3D Vascular Image Analysis via Segmentation and Parametric Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing 3D angiography images of blood vessels are limited in effectively isolating and quantifying diseases like aneurysms and stenosis, requiring significant manual interaction and providing only a limited number of quantitative measures, which hinders accurate diagnosis and treatment planning.
Innovation Solution
A method involving computer-assisted modeling of blood vessels in 3D images by isolating segments, mapping them onto standardized parametric spaces, and generating mapped representations using homeomorphic functions to facilitate automatic extraction of centerlines and analysis of vessel morphology.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual interaction is used to isolate aneurysms and stenosis, then accuracy of disease isolation is improved, but processing time and complexity increase
Solution Approach 1:
The blood vessel is segmented into multiple sections along its centerline, with each section independently analyzed for disease presence. This allows automated processing of each segment while maintaining the ability to detect diseases like aneurysms and stenosis at specific locations along the vessel.
Solution Approach 2:
A machine learning-based automated detection system serves as an intermediary between the 3D angiography images and the disease isolation process. The system uses trained models to automatically identify and isolate diseased segments without requiring manual intervention, thereby reducing processing time while maintaining accuracy.
2Productivity
If automated centerline extraction is used, then processing speed is improved, but the number of quantitative measures available is limited
Solution Approach 1:
The blood vessel is divided into multiple sections along its centerline, allowing automated extraction of quantitative measures for each segment. This segmentation enables comprehensive analysis including diameter profiles, volume calculations, and disease severity assessments across multiple parameters simultaneously.
Solution Approach 2:
The system extracts multiple quantitative parameters from the 3D angiography images, including vessel diameter, volume, surface area, and disease severity metrics. By changing and analyzing multiple parameters across different vessel sections, the system provides rich quantitative data while maintaining automated processing speed.
3Ease of manufacture
If idealized tubular models are used for analysis, then simplicity of analysis is improved, but accuracy in isolating complex diseases like aneurysms decreases
Solution Approach 1:
The blood vessel is segmented into multiple sections along its centerline, with each section analyzed using appropriate models. This allows simple tubular models to be used for normal sections while enabling complex disease isolation in specific segments where aneurysms or stenosis are detected, thereby maintaining both simplicity and accuracy.
Solution Approach 2:
Different analysis approaches are applied to different sections of the blood vessel based on their characteristics. Normal sections are analyzed using simple tubular models, while sections showing signs of aneurysms or stenosis are analyzed using more complex methods, allowing the system to adapt its complexity locally to match the actual vessel morphology.
Data Source
AI summary
A method (100) of processing clinical 3D imaging of blood vessels in order to enable an analysis of the shape of blood vessels of a person, a statistical analysis of the shape and properties of blood vessels in a group of individuals, and the detection and quantification of blood vessel diseases.