STATISTICAL ASSOCIATIVE CLASSIFICATION OF MAMMOGRAMS - The SACMiner Method

Carolina Y. V. Watanabe, Marcela X. Ribeiro, Caetano Traina Jr., Agma J. M. Traina

2010

Abstract

In this paper, we present a new method called SACMiner for mammogram classification using statistical association rules. The method employs two new algorithms the StARMiner* and the Voting classifier (V-classifier). StARMiner* mines association rules over continuous feature values, avoiding introducing bottleneck and inconsistencies in the learning model due to a discretization step. The V-classifier decides which class best represents a test image, based on the statistical association rules mined. The experiments comparing SACMiner with other traditional classifiers in detecting breast cancer in mammograms show that the proposed method reaches higher values of accuracy, sensibility and specificity. The results indicate that SACMiner is well-suited to classify mammograms. Moreover, the proposed method has a low computation cost, being linear on the number of dataset items, when compared with other classifiers. Furthermore, SACMiner is extensible to work with other types of medical images.

Paper Citation

in Harvard Style

Y. V. Watanabe C., X. Ribeiro M., Traina Jr. C. and J. M. Traina A. (2010). STATISTICAL ASSOCIATIVE CLASSIFICATION OF MAMMOGRAMS - The SACMiner Method . In Proceedings of the 12th International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-989-8425-05-8, pages 121-128. DOI: 10.5220/0002970501210128

in Bibtex Style

@conference{iceis10,
author={Carolina Y. V. Watanabe and Marcela X. Ribeiro and Caetano Traina Jr. and Agma J. M. Traina},
title={STATISTICAL ASSOCIATIVE CLASSIFICATION OF MAMMOGRAMS - The SACMiner Method},
booktitle={Proceedings of the 12th International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2010},
pages={121-128},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002970501210128},
isbn={978-989-8425-05-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - STATISTICAL ASSOCIATIVE CLASSIFICATION OF MAMMOGRAMS - The SACMiner Method
SN - 978-989-8425-05-8
AU - Y. V. Watanabe C.
AU - X. Ribeiro M.
AU - Traina Jr. C.
AU - J. M. Traina A.
PY - 2010
SP - 121
EP - 128
DO - 10.5220/0002970501210128