21 March 2016 Mutual information criterion for feature selection with application to classification of breast microcalcifications
Author Affiliations +
Abstract
Classification of clustered breast microcalcifications into benign and malignant categories is an extremely challenging task for computerized algorithms and expert radiologists alike. In this paper we present a novel method for feature selection based on mutual information (MI) criterion for automatic classification of microcalcifications. We explored the MI based feature selection for various texture features. The proposed method was evaluated on a standardized digital database for screening mammography (DDSM). Experimental results demonstrate the effectiveness and the advantage of using the MI-based feature selection to obtain the most relevant features for the task and thus to provide for improved performance as compared to using all features.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Idit Diamant, Idit Diamant, Moran Shalhon, Moran Shalhon, Jacob Goldberger, Jacob Goldberger, Hayit Greenspan, Hayit Greenspan, } "Mutual information criterion for feature selection with application to classification of breast microcalcifications", Proc. SPIE 9784, Medical Imaging 2016: Image Processing, 97841S (21 March 2016); doi: 10.1117/12.2216466; https://doi.org/10.1117/12.2216466
PROCEEDINGS
6 PAGES


SHARE
Back to Top