Active Learning for Deep Learning-Based Hemodynamic Parameter Estimation

2025-03-05

AI Summary

In cardiovascular diagnostics, rapid and accurate estimation of hemodynamic parameters—such as pressure and wall shear stress—relies heavily on computationally expensive computational fluid dynamics (CFD) simulations, hindering clinical deployment of deep learning surrogate models. To address this, we propose a novel active learning framework integrating three complementary criteria: geometric dissimilarity, ensemble uncertainty, and physical consistency—enabling the first multi-source query strategy for synergistic surrogate model training. Our physics-constrained deep neural network significantly reduces CFD labeling requirements, cutting annotation costs by up to 50% on coronary artery bifurcation models. Moreover, it enhances prediction accuracy and generalizability for complex flow fields, particularly improving robustness on challenging clinical cases. This work establishes an efficient, reliable paradigm for rapid hemodynamic assessment in clinical practice.

Technology Category

• Machine Learning: Active Learning
• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Hemodynamic parameters such as pressure and wall shear stress play an important role in diagnosis, prognosis, and treatment planning in cardiovascular diseases. These parameters can be accurately computed using computational fluid dynamics (CFD), but CFD is computationally intensive. Hence, deep learning methods have been adopted as a surrogate to rapidly estimate CFD outcomes. A drawback of such data-driven models is the need for time-consuming reference CFD simulations for training. In this work, we introduce an active learning framework to reduce the number of CFD simulations required for the training of surrogate models, lowering the barriers to their deployment in new applications. We propose three distinct querying strategies to determine for which unlabeled samples CFD simulations should be obtained. These querying strategies are based on geometrical variance, ensemble uncertainty, and adherence to the physics governing fluid dynamics. We benchmark these methods on velocity field estimation in synthetic coronary artery bifurcations and find that they allow for substantial reductions in annotation cost. Notably, we find that our strategies reduce the number of samples required by up to 50% and make the trained models more robust to difficult cases. Our results show that active learning is a feasible strategy to increase the potential of deep learning-based CFD surrogates.

Problem

• Reducing CFD simulations for training deep learning models
• Developing active learning strategies for hemodynamic parameter estimation
• Enhancing model robustness and reducing annotation costs

Innovation

• Active learning reduces CFD simulation needs.
• Three querying strategies optimize sample selection.
• Reduces training samples by up to 50%.