Unsupervised machine learning can delineate central sulcus by using the spatiotemporal characteristic of somatosensory evoked potentials

Abstract

Objective. Somatosensory evoked potentials (SSEPs) recorded with electrocorticography (ECoG) for central sulcus (CS) identification is a widely accepted procedure in routine intraoperative neurophysiological monitoring. Clinical practices test the short-latency SSEPs for the phase reversal over strip electrodes. However, assessments based on waveform morphology are susceptible to variations in interpretations due to the hand area’s localized nature and usually require multiple electrode placements or electrode relocation. We investigated the feasibility of unsupervised delineation of the CS by using the spatiotemporal patterns of the SSEP captured with the ECoG grid. Approach. Intraoperatively, SSEPs were recorded from eight patients using ECoG grids placed over the sensorimotor cortex. Neurosurgeons blinded to the electrophysiology identified the sensory and motor gyri using neuronavigation based on sulcal anatomy. We quantified the most discriminatory time points in SSEPs temporal profile between the primary motor (M1) and somatosensory (S1) cortex using the Fisher discrimination criterion. We visualized the amplitude gradient of the SSEP over a 2D heat map to provide visual feedback for the delineation of the CS based on electrophysiology. Subsequently, we employed spectral clustering using the entire the SSEP waveform without selecting any time points and grouped ECoG channels in an unsupervised fashion. Main results. Consistently in all patients, two different time points provided almost equal discrimination between anterior and posterior channels, which vividly outlined the CS when we viewed the SSEP amplitude distribution as a spatial 2D heat map. The first discriminative time point was in proximity to the conventionally favored ∼20 ms peak (N20), and the second time point was slightly later than the markedly high ∼30 ms peak (P30). Still, the location of these time points varied noticeably across subjects. Unsupervised clustering approach separated the anterior and posterior channels with an accuracy of 96.3% based on the time derivative of the SSEP trace without the need for a subject-specific time point selection. In contrast, the raw trace resulted in an accuracy of 88.0%. Significance. We show that the unsupervised clustering of the SSEP trace assessed with subdural electrode grids can delineate the CS automatically with high precision, and the constructed heat maps can localize the motor cortex. We anticipate that the spatiotemporal patterns of SSEP fused with machine learning can serve as a useful tool to assist in surgical planning.

Mapping of the central sulcus using non-invasive ultra-high-density brain recordings

“…Channels 209, 210, 212, and 215, expected to be located posterior to the central sulcus, exhibit the desired SSEP waveform with a negative peak (N) followed by a positive (P). This pattern aligns with the typical cortical response seen in somatosensory processing 3 , 30 . These findings indicate the successful activation of sensory pathways and the propagation of neural signals across the primary somatosensory cortex.…”

“…These inter-subject differences in peak latencies appear in comparable studies and may reflect variations in neural conduction velocities or discrepancies in the processing mechanisms of the somatosensory systems. However, the timing of the 2nd N peak has generally higher latencies, as found in comparative literature 3 , 26 , 30 . This could be explained by the lower bandpass cutoff at 20 Hz, which is lower compared to other studies but has shown the best results for delineation with the uHD EEG.…”

“…This suggests a change in the polarity of the SSEP waveform at these specific locations. The phase reversal phenomenon could be attributed to the differential activation of neural populations within the somatosensory cortex, as found by several studies 26 , 30 , 39 , 40 . Compared to ECoG SSEP studies, the traces acquired from EEG show reduced amplitude but similar latencies, as found in similar studies 41 .…”

“…However, to receive more prominent and robust neural responses, electrical stimulation of peripheral nerves is favored in clinical studies 28 . The somatosensory evoked potential phase reversal (SSEP-PR) phenomenon is characterized by the cortical N20 potential when detected from the postcentral gyrus, and the cortical P20 potential from the pre-central gyrus is a widely applied methodology to identify the somatosensory cortex 29 , 30 .…”

Automated intraoperative central sulcus localization and somatotopic mapping using median nerve stimulation

“…MacDonald et al 2019, Asman et al 2021). PRT consists of visually detecting specific features of the somatosensory evoked potentials (SSEPs) evoked by median nerve stimulation (MNS) and recording from electrocorticographic (ECoG) electrode grids placed on the surface of the cortex.…”