ICA-Based Segmentation of the Brain on Perfusion Data

Abstract

An Independent Component Analysis (ICA) based segmentation technique is presented allowing the quantitative assessment of cerebral blood volume (CBV), cerebral blood flow (CBF) and mean transit time (MTT) from dynamic susceptibility contrast magnetic resonance (MR) images of the brain. Tissue types such as gray matter (GM), white matter (WM), and pathology appear as different ICA components as a result of their distinct temporal response to the first passage of contrast agent through the brain. The average CBV, CBF, and MTT values calculated for each component/tissue type could help evaluate the evolution of pathology and provide the opportunity for intersubject comparisons.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 25, 2001
Accession Number
ADA410449

Entities

People

  • C. F. Beckmann
  • E. D. Morris
  • S.M. Smith
  • T. A. Tasciyan

Organizations

  • University of Oxford

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Abstracts
  • Acquisition
  • Analysis Of Variance
  • Bayesian Networks
  • Biomedical Research
  • Blood Flow
  • Blood Volume
  • Computer Vision
  • Contrast
  • Data Science
  • Gaussian Noise
  • Intensity
  • Magnetic Resonance
  • Magnetic Resonance Imaging
  • Models
  • Perfusion
  • Probability

Fields of Study

  • Medicine
  • Physics

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Child and Adolescent Substance Abuse Science in Autism Spectrum Disorders.
  • Computer Vision.