Learning-based estimation of dielectric properties and tissue density in head models for personalized radio-frequency dosimetry

Abstract

Radio-frequency dosimetry is an important process in assessments for human exposure safety and for compliance of related products. Recently, computational human models generated from medical images have often been used for such assessment, especially to consider the inter-subject variability. However, a common procedure to develop personalized models is time consuming because it involves excessive segmentation of several components that represent different biological tissues, which is a major obstacle in the inter-subject variability assessment of radiation safety. Deep learning methods have been shown to be a powerful approach for pattern recognition and signal analysis. Convolutional neural networks with deep architecture are proven robust for feature extraction and image mapping in several biomedical applications. In this study, we develop a learning-based approach for fast and accurate estimation of the dielectric properties and density of tissues directly from magnetic resonance images in a single shot. The smooth distribution of the dielectric properties in head models, which is realized using a process without tissue segmentation, improves the smoothness of the specific absorption rate (SAR) distribution compared with that in the commonly used procedure. The estimated SAR distributions, as well as that averaged over 10-g of tissue in a cubic shape, are found to be highly consistent with those computed using the conventional methods that employ segmentation.

Large-Scale Analysis of the Head Proximity Effects on Antenna Performance Using Machine Learning Based Models

“…The second set of head models possesses non-uniformly distributed dielectric properties, which are generated using CondNet [41]. This deep learning architecture (shown in Fig.…”

“…Moreover, the computational burden of intensive segmentation is not required. Note that conventional voxel models were based on segmentation, and thus the tissue dielectric properties suddenly changed at the tissue boundary, resulting in an abrupt change in the power absorption distribution [41].…”

“…The appropriateness of using a homogenous tissue simulant liquid for performance evaluation of personalized wireless devices is unclear. Recently, promising techniques have been proposed to develop computational head models directly from medical images without tissue segmentation [38]- [41]. These models have been utilized to improve brain stimulation apparatus at low frequencies [40] and radio-frequency therapeutic applications [42].…”

“…These models have been utilized to improve brain stimulation apparatus at low frequencies [40] and radio-frequency therapeutic applications [42]. In our previous work [41], eight head models were developed from MRIs using a deep learning approach with network architecture (known as CondNet) without tissue segmentation because of imagebased dielectric property assignment, and were successfully used for numerical dosimetry assessments. The feature of this approach is that tissue-specific conductivity assignment is not required.…”

Technical developments for MR-based electrical property mapping

“…Earlier this year, Rashed et al [305] published a dl-based method that infers both eps (at different frequencies) and the tissue density ρ from T 1 and T 2 -weighted mr images, which are commonly acquired in the clinics. Although the three output maps exhibit the same anatomical information of input T 1 and T 2 weighted mri data, this method is most likely not capable to retrieve the subject-specific eps, since the cnn was trained only on fixed, literature ep values.…”