MRI Tumor Segmentation for Nasopharyngeal Carcinoma Using Knowledge-based Fuzzy Clustering
Jiayin Zhou, Vincent F. H. Chong, T. T. Lim, Jing Huang · 2002
Tumor segmentation is one of the important steps for volume measurement of nasopharyngeal carcinoma (NPC) tumor by imaging diagnostics. A knowledge-based fuzzy clustering (KBFC) MRI segmentation algorithm was proposed to obtain accurate NPC tumor segmentation. An initial segmentation was performed on T1 and contrast enhanced T1 MR images using a semi-supervised fuzzy c-means (SFCM) algorithm. Then, three types of anatomic and space knowledge--symmetry, connectivity and cluster center were used for image analysis which contributed to the final tumor segmentation. Visual evaluation on MR images of NPC patients showed that KBFC achieved better tumor segmentation results than seeds growing (SG) and maximal likelihood method (MLM), compared with ground truth (GT). KBFC could provide high quality of MRI tumor segmentation for further tumor volume measurement, 3D visualization and treatment planning.