Title: Morphological detection and neuro-genetic classification of masses and calcifications in mammograms for computer-aided diagnosis

Authors: Fatma Zohra Reguieg; Nadjia Benblidia; Mhania Guerti

Addresses: Laboratoire Signal & Communications, Ecole Nationale Polytechnique, Algiers, Algeria; Laboratoire du Traitement du Signal et de l'Image, Université Saâd Dahlab - Blida 1, Blida, Algeria ' Laboratoire du Traitement du Signal et de l'Image, Laboratoire de Recherche pour le Développement des Systèmes Informatisés, Université Saâd Dahlab - Blida 1, Blida, Algeria ' Laboratoire Signal & Communications, Ecole Nationale Polytechnique, Algiers, Algeria

Abstract: Diagnosis of breast cancer is the main worry of oncologists of this era, which knows an anxiogenic increase of the incidence in the world. This paper is destined for the semi-automatic detection of breast neoplasm taken, from digital mammograms of MIAS database (Mammographic Image Analysis Society). This research is focusing on analysis of masses and, calcifications. Therefore, the first phase of the system consists, on pre-processing of pathological structures, by morphological transformations in order to refine, the segmentation. The second step, realises extraction of clinical signs, according to adaptive deformable model which initialisation is guided by, the annotated suspicious zone. The third block is to characterise abnormalities, by morphometric and textural attributes, to generate their signature. The ultimate systemic description, categorises malignant and benign masses and calcifications from their knowledge, by a neuro-genetic classifier for computer-aided diagnosis. The elaborated decisional system, products, an accuracy of 99.25%, for the shape recognition.

Keywords: digital mammogram; deformable model; texture and morphometry; neuro-genetic classification; computer-aided diagnosis.

DOI: 10.1504/IJBET.2018.095217

International Journal of Biomedical Engineering and Technology, 2018 Vol.28 No.3, pp.203 - 231

Received: 09 Aug 2016
Accepted: 01 Feb 2017

Published online: 02 Oct 2018 *

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