Physics-Informed Neural Networks for Brain Hemodynamic Predictions Using Medical Imaging

Sarabian, Mohammad; Babaee, Hessam; Laksari, Kaveh

doi:10.1109/tmi.2022.3161653

Cited by 51 publications

(12 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the earliest applications of PINNs include nonlinear PDEs, such as the Navier-Stokes and Schrödinger equations [36]. Since then, PINNs have been successfully applied to various cardiovascular fluid dynamics problems, all of which are governed by the nonlinear Navier-Stokes equations [162,163,[174][175][176][177][178]. Individual complex geometries are relatively straightforward to handle with PINNs.…”

Section: Physics-informed Neural Network For Vascular Flow Accelerationmentioning

confidence: 99%

Accelerated simulation methodologies for computational vascular flow modelling

MacRaild,

Sarrami-Foroushani,

Lassila

et al. 2024

J. R. Soc. Interface.

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: Physics-informed Neural Network For Vascular Flow Accelerationmentioning

confidence: 99%

Accelerated simulation methodologies for computational vascular flow modelling

MacRaild,

Sarrami-Foroushani,

Lassila

et al. 2024

J. R. Soc. Interface.

View full text Add to dashboard Cite

show abstract

“…By combining the data-driven solution with physical constraints, PINN can represent the continuous solution space within the boundary conditions under the small samples training. With this tool, rapid modeling and prediction of myocardial and cerebral hemodynamics can be achieved in medical imaging (van Herten et al 2022, Sarabian et al 2022). However, among the proposed DL-based simulation methods, only a few works involve MRI and are all limited to accelerate magnetic resonance fingerprinting (MRF) (Hamilton and Seiberlich 2019, Balsiger et al 2020, Yang et al 2020.…”

Section: Introductionmentioning

confidence: 99%

High-efficient Bloch simulation of magnetic resonance imaging sequences based on deep learning

Huang

Yang²,

Wang

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Bloch simulation constitutes an essential part of magnetic resonance imaging (MRI) development. However, even with the graphics processing unit (GPU) acceleration, the heavy computational load remains a major challenge, especially in large-scale, high-accuracy simulation scenarios. This work aims to develop a deep learning-based simulator to accelerate Bloch simulation. Approach: The simulator model, called Simu-Net, is based on an end-to-end convolutional neural network and is trained with synthetic data generated by traditional Bloch simulation. It uses dynamic convolution to fuse spatial and physical information with different dimensions and introduces position encoding templates to achieve position-specific labeling and overcome the receptive field limitation of the convolutional network. Main Results: Compared with mainstream GPU-based MRI simulation software, Simu-Net successfully accelerates simulations by hundreds of times in both traditional and advanced MRI pulse sequences. The accuracy and robustness of the proposed framework were verified qualitatively and quantitatively. Besides, the trained Simu-Net was applied to generate sufficient customized training samples for deep learning-based T2 mapping and comparable results to conventional methods were obtained in the human brain. Significance: As a proof-of-concept work, Simu-Net shows the potential to apply deep learning for rapidly approximating the forward physical process of MRI and may increase the efficiency of Bloch simulation for optimization of MRI pulse sequences and deep learning-based methods.

show abstract

“…The ML and DL-based methodology is also considered as an alternative to the CFD method for blood flow analysis ( Taebi, 2022 ) because it is of high potential to implement the mapping of anatomic geometries and CFD-driven flow fields, which enables accomplishing fast and accurate hemodynamic prediction for clinical applications. Recently, the ML/DL models have been verified capable of predicting the reduced-order simulation results in a computationally inexpensive way when merely employing some limited flow information, i.e., the velocities and pressures at the centerline or cross-section of a vessel ( Itu et al, 2016 ; Sklet, 2018 ; Sarabian et al, 2021 ). However, from the viewpoint of clinical applications, an accurate prediction of the detailed information on 3D and transient local flows before and after surgical treatments is needed to provide sufficient clinical references for surgery-decision making, which remains poorly studied yet.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based hemodynamic prediction of carotid artery stenosis before and after surgical treatments

Wang

et al. 2023

Front. Physiol.

View full text Add to dashboard Cite

Hemodynamic prediction of carotid artery stenosis (CAS) is of great clinical significance in the diagnosis, prevention, and treatment prognosis of ischemic strokes. While computational fluid dynamics (CFD) is recognized as a useful tool, it shows a crucial issue that the high computational costs are usually required for real-time simulations of complex blood flows. Given the powerful feature-extraction capabilities, the deep learning (DL) methodology has a high potential to implement the mapping of anatomic geometries and CFD-driven flow fields, which enables accomplishing fast and accurate hemodynamic prediction for clinical applications. Based on a brain/neck CT angiography database of 280 subjects, image based three-dimensional CFD models of CAS were constructed through blood vessel extraction, computational domain meshing and setting of the pulsatile flow boundary conditions; a series of CFD simulations were undertaken. A DL strategy was proposed and accomplished in terms of point cloud datasets and a DL network with dual sampling-analysis channels. This enables multimode mapping to construct the image-based geometries of CAS while predicting CFD-based hemodynamics based on training and testing datasets. The CFD simulation was validated with the mass flow rates at two outlets reasonably agreed with the published results. Comprehensive analysis and error evaluation revealed that the DL strategy enables uncovering the association between transient blood flow characteristics and artery cavity geometric information before and after surgical treatments of CAS. Compared with other methods, our DL-based model trained with more clinical data can reduce the computational cost by 7,200 times, while still demonstrating good accuracy (error<12.5%) and flow visualization in predicting the two hemodynamic parameters. In addition, the DL-based predictions were in good agreement with CFD simulations in terms of mean velocity in the stenotic region for both the preoperative and postoperative datasets. This study points to the capability and significance of the DL-based fast and accurate hemodynamic prediction of preoperative and postoperative CAS. For accomplishing real-time monitoring of surgical treatments, further improvements in the prediction accuracy and flexibility may be conducted by utilizing larger datasets with specific real surgical events such as stent intervention, adopting personalized boundary conditions, and optimizing the DL network.

show abstract

Physics-Informed Neural Networks for Brain Hemodynamic Predictions Using Medical Imaging

Cited by 51 publications

References 64 publications

Accelerated simulation methodologies for computational vascular flow modelling

Accelerated simulation methodologies for computational vascular flow modelling

High-efficient Bloch simulation of magnetic resonance imaging sequences based on deep learning

Deep learning-based hemodynamic prediction of carotid artery stenosis before and after surgical treatments

Contact Info

Product

Resources

About