ADJUST: An automatic EEG artifact detector based on the joint use of spatial and temporal features

Authors

  • Andrea Mognon,

    1. Functional NeuroImaging Laboratory, Center for Mind/Brain Sciences, Department of Cognitive and Education Sciences, University of Trento, Trento, Italy
    2. NILab, Neuroinformatics Laboratory, Fondazione Bruno Kessler, Trento, Italy
    Search for more papers by this author
  • Jorge Jovicich,

    1. Functional NeuroImaging Laboratory, Center for Mind/Brain Sciences, Department of Cognitive and Education Sciences, University of Trento, Trento, Italy
    Search for more papers by this author
  • Lorenzo Bruzzone,

    1. Department of Information Engineering and Computer Science, University of Trento, Trento, Italy
    Search for more papers by this author
  • Marco Buiatti

    1. Functional NeuroImaging Laboratory, Center for Mind/Brain Sciences, Department of Cognitive and Education Sciences, University of Trento, Trento, Italy
    2. INSERM, U992, Cognitive Neuroimaging Unit, Gif/Yvette, France
    3. CEA, DSV/I2BM, NeuroSpin Center, Gif/Yvette, France
    4. Université Paris-Sud, Cognitive Neuroimaging Unit, Gif/Yvette, France
    Search for more papers by this author

  • We thank Mariano Sigman and Stanislas Dehaene for sharing the EEG data, Francesca Bovolo and Michele Dalponte for helpful advice on the use of the thresholding algorithm, and Sara Assecondi for valuable comments on an earlier version of the manuscript.

Address correspondence to: Marco Buiatti, CEA/DSV/I2BM/NeuroSpin, INSERM U992—Cognitive Neuroimaging Unit, Bât 145—Point Courrier 156, Gif sur Yvette F-91191, France. E-mail: marco.buiatti@gmail.com

Abstract

A successful method for removing artifacts from electroencephalogram (EEG) recordings is Independent Component Analysis (ICA), but its implementation remains largely user-dependent. Here, we propose a completely automatic algorithm (ADJUST) that identifies artifacted independent components by combining stereotyped artifact-specific spatial and temporal features. Features were optimized to capture blinks, eye movements, and generic discontinuities on a feature selection dataset. Validation on a totally different EEG dataset shows that (1) ADJUST's classification of independent components largely matches a manual one by experts (agreement on 95.2% of the data variance), and (2) Removal of the artifacted components detected by ADJUST leads to neat reconstruction of visual and auditory event-related potentials from heavily artifacted data. These results demonstrate that ADJUST provides a fast, efficient, and automatic way to use ICA for artifact removal.

Ancillary