fMRI Brain-Computer Interfaces

  title={fMRI Brain-Computer Interfaces},
  author={Ranganatha Sitaram and Nikolaus Weiskopf and Andrea Caria and Ralf Veit and Michael Erb and Niels Birbaumer},
  journal={IEEE Signal Processing Magazine},
Brain-computer interfaces based on fMRI enable real-time feedback of circumscribed brain regions to learn volitional regulation of those regions. This is an emerging field of intense research, with potential for multiple applications in neuroscientific research in brain plasticity and reorganization, movement restoration due to stroke, clinical rehabilitation of emotional disorders, quality assurance of fMRI experiments, and teaching functional imaging. This article presents a general… 
Real-Time fMRI-Based Brain Computer Interface: A Review
The basic architecture of rTFMRI-BCI is reviewed, the emerging machine learning based data analysis approaches (also known as multi-voxel pattern analysis), and the applications and recent advances of rtfMRI- BCI are reviewed.
Functional Magnetic Resonance Imaging-Based Brain Computer Interfaces
The foundations of the fMRI-BCI are reviewed, including the fundamental physics and physiology behind fMRI, a qualitative introduction to relevant statistical analysis techniques are presented, and current applications including control of an external device and therapeutic neurofeedback techniques are discussed.
Detection of Cerebral Reorganization Induced by Real-Time fMRI Feedback Training of Insula Activation
The authors demonstrate the application of multivariate methods for assessing cerebral reorganization during the learning of volitional control of local brain activity and provide insight into mechanisms of training-induced learning techniques for rehabilitation.
Real-Time Decoding of Brain Responses to Visuospatial Attention Using 7T fMRI
It is shown, using real-time fMRI at 7T, that eye movement-independent visuospatial attention can be used as a reliable control strategy for BCI, and is a promising new target for intracranial BCI.
Hemodynamic brain-computer interfaces for communication and rehabilitation
Real-Time fMRI
The authors describe the implementation and application of real-time fMRI with particular emphasis on the self-regulation of local brain activity and the investigation of brain-function relationships, which represents a promising new approach to cognitive neuroscience.
Real-time fMRI brain-computer interface: development of a “motivational feedback” subsystem for the regulation of visual cue reactivity
The newly developed visual feedback subsystem can be integrated into protocols for imaging-based brain-computer interfaces (BCI) and may facilitate neurofeedback research and applications into healthy and dysfunctional motivational processes, such as food craving or addiction.
Single-trial detection of realistic images with magnetoencephalography
  • H. Cecotti, G. Prasad
  • Computer Science
    2015 International Joint Conference on Neural Networks (IJCNN)
  • 2015
The present results show that MEG can be successfully used for target detection during a difficult RSVP task and suggest that single-trial detection can be obtained with an AUC superior to 0.8.
Visual Representation Model for fMRI-based Brain Decoding
It is shown that visual features derived from images can be well predicted for decoding fMRI patterns, and a novel fMRI-based brain decoding model is present that effectively learns a compact but discriminative model for characterizing neural coding.


Principles of a brain-computer interface (BCI) based on real-time functional magnetic resonance imaging (fMRI)
A fMRI-based BCI which performs data processing and feedback of the hemodynamic brain activity within 1.3 s is presented, which allows for studying behavioral effects and strategies of local self-regulation in healthy and diseased subjects.
Functional MRI for neurofeedback: feasibility studyon a hand motor task
An fMRI-based method that enables subjects to monitor and actively modulate their own brain activity as a form of biofeedback and suggests that the visual feedback of the functional brain activation maps guided subjects to adjust their task performance to achieve the desired modulation of cortical activity.
An EEG-driven brain-computer interface combined with functional magnetic resonance imaging (fMRI)
The thought translation device is a brain-computer interface that was developed for training and application of SCP self-regulation and was combined with functional magnetic resonance imaging to investigate the neurophysiological mechanisms of SCP regulation.
Brain–computer interface using fMRI: spatial navigation by thoughts
The proposed fMRI-BCI method allowed volunteer subjects to navigate through a simple 2D maze solely through their thought processes and was able to be translated into predetermined computer commands for moving four directional cursors.