Fundus Vessel Diameter Measurement Using Skeleton Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for measuring blood vessel diameters in fundus images are inaccurate and time-consuming, lacking automation, and do not effectively utilize computer image processing for high accuracy measurements.
Innovation Solution
A method involving fundus image acquisition, blood vessel segmentation, resolution enhancement, extraction of blood vessel skeletons, and calculation of vessel diameters using interpolation algorithms to enhance resolution and improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional measuring methods (projection method, ophthalmoscopic image measuring method) are used by professional oculists with measurement tools, then measurement accuracy is improved, but time consumption increases and automatic batch processing is not achieved
Solution Approach 1:
The patent replaces the mechanical measurement system (physical measurement tools and manual operations by oculists) with an automated image processing system using computer algorithms. The system automatically segments blood vessels from fundus images, extracts skeleton structures, and calculates diameters through computational methods, eliminating the need for manual mechanical measurement while maintaining accuracy.
Solution Approach 2:
The measurement system performs self-service by automatically processing fundus images without requiring professional oculist intervention. The algorithm independently completes vessel segmentation, skeleton extraction, and diameter calculation, enabling automatic batch processing of multiple images while preserving measurement precision through sophisticated image analysis techniques.
2Productivity
If automatic measurement methods (rectangular fitting method, second derivative null point method) are used on fundus images, then time consumption is reduced and automatic processing is achieved, but measurement accuracy deteriorates
Solution Approach 1:
The patent applies segmentation by dividing the blood vessel measurement process into distinct stages: vessel segmentation from the fundus image, skeleton extraction from the segmented vessels, and diameter calculation from the skeleton. This multi-stage segmentation approach enables automatic processing while maintaining accuracy by optimizing each stage independently with specialized algorithms.
Solution Approach 2:
The patent transitions from two-dimensional image space to one-dimensional skeleton space for measurement. By extracting the centerline skeleton of blood vessels and measuring diameters perpendicular to the skeleton at multiple points, the system achieves both automatic processing efficiency and high measurement accuracy through this dimensional transformation.
3Speed
If simple automatic measurement algorithms are applied to fundus images, then processing speed is improved, but measurement accuracy and resolution are insufficient
Solution Approach 1:
The patent performs preliminary action by conducting blood vessel segmentation and skeleton extraction before the actual diameter measurement. This preprocessing creates an optimized representation of the vessels in skeleton form, which enables faster and more accurate subsequent measurement operations while maintaining high resolution through careful skeleton construction.
Data Source
AI summary
Some embodiments of the disclosure provide a measuring method and measuring apparatus of a blood vessel diameter of a fundus image. In some examples, the measuring method include the following steps: acquiring a fundus image, generating a blood vessel segmentation image based on the fundus image, performing resolution enhancement on the blood vessel segmentation image, extracting blood vessel skeletons from the enhanced blood vessel segmentation image and performing fitting on the blood vessel skeletons to obtain a continuous blood vessel skeleton and a vessel diameter measurement direction of measurement pixel points, generating a blood vessel contour corresponding to the measurement pixel points based on the enhanced blood vessel segmentation image, and calculating a blood vessel diameter corresponding to the measurement pixel points based on a number of blood vessel pixel points in the blood vessel contour.