Title: Robust mass classification-based local binary pattern variance and shape descriptors

Authors: Alima Damak Masmoudi; Norhen Gargouri Ben Ayed; Dorra Sellami Masmoudi; Riad Abid

Addresses: Computers Imaging and Electronics Systems (CIELS), Sfax Engineering School, University of Sfax, BP W, 3038 Sfax, Tunisia ' Computers Imaging and Electronics Systems (CIELS), Sfax Engineering School, University of Sfax, BP W, 3038 Sfax, Tunisia ' Computers Imaging and Electronics Systems (CIELS), Sfax Engineering School, University of Sfax, BP W, 3038 Sfax, Tunisia ' EL FARABI Radiology Center, Rue Ahmed Essikilli Imm. El Farabi Sfax El Jadida, BP W, 3003 Sfax, Tunisia

Abstract: In several countries, breast cancer is a serious public health problem. Computer-Aided Detection and Diagnosis (CAD) systems have been used with relative success aiding healthcare professionals. The goal of such approach technique is contribute on the radiologist task aiding in the detection of different types of cancer at an early stage. This paper presents a methodology for masses detection on mammographic images based on the Local Binary Pattern Variance (LBPV) and shape descriptors. Classification of these structures is accomplished through Artificial Neural Network (ANN), which separate them in two groups: masses and non-masses. The performance of macro-calcification detection methods is developed using FARABI database. Performance results are given in terms of receiver operating characteristic.

Keywords: breast cancer; texture; classification; mammograms; feature extraction; LBPV; shape descriptors; mass detection; local binary patterns; pattern variance; cancer detection; mammographic images; mammography; artificial neural networks; ANNs; macro-calcification detection.

DOI: 10.1504/IJSISE.2015.067065

International Journal of Signal and Imaging Systems Engineering, 2015 Vol.8 No.1/2, pp.20 - 27

Received: 12 Jan 2013
Accepted: 10 Nov 2013
Published online: 25 Jan 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article