Quantitative Analysis of MR Brain Image Sequences by Adaptive Self-Organizing Finite Mixtures

  • Authors:
  • Yue Wang;Tü/lay Adali;Chi-Ming Lau;Sun-Yuan Kung

  • Affiliations:
  • Department of Electrical Engineering and Computer Science, The Catholic University of America, Washington, DC 20064/ and Department of Radiology, Georgetown University Medical Center, Washington, ...;Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, MD 21250;Department of Radiology, Georgetown University Medical Center, Washington, DC 20007;Department of Electrical Engineering, Princeton University, Princeton, NJ 08544

  • Venue:
  • Journal of VLSI Signal Processing Systems - special issue on applications of neural networks in biomedical image processing
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents an adaptive structure self-organizingfinite mixture network for quantification of magnetic resonance (MR) brain image sequences.We present justification for the use of standard finite normal mixture model for MR images and formulate image quantification as a distribution learning problem. The finite mixture network parameters are updated such that the relative entropy between the true and estimated distributions is minimized. The new learning scheme achieves flexible classifier boundaries by formingwinner-takes-in probability splits of the data allowing the datato contribute simultaneously to multiple regions. Hence, the result is unbiased and satisfies the asymptotic optimality properties ofmaximum likelihood.To achieve a fully automatic quantification procedure that can adaptto different slices in the MR image sequence, we utilize an information theoretic criterion that we have introduced recently, the minimum conditional bias/variance (MCBV) criterion.MCBV allows us to determine the suitable number of mixture components to represent the characteristics of each image in the sequence. We present examples to show that thenew method yields very efficient and accurate performance comparedto expectation-maximization, K-means, and competitive learning procedures.