Clinical magnetoencephalography for neurosurgery

Abstract

Noninvasive neuroimaging aids in surgical planning and in counseling patients about possible risks of surgery. Magnetoencephalography (MEG) performs the most common types of surgical planning that the neurosurgeon faces, including localization of epileptic discharges, determination of the hemispheric dominance of verbal processing, and the ability to locate eloquent cortex. MEG is most useful when it is combined with structural imaging, most commonly with structural magnetic resonance (MR) imaging and MR diffusion imaging. This article reviews the history of clinical MEG, introduces the basic concepts about the biophysics of MEG, and outlines the basic neurosurgical applications of MEG.

Figure 1

Dr. David Cohen, Ph.D performed the first magnetic fields from the brain. His laboratory at Massachusetts Institute of Technology in Boston, Massachusetts USA pioneered MEG experiments and applications.

Figure 2

Typical modern MEG device positioned in the upright position facing a back projection screen.

Figure 3

MEG somatosensory response from median nerve electrical stimulation. (A) equivalent current dipole fittings of the primary somatosensory SI (axial T1-wieghted MRI) and secondary SII areas (left lower). The 2 locations for SI are for ipsilateral (20ms latency) and contralateral (35ms) stimulation. (B) The distributed source solution using a noise-normalized minimum norm estimate (MNE) shown at 35 ms and 90 ms after stimulation (lower right).

Figure 4

Current algorithm for presurgical lateralization of language and memory. ESM is electrical stimulation map with the grid This diagram depicts language and memory assessment used at many centers, including ours. In this algorithm, noninvasive language and memory tests are sometimes followed by IAP and, if needed, subdural grid evaluation prior to resection. Modified after {Loddenkemper, 2008 #2470}.

Figure 5

Multiple imaging modalities for language mapping (MEG, fMRI, and DTI). (A) MEG waveforms for left and right temporal (LT and RT, respectively) and occipital (LO, RO) sensors, showing several peaks related to sensory and language activity. (B) Laterality index as a function of the goodness of fit (GOF )of a sequential equivalent current dipole (ECD) fit to the MEG data, suggesting left-hemisphere dominance. (C) Locations of the ECDs for the MEG data (top) and functional MRI (bottom) for a visual reading task, displayed in coronal and sagittal slices of of anatomical MRI. Note the cluster of MEG dipoles in the posterior superior temporal gyrus, presumably including Wernicke's area. Functional MRI shows largest activation in the inferior lateral left frontal cortex. The location of a tumor in the left temporal lobe is highlighted with the red oval. (D) MRI tractography showing the superior longitudinal fasciculus (SLF) that connects temporal and frontal language areas. Note that the tumor (red) does not interrupt or displace the SLF white matter fiber bundle.

Figure 6

Beamformer for presurgical mapping. The upper panel shows the map for language using a visually presented word with robust activation of anterior language cortex, comprising Broca's area. A verb generation paradigm was used to map the posterior language areas (Wernicke's area). [Figure courtesy of Dr. Erin Simon Schwartz and Dr. Timothy Roberts, Children's Hospital Philadelphia].

Figure 7

Localization of epileptic spikes. (A) Simultaneously acquired EEG (top) and MEG (bottom) signals from a patient with epilepsy. An epileptic spike is seen in MEG sensors over the right temporal and frontal regions. (B) An equivalent current dipole (ECD) computed at the peak of the spike (“0 ms”; the corresponding isocontour map of the MEG data, with the ECD as a green arrow, is shown at top left) is localized in the temporal lobe (blue dots superimposed on the anatomical MRI). (C) Distributed source estimates, the noise-normalized minimum-norm estimate (MNE), also known as dynamic statistical parametric map (dSPM), for the MEG data are displayed on the cortical surface representation reconstructed from anatomical MRI. The source estimates suggest that the activity propagates from a right temporal region (“0 ms”) to the right frontal region (“50 ms”). (D) Comparison of MEG data with intracranial EEG (iEEG). The left panel shows the estimated MEG source waveforms (MNE) at four locations (“1” and “2” temporal, “3” and “4” frontal). The right panel shows the iEEG of an epileptic spike at corresponding locations. The MEG and iEEG are consistent in suggesting temporal activity propagating to the frontal lobe over a 50 ms time period. [Figures created by Dr. Naoro Tanaka, M.D., Ph.D.]

Figure 8

Frequency spectrum and spatial distribution of imaginary coherence (IC). (A) Tumor tissue has lower functional connectivity in the alpha frequency range than nontumor tissue of lesion patients and healthy control subjects. (B) The functional connectivity from healthy subjects superimposed on 3D brain atlas. High functional connectivity is found in Broca's area and right visual cortex. [From {Guggisberg, 2008 #595}. Used with permission]

Figure 9

Functional maps obtained with MEG connectivity and ESM (yellow) and funcitonal connectivity images of four patients with brain tumors are superimposed over their three-dimensional-rendered individual brain. (A) Twenty-five-year-old woman with a right foot with grade III astrocytoma grade infiltrating the left medial sensorimotor cortex. Functional connectivity in the right foot area of the sensorimotor cortex was decreased. (B) MEG functional connectivity in three tumor patients without presurgical functional deficits, sugesting functional disconnection (blue) of the corresponding tumor tissue (graded 0–2, with 0 indicating smallest proportion of decreased functional connectivity). In agreement with the MEG functional connectivity images and the clinical status, eloquent cortex was mapped outside of decreased connectivity (blue) areas by MEG and cortical mapping in all patients. MEG functional connectivity predicts post-surgery function: whereas Patient 6 suffered from postsurgical sensible deficits in the left arm and leg, Patients 1 and 9 had no post-operative deficits. Red areas indicate increased connectivity. [From {Guggisberg, 2008 #595}. Used with permission]