Reproduce “A Spiking Neural Network (SNN) for detecting High Frequency Oscillations (HFOs) in the intraoperative ECoG” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Karla Burelo, Mohammadali Sharifshazileh, Niklaus Krayenbühl, Georgia Ramantani, Giacomo Indiveri, Johannes Sarnthein
Researchers developed a Spiking Neural Network (SNN) for automated detection of High Frequency Oscillations (HFOs) in intraoperative electrocorticography (ECoG), integrating a novel dis-inhibitory mechanism for artifact rejection. The SNN achieved 100% accuracy in predicting postsurgical seizure outcomes in a cohort of 8 epilepsy patients.
Key insights
- The SNN's dis-inhibitory artifact rejection mechanism effectively differentiated HFOs from fast transients by leveraging distinct temporal spiking patterns, allowing HFOs to be detected while transients were suppressed.
- The SNN-detected HFOs in post-resection ECoG channels showed a strong correlation with postsurgical seizure outcomes, suggesting their potential as a real-time clinical biomarker.
- The SNN architecture is compatible with neuromorphic hardware, offering advantages like low power consumption and compact size for potential real-time integration in operating rooms.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.