SANTIA

SANTIA performs automated detection and removal of artifacts from extracellular neuronal recordings to improve the quality of invasive local field potential (LFP) data for neuroscientific analysis.

Key Features:

• MATLAB implementation: MATLAB-based toolbox for signal processing and analysis of extracellular neuronal recordings.
• Neural network–based machine learning: Employs neural network–based machine learning techniques for artifact identification.
• Data labeling and model training: Provides workflows to label recordings and train models for identification and removal of artifacts.
• Artifact removal for LFPs: Automates removal of artifacts from invasive extracellular local field potential (LFP) signals.
• Quality control for large datasets: Targets noise and artifacts in high-volume neuronal recordings to support data quality control.

Scientific Applications:

• Neuronal signal preprocessing: Produces cleaner LFP data for downstream analyses such as spike-field and network activity studies.
• Brain activity research: Improves interpretation of neuronal network activation and brain functionalities from extracellular recordings.
• Neurological disorder studies: Supports research on brain activity and neurological disorders by providing artifact-reduced LFP datasets.

Methodology:

Implemented in MATLAB and using neural network–based machine learning to label recordings and train models for automated detection and removal of artifacts from invasive extracellular LFP signals.