Voxel similarity measures for 3D serial MR brain image registration

A Kuba, M Samal, A ToddPokropek (Editor), J M Jarosz, T C S Cox, D J Hawkes

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

8 Citations (Scopus)

Abstract

We investigated 7 different similarity measures for rigid body registration of serial MR brain scans. To assess their accuracy we used a set of 33 clinical 3D serial MR images, manually segmented by a radiologist to remove deformable extra-dural tissue, and also simulated brain model data. For each measure we determined the consistency of registration transformations for both sets of segmented and unsegmented data. The difference images produced by registration with and without segmentation were visually inspected by two radiologists in a blinded study. We have shown that of the measures tested, those based on joint entropy produced the best consistency and seemed least sensitive to the presence of extra-dural tissue. For this data the difference in accuracy of these joint entropy measures, with or without brain segmentation, was within the threshold of visually detectable change in the difference images.
Original languageEnglish
Title of host publicationLECT NOTE COMPUT SCI
Place of PublicationBERLIN
PublisherSpringer
Pages472 - 477
Number of pages6
ISBN (Print)3-540-66167-0
Publication statusPublished - 1999
Event16th International Conference on Information Processing in Medical Imaging (IPMI 99) - VISEGRAD, Hungary
Duration: 1 Jan 1999 → …

Publication series

NameLECTURE NOTES IN COMPUTER SCIENCE

Conference

Conference16th International Conference on Information Processing in Medical Imaging (IPMI 99)
Country/TerritoryHungary
CityVISEGRAD
Period1/01/1999 → …

Fingerprint

Dive into the research topics of 'Voxel similarity measures for 3D serial MR brain image registration'. Together they form a unique fingerprint.

Cite this