Advertisement

A Neural Network approach to detect functional MRI signal

  • F. Frisone
  • P. G. Morasso
  • P. Vitali
  • G. Rodriguez
  • A. Pilot
  • F. Sardanelli
  • M. Rosa
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)

Abstract

In fMRI the key problem of data analysis is to detect the weak BOLD signal component (about 2–5%) in the MR signal. Standard approaches, that typically use cross-correlation analysis or statistical parametric mapping, imply a presumptive knowledge of the expected stimulus-response pattern, which is not available in spontaneous events like hallucinations, sleep, or epileptic seizures. To evidence the possibility of analyzing these events by means of fMRI, we investigated a computational approach based on a self-organizing neural network (Neural Gas) that detects timedependent alterations in the regional intensity of the functional signal.

Keywords

Spontaneous Event Spectral Vector Receptive Field Center Word Recall Task Neural Filter 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    R. L. Buckner, P. A. Bandettini, R. M. O’Craven, R. L. Savoy, S. E. Petersen, Raichle M. E., and Rosen. B. R. Detection of cortical activation during averaged single trials of a cognitive task using functional magnetic resonance imaging. Proc. Nat. Acad. Sci. USA, 93:1478–1483, 1996.Google Scholar
  2. [2]
    T. Martinetz. Neural gas network for vector quantization and its application to time-series prediction. IEEE Transactions on Neural Networks, 4(4):558–569, 1993.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1999

Authors and Affiliations

  • F. Frisone
    • 1
  • P. G. Morasso
    • 1
  • P. Vitali
    • 2
  • G. Rodriguez
    • 2
  • A. Pilot
    • 3
  • F. Sardanelli
    • 4
  • M. Rosa
    • 5
  1. 1.DIST — Department of Informatics, Systems and TelecommunicatioUniversity of GenovaGenovaItaly
  2. 2.DIMI — Department of Internal Medicine, Service of Clinical Neurophysiology, Ospedale S. MartinoUniversity of GenovaGenovaItaly
  3. 3.Department of Medical PhysicsOspedale S. MartinoGenovaItaly
  4. 4.Radiology InstituteOspedale S. MartinoGenovaItaly
  5. 5.Service of Neuroradiology Ospedale S. MartinoGenovaItaly

Personalised recommendations