Breast Abnormality Detection Incorporating Breast Density Information Based on Independent Components Analysis

Authors:
Styliani Petroudi;Nicoletta Nicolaou;Julius Georgiou;Michael Brady
Affiliations:
Department of Electrical and Computer Engineering, University of Cyprus, Nicosia, Cyprus 1678 and Wolfson Medical Vision Laboratory, Oxford University, Oxford, United Kingdom OX2 7DD;Department of Electrical and Computer Engineering, University of Cyprus, Nicosia, Cyprus 1678;Department of Electrical and Computer Engineering, University of Cyprus, Nicosia, Cyprus 1678;Wolfson Medical Vision Laboratory, Oxford University, Oxford, United Kingdom OX2 7DD
Venue:
IWDM '08 Proceedings of the 9th international workshop on Digital Mammography
Year:
2008

Citing 5
Cited 0

Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Feature Extraction in Digital Mammography: An Independent Component Analysis Approach

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
Diagnosis of breast cancer in digital mammograms using independent component analysis and neural networks

CIARP'05 Proceedings of the 10th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis and Applications
Breast density dependent computer aided detection

IWDM'06 Proceedings of the 8th international conference on Digital Mammography

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces an approach to breast abnormality classification which incorporates breast density information. Features are extracted by a novel technique based on Independent Component Analysis, which decomposes the selected images into sets of independent source regions and corresponding basis functions (weights). The coefficients which result from the source regions are used in turn to describe normality and abnormality. The method has been tested on the MIAS database and has high sensitivity.