Efficient segmentation method using quantised and non-linear CeNN for breast tumour classification

Abstract

A new segmentation method for mammography imaging system is proposed. Segmentation of masses is always a difficult problem in radiological image interpretation. Conventional methods such as region growing suffer from their computational complexity and hence can hardly be used for segmentation of high-resolution images. In order to achieve efficiency in both computational complexity and accuracy, a novel digital cellular neural network (CeNN) based approach is presented for segmentation. The approach is featured with quantisation to significantly reduce the computational complexity and non-linear template for robustness. After segmentation, a multilayer perceptron classifier is used for feature extraction and classification. Compared with other prior works, the proposed work is able to reduce resource overhead up to 63% and energy consumption up to 41% on FPGA while maintaining only up to 1.5 and 0.6% accuracy deviations for mediolateral-oblique and cranial-caudal views, respectively.