Quantitation of brain tumor in MRI for treatment planning

Two different MRI segmentation methods that use multispectral image data are proposed for the estimation of the volume of brain tumors. A supervised k-nearest neighbor (kNN) and a semi-supervised fuzzy c-means (SFCM) pattern recognition methods are used for the image segmentation. The reproducibility of the two methods in determining the volume of different tumors and the change in volume with therapy are estimated. The results are compared with the volume estimates obtained by gray-level based seed-growing method that is being used clinically. The results indicate that kNN and SFCM methods should provide an accurate and reliable image segmentation and tumor volume estimate, as required for treatment planning and surgery simulation.<<ETX>>