MRI SEGMENTATION - METHODS AND APPLICATIONS

The current literature on MRI segmentation methods is reviewed. Partic ular emphasis is placed on the relative merits of single image versus multispectral segmentation, and supervised versus unsupervised segment ation methods. Image pre-processing and registration are discussed, as well as methods of validation. The application of MRI segmentation fo r tumor volume measurements during the course of therapy is presented here as an example, illustrating problems associated with inter- and i ntra-observer variations inherent to supervised methods.