Vascular Image Blood Flow Mapping with Physics-Constrained Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods lack an efficient and accurate way to determine blood flow field information for vascular segments, which is crucial for assessing vascular health and guiding medical interventions.
Innovation Solution
A method and device utilizing a pre-trained neural network to analyze vascular segment images, predicting physical quantities like pressure, velocity, and flow rate that satisfy physical constraints, enabling determination of human medical information such as fractional flow reserve (FFR) and plaque risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a neural network is used to predict blood flow field information, then the accuracy and comprehensiveness of the prediction is improved, but the computational complexity and training time increase
Solution Approach 1:
The neural network model is pre-trained using vascular segment image data and ground truth blood flow field information before actual prediction tasks. This preliminary training phase allows the model to learn optimal feature representations and prediction patterns, enabling accurate predictions during inference without requiring complex real-time training computations.
Solution Approach 2:
The patent replaces traditional mechanical or manual methods of blood flow analysis with a neural network-based computational system. The neural network automatically extracts features from vascular images and predicts blood flow field information, substituting complex manual analysis procedures with an automated intelligent system that achieves higher accuracy.
2Reliability
If physical constraint conditions are imposed on predicted values, then the reliability of the prediction is improved, but the complexity of the prediction process increases
Solution Approach 1:
The patent incorporates physical constraint conditions as feedback mechanisms that validate and refine the neural network's predictions. By checking whether predicted blood flow values satisfy physical constraints (such as continuity equations or boundary conditions), the system provides feedback to ensure reliability and can adjust predictions accordingly, maintaining physical plausibility without requiring complete redesign of the prediction architecture.
Data Source
AI summary
A method, device, computing equipment, and storage medium for determining blood flow field information are provided. The method can include: obtaining vascular segment images regarding a target vascular segment; and based on the vascular segment images, determining at least one blood flow field information for the said target vascular segment through a pre-trained neural network.