Maximum a Posteriori Local Histogram Estimation for Image Registration

  • Matthew Toews
  • D. Louis Collins
  • Tal Arbel
Conference paper

DOI: 10.1007/11566489_21

Part of the Lecture Notes in Computer Science book series (LNCS, volume 3750)
Cite this paper as:
Toews M., Collins D.L., Arbel T. (2005) Maximum a Posteriori Local Histogram Estimation for Image Registration. In: Duncan J.S., Gerig G. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2005. MICCAI 2005. Lecture Notes in Computer Science, vol 3750. Springer, Berlin, Heidelberg

Abstract

Image similarity measures for registration can be considered within the general context of joint intensity histograms, which consist of bin count parameters estimated from image intensity samples. Many approaches to estimation are ML (maximum likelihood), which tends to be unstable in the presence sparse data, resulting in registration that is driven by spurious noisy matches instead of valid intensity relationships. We propose instead a method of MAP (maximum a posteriori) estimation, which is well-defined for sparse data, or even in the absence of data. This estimator can incorporate a variety of prior assumptions, such as global histogram characteristics, or use a maximum entropy prior when no such assumptions exist. We apply our estimation method to deformable registration of MR (magnetic resonance) and US (ultrasound) images for an IGNS (image-guided guided neurosurgery) application, where our MAP estimation method results in more stable and accurate registration than a traditional ML approach.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Matthew Toews
    • 1
  • D. Louis Collins
    • 2
  • Tal Arbel
    • 1
  1. 1.Center for Intelligent MachinesMcGill UniversityMontréalCanada
  2. 2.McConnell Brain Imaging Center, Montreal Neurological InstituteMcGill UniversityMontréalCanada

Personalised recommendations