Clustering based classifier for the classification of benign and malignant patterns in digital mammograms

"Breast cancer is a leading cause of cancerous deaths and the most frequently diagnosed form of cancer in women ... The process of interpreting mammograms is a time consuming and fatiguing task where even will trained physicians have been know to misdiagnose or not idenify cancerous tumours. Accordingly the development of Computer Aided Diagnostic (CAD) systems offer large benefits in terms of reducing the mortaliity rate, reducing diagnosis time, providing a second opinion for radiologists as well as providing a tool for the training of radiologists. This thesis presents a technique, which explores the fusion of clustering and an intelligent classifier for the classification of suspicious areas within digital mammograms into benign and malignant classes ... The proposed technique has been tested on a benchmark database and the results from the experiments are discussed together with the direction of future reserach "--Abstract.