Learning Vector Quantization for Breast Cancer Prediction

Electrical impedance spectroscopy is a minimal invasive technique that has clear advantages for living tissue characterization owing to its low cost and eases of use. The present paper describes how this technique can be applied to breast tissue classification and breast cancer detection. Based on the features derived from the electrical impedance spectra a learning vector quantization (LVQ) network is trained to discriminate several classes of breast tissue. Results of LVQ classification obtained from a data set of 106 cases representing six classes of excised breast tissue show an overall classification efficiency varying from 77% to 100% depending on the parameters of the LVQ network