Basic HTML version of Foils prepared 22 February 97

Foil 5 Segmentation

From 3D Visualization of Visible Human Data Rome Lab Quarterly Review for CIV -- October 1 96. by Roman Markowski *

Automatic segmentation is not possible on anatomical images.
Interactive, semiautomatic segmentation is time consuming (one man-year to segment 300 anatomical objects)
Algorithms ( histogramming, thresholding, edge enhancement)
Image volume must be segmented into its anatomical constituents.
Minimum distance classifier written in C on AVS.
Segmentation was also implemented in Java.
Bone tissue cannot be separated from anatomical images.
We must come back to CT images and do aligning of CT images and anatomy images.



© Northeast Parallel Architectures Center, Syracuse University, npac@npac.syr.edu

If you have any comments about this server, send e-mail to webmaster@npac.syr.edu.

Page produced by wwwfoil on Thu Aug 14 1997