Combining deep learning and 3D contrast source inversion in MR‐based electrical properties tomography

Leijsen, Reijer L.; Berg, Cornelis A.T. van den; Webb, Andrew; Remis, Rob; Mandija, Stefano

doi:10.1002/nbm.4211

Cited by 28 publications

(33 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these inverse models require electromagnetic quantities that are not always accessible with MRI (incident electric field) (Balidemaj et al 2015). Better quality conductivity reconstructions from simulated data have been recently obtained with deep-learning based approaches (Hampe et al 2019;Leijsen et al 2019;Mandija et al 2019), but their generalization to in vivo cases remains challenging due to the lack of accurate in vivo reconstructions to train neural networks. Contrary to the studies above, the presented study does not introduce a new methodology for MR-EPT, nor does it aim at solving the noise amplification problem of Helmholtz-based MR-EPT reconstructions.…”

Section: Discussionmentioning

confidence: 99%

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

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 is reported and these values differ from ex vivo conductivity measurements. Given this lack of agreement, we performed an in vivo study on eight healthy subjects to provide reference in vivo brain conductivity values. MR-EPT reconstructions were performed at 3 T for eight healthy subjects. Mean conductivity and standard deviation values in the white matter, gray matter and cerebrospinal fluid (σWM, σGM, and σCSF) were computed for each subject before and after erosion of regions at tissue boundaries, which are affected by typical MR-EPT reconstruction errors. The obtained values were compared to the reported ex vivo literature values. To benchmark the accuracy of in vivo conductivity reconstructions, the same pipeline was applied to simulated data, which allow knowledge of ground truth conductivity. Provided sufficient boundary erosion, the in vivo σWM and σGM values obtained in this study agree for the first time with literature values measured ex vivo. This could not be verified for the CSF due to its limited spatial extension. Conductivity reconstructions from simulated data verified conductivity reconstructions from in vivo data and demonstrated the importance of discarding voxels at tissue boundaries. The presented σWM and σGM values can therefore be used for comparison in future studies employing different MR-EPT techniques.

show abstract

Section: Discussionmentioning

confidence: 99%

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…We acknowledge also that the current implementation fails to indicate such type of error. We believe that combining our DL-based reconstruction with an inverse EPT reconstruction method (which guarantees data consistency), similarly to the hybrid approach adopted by Leijsen et al, 53 could increase the confidence in the accuracy of reconstruction of outlier cases.…”

Section: F I G U R Ementioning

confidence: 95%

Deep learning‐based reconstruction of in vivo pelvis conductivity with a 3D patch‐based convolutional neural network trained on simulated MR data

Gavazzi

Berg

Savenije

et al. 2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To demonstrate that mapping pelvis conductivity at 3T with deep learning (DL) is feasible. Methods 210 dielectric pelvic models were generated based on CT scans of 42 cervical cancer patients. For all dielectric models, electromagnetic and MR simulations with realistic accuracy and precision were performed to obtain and transceive phase ( ϕ ± ). Simulated and ϕ ± served as input to a 3D patch‐based convolutional neural network, which was trained in a supervised fashion to retrieve the conductivity. The same network architecture was retrained using only ϕ ± in input. Both network configurations were tested on simulated MR data and their conductivity reconstruction accuracy and precision were assessed. Furthermore, both network configurations were used to reconstruct conductivity maps from a healthy volunteer and two cervical cancer patients. DL‐based conductivity was compared in vivo and in silico to Helmholtz‐based (H‐EPT) conductivity. Results Conductivity maps obtained from both network configurations were comparable. Accuracy was assessed by mean error (ME) with respect to ground truth conductivity. On average, ME < 0.1 Sm −1 for all tissues. Maximum MEs were 0.2 Sm −1 for muscle and tumour, and 0.4 Sm −1 for bladder. Precision was indicated with the difference between 90 th and 10 th conductivity percentiles, and was below 0.1 Sm −1 for fat, bone and muscle, 0.2 Sm −1 for tumour and 0.3 Sm −1 for bladder. In vivo, DL‐based conductivity had median values in agreement with H‐EPT values, but a higher precision. Conclusion Anatomically detailed, noise‐robust 3D conductivity maps with good sensitivity to tissue conductivity variations were reconstructed in the pelvis with DL.

show abstract

“…The ΔT assessment is also altered when individual mesh elements span multiple tissues. This can occur when a hexahedral mesh is not aligned with the voxels of the human model (see, e.g., the material property maps reported in [25]). Such modification of the material properties increases the uncertainty in the model output for voxel-based human body models.…”

Section: Introductionmentioning

confidence: 99%

Modeling radio-frequency energy-induced heating due to the presence of transcranial electric stimulation setup at 3T

Kozlov

Horner

Kainz

et al. 2020

Magn Reson Mater Phy

View full text Add to dashboard Cite

Purpose The purpose of the present study was to develop a numerical workflow for simulating temperature increase in a high-resolution human head and torso model positioned in a whole-body magnetic resonance imaging (MRI) radio-frequency (RF) coil in the presence of a transcranial electric stimulation (tES) setup. Methods A customized human head and torso model was developed from medical image data. Power deposition and temperature rise (ΔT) were evaluated with the model positioned in a whole-body birdcage RF coil in the presence of a tES setup. Multiphysics modeling at 3T (123.2 MHz) on unstructured meshes was based on RF circuit, 3D electromagnetic, and thermal co-simulations. ΔT was obtained for (1) a set of electrical and thermal properties assigned to the scalp region, (2) a set of electrical properties of the gel used to ensure proper electrical contact between the tES electrodes and the scalp, (3) a set of electrical conductivity values of skin tissue, (4) four gel patch shapes, and (5) three electrode shapes. Results Significant dependence of power deposition and ΔT on the skin’s electrical properties and electrode and gel patch geometries was observed. Differences in maximum ΔT (> 100%) and its location were observed when comparing the results from a model using realistic human tissue properties and one with an external container made of acrylic material. The electrical and thermal properties of the phantom container material also significantly (> 250%) impacted the ΔT results. Conclusion Simulation results predicted that the electrode and gel geometries, skin electrical conductivity, and position of the temperature sensors have a significant impact on the estimated temperature rise. Therefore, these factors must be considered for reliable assessment of ΔT in subjects undergoing an MRI examination in the presence of a tES setup.

show abstract

Combining deep learning and 3D contrast source inversion in MR‐based electrical properties tomography

Cited by 28 publications

References 24 publications

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

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

Deep learning‐based reconstruction of in vivo pelvis conductivity with a 3D patch‐based convolutional neural network trained on simulated MR data

Modeling radio-frequency energy-induced heating due to the presence of transcranial electric stimulation setup at 3T

Contact Info

Product

Resources

About