itksnap – semi-automatic segmentation of structures in 3D images

SNAP provides semi-automatic segmentation of structures in medical images (e.g. magnetic resonance images of the brain) using active contour methods, as well as manual delineation and image navigation. Noteworthy features are:

  • Linked cursor for seamless 3D navigation
  • Manual segmentation in three orthogonal planes at once
  • Support for many different 3D image formats, including NIfTI
  • Support for concurrent, linked viewing and segmentation of multiple images
  • Limited support for color images (e.g., diffusion tensor maps)
  • 3D cut-plane tool for fast post-processing of segmentation results
Paul A. Yushkevich, Joseph Piven, Heather Cody Hazlett, Rachel Gimpel Smith, Sean Ho, James C. Gee,, Guido Gerig (2006). User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. *Neuroimage, 31: 1116-1128, *, . [Abstract] [DOI]
Package availability chart
Distribution Base version Our version Architectures
Debian GNU/Linux 7.0 (wheezy) 2.2.0-1.1    
Debian GNU/Linux 8.0 (jessie) 2.2.0-1.1 3.2.0-1~nd80+1 amd64
Debian GNU/Linux 9.0 (stretch) 3.4.0-2 3.2.0-1~nd80+1+nd90+1 i386, amd64
Debian testing (buster) 3.6.0-2    
Debian unstable (sid) 3.6.0-2 3.2.0-1~nd+1 amd64
  3.6.0-2 2.2.0-1~nd+1 i386
Ubuntu 12.04 LTS “Precise Pangolin” (precise) 2.2.0-1build3    
Ubuntu 14.04 “Trusty Tahr” (trusty) 2.2.0-1.1    
Ubuntu 16.04 “Xenial Xerus” (xenial) 3.4.0-1build1    
Ubuntu 17.10 “Artful Aardvark” (artful) 3.6.0-2    
Ubuntu 18.04 “Bionic Beaver” (bionic) 3.6.0-2    


blog comments powered by Disqus