Hierarchical Markov Random Fields for Mast Cell Segmentation in Electron Microscopic Recordings
IEEE International Symposium on Biomedical Imaging (ISBI): 973 - 978, 2011
Abstract: We present a hierarchical Markov Random Field (HMRF)
for multi-label image segmentation. With such a hierarchical
model, we can incorporate global knowledge into our segmentation
algorithm. Solving the MRF is formulated as a
MAX-SUM problem for which there exist efficient solvers
based on linear programming. We show that our method
allows for automatic segmentation of mast cells and their cell
organelles from 2D electron microscopic recordings. The
presented HMRF outperforms classical MRFs as well as local
classification approaches wrt. pixelwise segmentation
accuracy. Additionally, the resulting segmentations are much
more consistent regarding the region compactness.
Other associated files :
![MastCells_paper.pdf [9.2MB]](/Publications/images/pdf.png "MastCells_paper.pdf [9.2MB]")
Images and movies
![cFrame9_7900x_h5_classif.jpg [276KB]](/Publications/2011/KSBBR11/cFrame9_7900x_h5_classif.jpg "cFrame9_7900x_h5_classif.jpg [276KB]")
BibTex reference
@InProceedings{KSBBR11,
author = "M. Keuper and T. Schmidt and M. Rodriguez-Franco and W. Schamel and T. Brox and H. Burkhardt and O. Ronneberger",
title = "Hierarchical Markov Random Fields for Mast Cell Segmentation in Electron Microscopic Recordings",
booktitle = "IEEE International Symposium on Biomedical Imaging (ISBI)",
pages = "973 - 978",
year = "2011",
url = "http://lmbweb.informatik.uni-freiburg.de/Publications/2011/KSBBR11"
}