Analyzing data from deep brain stimulation: Machine Learning provides a map
Simon Leszek
Klaus-Robert Müller
Neurosurgical and neuromodulation therapies require millimeter-level accuracy to effectively target functional brain regions. Yet, many neuroanatomical boundaries remain invisible to current imaging and electrophysiology methods, limiting precision and contributing to suboptimal patient outcomes. In this talk, we present a self-supervised machine learning (ML) framework that identifies functional subregions directly from local file potential (LFP) recordings without the need for predefined biomarkers or anatomical labels. This technology can transform intraoperative LFP recordings into a real-time guidance resource and advance our understanding of functional brain organization.
