Classification techniques in breast cancer diagnosis: A systematic literature review

ABSTRACT

Data mining (DM) consists in analysing a set of observations to find unsuspected relationships and then summarising the data in new ways that are both understandable and useful. It has become widely used in various medical fields including breast cancer (BC), which is the most common cancer and the leading cause of death among women worldwide. BC diagnosis is a challenging medical task and many studies have attempted to apply classification techniques to it.

The objective of the present study is to identify studies on classification techniques in BC diagnosis and to analyse them from three perspectives: classification techniques used, accuracy of the classifiers, and comparison of performance.

We performed a systematic literature review (SLR) of 176 selected studies published between January 2000 and November 2018. The results show that, of the nine classification techniques investigated, artificial neural networks, support vector machines and decision trees were the most frequently used. Moreover, artificial neural networks, support vector machines and ensemble classifiers performed better than the other techniques, with median accuracy values of 95%, 95% and 96% respectively. Most of the selected studies (57.4%) used datasets containing different types of images such as mammographic, ultrasound, and microarray images.

KEYWORDS:

• Breast cancer
• data mining
• classification
• diagnosis

Disclosure statement

The authors declare no conflicts of interest.

Additional information

Notes on contributors

Bouchra ElOuassif

Bouchra EL Ouassif, is a Ph.D. student at the Computer Science and Systems Analysis School (ENSIAS, University Mohammed V, Rabat, Morocco). She holds a master’s degree in Computer Science from the Faculty of Sciences of the University of Mohammed V, in 2016.  Her research focuses on developing and applying machine learning techniques in medicine, in particular in Breast Cancer.

Ali Idri

Ali Idri, is a Full Professor at the Computer Science and Systems Analysis School (ENSIAS, University Mohammed V, Rabat, Morocco. He received his Master and Doctorate of 3rd Cycle in Computer Science from the University of Mohamed V in 1994 and 1997 respectively. He received his Ph.D. in Cognitive and Computer Sciences from the University of Quebec at Montreal in 2003. He is the head of the Software Project Management Research Team since 2010 and the Chair of the department Web and Mobile Engineering for the period 2014-2020. He was the principal investigator of several leading national and international projects. He was ranked at the 3rd position of the Top-Ten researchers in the field of software effort estimation according to the study „Research Patterns and Trends in Software Effort Estimation (Information and Software Technology 91 (2017) 1–21). He was recently ranked 2nd of the Top-Ten researchers in doing Systematic Mapping Studies in Software Engineering according to the study “Landscaping systematic mapping studies in software engineering: A tertiary study”. He is an Associate Editor of BMC Medical Informatics and Decision. He is an Expert Evaluator of the CNRST (http://www.cnrst.ma/index.php/fr/).  He is very active in the fields of software engineering, machine learning and medical informatics and has published more than 180 papers in well recognized journals and conferences.

Mohamed Hosni

Mohamed Hosni, received an Engineering degree in Software Engineering and Software Quality form the National College of Applied Science from the University Mohammed First in Oujda in 2014. He received a PhD in Software Engineering in 2018 from the University Mohammed V in Rabat. His research interests include software engineering, machine learning and its applications in medicine.

Alain Abran

Alain Abran, research expertise includes software estimation, software quality measurement, software functional size measurement, software project & risks management and software maintenance management. He holds a Ph.D. in Electrical & Computer Engineering from Ecole Polytechnique (Canada) and master degrees in Management Sciences and Electrical Engineering from U. of Ottawa (Canada). His 20 years of work in software development and management within the Canadian banking industry was followed by +20 years of teaching and research at École de Technologie Supérieure (ETS) & Université du Québec à Montréal (UQAM) (Canada) where he graduated over 45 doctoral students in software engineering. Now retired from his full-time university position, he remains active in professional associations and in R&D as an adjunct professor at ETS. His industry-oriented research has influenced a number of international standards in software engineering, such as: ISO 9126, ISO 15939, ISO 19759, ISO 19761 and ISO 14143-3. He has published + 500 peer-reviewed papers with +11,000 citations (Google Scholar) as well as a number of books (including translations in Chinese, Japanese and Korean).