Development of accurate human head models for personalized electromagnetic dosimetry using deep learning

Rashed, Essam A.; Gómez-Tames, José; Hirata, Akimasa

doi:10.1016/j.neuroimage.2019.116132

Cited by 20 publications

(19 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In ( Nielsen et al, 2018 ) the authors review the skull segmentation accuracy of open-source software tools for simulation of TES against computed tomography (CT) scans and conclude that while accurate segmentation of the skull from MR is possible to a certain extent using current tools, robustness, spatial detail, and number of extra-cerebral tissue classes are still lacking. Recently a convolutional neural network architecture was proposed for automated segmentation of multiple head tissues ( Rashed et al, 2019 ), which obtained good agreement with semi-automated segmentations on the same data set. However, it is not clear how to generalize the segmentation performance to MR data sets acquired with scanners, scan sequences or settings that are different from those of the training data set ( Rashed et al, 2019 ).…”

Section: Introductionmentioning

confidence: 97%

“…Recently a convolutional neural network architecture was proposed for automated segmentation of multiple head tissues ( Rashed et al, 2019 ), which obtained good agreement with semi-automated segmentations on the same data set. However, it is not clear how to generalize the segmentation performance to MR data sets acquired with scanners, scan sequences or settings that are different from those of the training data set ( Rashed et al, 2019 ). Generalization performance and robustness are two crucial points for translating TBS to a clinical treatment tool, as the quality of clinical MR scans is limited by resolution, motion artifacts and scan time.…”

Section: Introductionmentioning

confidence: 97%

See 1 more Smart Citation

Accurate and robust whole-head segmentation from magnetic resonance images for individualized head modeling

et al. 2020

View full text Add to dashboard Cite

Transcranial brain stimulation (TBS) has been established as a method for modulating and mapping the function of the human brain, and as a potential treatment tool in several brain disorders. Typically, the stimulation is applied using a one-size-fits-all approach with predetermined locations for the electrodes, in electric stimulation (TES), or the coil, in magnetic stimulation (TMS), which disregards anatomical variability between individuals. However, the induced electric field distribution in the head largely depends on anatomical features implying the need for individually tailored stimulation protocols for focal dosing. This requires detailed models of the individual head anatomy, combined with electric field simulations, to find an optimal stimulation protocol for a given cortical target. Considering the anatomical and functional complexity of different brain disorders and pathologies, it is crucial to account for the anatomical variability in order to translate TBS from a research tool into a viable option for treatment. In this article we present a new method, called CHARM , for automated segmentation of fifteen different head tissues from magnetic resonance (MR) scans. The new method compares favorably to two freely available software tools on a five-tissue segmentation task, while obtaining reasonable segmentation accuracy over all fifteen tissues. The method automatically adapts to variability in the input scans and can thus be directly applied to clinical or research scans acquired with different scanners, sequences or settings. We show that an increase in automated segmentation accuracy results in a lower relative error in electric field simulations when compared to anatomical head models constructed from reference segmentations. However, also the improved segmentations and, by implication, the electric field simulations are affected by systematic artifacts in the input MR scans. As long as the artifacts are unaccounted for, this can lead to local simulation differences up to 30% of the peak field strength on reference simulations. Finally, we exemplarily demonstrate the effect of including all fifteen tissue classes in the field simulations against the standard approach of using only five tissue classes and show that for specific stimulation configurations the local differences can reach 10% of the peak field strength.

show abstract

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 97%

Accurate and robust whole-head segmentation from magnetic resonance images for individualized head modeling

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Recent developments in artificial intelligence, particularly deep learning, has led to remarkable breakthroughs in several medical imaging and signal processing applications [20]. In particular, it has become possible to generate reliable, high quality segmentation in a short time which is close to expert manual segmentation [21,22]. These techniques are expected to facilitate personalized modeling in the future.…”

Section: A Human Body Modelsmentioning

confidence: 99%

Assessment of Human Exposure to Electromagnetic Fields: Review and Future Directions

Hirata

Diao

Onishi

et al. 2021

IEEE Trans. Electromagn. Compat.

