Application of unsupervised clustering methods to biomedical image analysis

Abstract

Unsupervised clustering techniques represent a powerful technique for self-organized segmentation of biomedical image time-series data describing groups of pixels exhibiting similar properties of local signal dynamics. The theoretical background is presented in the beginning, followed by several medical applications demonstrating the flexibility and conceptual power of these techniques. These applications range from functional MRI data analysis to dynamic contrast-enhanced perfusion MRI and breast MRI. The present paper gives a review of potential applications of unsupervised clustering techniques in the important and current field of functional and dynamic MRI.