V. Krylov, S. Taylor, J. Nelson.
"Stochastic extraction of elongated curvilinear structures in mammographic images",
International Conference on Image Analysis and Recognition 2013,
Springer LNCS 7950, pp. 475-484, Povoa de Varzim (Portugal), June 26-28, 2013.
[link] [pdf] [poster]
Abstract
The extraction of elongated curvilinear structure in mammographic images is an important objective for the automated detection of breast cancers. We develop an approach which relies on a fixed-grid, localized Radon transform for line segment extraction and a Markov random field model to incorporate local interactions and refine the line structure. The energy of the resulting distribution is minimized stochastically via a Markov chain Monte Carlo iterative procedure. Experimental results demonstrate that the method can accurately extract blurred and low-contrast elongated continuous curvilinear structures, including those radiating from cancerous masses.
--------------------------------------------------------------------------------------------------------
Bibtex
@incollection{KrylovICIAR13,
author={Krylov, VladimirA. and Taylor, Stuart and Nelson, James D.B.},
title={Stochastic Extraction of Elongated Curvilinear Structures in Mammographic Images},
year={2013},
booktitle={Image Analysis and Recognition},
volume={7950},
series={Lecture Notes in Computer Science},
editor={Kamel, Mohamed and Campilho, Aurélio},
publisher={Springer},
pages={475--484}
}
--------------------------------------------------------------------------------------------------------
Code
MammoCLS - a MATLAB implementation for detecting elongated curvilinear structure on greyscale mammographic images, version 1.01, Oct. 2013.
[MATLAB code]