Registration of Non-Segmented Images Using a Genetic Algorithm

  • Jean-José Jacq
  • Christian Roux
Part of the Lecture Notes in Computer Science book series (LNCS, volume 905)


The proposed method aims at solving the global 3—D automatic non—rigid registration problem of two volume datasets coming from the same modality without any segmentation. The tested algorithm combines a voxel based approach with an optimization procedure carried out by a simple genetic algorithm. The method is based on the search for the polynomial warping model which minimizes a L 1 distance between two volumes datasets. To avoid prohibitive computational cost, the genetic algorithm uses a stochastic fitness function which operates on randomly selected measure sites in neighbourhoods of contours, with an adaptive search space scaling scheme. Application of the method is made to the elastic registration of 3—D CT volumes and gives good results in a reasonable processing time.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fitzpatrick, J.M., Grefenstette, J.J.: Image registration by genetic search. Proceeding of IEEE Southeast conference (1984) 460–464.Google Scholar
  2. 2.
    Fitzpatrick, J.M., Grefenstette, J.J.: Genetic algorithms in noisy environments. Machine learning 3 (1988) 101–120Google Scholar
  3. 3.
    Jacq, J.J., Roux, C.R.: Registration of successive DSA images using a simple genetic algorithm with a stochastic performance function. Proceeding of 19th IEEE Northeast Bioengineering Conf., Newark. NJ (1993) 223–224Google Scholar
  4. 4.
    Goldberg, D.E.: Genetic algorithms in search, optimization, and machine learning. Addison—Wesley. (1989)Google Scholar
  5. 5.
    Bramlette M.F.: Initialization, mutation and selection methods in genetic algorithms for function optimization. Proceeding of the fourth international conference on genetic algorithm, San Diego. (1991)Google Scholar
  6. 6.
    Jacq, J.J., C. Roux: Recalage mono—modalité automatique en imagerie médicale 2D et 3D l’aide d’un algorithme génétique traditionnel. Actes du 9ième congrès Reconnaissance des Formes et Intelligence Artificielle. (1994) 109–120Google Scholar
  7. 7.
    Jacq, J.J.: Rendu volumique direct multi—objets. Implantation et application en imagerie médicale. Internal Report. ITI department. Telecom Bretagne. (1994)Google Scholar
  8. 8.
    Jacq, J.J., C. Roux: Automatic registration of 3D images using a simple genetic algorithm with a stochastic performance function Proceeding of EMBS’93 (1993) 90–91Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Jean-José Jacq
    • 1
  • Christian Roux
    • 1
  1. 1.Département Images et Traitement de l’Information Télécom Bretagne, Laboratoire de Traitement de l’Information MédicaleTechnopôle de Brest IroiseBrest-CédexFrance

Personalised recommendations