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

Respiratory-related evoked potentials (RREPs) have been elicited by inspiratory occlusion and recorded at electroencephalographic (EEG) sites overlying the somatosensory cortex in adults. The present study was the first to be conducted in normal children and was designed to identify the scalp distribution of the early RREP components. EEG responses to occlusion were recorded from CZ-C3, CZ-C4, and 17 sites referenced to the linked earlobes. The RREP was observed in all subjects in the CZ-C3 and CZ-C4 electrode pairs. The earlobe-referenced recordings revealed two RREP patterns. The P1 and N1 peaks were found in C3, C4, P3, P4, T3, and T4. The RREPs recorded from the F3, F4, F7, and F8 electrodes did not exhibit either the P1 or N1 peaks. A negative peak (NF) occurred approximately 13 ms after the P1 peak. The results show that the RREPs to inspiratory occlusions were present bilaterally but diminished greatly over midline sites. Furthermore, consistent with mechanically and electrically elicited somatosensory evoked potentials, the RREP displayed a polarity inversion over the central sulcus in the early component latency range.

Download Full-text

Limiting the Current Density During Localization of the Primary Motor Cortex by Using a Tangential-Radial Cortical Somatosensory Evoked Potentials Model, Direct Electrical Cortical Stimulation, and Electrocorticography

Neurosurgery ◽

10.1227/neu.0b013e3182230ac3 ◽

2011 ◽

Vol 69 (4) ◽

pp. 893-898 ◽

Cited By ~ 4

Author(s):

Faisal R Jahangiri ◽

Jonathan H Sherman ◽

Jason Sheehan ◽

Mark Shaffrey ◽

Aaron S Dumont ◽

...

Keyword(s):

Evoked Potentials ◽

Somatosensory Evoked Potentials ◽

Primary Motor Cortex ◽

Cortical Stimulation ◽

Cortical Mapping ◽

Mapping Technique ◽

Central Sulcus ◽

Sensory Cortices ◽

Radial Model ◽

The University

Abstract BACKGROUND: Traditionally, the dual-radial model, which requires high cortical stimulation intensities and may evoke intraoperative seizures, is used for mapping during resection of lesions within or near the central sulcus. OBJECTIVE: To examine the potential utility of using the multimodal tangential-radial triphasic model, which may increase the accuracy and reliability of cortical mapping at lower stimulation intensities. METHODS: We performed a retrospective review of intracranial neuromonitoring cases at the University of Virginia. The tangential-radial triphasic model used direct electrical cortical stimulation (DECS), electrocorticography, and somatosensory evoked potentials with an additional P25 peak for waveform interpretation, instead of the older dual-radial model with N20 and P30 peaks alone. The central sulcus and sensory cortex were localized by generating multiple sensory maps. DECS with 50-Hz frequency was applied. Electrocorticography was used for detection of afterdischarges. RESULTS: Fifteen consecutive intracranial cases were identified. The patients consisted of 8 males and 7 females ranging in age from 12 to 74 years (median, 53 years). Fourteen patients had an intra-axial cortical mass, and 1 patient had a cortical arteriovenous malformation. The DECS thresholds ranged from 3.7 to 12 mA (median, 6.2 mA). Localization of motor and sensory cortices was accurately performed at low thresholds with bipolar DECS in all patients. Intraoperative seizures occurred in 1 patient (7%), and new permanent postoperative functional deficits occurred in 1 patient (7%). CONCLUSION: Our mapping technique appears safe and reliable for resection near the central sulcus. The tangential-radial triphasic model allows for lower stimulation intensities, reducing the risk of intraoperative seizures.

Download Full-text

Migraine classification using somatosensory evoked potentials

Cephalalgia ◽

10.1177/0333102419839975 ◽

2019 ◽

Vol 39 (9) ◽

pp. 1143-1155 ◽

Cited By ~ 12

Author(s):

Bingzhao Zhu ◽

Gianluca Coppola ◽

Mahsa Shoaran

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Evoked Potentials ◽

Healthy Volunteers ◽

Somatosensory Evoked Potentials ◽

Evoked Potential ◽

Machine Learning Algorithms ◽

Somatosensory Evoked Potential ◽

Support Vector ◽

Extreme Gradient Boosting

Objective The automatic detection of migraine states using electrophysiological recordings may play a key role in migraine diagnosis and early treatment. Migraineurs are characterized by a deficit of habituation in cortical information processing, causing abnormal changes of somatosensory evoked potentials. Here, we propose a machine learning approach to utilize somatosensory evoked potential-based biomarkers for migraine classification in a noninvasive setting. Methods Forty-two migraine patients, including 29 interictal and 13 ictal, were recruited and compared with 15 healthy volunteers of similar age and gender distribution. The right median nerve somatosensory evoked potentials were collected from all subjects. State-of-the-art machine learning algorithms including random forest, extreme gradient-boosting trees, support vector machines, K-nearest neighbors, multilayer perceptron, linear discriminant analysis, and logistic regression were used for classification and were built upon somatosensory evoked potential features in time and frequency domains. A feature selection method was employed to assess the contribution of features and compare it with previous clinical findings, and to build an optimal feature set by removing redundant features. Results Using a set of relevant features and different machine learning models, accuracies ranging from 51.2% to 72.4% were achieved for the healthy volunteers-ictal-interictal classification task. Following model and feature selection, we successfully separated the three groups of subjects with an accuracy of 89.7% for the healthy volunteers-ictal, 88.7% for healthy volunteers-interictal, 80.2% for ictal-interictal, and 73.3% for healthy volunteers-ictal-interictal classification tasks, respectively. Conclusion Our proposed model suggests the potential use of somatosensory evoked potentials as a prominent and reliable signal in migraine classification. This non-invasive somatosensory evoked potential-based classification system offers the potential to reliably separate migraine patients in ictal and interictal states from healthy controls.

