Rapid estimation of cortical neuron activation thresholds by transcranial magnetic stimulation using convolutional neural networks

Abstract

BackgroundTranscranial magnetic stimulation (TMS) can modulate neural activity by evoking action potentials in subpopulations of cortical neurons. The TMS-induced electric field (E-field) can be simulated in subject-specific head models derived from MR images, but the spatial distribution of the E-field alone does not predict the physiological response. Coupling E-field models to populations of biophysically realistic neuron models yields insights into the activation mechanisms of TMS, but the significant computational cost associated with these models limits their use and eventual translation to clinically relevant applications.ObjectiveThe objective was to develop computationally efficient estimators of the activation thresholds of multi-compartmental cortical neuron models in response to TMS-induced E-field distributions.MethodsMulti-scale models combining anatomically accurate finite element method (FEM) simulations of the TMS E-field with layer-specific representations of cortical neurons were used to generate a large dataset of activation thresholds. 3D convolutional neural networks (CNNs) were trained on these data to predict the activation threshold of specific model neurons given the local E-field distribution. Using training and test data from different head models, the CNN estimator was compared to an approach using the uniform E-field approximation to estimate thresholds in the non-uniform TMS-induced E-field.ResultsThe 3D CNNs were more accurate than the uniform E-field approach, with mean absolute percent error (MAPE) on the test dataset below 2.5% compared to 5.9 – 9.8% with the uniform E-field approach. Further, there was a strong correlation between the CNN predicted and actual thresholds for all cell types (R2 > 0.96) compared to the uniform E-field approach (R2 = 0.62 – 0.91). The CNNs estimate thresholds with a 2 – 4 orders of magnitude reduction in the computational cost of the multi-compartmental neuron models.Conclusion3D CNNs can estimate rapidly and accurately the TMS activation thresholds of biophysically realistic neuron models using sparse samples of the local E-field, enabling simulating responses of large neuron populations or parameter space exploration on a personal computer.

Responses of model cortical neurons to temporal interference stimulation and related transcranial alternating current stimulation modalities

“…Due to this simplification, the thresholds could not be directly correlated with current amplitudes applied to tACS electrodes, and the spatial distribution of neural activation within the cortex was not determined. Nevertheless, simulations of E-field distributions in realistic head models can fill this gap, whether using a multiscale model with neuron models embedded in the cortex [32] or using the uniform field results as a lookup table to determine thresholds based on the amplitude ratio and orientations of the cortical E-fields relative to the normal direction of the cortical layer [42,64]. Therefore, the combinations of E-field orientation and their amplitude ratios in this study are representative of neurons at different cortical locations.…”

Responses of Model Cortical Neurons to Temporal Interference Stimulation and Related Transcranial Alternating Current Stimulation Modalities

“…Due to this simplification, the thresholds could not be directly correlated with current amplitudes applied to tACS electrodes, and the spatial distribution of neural activation within the cortex was not determined. Nevertheless, simulations of E-field distributions in realistic head models can fill this gap, whether using a multiscale model with neuron models embedded in the cortex [32] or using the uniform field results as a lookup table to determine thresholds based on the amplitude ratio and orientations of the cortical E-fields relative to the normal direction of the cortical layer [42,64]. Therefore, the combinations of E-field orientation and their amplitude ratios in this study are representative of neurons at different cortical locations.…”

Electric field based dosing for TMS

“…For example, experimental approaches identified thresholds from 35 V/m to 60 V/m when quantified via EEG (double pulses, Rosanova et al, 2009;individual alpha frequency, Zmeykina et al, 2020) and from 60 to above 100 V/m when measured with EMG (single pulses, Numssen et al, 2021;Kuhnke & Numssen et al, 2023). In contrast, modeling approaches and in vitro experiments identified thresholds between 120 V/m and 300 V/m (Turi et al, 2022;Shirinpour et al, 2021;Aberra et al, 2020, Aberra et al, 2023. It is important to note that modeling approaches currently use simplified setups, such as isolated neurons instead of interconnected neuronal networks and other cell types, and that neuronal models originate from rodent samples (Weise et al, 2023).…”