Catherine V. Kulick-Soper

Annotating seizure onset and spread in intracranial EEG is essential for epilepsy surgical planning, yet manual annotation is unreliable and cannot scale to large datasets. We introduce Neural Dynamic Divergence (NDD), an unsupervised framework that detects seizure activity by measuring deviation from patient-specific baseline neural dynamics using autoregressive models. NDD requires no labeled training data and adapts to individual patients, channels, and brain states. Validating against expert consensus annotations from 46 seizures, NDD achieves human-level agreement ( ϕ = 0.58 vs. inter-rater ϕ = 0.64) and outperforms existing algorithms on 1,019 seizures with soft labels (AUROC = 0.87). We demonstrate clinical utility by automatically annotating 2,017 seizures, revealing that seizure spread patterns distinguish epilepsy subtypes and predict surgical outcomes. NDD also generalizes to continuous ICU scalp EEG monitoring (AUROC = 0.77). We provide NDD as an open-source Python package to enable scalable seizure annotation across research centers.

Automated seizure detection and localization from intracranial EEG requires validated benchmark datasets with expert annotations, yet existing open datasets lack multi-expert consensus annotations and exclude stimulation-induced seizures. We present stereotactic EEG recordings from 83 seizures (46 spontaneous, 37 stimulation-induced) across 32 patients (19 from the University of Pennsylvania, 13 from the Children’s Hospital of Philadelphia) with drug-resistant epilepsy. Three board-certified epileptologists independently annotated each seizure for onset time, onset channels, and channels seizing at 10 seconds post-onset using a standardized protocol. Consensus annotations were determined through majority voting. Inter-rater agreement was κ = 0.64 for onset channels and κ = 0.62 for spread channels. Individual rater agreement with consensus was κ = 0.81 for onset and κ = 0.80 for spread. Agreement metrics did not differ between spontaneous and stimulation-induced seizures. All data follow Brain Imaging Data Structure (BIDS) standards and include electrode localizations, patient demographics, and clinical outcomes. This dataset enables the validation of seizure onset and spread detection and localization against human expert performance and supports comparative analysis of seizure networks across spontaneous and stimulation-induced seizures.

Seizures are often induced by electrical stimulation (stim seizures) during intracranial EEG (iEEG) evaluation for epilepsy surgery, but their value for localizing seizure generating tissue remains unclear. We compared 441 low-frequency (1 Hz) stim and spontaneous seizures in a multi-center cohort of 105 patients using a novel, state-of-the-art validated automated seizure mapping algorithm. We found that stim seizures recruit a smaller, more spatially restricted network than spontaneous seizures that overlaps with their onset and propagation. Stim seizures with habitual semiology exhibited onset zones indistinguishable from spontaneous seizures. Both clinically habitual and non-habitual stim seizure onset zones were rapidly recruited during spontaneous seizures, suggesting that they arise from hyperexcitable, epileptogenic, tissue. Stim seizures preferentially originated from pathological mesial temporal structures, especially in adult-onset epilepsy. We propose that stimulation mapping has potential to supplant recording spontaneous seizures, and hypothesize that the method may identify portions of epileptic networks susceptible to seizure recurrence after focal interventions.

Objective: Widespread structural pathology in the limbic system is a hallmark of temporal lobe epilepsy (TLE). In this work, we sought to describe a comprehensive readout of limbic abnormalities in TLE using neurite orientation distribution and density imaging (NODDI). Methods: This is a retrospective study of patients with drug‐resistant TLE and healthy controls who underwent research magnetic resonance imaging. We estimated the degree of deviation of the NODDI parameters neurite density index (NDI) and orientation dispersion index (ODI) from healthy controls in limbic regions in the form of univariate z ‐scores. We calculated a multivariate deviation score combining both NDI and ODI (Mahalanobis distance). A summary score representing the overall level of deviation across limbic regions was then computed using the sum of regional deviation scores. We next assessed the diagnostic performance of summary scores in lateralizing TLE as well as associations with neuropsychological deficits and 12‐month surgical outcome. Results: The Mahalanobis distance revealed unique patterns of abnormalities between TLE participants ( n = 74) and controls ( n = 42), with only four of 18 (22%) areas displaying overlapping univariate and multivariate deviations. The multivariate summary score achieved the highest diagnostic accuracy in clinical lateralization of nonlesional TLE (area under the curve [AUC] = .95, 95% confidence interval [CI] = .77–1). Among surgical patients ( n = 30), summary scores corresponding to the hemisphere ipsilateral and contralateral to surgery were predictive of seizure freedom at 12 months (AUC = .84, 95% CI = .76–.93). Significance: We demonstrate unique patterns of abnormalities in neurite density and coherence in limbic microstructure in TLE. A summary score accounting for deviations in both neurite density and coherence achieved high diagnostic accuracy in clinical lateralization of TLE and was associated with surgical outcomes, warranting further study as a putative biomarker in TLE to be used alongside clinical data.

