Performance Evaluation of Segmentation Algorithm for MR Images

MRI intensity inhomogeneities can be attributed to imperfections in the RF. The result is slowly-varying shading artifact over the image that can produce errors with conventional intensity-based classification. Intensity inhomogeneity often occurs in real-world images, which presents a considerable challenge in image segmentation. The most widely used image segmentation algorithms are region-based and typically rely on the homogeneity of the image intensities in the regions of interest, which often fail to provide accurate segmentation results due to the intensity inhomogeneity In order to decrease the noise effect during image segmentation, the proposed method incorporates both the local spatial context and the non-local information into the standard FCM cluster algorithm using a novel dissimilarity index in place of the usual distance metric. Therefore a modified FCM algorithm is used to segment the image in this paper. In this paper results obtained from the proposed algorithm is compared with those obtained by using FLGMM, Level set method, and BCFCM and AFCM with raw image as input data and same is analyzed. Thus concluding that the proposed algorithm can largely overcome the difficulties raised by noise, low contrast, and bias field, and improves the accuracy of brain MR image segmentation.