Angiography Side Branch Segmentation for Accurate FFR Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for segmenting side branch vessels in angiography images are inaccurate and time-consuming, leading to errors in fractional flow reserve (FFR) calculations and difficulties in matching endoluminal and angiography images, which limits the application of fusion technologies.
Innovation Solution
A training method for angiography image processing using neural networks to perform local segmentation of side branch vessels, focusing on a specific range from the head end to a segmentation terminal, which includes training data with original angiography images and local segmentation results to enhance accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional fusion technology of endovascular images and coronary angiography is used, then matching accuracy can be improved, but operation complexity and time consumption increase significantly
Solution Approach 1:
The system performs automatic side branch vessel segmentation using neural networks, allowing the system to serve itself without requiring clinician intervention for manual segmentation, thus maintaining high matching accuracy while reducing operational complexity
Solution Approach 2:
Manual mechanical segmentation operations by clinicians are replaced with automated neural network-based image processing, substituting human manual work with an automated computational system that achieves both accuracy and efficiency
2Measurement precision
If traditional fusion technology is used, then matching accuracy can be improved, but time consumption increases
Solution Approach 1:
The neural network model is pre-trained on大量 angiography images to learn side branch vessel segmentation patterns, so that during actual clinical use, the model can quickly segment vessels without requiring time-consuming manual operations, achieving both accuracy and speed
Solution Approach 2:
Time-consuming manual segmentation operations are replaced with automated neural network processing that can rapidly analyze angiography images and identify side branch vessels, significantly reducing time consumption while maintaining matching accuracy
3Productivity
If simple linear descent mode is used for ideal lumen size, then calculation speed is improved, but FFR calculation accuracy deteriorates
Solution Approach 1:
The coronary artery tree is segmented into main branch vessels and side branch vessels using neural network analysis of angiography images. This segmentation allows the system to accurately identify and measure side branch vessels, providing precise input data for FFR calculation while maintaining computational efficiency through automated processing
Data Source
AI summary
A training method and apparatus for angiography image processing and a method and apparatus for automatically processing a vessel image. The training method includes obtaining training data that includes original angiography image data and local segmentation result data of a side branch vessel. The local segmentation result data of the side branch vessel are local segmentation image data of the side branch vessel on a main branch vessel determined from an original angiography image. A neural network is trained according to the obtained training data to make the neural network perform local segmentation on the side branch vessel on the determined main branch vessel in the original angiography image. The training method can obtain the neural network for performing local segmentation on the side branch vessel, thereby realizing improvement of segmentation accuracy while improving segmentation efficiency, and avoiding missing segmentation and wrong segmentation of the side branch vessel.