Probabilistic electrical stimulation mapping of human medial frontal cortex

Abstract

The medial frontal cortex remains functionally ill-understood; this is reflected by the heterogeneity of behavioural outcomes following damage to the region. We aim to use the rich information provided by extraoperative direct electrical cortical stimulation to enhance our understanding of its functional anatomy. Examining a cohort of 38 epilepsy patients undergoing direct electrical cortical stimulation in the context of presurgical evaluation, we reviewed stimulation findings and classified them in a behavioural framework (positive motor, negative motor, somatosensory, speech disturbances, and "other"). The spatially discrete cortical stimulation-derived data points were then transformed into continuous probabilistic maps, thereby enabling the voxel-wise spatial inference widely used in the analysis of functional and structural imaging data. A functional map of stimulation findings of the medial wall emerged. Positive motor responses occurred in 141 stimulations (31.2%), anatomically located on the paracentral lobule (threshold at p<.05), extending no further than the vertical anterior commissure (VCA) line. Thirty negative motor responses were observed (6.6%), localised to the VCA line (at p < .001 uncorrected). In 43 stimulations (9.5%) a somatosensory response localised to the caudal cingulate zone (at p < .001 uncorrected), with a second region posterior to central sulcus. Speech disturbances were elicited in 38 stimulations (8.4%), more commonly but not exclusively from the language fMRI dominant side, just anterior to VCA (p < .001 uncorrected). In only 2 stimulations, the patient experienced a subjective "urge" to move in the absence of overt movement. Classifying motor behaviour along the dimensions of effector, and movement vs arrest, we derive a wholly data-driven stimulation map of the medial wall, powered by the largest number of stimulations of the region reported (n = 452) in patients imaged with MRI. This model and the underlying data provide a robust framework for understanding the architecture of the region through the joint analysis of disruptive and correlative anatomical maps.

Keywords: Direct electrical cortical stimulation; Epilepsy surgery; Intracranial EEG recordings; Probability estimate; Supplementary motor cortex.

Fig. 1

Distribution of stimulation locations across the medal wall. The red spherical glyphs show the stimulated locations in MNI space in the rostrocaudal plane, where sampled more than once indicated by a proportionately larger diameter glyph. The colourmap shows the continuous probability density of sampling in the same plane, derived by convolving each stimulated location with a Gaussian kernel of 10 mm full-width-at-half-maximum. The locations are summed in the coronal plane extending 22 mm from the midline and transposed to one hemisphere. The image underlay is composed of the median of the normalized white matter tissue probability maps of all participants, thresholded at p < .05 (in white), and the median of the normalized grey matter tissue probability maps of all participants, thresholded at p < .05 (in translucent grey).

Fig. 2

Probability density maps of stimulation-induced behaviours. The colourmaps show the estimated probability density of eliciting each of six categories of behaviour, including no response at all, derived by convolving each stimulated location where the behaviour is observed with a Gaussian kernel of 10 mm full-width-at-half-maximum, normalised by the overall sampling density. The white and black contours labelled “fMRI” show the p < .05 family-wise error corrected boundaries in the rostrocaudal plane of BOLD activation observed in the fluency and verb generation tasks across the group. The image underlay is composed of the median of the normalized white matter tissue probability maps of all participants, thresholded at p < .05 (in white), and the median of the normalized grey matter tissue probability maps of all participants, thresholded at p < .05 (in translucent grey).

Fig. 3

Permutation-based voxel-wise statistical maps of stimulation-induced behaviours. The colourmaps show the estimated voxel-wise z score for a permutation test of the null hypothesis of exchangeability of behavioural categories in response to stimulation. The colourmaps are thresholded at p < .001 uncorrected. Voxels labelled with white glyphs indicate those surviving a threshold of p < .05 family-wise error corrected. The white and black contours labelled “fMRI” show the p < .05 family-wise error corrected boundaries in the rostrocaudal plane of BOLD activation observed in the fluency and verb generation tasks across the group. The image underlay is composed of the median of the normalized white matter tissue probability maps of all participants, thresholded at .05 (in white), and the median of the normalized grey matter tissue probability maps of all participants, thresholded at .05 (in translucent gray).