[vtkusers] Announcement: vtkCISG1.0 released (including Windows support)

Thomas.Hartkens thomas at hartkens.de
Wed Jan 30 12:14:33 EST 2002


                  Computational Imaging Science Group
                 Prof. D.J. Hawkes and Dr. D.L.G. Hill
                  Guy's Hopital, King's College London
                    http://www-ipg.umds.ac.uk/cisg
                             present the

*******************************************************************
                    VTK CISG Registration Toolkit

                             version 1.0

            for medical single- and multimodal 3D images
               tested on Linux, Solaris, and Windows
                 http://www.image-registration.com
*******************************************************************
written by T. Hartkens based on code by D. Rueckert and J. Schnabel


This software package provides two voxel-based image registration
algorithms on the basis of Normalised Mutual Information (NMI) which are
incorporated in a user-friendly command-line and graphical interface
including a visualisation tool for 3D image pairs in order to analyse
registration results. This software is implemented using the free and
widely-used visualisation software VTK version 4.0 by Kitware
(Visualization Toolkit; http://www.kitware.com) a powerful visualisation
pipeline for interactive image display.  VTK4.0 needs to be
installed before the VTK CISG Registration Toolkit can be used.

We have shown that voxel-based image registration using Normalised
Mutual Information (NMI) can register  single- and multi-modal 3D images
accurately without any user interaction using either rigid body or affine
transformations [1][2][3].  Our algorithm has been independently
validated as part of the Vanderbilt University RREP project [4].

Our group has also proposed a non-rigid registration algorithm based on
NMI [5], and has demonstrated these algorithms on a range of medical
applications such as serial MR images of the brain [6], breast [5],
cardiac and liver. We have recently proposed a validation strategy for
non-rigid registration algorithms and have used our non-rigid algorithm
as an example [7]. We have also shown how NMI based registration can
be used to provide a 3D calibration of MR and CT scanners [8] and US
scanners [9].

We would appreciate it if you would reference relevant papers from the
above list if you use the software and publish the results.

With this software we present a publicly available open-source
package that incorporates these algorithms in a user-friendly command-line
and graphical interface including a visualisation tool for 3D image
pairs in order to analyse registration results. Beside the pure usage
of registration algorithms,  the software can be easily adjusted to
specific enviroments (e.g. including other image file formats) and can
be modified for specific applications. We would be delighted to recieve
from you any modifications that you make to the software plus any comments
you have about its usability and any publications that result from your
use of the software.

The version 1.0 of the VTK CISG Registration Toolkit can be now downloaded
for free on

                  http://www.image-registration.com


The VTK CISG Registration Toolkit  is free software; you can redistribute
it and/or modify it under the terms of the GNU General Public License
as published by the Free Software Foundation; either version 2 of the
License, or (at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.


Best wishes,

Thomas Hartkens



References:

[1] Studholme C, Hill DLG, Hawkes DJ. "Automated 3D registration of MR and
    PET brain images by multi-resolution optimisation of voxel similarity
    measures." Medical Physics 24: 25-35 1997

[2] Studholme C, Hill DLG, Hawkes DJ, "Automated 3D registration of MR and
    CT images of the head." Medical Image Analysis 1(2): 163-175 1996

[3] Studholme C, Hill DLG, Hawkes DJ (1999) "An overlap invariant entropy
    measure of 3D medical image alignment". Pattern Recognition 32, 71-86.

[4] J. West et al. "Comparison and evaluation of retrospective
    intermodality brain image registration techniques", JCAT, vol. 21, No 4.,
    pp 554-566, 1997

[5] Rueckert D, Sonoda LI, Hayes C, Hill DLG, Leach MO, Hawkes DJ.
    "Non-rigid Registration using Free-Form Deformations: Application to
    Breast MR Images" IEEE Transactions on Medical Imaging, Vol. 18,
    NO. 8: 712-721, August 1999

[6] Holden M, Hill DLG, Denton ERE, Jarosz JM, Cox TCS, Goody J, Rohlfing T,
    Hawkes DJ. Voxel similarity measures for 3D serial MR image registration
    IEEE trans Med. Imag. 19(2):94-102 2000


[7] JA Schnabel et al., Validation of non-rigid registration using Finite
    Element Methods. Information Processing in Medical Imaging (IPMI'01),
    LNCS 2082:344-357, Springer Verlag, 2001

[8] D.L.G. Hill, C.R. Maurer, C. Studholme, J.M. Fitzpatrick and D.J. Hawkes,
    "Correcting scaling errors in tomographic images using a nine degree
    of freedom registration algorithm", JCAT, vol 22, pp 317-323, 1998

[9] J.M. Blackall, D. Rueckert, C.R. Maurer, G.P. Penny, D.L.G. Hill,
    D.J. Hawkes, "An Image Registration Approach to Automated Calibration
    for Freehand 3D Ultrasound", MICCAI2000, S.L. Delp et al. (Eds.),
    LNCS 1935:462-471, Springer-Verlag, 2000


------------------------------------------------------------------
                           Thomas Hartkens 
     Division of Radiological Sciences and Medical Engineering
          Guy's, King's and St. Thomas' School of Medicine
                    Guy's Hospital, London SE1 9RT 

       tel: +44 20 7955 2721        fax: +44 20 7955 4532
    mobile: +44 7967 323595
     email: thomas.hartkens at kcl.ac.uk , thomas at hartkens.de
       web: http://www-ipg.umds.ac.uk/t.hartkens
------------------------------------------------------------------




More information about the vtkusers mailing list