The methods and systems provided can automatically determine an Arteriolar-to-Venular diameter Ratio, AVR, in blood vessels, such as retinal blood vessels and other blood vessels in vertebrates. The AVR is an important predictor of increases in the risk for stroke, cerebral atrophy, cognitive decline. and myocardial infarct.