Feature Extraction Techniques for Mass Detection in Digital Mammogram (Review)
Adeyemo Temitope Tosin
Department of Computer Science and Engineering, Ladoke Akintola University of Technology, Ogbomoso, Nigeria.
Adepoju Temilola Morufat *
Department of Computer Engineering Technology, Federal Polytechnic Ede, Ede, Osun State, Nigeria.
Sobowale Adedayo Aladejobi
Department of Computer Engineering Technology, Federal Polytechnic Ede, Ede, Osun State, Nigeria.
Oyediran Mayowa Oyedepo
Department of Electrical, Electronics and Computer Engineering, Bells University of Technology, Ota, Ogun State, Nigeria.
Omidiora Elijah Olusayo
Department of Computer Science and Engineering, Ladoke Akintola University of Technology, Ogbomoso, Nigeria.
Olabiyisi Stephen Olatude
Department of Computer Science and Engineering, Ladoke Akintola University of Technology, Ogbomoso, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
One of the most common diseases in women today is breast cancer. The method of detection and analyzing breast images according to literature, to mention few are mammography, magnetic resonance, thermography and ultrasound of which mammography is the most accurate and low cost method. Mass is a major symptom of breast abnormality. Despite the high success of mammography in mass detection, radiologists find it difficult to interpret breast abnormality and take decision. Computer Aided Detection (CADe) and Computer Aided Diagnosis (CADx) are the two systems to improve radiologists’ accuracy of detection and, classification of breast cancer into benign or malignant prior to biopsy. However, the optimal classification rate of CAD system depends on effectiveness of feature extraction technique. This paper present review of different feature extraction Techniques (FETs) that have been adopted for mass detection and classification.
Keywords: Cancer, feature extraction, breast, mammogram, mass, region of interest, benign, malignant.