Share Email Print
cover

Proceedings Paper

Preprocessing for classification of thermograms in breast cancer detection
Author(s): Łukasz Neumann; Robert M. Nowak; Rafał Okuniewski; Witold Oleszkiewicz; Paweł Cichosz; Dariusz Jagodziński; Mateusz Matysiewicz
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Performance of binary classification of breast cancer suffers from high imbalance between classes. In this article we present the preprocessing module designed to negate the discrepancy in training examples. Preprocessing module is based on standardization, Synthetic Minority Oversampling Technique and undersampling. We show how each algorithm influences classification accuracy. Results indicate that described module improves overall Area Under Curve up to 10% on the tested dataset. Furthermore we propose other methods of dealing with imbalanced datasets in breast cancer classification.

Paper Details

Date Published: 28 September 2016
PDF: 8 pages
Proc. SPIE 10031, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016, 100313A (28 September 2016); doi: 10.1117/12.2249307
Show Author Affiliations
Łukasz Neumann, Warsaw Univ. of Technology (Poland)
Robert M. Nowak, Warsaw Univ. of Technology (Poland)
Rafał Okuniewski, Warsaw Univ. of Technology (Poland)
Witold Oleszkiewicz, Warsaw Univ. of Technology (Poland)
Paweł Cichosz, Warsaw Univ. of Technology (Poland)
Dariusz Jagodziński, Warsaw Univ. of Technology (Poland)
Mateusz Matysiewicz, Warsaw Univ. of Technology (Poland)


Published in SPIE Proceedings Vol. 10031:
Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016
Ryszard S. Romaniuk, Editor(s)

© SPIE. Terms of Use
Back to Top