Evolving Spiking Neural Network Topologies for Breast Cancer Classification in a Dielectrically Heterogeneous Breast
Martin O'Halloran ,
Seamus Cawley ,
Brian McGinley ,
Raquel Cruz Conceicao ,
Fearghal Morgan ,
Edward Jones and
Martin Glavin
Several studies have investigated the possibility of using the Radar Target Signature (RTS) of a tumour to classify the tumour as either benign or malignant, since the RTS has been shown to be influenced by the size, shape and surface texture of tumours. The Evolved-Topology Spiking Neural Neural (SNN) presented here extends the use of evolutionary algorithms to determine an optimal number of neurons and interneuron connections, forming a robust and accurate Ultra Wideband Radar (UWB) breast cancer classifier. The classifier is examined using dielectrically realistic numerical breast models, and the performance of the classifier is compared to an existing Fixed-Topology SNN cancer classifier.