The Community for Technology Leaders
Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07) (2007)
Maribor, Slovenia
June 20, 2007 to June 22, 2007
ISSN: 1063-7125
ISBN: 0-7695-2905-4
pp: 47-52
Marcela X. Ribeiro , University of Sao Paulo at Sao Carlos, Brazil
Agma J.M. Traina , University of Sao Paulo at Sao Carlos, Brazil
Andre G.R. Balan , University of Sao Paulo at Sao Carlos, Brazil
Caetano Traina Jr. , University of Sao Paulo at Sao Carlos, Brazil
Paulo M.A. Marques , University of Sao Paulo at Ribeirao Preto, Brazil
ABSTRACT
In this paper we present a framework based on association-rules to help diagnosis of mammogram abnormalities. Our framework - SuGAR - combines low-level features automatically extracted from images with high-level knowledge gotten from specialists to mine association rules, suggesting possible diagnoses. Our framework is optimized, in the sense that it combines, in a single step, feature selection and discretization, reducing the mining complexity. The framework was applied to real datasets and the results show high sensitivity (up to 95%) and accuracy (up to 92%), allowing us to claim that association rules can effectively aid in the diagnosing task.
INDEX TERMS
null
CITATION

M. X. Ribeiro, C. Traina Jr., A. G. Balan, P. M. Marques and A. J. Traina, "SuGAR: A Framework to Support Mammogram Diagnosis," Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07)(CBMS), Maribor, Slovenia, 2007, pp. 47-52.
doi:10.1109/CBMS.2007.101
94 ms
(Ver 3.3 (11022016))