Brain image registration based on cortical contour mapping

Chris Davatzikos, Jerry L. Prince, R. Nick Bryan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we address the problem of brain image registration, and we present a new, nonlinear registration technique. In the first step of our technique we obtain a point-to-point mapping between the outer cortical contours of the brain images using an elastic string algorithm. In the second step we register the two images based on the point-to-point correspondence established in the first step. We propose a new, nonlinear registration transformation, which is based on a spatially variable scaling and rotation that can describe highly nonlinear deformations. Finally, we test our algorithm on two different registration problems.

Original languageEnglish (US)
Title of host publicationIEEE Nuclear Science Symposium & Medical Imaging Conference
PublisherPubl by IEEE
Pages1823-1826
Number of pages4
Editionpt 3
ISBN (Print)0780314875
StatePublished - Jan 1 1994
EventProceedings of the 1993 IEEE Nuclear Science Symposium & Medical Imaging Conference - San Francisco, CA, USA
Duration: Oct 30 1993Nov 6 1993

Publication series

NameIEEE Nuclear Science Symposium & Medical Imaging Conference
Numberpt 3

Other

OtherProceedings of the 1993 IEEE Nuclear Science Symposium & Medical Imaging Conference
CitySan Francisco, CA, USA
Period10/30/9311/6/93

    Fingerprint

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Industrial and Manufacturing Engineering

Cite this

Davatzikos, C., Prince, J. L., & Bryan, R. N. (1994). Brain image registration based on cortical contour mapping. In IEEE Nuclear Science Symposium & Medical Imaging Conference (pt 3 ed., pp. 1823-1826). (IEEE Nuclear Science Symposium & Medical Imaging Conference; No. pt 3). Publ by IEEE.