Ensemble Classifier for Benign-Malignant Mass Classification

Ensemble Classifier for Benign-Malignant Mass Classification

Muhammad Hussain (Department of Software Engineering, King Saud University, Riyadh, Saudi Arabia)
Copyright: © 2013 |Pages: 12
DOI: 10.4018/ijcvip.2013010106


Mammography is currently the most effective imaging modality for early detection of breast cancer. In a CAD system for masses based on mammography, a mammogram is segmented to detect the masses. The segmentation gives rise to mass regions of interested (ROIs), which are either benign or malignant. There is a need to classify the extracted mass ROIs into benign and malignant masses; it is a hard problem because the texture micro-structures of benign and malignant masses have close resemblance. In this paper, a method for classifying mass ROIs into benign and malignant masses is presented. The key idea of the proposal is to build an ensemble classifier that employs Gabor features, consults different experts (classifiers) and takes the final decision based on majority vote. The system is evaluated on 512 (256 benign+256 malignant) mass ROIs extracted from mammograms of DDSM database. The ensemble classifier improves the classification rate for the problem of the discrimination of benign and malignant masses to 90.64%. Comparison with state-of-the-art techniques suggests that the proposed system outperforms similar methods.
Article Preview

Because of the impact of mass classification problem in detecting breast cancer, it has attracted the attention of many researchers, and many methods have been proposed. For a detailed review of these methods, an interested reader is referred to the review papers [17]; [18]; [19]; [20]. In the following paragraphs, we focus on the review the most related recent mass detection methods.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 9: 4 Issues (2019): Forthcoming, Available for Pre-Order
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 2 Issues (2016)
Volume 5: 2 Issues (2015)
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing