Channeler Ant Model: 3D segmentation of medical images through ant colonies

E. Fiorina, R. Arteche Diaz, P. Bosco, G. Gargano, A. Massafra, R. Megna, C. Oppedisano, S. Valzano

Research output: Contribution to journalArticlepeer-review


In this paper the Channeler Ant Model (CAM) and some results of its applications to the analysis of medical images are described. The CAM is an algorithm able to segment 3D structures with different shapes, intensity and background. It makes use of virtual ant colonies and exploits their natural capabilities to modify the environment and communicate with each other by pheromone deposition. Its performance has been validated with the segmentation of 3D artificial objects and it has been already used successfully in lung nodules detection on Computer Tomography images. This work tries to evaluate the CAM as a candidate to solve the quantitative segmentation problem in Magnetic Resonance brain images: to evaluate the percentage of white matter, gray matter and cerebrospinal fluid in each voxel. PACS 07.05.Mh-Neural networks, fuzzy logic, artificial intelligence. PACS 87.57.R-Computer-aided diagnosis. PACS 87.57.-s-Medical imaging. PACS 87.57.Q-Computed tomography.

Original languageEnglish
Pages (from-to)79-89
Number of pages11
JournalNuovo Cimento della Societa Italiana di Fisica C
Issue number1
Publication statusPublished - Jan 2011

ASJC Scopus subject areas

  • Astronomy and Astrophysics
  • Physics and Astronomy (miscellaneous)


Dive into the research topics of 'Channeler Ant Model: 3D segmentation of medical images through ant colonies'. Together they form a unique fingerprint.

Cite this