Precise targeting of the globus pallidus internus with quantitative susceptibility mapping for deep brain stimulation surgery

OBJECTIVE

The goal of this study was to demonstrate the use of quantitative susceptibility mapping (QSM)-based images to precisely localize the globus pallidus internus (GPi) for deep brain stimulation (DBS) planning and to enhance postsurgical visualization of the DBS lead positions.

METHODS

Presurgical T1-weighted (T1w), T2-weighted (T2w), and QSM images as well as postsurgical CT images were obtained in 29 patients with Parkinson's disease. To enhance the contrast within the GP, a hybrid contrast was created by linearly combining T1w and QSM images. Contrast-to-noise ratios (CNRs) of the GPi on T1w, T2w, QSM, and hybrid images were compared. The CNR differences were tested using the 1-way ANOVA method. The visualization of the DBS lead position was demonstrated by merging the postsurgical CT with presurgical MR images.

RESULTS

The hybrid images yield the best CNRs for GPi depiction and the visualization of the postsurgical DBS lead position was significantly improved.

CONCLUSIONS

QSM-based images allow for confident localization of borders of the GPi that is superior to T1w and T2w images. High-contrast hybrid images can be used for precisely directed DBS targeting, e.g., GPi DBS for the treatment of advanced Parkinson's disease.

Real-time machine learning classification of pallidal borders during deep brain stimulation surgery

OBJECTIVE

Deep brain stimulation (DBS) of the internal segment of the globus pallidus (GPi) in patients with Parkinson's disease and dystonia improves motor symptoms and quality of life. Traditionally, pallidal borders have been demarcated by electrophysiological microelectrode recordings (MERs) during DBS surgery. However, detection of pallidal borders can be challenging due to the variability of the firing characteristics of neurons encountered along the trajectory. MER can also be time-consuming and therefore costly. Here we show the feasibility of real-time machine learning classification of striato-pallidal borders to assist neurosurgeons during DBS surgery.

APPROACH

An electrophysiological dataset from 116 trajectories of 42 patients consisting of 11 774 MER segments of background spiking activity in five classes of disease was used to train the classification algorithm. The five classes included awake Parkinson's disease patients, as well as awake and lightly anesthetized genetic and non-genetic dystonia patients. A machine learning algorithm was designed to provide prediction of the striato-pallidal borders, based on hidden Markov models (HMMs) and the L₁-distance measure in normalized root mean square (NRMS) and power spectra of the MER. We tested its performance prospectively against the judgment of three electrophysiologists in the operating rooms of three hospitals using newly collected data.

MAIN RESULTS

The awake and the light anesthesia dystonia classes could be merged. Using MER NRMS and spectra, the machine learning algorithm was on par with the performance of the three electrophysiologists across the striatum-GPe, GPe-GPi, and GPi-exit transitions for all disease classes.

SIGNIFICANCE

Machine learning algorithms enable real-time GPi navigation systems to potentially shorten the duration of electrophysiological mapping of pallidal borders, while ensuring correct pallidal border detection.