Neuroprognostication for disorders of consciousness (DoC) after severe acute brain injury is a major challenge, and the conventional clinical approach struggles to keep pace with a rapidly evolving literature. Lacking specialization, and fragmented between providers, conventional neuroprognostication is variable, frequently incongruent with guidelines, and prone to error, contributing to avoidable mortality and morbidity. We review the limitations of the conventional approach to neuroprognostication and DoC care, and propose a paradigm entitled the Recovery of Consciousness Via Evidence-Based Medicine and Research (RECOVER) program to address them. The aim of the RECOVER program is to provide specialized, comprehensive, and longitudinal care that synthesizes interdisciplinary perspectives, provides continuity to patients and families, and improves the future of DoC care through research and education. This model, if broadly adopted, may help establish neuroprognostication as a new subspecialty that improves the care of this vulnerable patient population.

Background and Significance: Positron Emission Tomography (PET) using fluorodeoxyglucose (FDG-PET) is a standard imaging modality for detecting areas of hypometabolism associated with the seizure onset zone (SOZ) in temporal lobe epilepsy (TLE). However, FDG-PET is costly and involves the use of a radioactive tracer. Arterial Spin Labeling (ASL) offers an MRI-based quantification of cerebral blood flow (CBF) that could also help localize the SOZ, but its performance in doing so, relative to FDG-PET, is limited. In this study, we seek to improve ASL’s diagnostic performance by developing a deep learning framework for synthesizing FDG-PET-like images from ASL and structural MRI inputs. Methods: We included 68 epilepsy patients, out of which 36 had well lateralized TLE. We compared the coupling between FDG-PET and ASL CBF values in different brain regions, as well as the asymmetry of these values across the brain. We additionally assessed each modality’s ability to lateralize the SOZ across brain regions. Using our paired PET-ASL data, we developed FlowGAN, a generative adversarial neural network (GAN) that synthesizes PET-like images from ASL and T1-weighted MRI inputs. We tested our synthetic PET images against the actual PET images of subjects to assess their ability to reproduce clinically meaningful hypometabolism and asymmetries in TLE. Results: We found variable coupling between PET and ASL CBF values across brain regions. PET and ASL had high coupling in neocortical temporal and frontal brain regions (Spearman’s r > 0.30, p < 0.05) but low coupling in mesial temporal structures (Spearman’s r < 0.30, p > 0.05). Both whole brain PET and ASL CBF asymmetry values provided good separability between left and right TLE subjects, but PET (AUC = 0.96, 95% CI: [0.88, 1.00]) outperformed ASL (AUC = 0.81; 95% CI: [0.65, 0.96]). FlowGAN-generated images demonstrated high structural similarity to actual PET images (SSIM = 0.85). Globally, asymmetry values were better correlated between synthetic PET and original PET than between ASL CBF and original PET, with a mean correlation increase of 0.15 (95% CI: [0.07, 0.24], p d = 0.91). Furthermore, regions that had poor ASL-PET correlation (e.g. mesial temporal structures) showed the greatest improvement with synthetic PET images. Conclusions: FlowGAN improves ASL’s diagnostic performance, generating synthetic PET images that closely mimic actual FDG-PET in depicting hypometabolism associated with TLE. This approach could improve non-invasive SOZ localization, offering a promising tool for epilepsy presurgical assessment. It potentially broadens the applicability of ASL in clinical practice and could reduce reliance on FDG-PET for epilepsy and other neurological disorders.

Background The ictal examination is crucial for neuroanatomic localization of seizure onset, which informs medical and neurosurgical treatment of epilepsy. Substantial variation exists in ictal examination performance in epilepsy monitoring units (EMUs). We developed and implemented a standardized examination to facilitate rapid, reliable execution of all testing domains and adherence to patient safety maneuvers. Methods Following observation of examination performance, root cause analysis of barriers, and review of consensus guidelines, an ictal examination was developed and disseminated. In accordance with quality improvement methodology, revisions were enacted following the initial intervention, including differentiation between pathways for convulsive and nonconvulsive seizures. We evaluated ictal examination fidelity, efficiency, and EMU staff satisfaction before and after the intervention. Results We identified barriers to ictal examination performance as confusion regarding ictal examination protocol, inadequate education of the rationale for the examination and its components, and lack of awareness of patient-specific goals. Over an 18-month period, 100 ictal examinations were reviewed, 50 convulsive and 50 nonconvulsive. Ictal examination performance varied during the study period without sustained improvement for convulsive or nonconvulsive seizure examination. The new examination was faster to perform (0.8 vs 1.5 minutes). Postintervention, EMU staff expressed satisfaction with the examination, but many still did not understand why certain components were performed. Conclusion We identified key barriers to EMU ictal assessment and completed real-world testing of a standardized, streamlined ictal examination. We found it challenging to reliably change ictal examination performance in our EMU; further study of implementation is warranted.