Artificial neural network based characterization of the volume of tissue activated during deep brain stimulation

Abstract

Objective Clinical deep brain stimulation (DBS) systems can be programmed with thousands of different stimulation parameter combinations (e.g. electrode contact(s), voltage, pulse width, frequency). Our goal was to develop novel computational tools to characterize the effects of stimulation parameter adjustment for DBS. Approach The volume of tissue activated (VTA) represents a metric used to estimate the spatial extent of DBS for a given parameter setting. Traditional methods for calculating the VTA rely on activation function (AF)-based approaches and tend to overestimate the neural response when stimulation is applied through multiple electrode contacts. Therefore, we created a new method for VTA calculation that relied on artificial neural networks (ANNs). Main Results The ANN-based predictor provides more accurate descriptions of the spatial spread of activation compared to AF-based approaches for monopolar stimulation. In addition, the ANN was able to accurately estimate the VTA in response to multi-contact electrode configurations. Significance The ANN-based approach may represent a useful method for fast computation of the VTA in situations with limited computational resources, such as a clinical DBS programming application on a tablet computer.

Clinical Implications of Local Field Potentials for Understanding and Treating Movement Disorders

“…The use of LFPs in improving DBS clinical outcomes has largely been explored in the setting of DBS implantation into STN for the treatment of PD [30,35,80,81]. Recent work in STN LFP analysis suggests that programming could be improved through analysis of macroelectrode-recorded LFPs and modeling of stimulation parameters [79,82,83]. One direct clinical application relates to the chronic hypersynchrony evidenced in the basal ganglia of Parkinson's patients: better clinical outcomes correlate with the degree of beta hypersynchrony.…”

Theoretical Effect of DBS on Axonal Fibers of Passage: Firing Rates, Entropy, and Information Content

“…Once the axon is brought to threshold, 2 APs are generated; 1 that propagates orthodromically and 1 antidromically [Fig. 4 in [13]] within the volume of tissue activated [14]. Any intrinsic cell-generated APs that collide with the antidromic DBS-created APs will be annihilated.…”

Study of the visible light activity of Pt and Au-TiO2 photocatalysts in organic pollutants degradation

“…However, these curves do not reproduce the results of multicompartment models accurately and cannot be applied successfully when multiple contacts of the DBS electrode are active [12]. A possible solution to these problems is proposed by Chaturvedi et al [12]. It consists in training an artificial neuronal network, with the DBS stimulation parameters as inputs and the elliptic profiles defined by the active axons as outputs.…”

“…The diffusion tensors were estimated from the DTI30 dataset, with the RESTORE (Robust Estimation of Tensors by Outlier Rejection) algorithm [18], and then linearly transformed to conductivity tensors [19]. In both cases, a representation of a 0.5 mm encapsulation layer around the electrode was included, and its conductivity was set to three different values (0.680 Sm ) to represent low (~500 Ω), medium (~900 Ω), and high (~1,500 Ω) impedance conditions [12,20].…”