Machine learning for (non-)epileptic tissue detection from the intraoperative electrocorticogram.

OBJECTIVE: Clinical visual intraoperative electrocorticography (ioECoG) reading intends to localize epileptic tissue and improve epilepsy surgery outcome. We aimed to understand whether machine learning (ML) could complement ioECoG reading, how subgroups affected performance, and which ioECoG features were most important. METHODS: We included 91 ioECoG-guided epilepsy surgery patients with Engel 1A outcome. We allocated 71 training and 20 test set patients. We trained an extra trees classifier (ETC) with 14 spectral features to classify ioECoG channels as covering resected or non-resected tissue. We compared the ETC's performance with clinical ioECoG reading and assessed whether patient subgroups affected performance. Explainable artificial intelligence (xAI) unveiled the most important ioECoG features learnt by the ETC. RESULTS: The ETC outperformed clinical reading in five test set patients, was inferior in six, and both were inconclusive in nine. The ETC performed best in the tumor subgroup (area under ROC curve: 0.84 [95%CI 0.79-0.89]). xAI revealed predictors of resected (relative theta, alpha, and fast ripple power) and non-resected tissue (relative beta and gamma power). CONCLUSIONS: Combinations of subtle spectral ioECoG changes, imperceptible by the human eye, can aid healthy and pathological tissue discrimination. SIGNIFICANCE: ML with spectral ioECoG features can support, rather than replace, clinical ioECoG reading, particularly in tumors.

Pausing propofol during neurosurgery to record intraoperative electrocorticography is feasible;10 years of clinical experience.

OBJECTIVE: Intraoperative electrocorticography (ioECoG) during neurosurgery is influenced by anesthetics. In our center we stop the propofol to enable interpretation of ioECoG. We reported our clinical experience and evaluated awareness and hemodynamic changes during the propofol-free periods (PFP). METHODS: We retrospectively included surgeries with paused propofol administration to record ioECoG (period: 2008-2019). Clinical reports were screened for symptoms of awareness. We compared mean arterial blood pressure (MAP; mmHg) and heart rate (HR;bpm) during PFP to baseline (ten minutes preceding PFP). An increase > 15% was defined as clinically relevant. The association between hemodynamic changes and clinical characteristics was analyzed using logistic regression models. RESULTS: Propofol administration was paused 742 times in 352 surgeries (mean PFP duration 9 ± 5 min). No signs of awareness were reported. MAP and HR increased > 15% in 54 and six PFPs. Five PFPs showed both MAP and HR increases. Prolonged PFP was associated with having MAP and HR increase during surgery (OR=1.18, 95%CI [1.12-1.26]). CONCLUSIONS: Signs of inadequate sedation depth were rare. MAP and HR increases were related to the length of PFP. SIGNIFICANCE: We summarize 10 years of clinical experience with pausing propofol administration during epilepsy surgery to record ioECoG without evidence of awareness.

Intraoperative mapping of epileptogenic foci and tumor infiltration in neuro-oncology patients with epilepsy.

Background: Epileptogenesis and glioma growth have a bidirectional relationship. We hypothesized people with gliomas can benefit from the removal of epileptic tissue and that tumor-related epileptic activity may signify tumor infiltration in peritumoral regions. We investigated whether intraoperative electrocorticography (ioECoG) could improve seizure outcomes in oncological glioma surgery, and vice versa, what epileptic activity (EA) tells about tumor infiltration. Methods: We prospectively included patients who underwent (awake) ioECoG-assisted diffuse-glioma resection through the oncological trajectory. The IoECoG-tailoring strategy relied on ictal and interictal EA (spikes and sharp waves). Brain tissue, where EA was recorded, was assigned for histopathological examination separate from the rest of the tumor. Weibull regression was performed to assess how residual EA and extent of resection (EOR) related to the time-to-seizure recurrence, and we investigated which type of EA predicted tumor infiltration. Results: Fifty-two patients were included. Residual spikes after resection were associated with seizure recurrence in patients with isocitrate dehydrogenase (IDH) mutant astrocytoma or oligodendroglioma (HR = 7.6[1.4-40.0], P-value = .01), independent from the EOR. This was not observed in IDH-wildtype tumors. All tissue samples resected based on interictal spikes were infiltrated by tumor, even if the MRI did not show abnormalities. Conclusions: Complete resection of epileptogenic foci in ioECoG may promote seizure control in IDH-mutant gliomas. The cohort size of IDH-wildtype tumors was too limited to draw definitive conclusions. Interictal spikes may indicate tumor infiltration even when this area appears normal on MRI. Integrating electrophysiology guidance into oncological tumor surgery could contribute to improved seizure outcomes and precise guidance for radical tumor resection.

Spatial and temporal properties of intra-operatively recorded spikes and high frequency oscillations in focal cortical dysplasia.

OBJECTIVE: Focal cortical dysplasias (FCD) are characterized by distinct interictal spike patterns and high frequency oscillations (HFOs; ripples: 80-250 Hz; fast ripples: 250-500 Hz) in the intra-operative electrocorticogram (ioECoG). We studied the temporal relation between intra-operative spikes and HFOs and their relation to resected tissue in people with FCD with a favorable outcome. METHODS: We included patients who underwent ioECoG-tailored epilepsy surgery with pathology confirmed FCD and long-term Engel 1A outcome. Spikes and HFOs were automatically detected and visually checked in 1-minute pre-resection-ioECoG. Channels covering resected and non-resected tissue were compared using a logistic mixed model, assessing event numbers, co-occurrence ratios, and time-based properties. RESULTS: We found pre-resection spikes, ripples in respectively 21 and 20 out of 22 patients. Channels covering resected tissue showed high numbers of spikes and HFOs, and high ratios of co-occurring events. Spikes, especially with ripples, have a relatively sharp rising flank with a long descending flank and early ripple onset over resected tissue. CONCLUSIONS: A combined analysis of event numbers, ratios, and temporal relationships between spikes and HFOs may aid identifying epileptic tissue in epilepsy surgery. SIGNIFICANCE: This study shows a promising method for clinically relevant properties of events, closely associated with FCD.

Robust compression and detection of epileptiform patterns in ECoG using a real-time spiking neural network hardware framework.

Interictal Epileptiform Discharges (IED) and High Frequency Oscillations (HFO) in intraoperative electrocorticography (ECoG) may guide the surgeon by delineating the epileptogenic zone. We designed a modular spiking neural network (SNN) in a mixed-signal neuromorphic device to process the ECoG in real-time. We exploit the variability of the inhomogeneous silicon neurons to achieve efficient sparse and decorrelated temporal signal encoding. We interface the full-custom SNN device to the BCI2000 real-time framework and configure the setup to detect HFO and IED co-occurring with HFO (IED-HFO). We validate the setup on pre-recorded data and obtain HFO rates that are concordant with a previously validated offline algorithm (Spearman's ρ = 0.75, p = 1e-4), achieving the same postsurgical seizure freedom predictions for all patients. In a remote on-line analysis, intraoperative ECoG recorded in Utrecht was compressed and transferred to Zurich for SNN processing and successful IED-HFO detection in real-time. These results further demonstrate how automated remote real-time detection may enable the use of HFO in clinical practice.