Feature extraction for MRI segmentation

Magnetic resonance images (MRIs) of the brain are segmented to measure the efficacy of treatment strategies for brain tumors. To date, no reproducible technique for measuring tumor size is available to the clinician, which ha mpers progress of the search for good treatment protocols. Many segmentatio n techniques have been proposed, but the representation (features) of the M RI data has received little attention. A genetic algorithm (GA) search was used to discover a feature set from multi-spectral MRI data. Segmentations were performed using the fuzzy c-means (FCM) clustering technique. Seventee n MRI data sets from five patients were evaluated. The GA feature set produ ces a more accurate segmentation. The GA fitness function that achieves the best results is the Wilks's lambda statistic when applied to FCM clusters. Compared to linear discriminant analysis, which requires class labels, the same or better accuracy is obtained by the features constructed from a GA search without class labels, allowing fully operator independent segmentati on. The GA approach therefore provides a better starting point for the meas urement of the response of a brain tumor to treatment.