Candle improves brain activity imaging from eeg with mri data
CANDLE: Cortical Null-Space Decomposition for Noninvasive Brain Source Imaging
Machine Learning
Summary
Measuring brain activity from outside the head with EEG is tricky because many brain signals can produce similar measurements. The authors propose CANDLE, a computer method that uses detailed brain shapes from MRI scans to better estimate where brain activity is happening. They trained CANDLE on computer-generated brain data from over 1,100 people and showed it works well on real EEG tasks like locating brain stimulation and epilepsy zones. This approach helps in interpreting EEG signals more accurately for individual brains.
What this means in practice
- •For clinical neurophysiologists: Improve localization of brain activity from EEG using personalized MRI data for pre-surgical planning in epilepsy.
- •For medical device engineers: Develop EEG analysis tools that leverage subject-specific brain shapes to enhance source imaging accuracy.
Authors
Shuntaro Suzuki, Yuiga Wada, Komei Sugiura
Abstract
Electrophysiological source imaging (ESI) aims to estimate cortical source activity from noninvasive electrophysiological measurements such as electroencephalogram (EEG). However, ESI is fundamentally ill-posed because source activity is substantially higher-dimensional than sensor observations, resulting in non-unique solutions. Recent learning-based approaches address this ambiguity by learning data-driven source priors, yet they often struggle to generalize across subject-specific cortical geometries. To address this, we propose CANDLE, a learning-based ESI model that estimates source activity on subject-specific cortical geometries. CANDLE learns a prior over the null space induced by the source-to-sensor mapping derived from T1-weighted MRI, restricting learning to unobservable source components while preserving geometric constraints. To train CANDLE, we develop a whole-brain simulator spanning over 1,100 subject-specific cortical geometries with source configurations derived from over 26,000 statistical brain maps. Trained exclusively on simulated data, CANDLE outperformed prior ESI methods on simulated source activity estimation and generalized to two empirical tasks: (i) intracranial stimulation localization from simultaneously recorded scalp EEG and (ii) epileptogenic zone estimation from presurgical interictal EEG. Our project page is available at https://candle-esi.pages.dev}{https://candle-esi.pages.dev.