Clustering Algorithm for Lower Limb Vascular Calcification Index Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing lower limb vascular calcification indexes in diabetic patients are inadequate, as they lack accuracy and are prone to human error, particularly in diagnosing severe vascular lesions which can lead to amputation.
Innovation Solution
A clustering algorithm-based multi-parameter cumulative calculation method that processes CT images of lower limb blood vessels, using super-pixel segmentation, brightness characteristic values, and cumulative correction coefficients to quantify calcification degrees, reducing errors and providing a data basis for amputation risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If CT image technology is used to assess lower limb vascular calcification, then diagnostic coverage and visibility of deep blood vessels are improved, but human factors affect judgment results and measurement precision deteriorates
Solution Approach 1:
The patent replaces manual visual assessment (mechanical/human system) with automated image processing algorithms. The clustering algorithm automatically segments calcified plaques from CT images, calculating their area, density, and distribution without human intervention, thereby eliminating human factor variability while maintaining comprehensive diagnostic coverage
Solution Approach 2:
The system enables self-service assessment by allowing the CT imaging system and processing software to automatically generate calcification indexes without requiring clinician interpretation. The algorithm independently processes images, segments regions of interest, and produces quantitative results, making the diagnostic process self-sufficient and objective
2Device complexity
If manual assessment of CT images is used, then device complexity is reduced, but productivity and measurement precision deteriorate due to human error
Solution Approach 1:
The patent introduces an intermediary computational layer between CT image acquisition and clinical interpretation. The clustering algorithm acts as a mediator that automatically processes raw images, extracts calcification features, and generates standardized indexes, thereby improving productivity and precision without significantly increasing overall system complexity
Solution Approach 2:
The assessment process is segmented into distinct automated steps: image preprocessing, calcified plaque segmentation using clustering algorithms, feature extraction (area, density, distribution), and index calculation. This segmentation enables efficient automated processing while keeping each module relatively simple and interpretable
3Ease of operation
If conventional assessment methods are used, then ease of operation is improved, but reliability and measurement precision worsen due to inability to quantify calcification degree
Solution Approach 1:
The patent transforms qualitative visual assessment into quantitative measurement by calculating specific parameters: calcified plaque area (mm²), mean density (HU), distribution patterns, and composite indexes. These numerical parameters provide reliable, objective data for risk assessment while maintaining ease of operation through automated calculation
Solution Approach 2:
The system replaces subjective clinical judgment with objective algorithmic calculation. The clustering algorithm consistently applies the same segmentation and measurement criteria to all images, eliminating variability between different clinicians and improving diagnostic reliability through standardized quantitative assessment
Data Source
AI summary
The present invention discloses a clustering algorithm-based multi-parameter cumulative calculation method for lower limb vascular calcification indexes, including the following steps: firstly carrying out super-pixel segmentation of a CT image, and enabling calcified spots in the CT image to be segmented in each super-pixel region; after the super-pixel segmentation is accomplished, extracting a brightness characteristic value of a super-pixel region where the calcified spots are located by using a Lab color space, and performing edge detection and contour extraction on the calcified spots in the image; and after edge detection and contour extraction, fitting the calcified spots in the image by using a segmented ellipse, and extracting the area of the calcified spots after optimizing an ellipse contour.