Registering richly labelled 3D images

K. P. Babalola, T. F. Cootes

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    We propose a method of registering 3D images in which many regions have been segmented and labelled. Images in which some regions have been labelled can be registered by generating a vector valued image with a number of planes, one for each individual label class, and applying registration algorithms to the multi-plane images [1]. However, when there are many labels such an approach can lead to unpractically large images. We demonstrate that good results can be obtained by mapping each label value to a vector in a low dimensional space and applying a multi-plane registration algorithm to the resulting vector image. For the approach to work well, the vectors used for each label should be well separated, and chosen in such a way that there is minimal confusion between them. We demonstrate the method by using it to construct statistical shape models by applying a groupwise alignment method to a set of richly labelled 3D brain images. © 2006 IEEE.
    Original languageEnglish
    Title of host publication2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings|IEEE Int. Symp. Biomed. Imag. Nano Macro Proc.
    Pages868-871
    Number of pages3
    Volume2006
    Publication statusPublished - 2006
    Event2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Arlington, VA
    Duration: 1 Jul 2006 → …

    Conference

    Conference2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro
    CityArlington, VA
    Period1/07/06 → …

    Fingerprint

    Dive into the research topics of 'Registering richly labelled 3D images'. Together they form a unique fingerprint.

    Cite this