A Computer-Assisted Diagnostic (CAD) of Screening Mammography to Detect Breast Cancer Without a Surgical Biopsy

A Computer-Assisted Diagnostic (CAD) of Screening Mammography to Detect Breast Cancer Without a Surgical Biopsy

Hadj Ahmed Bouarara
DOI: 10.4018/IJSSCI.2019100103
(Individual Articles)
No Current Special Offers


Breast cancer has become a major health problem in the world over the past 50 years and its incidence has increased in recent years. It accounts for 33% of all cancer cases, and 60% of new cases of breast cancer occur in women aged 50 to 74 years. In this work we have proposed a computer-assisted diagnostic (CAD) system that can predict whether a woman has cancer or not by analyzing her mammogram automatically without passing through a biopsy stage. The screening mammogram will be vectorized using the n-gram pixel representation. After the vectors obtained will be classified into one of the classes—with cancer or without cancer—using the social elephant algorithm. The experimentation using the digital database for screening mammography (DDSM) and validation measures—f-measure entropy recall, accuracy, specificity, RCT, ROC, AUC—show clearly the effectiveness and the superiority of our proposed bioinspired technique compared to others techniques existed in the literature such as naïve bayes, Knearest neighbours, and decision tree c4.5. The goal is to help radiologists with early detection to reduce the mortality rate among women with breast cancer.
Article Preview

1. Introduction And Problematic

The Breast cancer is a malignant tumor that arises within the tissues of the breast as illustrated in the Figure 1. This type of cancer remains the leading cancer in women worldwide, it is a real social problem that can be fatal. In general, the epidemiological studies of breast cancer are becoming increasingly important because there are 460000 deaths every year in the world (Jafarpisheh et al., 2018).

Figure 1.

Breast cancer (Jafarpisheh et al., 2018)


The fight against cancer is far from being a complete advance of medicine on all fronts because it is difficult for a medical specialist to diagnose a patient if he/she has cancer or not and to determine its characteristics (for example type of cancer malignant or benign).

A surgical biopsy is an operation in which the tissues are surgically removed for microscopic examination. A surgical biopsy may be excisional (removal of an entire mass or abnormal region) or incisional (removal of a fragment from an abnormal mass or region). It is performed when one of the mammography screening test (such Figure 2) does not confirm the suspicion of cancer.

Figure 2.

Radiological aspect of the breast. Different shapes and margins of masses. (a) Mammography of breast with cancer; (b) Mammography of breast without cancer; (c) Mass shape with oval well-circumscribed margins, having a high probability of being benign; (d) Mass shape with irregular and spiculated margins, having a high probability of being malignant. The images are from the DDSM database (http://marathon.csee.usf.edu/Mammography/Database.html).


With the advent of new technologies in the field of medicine, large amounts of cancer data have been collected and are available to the medical research community. However, the accurate prediction of a disease outcome is one of the most interesting and challenging tasks. The current situation has motivated us to build an algorithm that can detect breast cancer without the transition to a surgical biopsy by:

  • The vectorization of mammography screening using the representation n-gram pixels;

  • An algorithm inspired from the social life of Asian elephants to predict if a breast in a mammography has a cancer or not.

The general structure of this paper will be as follows: we start with a state of the art for presenting the essential works in this topic, after we go on with a section detailing our approach and proposed components then an experimental and comparative study will be carried out for presenting the best results obtained. Finally, we will finish with a conclusion and describing some lines of thought that remain open and that we want to share them with you.


2. Review Of Literature

The most important works around the problem of breast cancer detection are grouped in Table 1 and detailed in the next paragraphs:

Complete Article List

Search this Journal:
Volume 15: 1 Issue (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing