We describe the design, implementation, and preliminary evaluation of a computer system to aid clinicians in the interpretation of cranial magnetic-resonance images. The system classifies normal and pathologic tissues in a test set of MR scans with high accuracy. It also provides a simple, rapid means whereby an unassisted expert may reliably label an image with her best judgment of its histologic composition, yielding a gold-standard image; this step facilitates objective evaluation of classifier performance. The system’s components are a preprocessing module for normalizing images, an unsupervised clustering algorithm (ISODATA), a maximum-likelihood classifier, and an evaluation module based on confusion-matrix generation. The algorithms for classifier evaluation and gold-standard acquisition are advances over previous methods. The system is best thought of as a data-reduction tool, rather than as an expert system; it highlights salient features of the image for the clinician without requiring user intervention.