Non-invasive Renal Artery Stenosis Assessment via ML Surrogate Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing renal artery stenosis rely on invasive and costly procedures, which increase patient risk and healthcare costs, and lack comprehensive analysis of hemodynamic effects at rest and hyperemia.
Innovation Solution
A machine learning-based computational framework that uses a data-driven surrogate model trained on multiscale physiological models of renal arterial circulation and the renin-angiotensin-aldosterone system to predict patient-specific hemodynamic indices from medical image data, eliminating the need for invasive pressure measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive catheter based pressure measurements are used to assess renal artery stenosis, then measurement precision of hemodynamic indices is improved, but patient risk and device complexity increase
Solution Approach 1:
The patent creates a virtual copy of the patient's renal arterial geometry from medical images and performs computational fluid dynamics simulations on this digital model to predict hemodynamic indices, eliminating the need for physical invasive measurements while maintaining measurement accuracy
Solution Approach 2:
The patent replaces the mechanical invasive catheter-based pressure measurement system with a computational model that uses machine learning algorithms and fluid dynamics simulations to predict hemodynamic indices from anatomical images, substituting physical intervention with information processing
2Measurement precision
If invasive pressure measurements are used to assess renal artery stenosis, then measurement precision is improved, but device complexity and healthcare costs increase
Solution Approach 1:
The patent creates a virtual copy of the patient's renal arterial geometry from medical images and performs computational fluid dynamics simulations on this digital model to predict hemodynamic indices, eliminating the need for physical invasive measurements while maintaining measurement accuracy
Solution Approach 2:
The patent transforms the assessment approach by changing from direct physical measurement parameters to computational prediction parameters, using machine learning models trained on synthetic data to estimate hemodynamic indices from anatomical measurements alone
3Ease of operation
If traditional visual estimation methods are used for renal artery stenosis assessment, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent enables the assessment system to automatically extract geometric features from medical images and compute hemodynamic indices through computational simulations, making the procedure as easy to perform as visual estimation while achieving superior measurement precision through automated analysis
Solution Approach 2:
The patent replaces the subjective visual estimation process with an automated computational system that uses machine learning algorithms and fluid dynamics simulations to objectively quantify stenosis severity, maintaining operational simplicity while dramatically improving measurement accuracy
Data Source
AI summary
A method and system for personalized non-invasive assessment of renal artery stenosis for a patient is disclosed. Medical image data of a patient is received. Patient-specific renal arterial geometry of the patient is extracted from the medical image data. Features are extracted from the patient-specific renal arterial geometry of the patient. A hemodynamic index is computed for one or more locations of interest in the patient-specific renal arterial geometry based on the extracted features using a trained machine-learning based surrogate model. The machine-learning based surrogate model is trained based on features extracted from synthetically generated renal arterial geometries.