Evaluation of DBS computational modeling methodologies using in-vivo electrophysiology in Parkinson's disease

Abstract

Deep brain stimulation (DBS) is an effective therapy for Parkinson's disease (PD) and other neuropsychiatric disorders, but its outcomes vary due to differences in patient selection, electrode placement, and programming. Optimizing DBS parameter settings requires postoperative adjustments through a trial-and-error process, which is complex and time-consuming. As such, researchers have been developing patient-specific computational models to help guide DBS programming. Despite growing interest in image-guided DBS technology, and recent adoption into clinical practice, the direct validation of the prediction accuracy remains limited. The objective of this study was to establish a comparative framework for validating the accuracy of various DBS computational modeling methodologies in predicting the activation of clinically relevant pathways using in vivo measurements from PD patients undergoing subthalamic (STN) DBS surgery. Our prior work assessed the accuracy of driving force (DF) models in native space by predicting activation of the corticospinal/bulbar tract (CSBT) and cortico-subthalamic hyperdirect pathway (HDP) using very short- (<2 ms) and short-latency (2-4 ms) cortical evoked potentials (cEPs). In this study, we extended our previous work by comparing the accuracy of five computational modeling variations for predicting the activation of HDP and CSBT based on three key factors: modeling method (DF vs. Volume of Tissue Activated [VTA]), imaging space (native vs. normative), and anatomical representation (pathway vs. volume). The model performances were quantified using the coefficient of determination (R²) between the cEP amplitudes and percent pathway activation or percent volume (structure) overlap. We compared model accuracy for 11 PD patients. The DF-Native-Pathway model was the most accurate method for quantitatively predicting experimental subcortical pathway activations. Additionally, our analysis showed that using normative brain space, instead of native (i.e., patient-specific) space, significantly diminished the accuracy of model predictions. Although the DF and VTA modeling methods exhibited comparable accuracy for the hyperdirect pathway, they diverged significantly in their predictions for the corticospinal tract. In conclusion, we believe that the choice of methodology should depend on the specific application and the required level of precision in clinical, surgical, or research settings. These findings offer valuable guidance for developing more accurate models, facilitating reliable DBS outcome predictions, and advancing both clinical practice and research.

Figure 1-

Experimental Setup and Target Pathways. A) Top: Sagittal view of a temporary 28-contact subdural electrocorticography (ECoG) strip placed over the M1 region. Bottom: Top-down view of the ECoG placement visualized by Slicer 5.2. B) Modeling of the DBS electrode implanted in the subthalamic nucleus (STN) (orange), shown in relation to the thalamus (yellow), the hyperdirect pathway (HDP, green), and the cortico-spinal bulbar tract (CSBT, blue), visualized by StimVision. C) Top: Schematic representation of HDP and CSBT antidromic activation in response to STN stimulation. Bottom: Example of a cortical evoked potential (cEP) recorded from one of the ECoG strip contacts in response to STN stimulation. The first and second peak amplitudes, referred to as very short-latency evoked potential (EP0) and short-latency evoked potential (EP1) (Miocinovic et al., 2018), are used here as measures of HDP and CSBT activation. STN= subthalamic nucleus; HDP = hyperdirect pathway; and CSBT = corticospinal/bulbar tract.

Figure 2-

Computational model variations based on three factors: Modeling methods (VTA or DF), Imaging space (Native or Normative), and Anatomical representation (Volume or Pathway). DF by definition only models pathway activations, so there is no DF with volume-based atlases. The VTA-Native pathway modeling (pale gray) is not currently adaptable to the Lead-DBS software pipeline. The highlighted models (in yellow and red) are the most commonly used in published modeling studies.

Figure 3-

Example of different modeling methods for one patient (P06): Top images are generated in Lead DBS V3.1 and bottom ones in StimVision. Top-Left: Volume of Tissue Activated (VTA) estimate in red in response to monopolar stimulation at ventral-most contact (grey). White arrows represent electric field lines; Top-Right: VTA overlap with STN structure (orange) and HDP (green); Bottom-Left: Driving Force (DF) estimate of voltage distribution gradients along the axonal streamlines; Bottom-Right: Estimate of activated pathway streamlines for HDP (green) and CSBT (blue) in response to the same stimulation setting as above.

Figure 4-

Example of modeling in different imaging spaces for one patient (P06). The normative space used here is MNI2009b. All images are generated in StimVision. The lead type is ABT6172, and STN, HDP, and CSBT are shown in orange, green, and blue, respectively. Transformation into normative space introduces visually subtle warping of the anatomical structures and the lead shaft. A) Illustration of the STN, lead, and pathways in native space, B) Warped image in normative space before fitting a lead shaft to a straight line between the contacts and tip. C) Warped image in normative space after fitting a lead shaft to a straight line between the contacts and tip.

Figure 5-

Example of different anatomical representations for one patient (P06). Top row illustrates the volume representation using Distal atlas showing overlaps of a VTA with STN (orange-Left) and IC (purple-Right). Bottom row illustrates the intersection of a VTA in response to the same stimulation with HDP (in green-Left) and CSBT (in blue-Right).

Figure 6-

Comparison between the predictive performance of two common model types: DF-Native-Pathway and VTA-Normative-Volume for two pathways of interest: HDP (green-left) and CSBT (blue-right). Each data point in a box plot is the R2 value for one patient, i.e. the square of the correlation coefficient between the modeling activation predictions and experimental cEP amplitudes. Example correlation plots are shown for one patient (P03) comparing model predictions and cEP amplitudes for all stimulation settings.

Figure 7-

The effect of three key factors on model performance when predicting activation of HDP (green-left) and CSBT (blue-right) pathways. Significant differences are marked with asterisk (*). Top: Two model types – DF-Pathway and VTA-Volume were generated in native and normative space and in all cases the native model outperformed its normative counterpart. Middle: DF and VTA modeling methods were directly compared in normative space. DF outperformed VTA in predicting CSBT activation. Bottom: Pathway and volume anatomical representation were compared in VTA-Normative models with no significant differences.