Improving the Mann-Whitney statistical test for feature selection: an approach in breast cancer diagnosis on mammography.

Journal: Artificial intelligence in medicine

Published Date: Dec 12, 2014

Abstract

OBJECTIVE: This work addresses the theoretical description and experimental evaluation of a new feature selection method (named uFilter). The uFilter improves the Mann-Whitney U-test for reducing dimensionality and ranking features in binary classification problems. Also, it presented a practical uFilter application on breast cancer computer-aided diagnosis (CADx).

Authors

Noel Pérez Pérez

Institute of Mechanical Engineering and Industrial Management (INEGI), Campus da FEUP, Rua Dr. Roberto Frias, 400, 4200-465 Porto, Portugal. Electronic address: nperez@inegi.up.pt.
Miguel A Guevara López

Institute of Electronics and Telematics Engineering of Aveiro, Campus Universitário de Santiago, 3810-193 Aveiro, Portugal; Institute of Mechanical Engineering and Industrial Management (INEGI), Campus da FEUP, Rua Dr. Roberto Frias, 400, 4200-465 Porto, Portugal.
Augusto Silva

Institute of Electronics and Telematics Engineering of Aveiro, Campus Universitário de Santiago, 3810-193 Aveiro, Portugal.
Isabel Ramos

Faculty of Medicine - Centro Hospitalar São Joao, Al. Prof. Hernâni Monteiro, 4200-319 Porto, Portugal.

Keywords

Algorithms Bayes Theorem Breast Neoplasms Chi-Square Distribution Databases, Factual Diagnosis, Computer-Assisted Discriminant Analysis Female Humans Linear Models Machine Learning Mammography Models, Statistical Predictive Value of Tests Radiographic Image Interpretation, Computer-Assisted Reproducibility of Results

External Resources

View on PubMed Access via DOI PubMed (25555756)

Improving the Mann-Whitney statistical test for feature selection: an approach in breast cancer diagnosis on mammography.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals