Skip to Main Content
Mass in mammogram can be an indicator of breast cancer. In this work we propose a new approach using twin support vector machine (TWSVM) for automated detection of mass in digital mammograms. This algorithm finds two hyperplanes to classify data points into different classes according to the relevance between a given point and either plane. It works much faster than original SVM classifier. The proposed scheme is evaluated by a data set of 100 clinical mammograms from DDSM. Experimental results demonstrate that the proposed TWSVM-based CAD system offers a very satisfactory performance for mass detection in digitizing mammograms. Compare with previous SVM-based classifier, it provides higher classification accuracy and computational speed.