Long-term seizure and psychiatric outcomes following laser ablation of mesial temporal structures.

OBJECTIVE: Postsurgical seizure outcome following laser interstitial thermal therapy (LiTT) for the management of drug-resistant mesial temporal lobe epilepsy (MTLE) has been limited to 2 years. Furthermore, its impact on presurgical mood and anxiety disorders has not been investigated. The objectives of this study were (1) to identify seizure outcome changes over a period ranging from 18 to 81 months; (2) to investigate the seizure-free rate in the last follow-up year; (3) to identify the variables associated with seizure freedom; and (4) to identify the impact of LiTT on presurgical mood and anxiety disorders. METHODS: Medical records of all patients who underwent LiTT for MTLE from 2013 to 2019 at the University of Miami Comprehensive Epilepsy Center were retrospectively reviewed. Demographic, epilepsy-related, cognitive, psychiatric, and LiTT-related data were compared between seizure-free (Engel Class I) and non-seizure-free (Engel Class II + III + IV) patients. Statistical analyses included univariate and multivariate stepwise logistic regression analyses. RESULTS: Forty-eight patients (mean age = 43 ± 14.2 years, range = 21-78) were followed for a mean period of 50 ± 20.7 months (range = 18-81); 29 (60.4%) achieved an Engel Class I outcome, whereas 11 (22.9%) had one to three seizures/year. Seizure-freedom rate decreased from 77.8% to 50% among patients with 24- and >61-month follow-up periods, respectively. In the last follow-up year, 83% of all patients were seizure-free. Seizure freedom was associated with having mesial temporal sclerosis (MTS), no presurgical focal to bilateral tonic-clonic seizures, and no psychopathology in the last follow-up year. Presurgical mood and/or anxiety disorder were identified in 30 patients (62.5%) and remitted after LiTT in 19 (62%). SIGNIFICANCE: LiTT appears to be a safe and effective surgical option for treatment-resistant MTLE, particularly among patients with MTS. Remission of presurgical mood and anxiety disorders can also result from LiTT.

Deep learning for robust detection of interictal epileptiform discharges.

Objective.Automatic detection of interictal epileptiform discharges (IEDs, short as 'spikes') from an epileptic brain can help predict seizure recurrence and support the diagnosis of epilepsy. Developing fast, reliable and robust detection methods for IEDs based on scalp or intracranial electroencephalogram (iEEG) may facilitate online seizure monitoring and closed-loop neurostimulation.Approach.We developed a new deep learning approach, which employs a long short-term memory network architecture ('IEDnet') and an auxiliary classifier generative adversarial network (AC-GAN), to train on both expert-annotated and augmented spike events from iEEG recordings of epilepsy patients. We validated our IEDnet with two real-world iEEG datasets, and compared IEDnet with the support vector machine (SVM) and random forest (RF) classifiers on their detection performances.Main results.IEDnet achieved excellent cross-validated detection performances in terms of both sensitivity and specificity, and outperformed SVM and RF. Synthetic spike samples augmented by AC-GAN further improved the detection performance. In addition, the performance of IEDnet was robust with respect to the sampling frequency and noise. Furthermore, we demonstrated the cross-institutional generalization ability of IEDnet while testing between two datasets.Significance.IEDnet achieves excellent detection performances in identifying interictal spikes. AC-GAN can produce augmented iEEG samples to improve supervised deep learning.