Description

This book is divided into two parts. The first part
is about non-redundant clustering and feature
selection for high dimensional data. The second
part is on applying learning techniques to lung
tumor image-guided radiotherapy. In the first part,
a new clustering paradigm is investigated for
exploratory data analysis: find all non-redundant
clustering views of the data. Also a feature
selection method is developed based on the popular
transformation approach: principal component
analysis (PCA). In the second part, machine
learning algorithms are designed to aid lung tumor
image-guided radiotherapy (IGRT). Specifically,
intensive studies are preformed for gating and for
directly tracking the tumor. For gating, two
methods are developed: (1) an ensemble of templates
where the representative templates are selected by
Gaussian mixture clustering, and (2) a support
vector machine (SVM) classifier with radial basis
kernels. For the tracking problem, a multiple-
template matching method is explored to capture the
varying tumor appearance throughout the different
phases of the breathing cycle.