|
<bimagicLab> |
home \ people \ research \ publications
\ software
\ teaching
\ contact
|
Compendium Paper information and status G.
Srinivasa, M. C. Fickus, Y. Guo, A. D. Linstedt and J. Kovačević,
“Active mask segmentation of fluorescence microscope images,”
IEEE Trans. Image Proc., vol. 18, no. 8, Aug. 2009. [pdf | article on
IEEE Xplore | BibTeX] Abstract We propose
a new active mask algorithm for the segmentation of fluorescence microscope
images of punctate patterns. It
combines the (a) flexibility offered by active-contour methods, (b) speed
offered by multiresolution methods, (c) blurring offered by multiscale
methods, and (d) statistical modeling offered by region-growing methods into
a fast and accurate segmentation tool.
The framework moves from the idea of the ``contour'' to that of
``inside and outside'', or, masks, allowing for easy multidimensional
segmentation. It adapts to the
topology of the image through the use of multiple masks. The algorithm is
almost invariant under initialization, allowing for random initialization,
and uses a few easily tunable parameters. Experiments show that the active
mask algorithm matches the ground truth well, and outperforms the algorithm
widely used in fluorescence microscopy, seeded watershed, both qualitatively
as well as quantitatively. Data The zipped archive contains the images from five different stacks used as test data in this study. [download] Details
about the preparation of data and imaging as well as the details for citing
the images in your own work can be obtained from Linstedt
Lab. Code § Matlab The zipped archive contains a
readme file along with the code to generate the results in the paper. [download] § ImageJ The zipped archive contains a
help file and the ImageJ plugin. [download] This
work is licensed under a Creative Commons GNU General Public License. To view
a copy of this license, visit http://creativecommons.org/licenses/GPL/2.0.
If you use this code or any part thereof in your research or publication,
please also include a reference to this paper. Thank you! Proofs NA Other material This
zipped archive contains hand-segmented masks for the test images as well
as valid cell masks for seeded watershed and active mask algorithms (with
automatic and hand-drawn seeds) and all of the intermediate results together
with their respective MATLAB scripts used to generate Table II. [download] List of tested configurations 1. MATLAB 7.0.1 on Windows XP Professional (Note: Seeded watershed with perfect seeds does not work on this version) 2. MATLAB 2007a on Windows XP Professional For more information or to
report bugs |