Table of Contents Author Guidelines Submit a Manuscript
International Journal of Biomedical Imaging
Volume 2006, Article ID 53186, 17 pages

3D Brain Segmentation Using Dual-Front Active Contours with Optional User Interaction

1School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA
2CEREMADE, CNRS UMR 7534, Université Paris-Dauphine, Paris Cedex 75775, France

Received 1 December 2005; Revised 30 May 2006; Accepted 31 May 2006

Copyright © 2006 Hua Li et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Important attributes of 3D brain cortex segmentation algorithms include robustness, accuracy, computational efficiency, and facilitation of user interaction, yet few algorithms incorporate all of these traits. Manual segmentation is highly accurate but tedious and laborious. Most automatic techniques, while less demanding on the user, are much less accurate. It would be useful to employ a fast automatic segmentation procedure to do most of the work but still allow an expert user to interactively guide the segmentation to ensure an accurate final result. We propose a novel 3D brain cortex segmentation procedure utilizing dual-front active contours which minimize image-based energies in a manner that yields flexibly global minimizers based on active regions. Region-based information and boundary-based information may be combined flexibly in the evolution potentials for accurate segmentation results. The resulting scheme is not only more robust but much faster and allows the user to guide the final segmentation through simple mouse clicks which add extra seed points. Due to the flexibly global nature of the dual-front evolution model, single mouse clicks yield corrections to the segmentation that extend far beyond their initial locations, thus minimizing the user effort. Results on 15 simulated and 20 real 3D brain images demonstrate the robustness, accuracy, and speed of our scheme compared with other methods.