Open AccessSuperpixel texture analysis for classification of breast masses in dense background
Author(s) -
Sajeev Shelda,
Bajger Mariusz,
Lee Gobert
Publication year - 2018
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2017.0586
Subject(s) - local binary patterns , pattern recognition (psychology) , artificial intelligence , linear discriminant analysis , mammography , computer science , receiver operating characteristic , classifier (uml) , texture (cosmology) , histogram , medicine , breast cancer , image (mathematics) , machine learning , cancer
Finding masses in dense background is a difficult task for even experienced radiologist. It is due to the similarity of intensity between the masses and the overlapped normal dense tissues. A novel method for classification of masses localised in dense background of breast is proposed. Nine structured superpixel patterns were generated using local binary pattern technique on superpixels. Analysis of these nine structured superpixel patterns revealed the most prominent ones, allowing for successful classification of malignant masses and normal dense breast regions. Two mammographic databases were used to evaluate the proposed approach: the publicly available digital database for screening mammography (DDSM), and a local database of mammograms (BreastScreen SA, BSSA). A total of 525 regions of interest (ROIs) were used (301 extracted from DDSM and 224 from BSSA). All 525 ROIs were localised in dense backgrounds of breasts. The results indicate that features generated from structured superpixel patterns can produce very effective and efficient texture descriptors of breast masses localised in dense background. Using Fisher linear discriminant analysis classifier, an area under the receiver operating characteristic curve score of 0.96 was achieved for DDSM and 0.93 for BSSA with only six features.