MIAL

n-SIFT for Matching Medical Images

Principle Investigator: Ghassan Hamarneh
Research Assistant: Warren Cheung

We extended the well known computer vision technique, SIFT, to arbitrary dimensions and applied to matching medical images.

Note that usage of SIFT in the United States is governed by US Patent 6,711,293 and a license must be obtained from the University of British Columbia for any commercial applications. For more information visit: http://www.cs.ubc.ca/~lowe/keypoints/

News:

  • 2009-05-01: IEEE TIP n-SIFT paper accepted (see link below under publications).
  • 2007-12-24: Insight Journal publication here
  • 2007-11-27: Updated nsift code. You must obtain a password first from here.
  • 2007-11-27: Doxygen for n-sift

Lines connects points corresponding to matched n-SIFT features in 4D CT slices

Lines connect points corresponding to matched n-SIFT features between Brainweb T1 and PD slices

Publication

Warren Cheung and Ghassan Hamarneh. N-SIFT: N-dimensional Scale Invariant Feature TransformIEEE Transactions on Image Processing, 2009.


Warren Cheung and Ghassan Hamarneh. n-SIFT: n-dimensional Scale Invariant Feature Transform for Matching Medical Images. In IEEE International Symposiom on Biomedical Imaging (IEEE ISBI), pages 720-723, 2007.

Warren Cheung and Ghassan Hamarneh. Scale Invariant Feature Transform for n-Dimensional Images (n-SIFT). Insight Journal, Aug-Dec 2007:1-7, 2007


Site by Faculty of Applied Science web team, Simon Fraser University