This paper evaluates a segmentation technique for Magnetic Resonance (MR) images of the brain based on the adaptive fuzzy leader clustering (AFLC) algorithm. This approach performs vector quantization by updating the winning prototype of a competitive network through an unsupervised learning process. Segmentation of MR images is formulated as an unsupervised vector quantization process, where the value of a vigilance parameter restricts the number of prototypes representing the feature vectors. The choice of the misclassification rate (MCR) as a quantitative measure shows that AFLC outperforms other existing segmentation methods.