Derek J. Doss

KenazLBM is a model that characterizes and predicts brain states from raw iEEG data, generalizing across subjects with heterogeneous recording channels.

This paper analyzes peri-ictal network dynamics in drug-resistant epilepsy patients to show that NIZs increase inhibitory signaling to SOZs during seizures, but this suppression is insufficient to prevent seizure onset.

This study identifies reward circuitry activity predictive of risk-taking in humans using local field potential recordings during a gambling task.

This study examines how connectivity patterns of arousal regulation centers change with vigilance states using EEG and fMRI, showing distinct network correlations in low and high alertness.

This paper introduces BrainState, a self-supervised method to model complex brain states from EEG data, applied to epilepsy patients to capture pre-seizure states and neuromodulation effects.

This paper develops a deep learning model to accurately segment the nucleus basalis of Meynert on 3T MRI, showing improved performance over standard atlases in both healthy subjects and TLE patients.

The paper tests the interictal suppression hypothesis in focal epilepsy using electrographic and structural data to identify seizure onset zones and develop a classification model with high accuracy.

This paper develops a deep learning model to classify seizure onset zones using cortico-cortical evoked potentials from intracranial neurostimulation recordings.