# Combining Deep Learning and 3D Contrast Source Inversion in MR-based Electrical Properties Tomography

## TL;DR

This paper proposes a hybrid approach combining deep learning and contrast source inversion in MR-based electrical properties tomography, improving accuracy and robustness over traditional methods.

## Contribution

It introduces a novel hybrid method that uses deep learning as an initialization for 3D CSI-EPT, enhancing reconstruction quality and clinical applicability.

## Key findings

- Hybrid method improves reconstruction accuracy.
- Deep learning initialization reduces noise sensitivity.
- Enhanced generalization over standard CSI-EPT.

## Abstract

Magnetic resonance-electrical properties tomography (MR-EPT) is a technique used to estimate the conductivity and permittivity of tissues from MR measurements of the transmit magnetic field. Different reconstruction methods are available, however all these methods present several limitations which hamper the clinical applicability. Standard Helmholtz based MR-EPT methods are severely affected by noise. Iterative reconstruction methods such as contrast source inversion-EPT (CSI-EPT) are typically time consuming and are dependent on their initialization. Deep learning (DL) based methods require a large amount of training data before sufficient generalization can be achieved. Here, we investigate the benefits achievable using a hybrid approach, i.e. using MR-EPT or DL-EPT as initialization guesses for standard 3D CSI-EPT. Using realistic electromagnetic simulations at 3 T and 7 T, the accuracy and precision of hybrid CSI reconstructions are compared to standard 3D CSI-EPT reconstructions. Our results indicate that a hybrid method consisting of an initial DL-EPT reconstruction followed by a 3D CSI-EPT reconstruction would be beneficial. DL-EPT combined with standard 3D CSI-EPT exploits the power of data driven DL-based EPT reconstructions while the subsequent CSI-EPT facilitates a better generalization by providing data consistency.