Opportunities of connectomic neuromodulation

Abstract

The process of altering neural activity - neuromodulation - has long been used to treat patients with brain disorders and answer scientific questions. Deep brain stimulation in particular has provided clinical benefit to over 150,000 patients. However, our understanding of how neuromodulation impacts the brain is evolving. Instead of focusing on the local impact at the stimulation site itself, we are considering the remote impact on brain regions connected to the stimulation site. Brain connectivity information derived from advanced magnetic resonance imaging data can be used to identify these connections and better understand clinical and behavioral effects of neuromodulation. In this article, we review studies combining neuromodulation and brain connectomics, highlighting opportunities where this approach may prove particularly valuable. We focus on deep brain stimulation, but show that the same principles can be applied to other forms of neuromodulation, such as transcranial magnetic stimulation and MRI-guided focused ultrasound. We outline future perspectives and provide testable hypotheses for future work.

Keywords: Brain networks; Brain stimulation; Connectomics; Deep brain stimulation; Diffusion MRI; Functional MRI; Network fingerprinting; Neuromodulation; Tractography; dMRI; fMRI.

Fig. 1.

Methods used for clinical neuromodulation of the brain. List on the left shows recent device approvals issued by the U.S. Food and Drug Administration (FDA). HDE = Humanitarian device excemption. Various lesioning devices have been previously approved by the FDA for ablation of neural tissue (radiofrequency thermoablation, laser interstitial thermal therapy, sterotactic radiosurgery) with applications including thalamotomy for tremor, pallidotomy for Parkinson’s or dystonia, and cingulotomy for pain. Other technologies exist but have not been FDA approved for clinical neuromodulation of the brain (e.g. transcranial electrical current stimulation).

Fig. 2.

Noninvasive MRI based methods to estimate brain connectivity. Top: resting-state functional connectivity MRI (rs-fMRI) is based on spontaneous fluctuations in brain activity as indexed by the blood-oxygen-level-dependent (BOLD) signal. This signal is recorded from all voxels simultaneously, and voxels in which the fluctuations are correlated are considered functionally connected. Areas positively correlated to a seed region (right subthalamic nucleus, red box) are shown in hot colors, while regions negatively correlated (anticorrelated) to the seed region are shown in cool colors. Results based on a single subject are shown in the middle column (individualized connectome) while results based on 1000 subjects are shown in the right column (normative connectome). Bottom: diffusion-weighted imaging (dMRI) measures water diffusion which is anisotropic in the brain. In general, diffusion is stronger along the direction of larger fiber bundles as opposed to orthogonal to them. Based on local diffusion properties of each voxel (which can be represented as orientation distribution functions), tractography algorithms can estimate the location of white-matter bundles to provide an estimate of structural connectivity. White matter bundles passing through the subthalamic nucleusare shown for a single subject in the middle column and for a group of 1000 subjects in the right column. Displayed data are from the human connectome andgenome superstruct projects (Holmes et al., 2015; van Essen and Ugurbil, 2012).

Fig. 3.

Functional connections with deep brain stimulation (DBS) sites that are correlated with clinical improvement. Top: DBS electrode locations targeting the subthalamic nucleus (STN) in patient’s with Parkinson’s disease (left), the ventral intermediate nucleus of the thalamus (VIM) in patients with essential tremor (middle), and the anterior limb of the internal capsule (ALIC) in patients with OCD (right). Bottom: brain regions whose functional connectivity to DBS sitesis correlated with clinical improvement. Positive correlations are shown in warm colors and negative correlations are shown in cool colors. DBS data are from previous studies (Al-Fatly et al., 2019; Baldermann et al., 2019b; Horn et al.,2017) and electrodes are displayed with axial slices from the 100um 7T postmortem MRI template (Edlow et al., 2019). Ca: Caudate nucleus, Pu: Putamen, NAcc: Nucleus Accumbens, vPall: ventral Pallidum.

Fig. 4.

Filtering structural connectomes based on clinical improvement. (A) Active contact locations from 50 patients (four cohorts) that underwent DBS surgery for OCD to multiple different neuranatomical targets are shown as small spheres. The color of each sphere refers to the cohort (Li et al., 2020). Fiber tracts from a normative structural connectome were identified that traversed the stimulation site more frequently in patients with good clinical response (red) versus poor clinical response (blue). (B) The same method was applied to data from 51 patients that underwent STN-DBS for PD and identified the premotor hyperdirect pathway (red fibers) as being associated with better clinical response (Treu et al., 2020).