Self Cite

View full text Add to dashboard Cite

This paper reviews recent standardization activities and scientific studies related to the assessment of human exposure to electromagnetic fields (EMF). The differences of human exposure standards and assessment of consumer products and medical applications are summarized. First, we reviewed human body modeling and tissue dielectric properties. Then, we explain the rationale of current exposure standards from the viewpoint of EMF and the standardization process for product compliance based on these exposure standards. The assessment of wireless power transfer, as an example of emerging wireless devices, and environmental EMFs in our daily lives are reviewed. Safety in magnetic resonance systems, where the EMF exposure is much larger than from typical consumer devices, is also reviewed. Finally, we summarize future research directions and research needs for EMF safety.

show abstract

“…Therefore, fast and accurate segmentation would lead to a more feasible personalized brain stimulation. Within this scope, different methods are used to perform automatic segmentation of the brain (Despotović et al 2015), but only a few attempts exist for the segmentation of all head tissues (Makris et al 2008, Laakso et al 2015, Rashed et al 2019, Huang et al 2019, Penny et al 2011, Nielsen et al 2018, Thielscher et al 2015. While brain tissues are the main focus of this problem, non-brain tissues are also important to be identified correctly as it has nonnegligible influence on the computation of induced electric field in particular for tES.…”

Section: Introductionmentioning

confidence: 99%

“…More recently, deep learning approaches are emerging as the leading segmentation strategy with ability to generate a human-level accuracy in short time (Wachinger et al 2018, Rashed et al 2019, Henschel et al 2020. Unlike conventional automatic segmentation, deep learning-based segmentation is powerful approach because it can easily learn, observe and extract anatomical features without pre-engineered feature design (Akkus et al 2017).…”

Section: Introductionmentioning

confidence: 99%

Influence of segmentation accuracy in structural MR head scans on electric field computation for TMS and tES

Rashed,

Gomez-Tames,

Hirata

2020

Preprint

Self Cite

View full text Add to dashboard Cite

In several diagnosis and therapy procedures based on electrostimulation effect, the internal physical quantity related to the stimulation is the induced electric field. To estimate the induced electric field in an individual human model, the segmentation of anatomical imaging, such as (magnetic resonance image (MRI) scans, of the corresponding body parts into tissues is required. Then, electrical properties associated with different annotated tissues are assigned to the digital model to generate a volume conductor. However, the segmentation of different tissues is a tedious task with several associated challenges specially with tissues appear in limited regions and/or low-contrast in anatomical images. An open question is how segmentation accuracy of different tissues would influence the distribution of the induced electric field. In this study, we applied parametric segmentation of different tissues to exploit the segmentation of available MRI to generate different quality of head models using deep learning neural network architecture, named ForkNet. Then, the induced electric field are compared to assess the effect of model segmentation variations. Computational results indicate that the influence of segmentation error is tissue-dependent. In brain, sensitivity to segmentation accuracy is relatively high in cerebrospinal fluid (CSF), moderate in gray matter (GM) and low in white matter for transcranial magnetic stimulation (TMS) and transcranial electrical stimulation (tES). A CSF segmentation accuracy reduction of 10% in terms of Dice coefficient (DC) lead to decrease up to 4% in normalized induced electric field in both applications. However, a GM segmentation accuracy reduction of 5.6% DC leads to increase of normalized induced electric field up to 6%. Opposite trend of electric field variation was found between CSF and GM for both TMS and tES. The finding obtained here would be useful to quantify potential uncertainty of computational results.

show abstract

Development of accurate human head models for personalized electromagnetic dosimetry using deep learning

Cited by 20 publications

References 59 publications

Accurate and robust whole-head segmentation from magnetic resonance images for individualized head modeling

Accurate and robust whole-head segmentation from magnetic resonance images for individualized head modeling

Assessment of Human Exposure to Electromagnetic Fields: Review and Future Directions

Influence of segmentation accuracy in structural MR head scans on electric field computation for TMS and tES

Contact Info

Product

Resources

About