ABSTRACT
This chapter discusses the slices processed and gives a brief overview of the system. It argues that the system's major processing stages and the knowledge used at each stage. The chapter presents the experimental results, an analysis of them and future directions for this research. The system's unsupervised nature avoids the problem of observer variability found in supervised methods, providing complete reproducibility of results. One of the primary diagnostic and treatment evaluation tools for brain tumors has been magnetic resonance (MR) imaging. The knowledge-based tumor segmentation was compared with radiologist-verified ground truth tumor volumes and results generated by a number of supervised methods. The labeled normal intra-cranial tissues of interest are CSF and the parenchyma tissues, white matter and gray matter. The distributions were examined and interviews were conducted with experts concerning the general makeup of tumorous tissue, and the behavior of gadolinium enhancement in the three MRI protocols.
