Rapid computation of TMS-induced E-fields using a dipole-based magnetic stimulation profile approach

Daneshzand, Mohammad; Makarov, Sergey N.; Lara, Lucia I. Navarro de; Guérin, Bastien; McNab, Jennifer A.; Rosen, Bruce R.; Hämäläinen, Matti S.; Raij, Tommi; Nummenmaa, Aapo

doi:10.1016/j.neuroimage.2021.118097

Cited by 26 publications

(30 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, a fast computational algorithm was introduced in [45] to estimate Efield in a selected ROI so that the E-fields generated by coils placed at 5900 different scalp positions and 360 orientation per position can be computed under 15 minutes. In [46], a rapid algorithm was introduced to compute E-field in~100 ms on a cortical surface mesh with 120k facets and with about 5 hours of preparation time. Compared to these methods, the merits of our DNN-based method lie in the simplification in data preprocessing since it does not need mesh models and the acceleration in whole-brain E-field volume prediction.…”

Section: On Prediction Speedmentioning

confidence: 99%

Rapid whole-brain electric field mapping in transcranial magnetic stimulation using deep learning

Rathi

Camprodon

et al. 2021

PLoS ONE

View full text Add to dashboard Cite

Transcranial magnetic stimulation (TMS) is a non-invasive neurostimulation technique that is increasingly used in the treatment of neuropsychiatric disorders and neuroscience research. Due to the complex structure of the brain and the electrical conductivity variation across subjects, identification of subject-specific brain regions for TMS is important to improve the treatment efficacy and understand the mechanism of treatment response. Numerical computations have been used to estimate the stimulated electric field (E-field) by TMS in brain tissue. But the relative long computation time limits the application of this approach. In this paper, we propose a deep-neural-network based approach to expedite the estimation of whole-brain E-field by using a neural network architecture, named 3D-MSResUnet and multimodal imaging data. The 3D-MSResUnet network integrates the 3D U-net architecture, residual modules and a mechanism to combine multi-scale feature maps. It is trained using a large dataset with finite element method (FEM) based E-field and diffusion magnetic resonance imaging (MRI) based anisotropic volume conductivity or anatomical images. The performance of 3D-MSResUnet is evaluated using several evaluation metrics and different combinations of imaging modalities and coils. The experimental results show that the output E-field of 3D-MSResUnet provides reliable estimation of the E-field estimated by the state-of-the-art FEM method with significant reduction in prediction time to about 0.24 second. Thus, this study demonstrates that neural networks are potentially useful tools to accelerate the prediction of E-field for TMS targeting.

show abstract

Section: On Prediction Speedmentioning

confidence: 99%

Rapid whole-brain electric field mapping in transcranial magnetic stimulation using deep learning

Rathi

Camprodon

et al. 2021

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Powerful mathematical tools have recently been developed and implemented ( Gomez et al, 2021 , Daneshzand et al, 2021 ) for fast computations of the TMS-IP solutions via the auxiliary dipole method (ADM) or the magnetic stimulation profile approach, for determining the optimum coil position and orientation. The goal of the present study is not to compete with these tools but rather to evaluate the usefulness and degree of improvement of the TMS-IP solution itself.…”

Section: Discussionmentioning

confidence: 99%

“…From the practical point of view, the solution of a particular TMS-IP will likely be best accomplished by using specialized highly efficient algorithms such as ( Gomez et al, 2021 , Daneshzand et al, 2021 ) instead of the straightforward yet slow approach of this study.…”