Download Full-text

Reliability of somatosensory evoked potentials in intraoperative localization of the central sulcus in patients with perirolandic mass lesions

British Journal of Neurosurgery ◽

10.1080/02688699745907 ◽

1997 ◽

Vol 11 (5) ◽

pp. 411-417 ◽

Cited By ~ 10

Author(s):

K. S. BABU, M. J. CHANDY

Keyword(s):

Evoked Potentials ◽

Somatosensory Evoked Potentials ◽

Central Sulcus ◽

Intraoperative Localization ◽

Mass Lesions

Download Full-text

Tumors localized near the central sulcus may cause increased somatosensory evoked potentials

Clinical Neurophysiology ◽

10.1016/j.clinph.2006.03.009 ◽

2006 ◽

Vol 117 (6) ◽

pp. 1359-1366 ◽

Cited By ~ 2

Author(s):

Ivana Štetkárová ◽

Lubor Stejskal ◽

Markus Kofler

Keyword(s):

Evoked Potentials ◽

Somatosensory Evoked Potentials ◽

Central Sulcus

Download Full-text

Functional localization of sensorimotor cortex by somatosensory evoked potentials produced by femoral nerve stimulation

Neurosurgical FOCUS ◽

10.3171/foc.1996.1.3.7 ◽

1996 ◽

Vol 1 (3) ◽

pp. E7 ◽

Cited By ~ 2

Author(s):

Akifumi Suzuki ◽

Kimio Yoshioka ◽

Hiromi Nishimura ◽

Nobuyuki Yasui

Keyword(s):

Evoked Potentials ◽

Median Nerve ◽

Nerve Stimulation ◽

Somatosensory Evoked Potentials ◽

Sensorimotor Cortex ◽

Femoral Nerve ◽

Central Sulcus ◽

Functional Localization ◽

Postcentral Gyrus ◽

Interhemispheric Fissure

Cortical somatosensory evoked potentials (SSEPs) can be used to localize the central sulcus during a craniotomy. In particular, contralateral median nerve stimulation producing SSEPs can disclose the location of the central sulcus around the sensorimotor hand representation area. However, the median nerve cannot be stimulated in patients who undergo craniotomy at locations other than the hand representation area. The present study attempts to localize the central sulcus in the lateral surface of the brain near the interhemispheric fissure by stimulating the contralateral femoral nerve to produce SSEPs. Somatosensory evoked potentials were recorded between the superior lip of the interhemispheric fissure and 1.5 to 2 cm laterally in the cortex. Only seven of the 12 patients studied showed a phase reversal of the initial component across the central sulcus. The polarity was negative in the postcentral gyrus and positive in the precentral gyrus. The other five patients did not show a phase reversal of the initial component across the central sulcus. The amplitude was highest in the postcentral gyrus and the polarity was positive. Based on these results, the authors hypothesize that stimulating the contralateral femoral nerve to produce SSEPs and then analyzing the distribution of the SSEPs may provide a method for functional localization of the sensorimotor cortex around the interhemispheric fissure during craniotomy.

Download Full-text

Intraoperative localization of the central sulcus by cortical somatosensory evoked potentials in brain tumor

Journal of Neurosurgery ◽

10.3171/jns.1992.76.5.0867 ◽

1992 ◽

Vol 76 (5) ◽

pp. 867-870 ◽

Cited By ~ 26

Author(s):

Akifumi Suzuki ◽

Nobuyuki Yasui

Keyword(s):

Brain Tumor ◽

Evoked Potentials ◽

Somatosensory Evoked Potentials ◽

Topographic Mapping ◽

Central Sulcus ◽

Content Type ◽

Accurate Localization ◽

Intraoperative Localization ◽

Sep Waves ◽

Stimulation Of

✓ Perplexing findings of cortical somatosensory evoked potentials (SEP's) for determining the central sulcus during a craniotomy are reported in a case of brain tumor. On stimulation of the contralateral median nerve in that patient, phase-reversal of SEP waves N1 and P2 was observed not only across the central sulcus but also across the precentral sulcus. In topographic mapping of the N1-P2 amplitude, the sulcus dividing the maximum polarity was the central sulcus; this was confirmed by the cortical stimulation-evoked motor responses. For accurate localization of the central sulcus by cortical SEP's, the distribution of potentials must be analyzed with extensive exposure of the sensorimotor cortex.

Download Full-text