Real-time fMRI using brain-state classification

• Type of Material: Article
• Authors: Stephen M. LaConte, Georgia Institute of Technology; Scott J. Peltier, Georgia Institute of Technology; Xiaoping Hu, Emory University
• Language: English
• Date: 2007-10-01
• Publisher: Wiley
• Publication Version: Final Published Version
• Copyright Statement: © 2006 Wiley-Liss, Inc.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1002/hbm.20326
• Title of Journal or Parent Work: Human Brain Mapping
• Volume: 28
• Issue: 10
• Start Page: 1033
• End Page: 1044
• Grant/Funding Information: None declared
• Keywords: Quantitive evaluation; Life Sciences & Biomedicine; Functional neuroimaging; Patterns; Resonance imaging FMRI; Prediction; real-time fMRI; support vector machine; Radiology, Nuclear Medicine & Medical Imaging; MRI; Objects; Neurosciences; Activation; Neurosciences & Neurology; Preprocessing; Neuroimaging; brain state; Science & Technology; Representations; biofeedback
• Research Categories: Health Sciences, Radiology; Engineering, Biomedical; Biology, Neuroscience

Abstract

We have implemented a real-time functional magnetic resonance imaging system based on multivariate classification. This approach is distinctly different from spatially localized real-time implementations, since it does not require prior assumptions about functional localization and individual performance strategies, and has the ability to provide feedback based on intuitive translations of brain state rather than localized fluctuations. Thus this approach provides the capability for a new class of experimental designs in which real-time feedback control of the stimulus is possible - rather than using a fixed paradigm, experiments can adaptively evolve as subjects receive brain-state feedback. In this report, we describe our implementation and characterize its performance capabilities. We observed ∼80% classification accuracy using whole brain, block-design, motor data. Within both left and right motor task conditions, important differences exist between the initial transient period produced by task switching (changing between rapid left or right index finger button presses) and the subsequent stable period during sustained activity. Further analysis revealed that very high accuracy is achievable during stable task periods, and that the responsiveness of the classifier to changes in task condition can be much faster than signal time-to-peak rates. Finally, we demonstrate the versatility of this implementation with respect to behavioral task, suggesting that our results are applicable across a spectrum of cognitive domains. Beyond basic research, this technology can complement electroencephalography-based brain computer interface research, and has potential applications in the areas of biofeedback rehabilitation, lie detection, learning studies, virtual reality-based training, and enhanced conscious awareness.