Automated Vessel Pathology Detection and FFR Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current clinical practices for analyzing artery diseases rely on visual assessment and require heavy user input, leading to slow processing times and the inability to provide immediate, real-time results.
Innovation Solution
A fully automated system for vessel analysis from image data that detects pathologies without user input, tracks them across multiple images, and provides real-time analysis of functional measurements like FFR, using computer vision techniques and virtual marks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If visual assessment and manual marking are used for vessel analysis, then measurement precision can be achieved, but processing time increases and real-time results cannot be provided
Solution Approach 1:
The system performs automated detection of vessel pathologies and functional measurements without requiring manual user input or marking. The computer vision system independently identifies stenoses and calculates FFR values, eliminating the need for health professional intervention in the measurement process itself.
Solution Approach 2:
The patent replaces manual mechanical marking and visual assessment with automated computer vision algorithms. The system uses image processing techniques to automatically detect pathologies and calculate functional measurements, substituting human expertise with computational methods.
2Measurement precision
If 3D model reconstruction is used for functional measurements, then measurement precision improves, but device complexity and memory requirements increase
Solution Approach 1:
The system extracts functional measurement calculations directly from 2D angiogram images without requiring full 3D model reconstruction. By extracting necessary geometric and functional parameters from the 2D images themselves, the system avoids the complexity of 3D modeling while maintaining measurement accuracy.
Solution Approach 2:
Instead of reconstructing complete 3D models, the system performs partial analysis using 2D image data to calculate functional measurements. This partial action approach provides sufficient measurement precision without the excessive complexity of full 3D reconstruction.
3Adaptability or versatility
If manual marking and user input are required, then adaptability to different cases improves, but ease of operation decreases and real-time processing is prevented
Solution Approach 1:
The system automatically adapts to different vessel cases by using computer vision algorithms that can identify pathologies and calculate functional measurements independently. The system self-adjusts to different imaging conditions and vessel geometries without requiring user guidance or input.
4Productivity
If automated detection without tracking is used, then processing speed increases, but measurement precision decreases due to inability to identify same pathology across images
Solution Approach 1:
The system uses virtual marks as feedback mechanisms to track and identify the same pathology across multiple images. The virtual marks provide reference points that enable the system to consistently locate and measure the same stenosis in different angiogram frames, maintaining precision while processing images automatically.
Data Source
AI summary
A system and method for analysis of a vessel automatically detects a pathology in a first image of the vessel and attaches a virtual mark to the pathology in the first image. The system may detect the same pathology in a second image of the vessel, based on the virtual mark, and may then provide analysis (e.g., determine an FFR value) of the pathology based on the pathology detected in the first and second images.