AI-Guided 3D Coronary Reconstruction for Real-Time PCI Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current coronary artery disease interventions face challenges with 2D imaging systems that lack clear 3D reconstructions, leading to cumbersome material identification and segmentation, which are time-consuming and not suitable for real-time PCI guidance, resulting in non-personalized stent selection and sizing.
Innovation Solution
An AI-based PCI guiding system that integrates multiple imaging modalities to automate 3D modeling, segment materials, and assign properties, enabling real-time balloon pre-dilation, PCI, and post-dilation with personalized stent guidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple software processes and manual processes are used for 2D image segmentation and 3D reconstruction, then material segmentation and 3D modeling can be achieved, but processing time becomes too long (hours) and cannot be used in real-time PCI procedures
Solution Approach 1:
The patent combines multiple separate software processes (2D image segmentation, 3D reconstruction, material classification) into a single integrated AI-based processing pipeline. This consolidation eliminates intermediate file transfers and manual intervention steps, reducing processing time from hours to minutes while maintaining segmentation accuracy through unified model architecture.
Solution Approach 2:
The patent replaces manual mechanical processes (physician manual segmentation and 3D reconstruction operations) with automated AI-based image processing. Deep learning models automatically perform plaque segmentation, calcium detection, and 3D vessel reconstruction, eliminating time-consuming manual operations while improving consistency and accuracy.
2Loss of information
If manual processes are used for 2D image segmentation and 3D reconstruction, then material identification can be performed, but the process is cumbersome and not suitable for real-time PCI guidance
Solution Approach 1:
The AI-based system performs self-service by automatically segmenting plaque materials, classifying calcium deposits, and reconstructing 3D vessel models without requiring manual physician intervention. The system independently completes the entire workflow from 2D image input to 3D material characterization, making the process both complete and operationally simple.
Solution Approach 2:
The system performs preliminary automated segmentation and 3D reconstruction before the PCI procedure begins, preparing personalized anatomical models and material maps in advance. This allows physicians to review pre-processed 3D models and treatment plans without time pressure during the actual procedure, improving both completeness and ease of use.
3Productivity
If general rules are used for PCI planning and stent selection, then procedures can be performed quickly, but personalization and accuracy are compromised
Solution Approach 1:
The patent applies local quality by providing personalized 3D anatomical models and material-specific recommendations for each patient's unique coronary artery geometry and plaque composition. Instead of applying general stent selection rules uniformly, the system tailors treatment plans to local anatomical characteristics, plaque types (calcium, fibrous, lipid), and vessel dimensions, achieving both speed through automation and precision through personalization.
Data Source
AI summary
Systems and methods disclosed herein provide a method for real-time PCI guidance. A method comprises receiving one or more images of a blood vessel from an imaging modality system, the blood vessel having a lumen, a lumen surface, and a wall; building a 3D model of the blood vessel based on the one or more images; segmenting one or more materials between the lumen and the wall of the blood vessel; reconstructing the blood vessel based on the one or more images; assigning material properties to the reconstructed surface of the blood vessel; determining a wall thickness, a plaque thickness, a lumen area, a plaque eccentricity and one or more plaque constituents; guiding an interventional procedure in real-time based on the 3D reconstructed vessel lumen surface and segmented materials; and performing balloon pre-dilation, a percutaneous coronary intervention, and balloon post-dilation with the 3D reconstructed vessel lumen surface and segmented materials.