Physician experience of detecting breast cancer can be assisted by using some computerized feature extraction algorithms. The key point is to use the most significant features with the most suitable classifiers. In this study, we introduce a comparative study between two features selection methods like the t-test and the Kull-Leibler divergence and between a, somehow, new selection method done visually by displaying the features through a color heat map. The visual method showed moderate results, but it needs more considerations at applying it. Experimental results are provided to support this claim.
1st Mosharaka International Conference on Biomedical Engineering, Electronics and Nanotechnology (MIC-BEN 2011)
Congress
2011 Global Congress on Biomedical Engineering, Electronics and Nanotechnology (GC-BEN 2011), 9-11 September 2011, Amman, Jordan
Pages
37-42
Topics
Digital Image Processing Biomedical Imaging Systems
ISSN
2227-331X
DOI
BibTeX
@inproceedings{193BEN2011,
title={Mammography mass detection: visual versus statistical features selection},
author={Ibrahim M. Ibrahim, and Manal Abdel-Wahed},
booktitle={2011 Global Congress on Biomedical Engineering, Electronics and Nanotechnology (GC-BEN 2011)},
year={2011},
pages={37-42},
doi={}},
organization={Mosharaka for Research and Studies}
}