Classification of Stereo-EEG Contacts in White Matter vs. Gray Matter Using Recorded Activity

Abstract

For epileptic patients requiring resective surgery, a modality called stereo-electroencephalography (SEEG) may be used to monitor the patient's brain signals to help identify epileptogenic regions that generate and propagate seizures. SEEG involves the insertion of multiple depth electrodes into the patient's brain, each with 10 or more recording contacts along its length. However, a significant fraction (≈ 30% or more) of the contacts typically reside in white matter or other areas of the brain which can not be epileptogenic themselves. Thus, an important step in the analysis of SEEG recordings is distinguishing between electrode contacts which reside in gray matter vs. those that do not. MRI images overlaid with CT scans are currently used for this task, but they take significant amounts of time to manually annotate, and even then it may be difficult to determine the status of some contacts. In this paper we present a fast, automated method for classifying contacts in gray vs. white matter based only on the recorded signal and relative contact depth. We observe that bipolar referenced contacts in white matter have less power in all frequencies below 150 Hz than contacts in gray matter, which we use in a Bayesian classifier to attain an average area under the receiver operating characteristic curve of 0.85 ± 0.079 (SD) across 29 patients. Because our method gives a probability for each contact rather than a hard labeling, and uses a feature of the recorded signal that has direct clinical relevance, it can be useful to supplement decision-making on difficult to classify contacts or as a rapid, first-pass filter when choosing subsets of contacts from which to save recordings.

Keywords: SEEG; bipolar reference; classification; power spectrum; stereo-electroencephalography; white matter.

Figure 1

Example of SEEG electrode placement and raw voltage data for sample subject EFRI13 over a 20 s snapshot. Blue traces denote gray matter and red traces denote white matter. Each trace has a scale of 400 uV and has a monopolar reference.

Figure 2

Power spectral density (PSD) plots for two example patients over a snapshot of 10 s with monopolar and bipolar referencing. EFRI13 (A), and EFRI16 (B) are shown with PSD segregated based on contacts in white matter (red traces) or gray matter (blue traces). Shaded regions denote one standard deviation. Spikes at multiples of 60 Hz are due to line frequency noise.

Figure 3

Graphical model for a patient in the test set. There are S electrode shanks to be classified, each with N_s electrode contacts. The contact label is given by z_i, and the observed features are given by x_i. α and β are parameters whose distribution is estimated using the training set D, which is not shown here.

Figure 4

Two dimensional white and gray matter distributions of features: power spectrum difference from average (relative power) and contact depth. These distributions (specifically the training subsets of them) form our white and gray matter likelihoods. All contacts from all patients are shown here, with the feature distribution of white matter contacts shown in red and the distribution for gray matter contacts shown in blue. (A) Histogram. (B) Overlaid contour plots of estimated kernel densities.

Figure 5

Examples of estimated white matter probabilities for several patients. For each patient, the left column is the probabilities estimated by our classifier, while the right column is the reference labeling done by clinicians using MRI+CT. Each row represents one electrode shank, with individual contacts labeled below. In the reference labeling, red indicates that the contact was labeled as white matter, blue indicates gray matter. In the estimated probabilities, red indicates higher probability of a contact being in white matter according to our classifier. First row: Two of the best patients (EFRI18, LA11), each with > 0.9 AUC. Second row: Two median patients (LA24, LA08), each with 0.86 AUC. Third row: The two worst patients (EFRI17, LA01), representing 0.65 and 0.62 AUC, respectively.

Figure 6

Receiver operating characteristic (ROC) curves for all patients. For a given threshold value p_thresh, a contact is classified as white matter if the probability computed by the classifier is above that threshold. Each curve shows how the fraction of false positives (gray matter contacts incorrectly classified as white matter) and true positives (white matter contacts correctly identified) varies with the threshold level. The red dots indicate the point on the curve obtained when p_thresh = 0.5. The area under the curve (AUC) is the integral of the ROC curve and measures overall performance. (A) ROC curves when prior smoothing parameter β is automatically integrated over with respect to its estimated posterior distribution (see section 2). Mean AUC = 0.845 ± 0.079 (SD). Patients shown in Figure 5 are labeled. The mean ROC curve is shown in bold. (B) ROC curves when β is chosen to maximize AUC over the training set. Mean AUC = 0.859 ± 0.097 (SD).

Figure 7

Estimated probability of white matter for electrode contacts as a function of distance from the nearest white matter/gray matter transition. The transition point is defined to be at x = 0, and the first contact on the white matter side is at x = 0.5, the second contact is at x = 1.5, and so forth in unit increments. Positive distances indicate that the contact is deeper into a white matter region, while negative distances indicate the same for gray matter regions. The center circle of each box plot is the median, the thick line indicates the first and third quartiles, and the thin line represents an additional 1.5 times the interquartile range. Points outside this are plotted individually as circles.