Tumor segmentation from magnetic resonance MR images may aid in tumor treatment b y tracking the progress of tumor growth and or shrinkage. In this paper we present the rst automatic segmentation method which separates non-enhancing brain tumors from healthy tissues in MR images to aid in the task of tracking tumor size over time. The MR feature images used for the segmentation consist of three weighted images T1, T2 and proton density for each axial slice through the head. An initial segmentation is computed using an unsupervised fuzzy clustering algorithm. Then, integrated domain knowledge and image processing techniques contribute to the nal tumor segmentation. They are applied under the control of a knowledge-based system. The system knowledge was acquired by training on two patient v olumes 14 images. Testing has shown successful tumor segmentations on four patient volumes 31 images. Our results show that we detected all six non-enhancing brain tumors, located tumor tissue in 35 of the 36 ground truth radiologist labeled slices containing tumor and successfully separated tumor regions from physically connected CSF regions in nine of nine slices. Quantitative measurements are promising as correspondence ratios between ground truth and segmented tumor regions ranged between 0.368 and 0.871 per volume, with percent match ranging between 0.530 and 0.909 per volume.