Physics-Driven Deep Learning for Computational Magnetic Resonance
Imaging
- URL: http://arxiv.org/abs/2203.12215v1
- Date: Wed, 23 Mar 2022 06:04:11 GMT
- Title: Physics-Driven Deep Learning for Computational Magnetic Resonance
Imaging
- Authors: Kerstin Hammernik, Thomas K\"ustner, Burhaneddin Yaman, Zhengnan
Huang, Daniel Rueckert, Florian Knoll, Mehmet Ak\c{c}akaya
- Abstract summary: Physics-driven deep learning methods have emerged as a powerful tool for computational magnetic resonance imaging (MRI) problems.
This article provides an overview of the recent developments in incorporating physics information into learning-based MRI reconstruction.
- Score: 7.404599356384102
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Physics-driven deep learning methods have emerged as a powerful tool for
computational magnetic resonance imaging (MRI) problems, pushing reconstruction
performance to new limits. This article provides an overview of the recent
developments in incorporating physics information into learning-based MRI
reconstruction. We consider inverse problems with both linear and non-linear
forward models for computational MRI, and review the classical approaches for
solving these. We then focus on physics-driven deep learning approaches,
covering physics-driven loss functions, plug-and-play methods, generative
models, and unrolled networks. We highlight domain-specific challenges such as
real- and complex-valued building blocks of neural networks, and translational
applications in MRI with linear and non-linear forward models. Finally, we
discuss common issues and open challenges, and draw connections to the
importance of physics-driven learning when combined with other downstream tasks
in the medical imaging pipeline.
Related papers
- MindFormer: A Transformer Architecture for Multi-Subject Brain Decoding via fMRI [50.55024115943266]
We introduce a new Transformer architecture called MindFormer to generate fMRI-conditioned feature vectors.
MindFormer incorporates two key innovations: 1) a novel training strategy based on the IP-Adapter to extract semantically meaningful features from fMRI signals, and 2) a subject specific token and linear layer that effectively capture individual differences in fMRI signals.
arXiv Detail & Related papers (2024-05-28T00:36:25Z) - fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for
Multi-Subject Brain Activity Decoding [54.17776744076334]
We propose fMRI-PTE, an innovative auto-encoder approach for fMRI pre-training.
Our approach involves transforming fMRI signals into unified 2D representations, ensuring consistency in dimensions and preserving brain activity patterns.
Our contributions encompass introducing fMRI-PTE, innovative data transformation, efficient training, a novel learning strategy, and the universal applicability of our approach.
arXiv Detail & Related papers (2023-11-01T07:24:22Z) - Implicit neural representation with physics-informed neural networks for
the reconstruction of the early part of room impulse responses [16.89505645696765]
We exploit physics-informed neural networks to reconstruct the early part of missing room impulse responses in a linear array.
The proposed model achieves accurate reconstruction and performance in line with respect to state-of-the-art deep-learning and compress sensing techniques.
arXiv Detail & Related papers (2023-06-20T13:01:00Z) - Physics Embedded Machine Learning for Electromagnetic Data Imaging [83.27424953663986]
Electromagnetic (EM) imaging is widely applied in sensing for security, biomedicine, geophysics, and various industries.
It is an ill-posed inverse problem whose solution is usually computationally expensive. Machine learning (ML) techniques and especially deep learning (DL) show potential in fast and accurate imaging.
This article surveys various schemes to incorporate physics in learning-based EM imaging.
arXiv Detail & Related papers (2022-07-26T02:10:15Z) - Physics-driven Deep Learning for PET/MRI [2.2113800586902608]
We review physics- and data-driven reconstruction techniques for simultaneous positron emission tomography (PET) / magnetic resonance imaging (MRI) systems.
These reconstruction approaches utilize priors, either structural or statistical, together with a physics-based description of the PET system response.
We elucidate how a multi-faceted approach accommodates hybrid data- and physics-driven machine learning for reconstruction of 3D PET/MRI.
arXiv Detail & Related papers (2022-06-11T21:35:27Z) - Data and Physics Driven Learning Models for Fast MRI -- Fundamentals and
Methodologies from CNN, GAN to Attention and Transformers [72.047680167969]
This article aims to introduce the deep learning based data driven techniques for fast MRI including convolutional neural network and generative adversarial network based methods.
We will detail the research in coupling physics and data driven models for MRI acceleration.
Finally, we will demonstrate through a few clinical applications, explain the importance of data harmonisation and explainable models for such fast MRI techniques in multicentre and multi-scanner studies.
arXiv Detail & Related papers (2022-04-01T22:48:08Z) - Physics-informed ConvNet: Learning Physical Field from a Shallow Neural
Network [0.180476943513092]
Modelling and forecasting multi-physical systems remain a challenge due to unavoidable data scarcity and noise.
New framework named physics-informed convolutional network (PICN) is recommended from a CNN perspective.
PICN may become an alternative neural network solver in physics-informed machine learning.
arXiv Detail & Related papers (2022-01-26T14:35:58Z) - Recurrent Variational Network: A Deep Learning Inverse Problem Solver
applied to the task of Accelerated MRI Reconstruction [3.058685580689605]
We present a novel Deep Learning-based Inverse Problem solver applied to the task of accelerated MRI reconstruction.
The RecurrentVarNet consists of multiple blocks, each responsible for one unrolled iteration of the gradient descent algorithm for solving inverse problems.
Our proposed method achieves new state of the art qualitative and quantitative reconstruction results on 5-fold and 10-fold accelerated data from a public multi-channel brain dataset.
arXiv Detail & Related papers (2021-11-18T11:44:04Z) - Constructing Neural Network-Based Models for Simulating Dynamical
Systems [59.0861954179401]
Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system.
This paper provides a survey of the different ways to construct models of dynamical systems using neural networks.
In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome.
arXiv Detail & Related papers (2021-11-02T10:51:42Z) - Physics informed neural networks for continuum micromechanics [68.8204255655161]
Recently, physics informed neural networks have successfully been applied to a broad variety of problems in applied mathematics and engineering.
Due to the global approximation, physics informed neural networks have difficulties in displaying localized effects and strong non-linear solutions by optimization.
It is shown, that the domain decomposition approach is able to accurately resolve nonlinear stress, displacement and energy fields in heterogeneous microstructures obtained from real-world $mu$CT-scans.
arXiv Detail & Related papers (2021-10-14T14:05:19Z) - Hard Encoding of Physics for Learning Spatiotemporal Dynamics [8.546520029145853]
We propose a deep learning architecture that forcibly encodes known physics knowledge to facilitate learning in a data-driven manner.
The coercive encoding mechanism of physics, which is fundamentally different from the penalty-based physics-informed learning, ensures the network to rigorously obey given physics.
arXiv Detail & Related papers (2021-05-02T21:40:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.