Retinal Vessel Width Ratio for Hypertension Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining hypertension from retinal images face challenges due to the variability of retinal vasculature and the need to estimate the diameter of the hidden central retinal vasculature, leading to potential inaccuracies in hypertension detection.
Innovation Solution
A computer-implemented method that processes retinal images by identifying vessel segments, determining their widths, and calculating vascular summary metrics such as average or median widths, allowing for the direct prediction of hypertension levels without relying on estimates of the hidden central retinal vasculature.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the diameter of the hidden central retinal vasculature is estimated using the Knudtson method, then a metric for hypertension detection can be obtained, but measurement precision deteriorates due to reliance on empirical branching coefficients and arbitrary pairing assumptions
Solution Approach 1:
The patent extracts and eliminates the problematic intermediate estimation step of calculating central retinal vasculature diameter. Instead of estimating CRV diameter using empirical branching coefficients and arbitrary vessel pairing, the method directly measures visible retinal vessel widths and uses their ratio as the hypertension metric, thereby removing the source of measurement imprecision while simplifying the overall measurement approach
Solution Approach 2:
The patent inverts the traditional measurement approach by not trying to infer the hidden central retinal vasculature diameter from branch point relationships. Instead, it directly uses the visible retinal vessels and their width ratios as the primary metric, reversing the logical direction from estimation-based to observation-based measurement
2Reliability
If retinal images are processed to detect hypertension using visible vasculature, then non-invasive examination is enabled, but reliability deteriorates due to high variability of retinal vasculature between individuals
Solution Approach 1:
The patent applies local quality by focusing measurement on specific retinal vessel segments rather than attempting to account for all variations across the entire retinal vasculature. By selecting and measuring particular vessel segments and calculating their width ratios, the method achieves reliable hypertension detection without needing to adapt to all individual variations in retinal vascular architecture
Solution Approach 2:
The patent changes the measurement parameter from absolute vessel diameter (which varies between individuals) to the ratio of arterial to venular width (which remains relatively stable across individuals). This parameter transformation eliminates the reliability issue caused by inter-individual variability in retinal vasculature
Data Source
AI summary
A computer-implemented method, system, and computer-readable medium, for determining a level of hypertension of a person. Image data defining a retinal image of a retina of the person that has been captured by a retinal imaging system is acquired. Processing the image data is performed to identify a plurality of vessel segments present in the retinal image. Determining is performed of respective widths of vessel segments of at least a subset of the plurality of vessel segments present in the retinal image. Calculating, as a vascular summary metric, at least one average value or median value of the determined widths of the vessel segments present in the retinal image, is performed to determine a level of hypertension by which the person has been affected.