A Robust Convergence Index Filter for Breast Cancer Cell Segmentation
COnvergenceINdex (COIN) filter, a successful tool for
cell localization, evaluates the degree of convergence of
the gradient vectors within the neighborhood (region of
support) toward a pixel of interest. The adaptability of the
region of support was increased to make COIN filter robust
and accurate. However, improving the quality of the image
gradient map was ignored which results in poor performance
of the members of the COIN family in noisy setting. We
propose a new Robust Convergence Index (RCI) filter that
tailors COIN filter in noisy environment by (a) spreading
the gradient vectors within non-homogeneous object
regions through the convolution of an Aggregated Edge
Probability Map (AEPM) based weighted edge map by an
edge preserving gradient vector kernel, and (b)increasing the
convergence of the gradient vectors through the integration
of the sine and cosine distribution as well as the magnitude
of the gradient vectors. AEPM is computed through the
consensus of the responses of a number of edge detectors
over a wide range of scales which lessen the effects of
clutter by enforcing higher weights to the actual edges, and
then a non-parametric KDE is used to compute the edge
probability map.Experimental results demonstrate that it
obtains state-of-the-art performance.
Citation
B. Saha,
A. Saini,
N. Ray,
R. Greiner,
J. Hugh,
M. Tambasco.
"A Robust Convergence Index Filter for Breast Cancer Cell Segmentation".
International Conference on Image Processing, pp 922-926, October 2014.
Keywords: |
breast cancer, medical imaging |
Category: |
In Conference |
Web Links: |
IEEE |
BibTeX
@incollection{Saha+al:ICIP14,
author = {B Nath Saha and Amritpal Saini and Nilanjan Ray and Russ Greiner
and Judith Hugh and Mauro Tambasco},
title = {A Robust Convergence Index Filter for Breast Cancer Cell
Segmentation},
Pages = {922-926},
booktitle = {International Conference on Image Processing},
year = 2014,
}
Last Updated: February 12, 2020
Submitted by Sabina P