Independent component analysis of four-phase abdominal CT images

Abstract

This paper presents a new analysis result of two-dimensional four-phase abdominal CT images using variational Bayesian mixture of ICA. The four-phase CT images are modeled as being produced by a mixture of data generators, where each data generator consists of a set of independent components and is responsible for generating a particular cluster. ICA results show that the CT images could be divided into a set of clinically and anatomically meaningful components. Initial analysis of the independent components shows its promising prospect in medical image processing and computer-aided diagnosis. © Springer-Verlag Berlin Heidelberg 2004.