Prostate cancer classification using multispectral imagery and metaheuristics

The introduction of multispectral imaging in pathology problems such as the identification of prostatic cancer is recent. Unlike conventional RGB color space, it allows the acquisition of a large number of spectral bands within the visible spectrum. The major problem arising in using multispectral data is high-dimensional feature vector size. The number of training samples used to design the classifier is small relative to the number of features. For such a high dimensionality problem, pattern recognition techniques suffer from the well known curse of dimensionality. The aim of this chapter is to discuss and compare two tabu search–based computational intelligence algorithms proposed recently by authors for the detection and classification of prostatic tissues using multispectral imagery.