Functional MR Imaging in Real-Time using a sliding-window correlation technique

Gembris, Daniel; Taylor, Jonathan; Schor, Stefan; Suter, Dieter; Posse, Stefan

doi:10.1016/s1053-8119(18)31446-0

Cited by 6 publications

(10 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is well suited for realtime applications, as it has a fast classification response and a fast training. We have recently interfaced the classifier to our real-time fMRI analysis software (TurboFIRE) (Gembris et al, 2000;Gao and Posse, 2004;Posse et al, 2001Posse et al, , 2003) (see also http://www.mic.health.unm.edu/turbofire) and are currently evaluating training and testing performance with cognitive paradigms. The limitations of the method are related to the sparsity of the information in the brain.…”

mentioning

confidence: 99%

fMRI pattern classification using neuroanatomically constrained boosting

et al. 2006

View full text Add to dashboard Cite

Pattern classification in functional MRI (fMRI) is a novel methodology to automatically identify differences in distributed neural substrates resulting from cognitive tasks. Reliable pattern classification is challenging due to the high dimensionality of fMRI data, the small number of available data sets, interindividual differences, and dependence on the acquisition methodology. Thus, most previous fMRI classification methods were applied in individual subjects. In this study, we developed a novel approach to improve multiclass classification across groups of subjects, field strengths, and fMRI methods. Spatially normalized activation maps were segmented into functional areas using a neuroanatomical atlas and each map was classified separately using local classifiers. A single multiclass output was applied using a weighted aggregation of the classifier's outputs. An Adaboost technique was applied, modified to find the optimal aggregation of a set of spatially distributed classifiers. This Adaboost combined the regionspecific classifiers to achieve improved classification accuracy with respect to conventional techniques. Multiclass classification accuracy was assessed in an fMRI group study with interleaved motor, visual, auditory, and cognitive task design. Data were acquired across 18 subjects at different field strengths (1.5 T, 4 T), with different pulse sequence parameters (voxel size and readout bandwidth). Misclassification rates of the boosted classifier were between 3.5% and 10%, whereas for the single classifier, these were between 15% and 23%, suggesting that the boosted classifier provides a better generalization ability together with better robustness. The high computational speed of boosting classification makes it attractive for real-time fMRI to facilitate online interpretation of dynamically changing activation patterns.Keywords: Functional magnetic resonance imaging; Pattern classification; Support vector machines; Adaboost IntroductionBrain activation changes in response to even simple sensory input and motor tasks encompass a widely distributed network of functional brain areas. Information embedded in the spatial shape and extent of these activation patterns, and differences in voxel-tovoxel time course, are not easily quantified with conventional analysis tools, such as statistical parametric mapping (SPM) (Kiebel and Friston, 2004a,b). Pattern classification in functional MRI (fMRI) is a novel approach, which promises to characterize subtle differences in activation patterns between different tasks. However, automatic and reliable classification of patterns is challenging due to the high dimensionality of fMRI data, the small number of available data sets, interindividual differences in activation patterns, and dependence on the image acquisition methodology. Recent work by Cox and Savoy (2003) demonstrated that linear discriminant analysis and support vector machines (SVM) allow 10-way discrimination of visual activation patterns evoked by the visual presentation of various categories of ...

show abstract

mentioning

confidence: 99%

fMRI pattern classification using neuroanatomically constrained boosting

et al. 2006

View full text Add to dashboard Cite

show abstract

“…The clientserver based Functional Imaging in REal time (FIRE) software package (Fig. 2) has partly been described in previous reports [Schor et al, 1998;Gembris et al, 2000;Mathiak and Posse, 2000]. Briefly, the server sends LZ77-compressed images [Press et al, 1992] via TCP/IP from the host computer to the external workstation where the client uncompresses, rescales, and displays the images.…”

Section: Real-time Data Analysismentioning

confidence: 99%

“…Real-time fMRI is currently being developed by an increasing number of research groups [Cox et al, 1995;Goddard et al, 1997;Cohen et al, 1998;Gering and Weber, 1998;Lee et al, 1998;Frank et al, 1999;Voyvodic, 1999;Yoo et al, 1999;Gembris et al, 2000], and major MR manufacturers have started the development of their own real-time analysis tools. However, in contrast to our methodology, the data acquisition and analysis techniques that were used in previous studies are not suitable for real-time monitoring of dynamic changes in brain activity during the ongoing scan.…”

Section: Real-tme Signal Analysismentioning

confidence: 99%

“…These advances stimulated the development of "real-time fMRI" [Cox et al, 1995;Goddard et al, 1997;Lee et al, 1998;Gering and Weber 1998;Cohen et al, 1998;Frank et al, 1999;Voyvodic 1999;Yoo et al, 1999;Gembris et al, 2000], which is characterized by steady state data acquisition, image reconstruction, motion correction, and statistical image analysis during the ongoing scan, preferably with a time delay of less than a single TR cycle. With realtime fMRI the delay between task initiation and clear display of involved cortical areas is no longer determined by computation time.…”

Section: Introductionmentioning

confidence: 99%

“…These methods include real-time image transfer and display [Schor et al, 1998], "sliding-window" correlation analysis ( Fig. 1b) [Gembris et al, 2000], reference vector optimization [Gembris et al, 2000], and real-time motion correction [Mathiak and Posse, 2000].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A new approach to measure single-event related brain activity using real-time fMRI: Feasibility of sensory, motor, and higher cognitive tasks

Posse¹,

Binkofski

Schneider

et al. 2000

Hum. Brain Mapp.

View full text Add to dashboard Cite

Real-time independent component analysis of fMRI time-series

et al. 2003

View full text Add to dashboard Cite

Real-time functional magnetic resonance imaging (fMRI) enables one to monitor a subject's brain activity during an ongoing session. The availability of online information about brain activity is essential for developing and refining interactive fMRI paradigms in research and clinical trials and for neurofeedback applications. Data analysis for real-time fMRI has traditionally been based on hypothesis-driven processing methods. Off-line data analysis, conversely, may be usefully complemented by data-driven approaches, such as independent component analysis (ICA), which can identify brain activity without a priori temporal assumptions on brain activity. However, ICA is commonly considered a time-consuming procedure and thus unsuitable to process the high flux of fMRI data while they are acquired. Here, by specific choices regarding the implementation, we exported the ICA framework and implemented it into real-time fMRI data analysis. We show that, reducing the ICA input to a few points within a time-series in a sliding-window approach, computational times become compatible with real-time settings. Our technique produced accurate dynamic readouts of brain activity as well as a precise spatiotemporal history of quasistationary patterns in the form of cumulative activation maps and time courses. Results from real and simulated motor activation data show comparable performances for the proposed ICA implementation and standard linear regression analysis applied either in a sliding-window or in a cumulative mode. Furthermore, we demonstrate the possibility of monitoring transient or unexpected neural activities and suggest that real-time ICA may provide the fMRI researcher with a better understanding and control of subjects' behaviors and performances.

show abstract

Functional MR Imaging in Real-Time using a sliding-window correlation technique

Cited by 6 publications

References 2 publications

fMRI pattern classification using neuroanatomically constrained boosting

fMRI pattern classification using neuroanatomically constrained boosting

A new approach to measure single-event related brain activity using real-time fMRI: Feasibility of sensory, motor, and higher cognitive tasks

Real-time independent component analysis of fMRI time-series

Contact Info

Product

Resources

About