Opening a new window on MR-based Electrical Properties Tomography with deep learning

@article{Mandija2019OpeningAN,
  title={Opening a new window on MR-based Electrical Properties Tomography with deep learning},
  author={Stefano Mandija and Ettore Flavio Meliad{\`o} and Niek R. F. Huttinga and Peter R. Luijten and Cornelis A. T. van den Berg},
  journal={Scientific Reports},
  year={2019},
  volume={9}
}
In the radiofrequency (RF) range, the electrical properties of tissues (EPs: conductivity and permittivity) are modulated by the ionic and water content, which change for pathological conditions. Information on tissues EPs can be used e.g. in oncology as a biomarker. The inability of MR-Electrical Properties Tomography techniques (MR-EPT) to accurately reconstruct tissue EPs by relating MR measurements of the transmit RF field to the EPs limits their clinical applicability. Instead of employing… 

Physics-Coupled Neural Network Magnetic Resonance Electrical Property Tomography (MREPT) for Conductivity Reconstruction

TLDR
A physics-coupled NN for MREPT is proposed, in which an analytic model, cr-MREPT, works with diffusion and convection coefficients, learned by NNs from the difference between the reconstructed and ground-truth EPs to reduce artifacts.

Deep learning brain conductivity mapping using a patch-based 3D U-net

TLDR
High quality of reconstructions from networks trained on simulations with and without noise confirms the potential of deep learning for EPT, however, artifact encumbered results in this work uncover challenges in application of DLEPT to in-vivo data.

Investigating the challenges and generalizability of deep learning brain conductivity mapping

TLDR
3D patch-based convolutional neural networks were trained to predict conductivity maps from B1 transceive phase data to investigate deep learning electrical properties tomography (EPT) for application on different simulated and in-vivo datasets, including pathologies for brain conductivity reconstructions.

Brain Tissue Conductivity Measurements with MR-Electrical Properties Tomography: An In Vivo Study

First in vivo brain conductivity reconstructions using Helmholtz MR-Electrical Properties Tomography (MR-EPT) have been published. However, a large variation in the reconstructed conductivity values

Improving Tissue Electrical Properties Reconstructions by Exploiting the Benefits of Combining Deep Learning-EPT and 3D Contrast Source Inversion-EPT

Synopsis We propose a two-step approach to EPT reconstruction where we use the results from a deep-learning approach as the initial estimate for a 3D contrast-source inversion algorithm. The

Magnetic-Resonance-Based Electrical Property Mapping Using Global Maxwell Tomography With an 8-Channel Head Coil at 7 Tesla: A Simulation Study

TLDR
Global Maxwell Tomography could provide accurate estimations of tissue EP, which could be used as biomarkers and could enable patient-specific estimation of RF power deposition, which is an unsolved problem for ultra-high-field magnetic resonance imaging.

TRANSVERSE-EPT: A LOCAL FIRST ORDER ELECTRICAL PROPERTIES TOMOGRAPHY APPROACH NOT REQUIRING ESTIMATION OF THE INCIDENT FIELDS

—A new local method for magnetic resonance electrical properties tomography (EPT), dubbed transverse-EPT (T-EPT), is introduced. This approach iteratively optimizes the dielectric properties

Electrical Properties Tomography: A Methodological Review

TLDR
A thorough mathematical overview of EPT harmonizes several EPT techniques in a single type of formulation and gives insight into how they act on the data and what their data requirements are.

Low frequency conductivity reconstruction based on a single current injection via MREIT

TLDR
It is concluded that it is possible to reconstruct high quality electrical conductivity images using MREIT techniques and one current injection only and is capable of reconstructing isotropic conductivity image that agree well in terms of L2error and structural similarity with exact conductivity distributions or two-current-based MREit reconstructions.

MR-Based Electrical Conductivity Imaging Using Second-Order Total Generalized Variation Regularization

Electrical properties provide essential information for cancer detection and specific absorption rate (SAR) estimation. Magnetic resonance electrical properties tomography (MREPT) is an approach to

References

SHOWING 1-10 OF 47 REFERENCES

Deep learning brain conductivity mapping using a patch-based 3D U-net

TLDR
High quality of reconstructions from networks trained on simulations with and without noise confirms the potential of deep learning for EPT, however, artifact encumbered results in this work uncover challenges in application of DLEPT to in-vivo data.

An Inverse Problems Approach to MR-EPT Image Reconstruction

TLDR
The proposed inverse approach to MR-EPT reconstruction correctly identifies contrasts and accurately reconstructs the geometry in both simulations and experiments, and the TV regularized scheme reconstructs sharp spatial transitions, which are difficult to reconstruct with other, more traditional approaches.

Electric properties tomography: Biochemical, physical and technical background, evaluation and clinical applications

TLDR
The physical equations underlying EPT, the corresponding basic and advanced reconstruction techniques and practical numerical aspects to realize these reconstruction techniques are summarized and the clinical findings which have been obtained so far are described.

Determination of Electric Conductivity and Local SAR Via B1 Mapping

TLDR
Electro properties tomography derives the patient's electric conductivity, along with the corresponding electric fields, from the spatial sensitivity distributions of the applied RF coils, which are measured via MRI, which might lead to significantly higher spatial image resolution.

Fast synthetic CT generation with deep learning for general pelvis MR-only Radiotherapy

TLDR
Accurate MR-based dose calculation using sCT images generated with a cGAN is feasible for the entire pelvis, and the sCT generation was sufficiently fast to be integrated into an MR-guided radiotherapy workflow.

Error analysis of helmholtz‐based MR‐electrical properties tomography

TLDR
The error arising from the computation of spatial derivatives using finite difference kernels (FD error) has been investigated and it is investigated whether mitigation strategies such as Gibbs ringing correction and Gaussian apodization can be beneficial for conductivity reconstructions.

B  1+ Phase mapping at 7 T and its application for in vivo electrical conductivity mapping

TLDR
A new approach to measure local electrical conductivity in tissue is presented, which is based on the propagating B  1+ phase and the homogeneous Helmholtz equation and might open future opportunities for tumor and lesion characterization based on conductivity differences, while it may also find application in radio frequency safety assessment.

Theoretical Investigation of Random Noise-Limited Signal-to-Noise Ratio in MR-Based Electrical Properties Tomography

TLDR
The SNR formula can be used to estimate minimum input data SNR and ROI size required to obtain tissue EP maps of desired quality and is found to provide explanation of certain aspects of previous experimental results in the literature.

Gradient‐based electrical properties tomography (gEPT): A robust method for mapping electrical properties of biological tissues in vivo using magnetic resonance imaging

TLDR
To develop high‐resolution EPT methods and investigate a gradient‐based EPT approach that aims to reconstruct the electrical properties of an imaged sample from experimentally measured B1 maps with improved boundary reconstruction and robustness against measurement noise.

In vivo electric conductivity of cervical cancer patients based on B1+ ?> maps at 3T MRI

TLDR
Considerable deviations were found for the electrical conductivity observed in this study and the commonly used values for SAR assessment, emphasizing the importance of acquiring in vivo conductivity for more accurate SAR assessment in various applications.