Authors:

Jorge L Alberto

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

for DBS applications Objective. Artificial neural network (ANNs) based rapid predictors optimize deep brain stimulation (DBS) by predicting neural activation in response to electrical stimulation, while minimizing tradeoffs between computational expense and accuracy. Previous ANNs have predicted neural activation under monopolar electrode configurations, but this is only representative of a subset of configurations that can occur during DBS programming. We sought to expand the generalization capability of this ANN to many commonly used electrode configurations. Approach. We developed two variations to predict the response of individual, myelinated axons to extracellular electrical stimulation. Training used datasets generated from a finite-element model of an implanted DBS system together with multi-compartment cable models of artificially generated axons. We evaluated the ANN-based predictors using white matter pathways derived from group-averaged connectome data within a patient-specific tissue conductivity field, comparing both predicted stimulus activation thresholds and pathway recruitment across a clinically relevant range of stimulus amplitudes and pulse widths. Preliminary results. The ANN successfully predicted neural fiber activation for monopolar, multimonopolar and bipolar electrode configurations, expanding the scope of our previous predictor model. 401

Source:

University of Florida / 2024

Topics:

No topics listed

Co-authors:

Jorge L Alberto