Statistical Analysis of Brain MRI Image segmentation for the Level Set Method
Saylee Gharge, Meenu Bhatia · 2013
Level set methods have been widely used in image processing and computer vision. Intensity inhomogeneity often occurs in real-world images, which presents a considerable challenge in image segmentation. 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. 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 this paper statistical property of level set method for image segmentation is analyzed, which is able to deal with intensity inhomogeneities in the segmentation. In a level set formulation, the local intensity clustering property criterion is used to define energy that represent a partition of the image domain and a bias field that accounts for the intensity inhomogeneity of the image. Therefore, by minimizing this energy, the level set method is able to simultaneously segment the image and estimate the bias field, which can be used for bias correction. Statistical analysis is performed by calculating probability, variance and entropy for both the images i.e. Input image and Bias corrected image.