Vascular Lesion Detection Using Trendlines and Reference Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting calcified lesions in vascular imaging, such as X-ray angiography, lack the ability to accurately identify and quantify multiple lesions and require manual analysis, which can be challenging for analysts without medical experience.
Innovation Solution
An electronic device that automates the segmentation and quantitative analysis of vascular images by calculating trendlines from medical images, identifying lesion candidates, and determining lesion sites using reference points and regression analysis to enhance detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual analysis of vascular images is performed, then flexibility and adaptability are maintained, but analysis time and complexity increase significantly
Solution Approach 1:
The automated analysis system segments the vascular image into multiple vessel segments based on centerline extraction and branching points. Each segment is independently analyzed for lesion detection, allowing parallel processing and reducing overall analysis time while maintaining systematic complexity management through modular segmentation.
Solution Approach 2:
The system performs preliminary actions by pre-processing the vascular image to extract the centerline, identify branching points, and segment vessels before actual lesion detection. This preliminary structuring enables faster subsequent analysis and reduces the complexity of the main detection task by organizing data in advance.
2Loss of time
If automated lesion detection is implemented, then analysis time is reduced, but measurement precision may be compromised
Solution Approach 1:
The system implements feedback mechanisms by comparing detected lesion candidates against multiple criteria including diameter reduction thresholds, trendline deviations, and reference point comparisons. This multi-layered verification provides feedback loops that refine detection accuracy while maintaining automated processing speed.
Solution Approach 2:
The system changes and compares multiple parameters simultaneously - vessel diameter, diameter reduction ratio, trendline slope, and position relative to reference points. By monitoring multiple parameters rather than a single metric, the system achieves both speed and precision in automated lesion detection.
3Loss of information
If multiple lesions are detected and visualized, then diagnostic completeness is improved, but image complexity and difficulty of interpretation increase
Solution Approach 1:
The system adds another dimension to the visualization by overlaying trendlines that show diameter changes along the vessel length. This dimensional addition allows multiple lesions to be visualized simultaneously with their severity and position clearly indicated, improving diagnostic completeness without overwhelming the viewer with raw data.
Solution Approach 2:
The system uses color coding to differentiate between normal vessels, lesion candidates, and confirmed lesions. This visual encoding allows multiple lesions to be quickly identified and distinguished by color rather than requiring detailed analysis of each individual marker, reducing interpretation complexity while maintaining information completeness.
Data Source
AI summary
An electronic device according to one embodiment can acquire a first trendline related to vessels from a medical image; determine lesion candidates among the vessels on the basis of the first trendline; acquire a second trendline on the basis of a reference point selected in the vicinity of the lesion candidates; and determine a lesion site among the lesion candidates on the basis of the acquired second trendline.