Endovascular Implant Deployment Simulation for Hemodynamic Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Clinicians face challenges in selecting and optimizing endovascular implants for treating pathologies like aneurysms due to the complexity of available options and the need to consider multiple factors, including device type, placement, and hemodynamic parameters, often requiring multiple devices with varying configurations.
Innovation Solution
A physics-based model simulates endovascular implant deployment in a patient's vessel using medical imaging data, incorporating machine learning to predict outcomes and optimize implant selection and placement, accounting for patient-specific information and hemodynamic parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a complete explicit representation of the mesh and the Finite Element Analysis method is used, then the accuracy of implant deployment simulation is improved, but the computational cost increases significantly
Solution Approach 1:
The patent changes the mathematical parameters and approximation methods used in the simulation. Instead of using complete explicit representations and full Finite Element Analysis, the system employs simplified geometric models, implicit representations, and reduced-order modeling techniques that maintain sufficient accuracy while dramatically reducing computational requirements.
Solution Approach 2:
The patent extracts and removes unnecessary computational complexity from the simulation process. By separating essential physical principles from redundant mathematical computations, the system retains the core functionality of implant deployment simulation while eliminating the computationally expensive complete explicit representation and full FEA methodology.
2Adaptability or versatility
If multiple flow diverters with varying configurations are considered, then the treatment options for aneurysms increase, but the decision-making complexity increases
Solution Approach 1:
The patent creates virtual copies and simulations of different implant configurations and deployment scenarios. By modeling multiple flow diverter options and their potential placements in the patient's vasculature through computational simulations, the system provides clinicians with predictive information about outcomes for different treatment paths without requiring manual analysis of each complex configuration.
Solution Approach 2:
The patent implements feedback mechanisms that provide clinicians with predictive information about treatment outcomes based on the simulated deployment of different implant configurations. The system analyzes hemodynamic parameters, aneurysm occlusion probability, and other critical factors to provide feedback on which configurations are most likely to succeed, thereby simplifying the decision-making process.
3Shape
If ad-hoc external forces and internal stresses are used in stent modeling, then the geometric deformation can be simulated, but the mechanical properties of the stent may not be accurately represented
Solution Approach 1:
The patent replaces ad-hoc mechanical force models with more physically accurate representations of stent mechanics. Instead of using arbitrary external forces and internal stresses, the system employs material constitutive models, contact mechanics, and physics-based deformation theories that accurately capture the mechanical behavior of stents under physiological conditions.
Data Source
AI summary
A vascular implant decision support uses a medical imaging system. A physics-based model of the endovascular implant is used to simulate deployment in a vessel model of a patient based on medical imaging. A porosity of the deployed implant and the simulation are used to determine a value for each of one or more hemodynamic parameters to support the decision for endovascular treatment. A machine-learned network uses patient-specific information to select the endovascular implant, placement, and/or other implant configuration used to simulate deployment and/or to predict outcome from deployment for the patient. The clinician may use the decision support to select among options for implanting and/or to confirm adequacy of a plan. Various of these approaches may be used alone or in combination.