Section: Discussionmentioning

confidence: 99%

Degree of improving TMS focality through a geometrically stable solution of an inverse TMS problem

et al. 2021

View full text Add to dashboard Cite

The Transcranial Magnetic Stimulation (TMS) inverse problem (TMS-IP) investigated in this study aims to focus the TMS induced electric field close to a specified target point defined on the gray matter interface in the M 1 HAND area while otherwise minimizing it. The goal of the study is to numerically evaluate the degree of improvement of the TMS-IP solutions relative to the well-known sulcus-aligned mapping (a projection approach with the 90° local sulcal angle). In total, 1536 individual TMS-IP solutions have been analyzed for multiple target points and multiple subjects using the boundary element fast multipole method (BEM-FMM) as the forward solver. Our results show that the optimal TMS inverse-problem solutions improve the focality – reduce the size of the field “hot spot ” and its deviation from the target – by approximately 21–33% on average for all considered subjects, all observation points, two distinct coil types, two segmentation types, two intracortical observation surfaces under study, and three tested values of the field threshold. The inverse-problem solutions with the maximized focality simultaneously improve the TMS mapping resolution (differentiation between neighbor targets separated by approximately 10 mm) although this improvement is quite modest. Coil position/orientation and conductivity uncertainties have been included into consideration as the corresponding de-focalization factors. The present results will change when the levels of uncertainties change. Our results also indicate that the accuracy of the head segmentation critically influences the expected TMS-IP performance.

show abstract

“…Our method is designed as a general-purpose method for the computation of E-field, and it could obtain the E-field for a new subject (whole head model with 208×288×304 voxels at a spatial resolution of 0.8×0.8×0.8 mm 3 ) in about 1.47 seconds. Several alternative fast E-field computation methods have been developed (Daneshzand et al, 2021;Stenroos and Koponen, 2019). Particularly, a magnetic stimulation profile for each subject needs to be computed in advance (Daneshzand et al, 2021) (3) and replacing the scalar conductivity with anisotropic conductivity tensor properly as the network input.…”

Section: Discussionmentioning

confidence: 99%

“…Several alternative fast E-field computation methods have been developed (Daneshzand et al, 2021;Stenroos and Koponen, 2019). Particularly, a magnetic stimulation profile for each subject needs to be computed in advance (Daneshzand et al, 2021) (3) and replacing the scalar conductivity with anisotropic conductivity tensor properly as the network input.…”

Section: Discussionmentioning

confidence: 99%

Computation of transcranial magnetic stimulation electric fields using self-supervised deep learning

Li¹,

Deng

Oathes

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundElectric fields (E-fields) induced by transcranial magnetic stimulation (TMS) can be modeled using partial differential equations (PDEs) with boundary conditions. However, existing numerical methods to solve PDEs for computing E-fields are usually computationally expensive. It often takes minutes to compute a high-resolution E-field using state-of-the-art finite-element methods (FEM).MethodsWe developed a self-supervised deep learning (DL) method to compute precise TMS E-fields in real-time. Given a head model and the primary E-field generated by TMS coils, a self-supervised DL model was built to generate a E-field by minimizing a loss function that measures how well the generated E-field fits the governing PDE and Neumann boundary condition. The DL model was trained in a self-supervised manner, which does not require any external supervision. We evaluated the DL model using both a simulated sphere head model and realistic head models of 125 individuals and compared the accuracy and computational efficiency of the DL model with a state-of-the-art FEM.ResultsIn realistic head models, the DL model obtained accurate E-fields with significantly smaller PDE residual and boundary condition residual than the FEM (p<0.002, Wilcoxon signed-rank test). The DL model was computationally efficient, which took about 0.30 seconds on average to compute the E-field for one testing individual. The DL model built for the simulated sphere head model also obtained an accurate E-field whose difference from the analytical E-fields was 0.004, more accurate than the solution obtained using the FEM.ConclusionsWe have developed a self-supervised DL model to directly learn a mapping from the magnetic vector potential of a TMS coil and a realistic head model to the TMS induced E-fields, facilitating real-time, precise TMS E-field modeling.

show abstract

Rapid computation of TMS-induced E-fields using a dipole-based magnetic stimulation profile approach

Cited by 26 publications

References 44 publications

Rapid whole-brain electric field mapping in transcranial magnetic stimulation using deep learning

Rapid whole-brain electric field mapping in transcranial magnetic stimulation using deep learning

Degree of improving TMS focality through a geometrically stable solution of an inverse TMS problem

Computation of transcranial magnetic stimulation electric fields using self-supervised deep learning

Contact Info

Product

Resources

About