Feature selection and definition for contours classification of thermograms in breast cancer detection
Dariusz Jagodziński , Mateusz Matysiewicz , Łukasz Neumann , Robert Marek Nowak , Rafał Okuniewski , Witold Oleszkiewicz , Paweł Cichosz
AbstractThis contribution introduces the method of cancer pathologies detection on breast skin temperature distribution images. The use of thermosensitive foils applied to the breasts skin allows to create thermograms, which displays the amount of infrared energy emitted by all breast cells. The significant foci of hyperthermia or inflammation are typical for cancer cells. That foci can be recognized on thermograms as a contours, which are the areas of higher temperature. Every contour can be converted to a feature set that describe it, using the raw, central, Hu, outline, Fourier and colour moments of image pixels processing. This paper defines also the new way of describing a set of contours through theirs neighbourhood relations. Contribution introduces moreover the way of ranking and selecting most relevant features. Authors used Neural Network with Gevrey`s concept and recursive feature elimination, to estimate feature importance.
|Publication size in sheets||0.5|
|Book||Romaniuk Ryszard (eds.): Proc. SPIE. 10031, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016, vol. 10031, 2016, SPIE , ISBN 9781510604858, [781510604865 (electronic) ], 1170 p., DOI:10.1117/12.2257157|
|Score|| = 15.0, 27-03-2017, BookChapterMatConf|
= 15.0, 27-03-2017, BookChapterMatConf
|Citation count*||7 (2018-02-21)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.