Experiences on data quality in automatic tissue classification

Automatic intensity-based tissue classification sets requirements for the q uality of multispectral magnetic resonance (MR) images. Tests for evaluatin g the separability of tissue classes, and on the other hand class distances required to obtain reliable classification, are presented in this study. I ntraslice, interslice and interpatient training schemes for 5-nn classifica tion were considered. Interslice training was utilized in classification of images from 10 patients with ischemic stroke giving results of satisfactor y but highly variable quality. Based on the experience with these data sets , similar tests are recommended before imaging a large patient series in or der to avoid extra manual work and to obtain reliable classification result s. (C) 2001 Elsevier Science B.V. All rights reserved.