Research

Understanding brain dynamics across modalities and populations.

I develop computational approaches for non-invasive neuroimaging, connecting methodological advances in AI with questions in cognition, sleep, pediatric cancer survivorship, and neuromodulation.

01

Sleep, memory & pediatric survivorship

Examining fast and slow sleep spindles and their association with post-sleep memory consolidation in long-term pediatric cancer survivors using EEG.

  • Sleep EEG
  • Memory
  • Childhood cancer
02

Functional networks & rehabilitation

Characterizing cerebral network disruption after medulloblastoma surgery and supporting cognitive rehabilitation through real-time fMRI neurofeedback.

  • Connectivity
  • Graph theory
  • Neurofeedback
03

Foundation models for brain signals

Developing self-supervised frameworks for resting-state fMRI connectivity and sleep EEG dynamics with region-aware and explainable representations.

  • Self-supervision
  • fMRI
  • EEG

Current directions

Translational and multimodal methods

My current work at St. Jude combines computational modeling, clinical neuroscience, and non-invasive brain technologies.

Focused-ultrasound neuromodulation

Establishing a simulation pipeline for low-intensity transcranial focused ultrasound in sickle cell disease, integrating Brainsight, SimNIBS-based anatomical extraction, and BabelBrain to study targeting and pediatric safety constraints.

Multimodal neural decoding

Building on postdoctoral work in EEG-fNIRS fusion, auditory processing, and overparameterized neural decoding to understand complementary electrophysiological and hemodynamic signals.

Brain rhythms and naturalistic cognition

Extending doctoral research on music perception, emotion, meditation, mind-wandering, and cognitive-state decoding from EEG signals and functional networks.

Open and reproducible neuroimaging

Creating reusable analysis pipelines, public EEG datasets, and computational resources that support transparent, collaborative brain research.

Methods

From signal acquisition to interpretable models.

My work spans experimental design, multimodal acquisition, signal processing, functional connectivity, deep learning, high-performance analysis, and scientific software development.

  • Python
  • PyTorch
  • MNE
  • FSL
  • SPM
  • EEGLAB