Biomedical image segmentation using geometric deformable models and metaheuristics.

Journal: Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
Published Date:

Abstract

This paper describes a hybrid level set approach for medical image segmentation. This new geometric deformable model combines region- and edge-based information with the prior shape knowledge introduced using deformable registration. Our proposal consists of two phases: training and test. The former implies the learning of the level set parameters by means of a Genetic Algorithm, while the latter is the proper segmentation, where another metaheuristic, in this case Scatter Search, derives the shape prior. In an experimental comparison, this approach has shown a better performance than a number of state-of-the-art methods when segmenting anatomical structures from different biomedical image modalities.

Authors

  • Pablo Mesejo
    Department of Information Engineering, University of Parma, Parma 43124, Italy , ISIT-UMR 6284 CNRS, University of Auvergne, Clermont-Ferrand 63000, France.
  • Andrea Valsecchi
    European Center for Soft Computing, C/Gonzalo Gutiérrez Quirós, s/n - 3(a) planta, 33600 Mieres, Spain. Electronic address: andrea.valsecchi@softcomputing.es.
  • Linda Marrakchi-Kacem
    Neurospin, CEA, Gif-sur-Yvette, France; CRICM, UPMC Université Paris 6, France. Electronic address: linda.marrakchi@gmail.com.
  • Stefano Cagnoni
    Intelligent Bio-Inspired Systems laboratory (IBISlab), Department of Information Engineering, University of Parma, Viale G.P. Usberti 181a, 43124 Parma, Italy. Electronic address: cagnoni@ce.unipr.it.
  • Sergio Damas
    European Center for Soft Computing, C/Gonzalo Gutiérrez Quirós, s/n - 3(a) planta, 33600 Mieres, Spain. Electronic address: sergio.damas@softcomputing.es.