A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy

Dou, Haoran; Ravikumar, Nishant; Frangi, Alejandro F.

doi:10.1007/978-3-031-43990-2_14

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While this is necessary to create sufficiently large datasets, there is a risk that the augmentation may produce unrealistic results, as demonstrated by Morales et al [189] discarding 30% of their initial training samples due to unrealistic flow features. It is possible that data augmentation approaches from the wider machine learning field, such as variational autoencoders or generative adversarial networks, could provide techniques to generate highly realistic synthetic datasets [195–197]. Another issue with physics-agnostic machine learning simulation methods is that the up-front cost of running CFD simulations in large cohorts to generate training data and the subsequent cost of training the complex network can lead to large overall costs.…”

Section: Accelerating Simulations With Machine Learningmentioning

confidence: 99%

Accelerated simulation methodologies for computational vascular flow modelling

MacRaild,

Sarrami-Foroushani,

Lassila

et al. 2024

J. R. Soc. Interface.

Self Cite

View full text Add to dashboard Cite

Vascular flow modelling can improve our understanding of vascular pathologies and aid in developing safe and effective medical devices. Vascular flow models typically involve solving the nonlinear Navier–Stokes equations in complex anatomies and using physiological boundary conditions, often presenting a multi-physics and multi-scale computational problem to be solved. This leads to highly complex and expensive models that require excessive computational time. This review explores accelerated simulation methodologies, specifically focusing on computational vascular flow modelling. We review reduced order modelling (ROM) techniques like zero-/one-dimensional and modal decomposition-based ROMs and machine learning (ML) methods including ML-augmented ROMs, ML-based ROMs and physics-informed ML models. We discuss the applicability of each method to vascular flow acceleration and the effectiveness of the method in addressing domain-specific challenges. When available, we provide statistics on accuracy and speed-up factors for various applications related to vascular flow simulation acceleration. Our findings indicate that each type of model has strengths and limitations depending on the context. To accelerate real-world vascular flow problems, we propose future research on developing multi-scale acceleration methods capable of handling the significant geometric variability inherent to such problems.

show abstract

Section: Accelerating Simulations With Machine Learningmentioning

confidence: 99%