Combining SOM based Clustering and MGS for Classification of Suspicious Areas within Digital Mammograms
Peter Mc Leod, Brijesh Verma, Rinku Panchal · 2007
The fusion of clustering and least square based method for the classification of suspicious areas into benign and malignant classes in digital mammograms was investigated in our previous paper which showed some promising results. This paper extends the investigation by combining a self organising map (SOM) based clustering with modified gram-schmidt (MGS) method. The main focus of the research presented in this paper is to investigate the effect that the assignment of input weights from the SOM clustering algorithm have on the efficiency and accuracy of the neural network classifier. A number of experiments have been conducted on a benchmark database. A comparative analysis with our previous results and other known techniques in the literature is presented in this paper.