Automated Coronary Stenting Planning via Hemodynamic Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for treating arterial stenosis lack effective decision support for selecting which stenoses to stent based on medical image data, as they do not provide comprehensive and automated analysis of hemodynamic changes post-stenting, leading to suboptimal treatment planning.
Innovation Solution
A method and system that acquire medical image data, segment coronary arteries, compute hemodynamic quantities using computational techniques, and generate treatment options with predicted outcomes to support clinical decision-making, including the use of fractional flow reserve (FFR) calculations and multi-scale computational models for blood flow simulation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If comprehensive hemodynamic analysis is performed for all possible stenting configurations, then treatment planning accuracy is improved, but computational time and complexity increase
Solution Approach 1:
The system performs preliminary segmentation of medical images and extraction of coronary artery geometry before treatment planning. By pre-processing the anatomical data and creating a digital twin of the patient's coronary tree, the system prepares the computational model in advance, enabling faster evaluation of multiple stenting configurations without repeating the full image analysis for each scenario.
Solution Approach 2:
The system segments the coronary artery tree into discrete vessel segments and identifies individual stenoses as separate entities. This segmentation allows the treatment planning algorithm to evaluate stenting options at the segment level, combining segments to form different treatment configurations. The segmented model enables systematic exploration of treatment options while avoiding redundant computations across overlapping configurations.
2Reliability
If multiple treatment options are evaluated with detailed hemodynamic simulation, then decision support quality is improved, but device complexity increases
Solution Approach 1:
The system introduces a digital twin (virtual model) of the patient's coronary artery tree as an intermediary between the physical anatomy and the treatment evaluation process. This digital twin incorporates patient-specific geometry, stenosis characteristics, and hemodynamic properties, serving as a computational proxy that enables detailed simulation without requiring direct manipulation of the patient's actual anatomy. The digital twin mediates between complex physiological reality and simplified treatment modeling.
3Measurement precision
If patient-specific anatomical models are extracted and used for simulation, then measurement precision is improved, but loss of time in data processing increases
Solution Approach 1:
The system performs preliminary extraction and processing of patient-specific anatomical models from medical images before the treatment planning phase. By completing the image segmentation, vessel centerline extraction, and 3D reconstruction in advance, the system creates a ready-to-use digital anatomical model that can be rapidly queried during treatment evaluation without repeating the time-consuming image processing steps for each treatment scenario.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method and system for automated decision support for treatment planning of arterial stenoses is disclosed. A set of stenotic lesions is identified in a patient's coronary arteries from medical image data of the patient. A plurality of treatment options are generated for the set of stenotic lesions, wherein each of the plurality of treatment options corresponds to a stenting configuration in which one or more of the stenotic lesions are stented. For each of the plurality of treatment options, predicted hemodynamic metrics for the set of stenotic lesions resulting from the stenting configuration corresponding to that treatment option are calculated.