Morphological detection and neuro-genetic classification of masses and calcifications in mammograms for computer-aided diagnosis
by Fatma Zohra Reguieg; Nadjia Benblidia; Mhania Guerti
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 28, No. 3, 2018

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.

Online publication date: Tue, 02-Oct-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com