A distribution-matching approach to MRI brain tumor segmentation

This study investigates a fast distribution-matching algorithm for brain tumor segmentation. From a very simple user input, we learn a non-parametric model distribution which contains all the statistical information about the normal regions in the current brain image. We state the problem as the optimization of a cost function containing (1) an intensity distribution matching prior which measures a global similarity between non-parametric distributions, and (2) a smoothness prior to avoid the occurrence of small, isolated regions in the solution. Obtained following recent bound-relaxation results, the optimum of the cost function yields the complement of the tumor region in nearly real-time. Based on global rather than pixelwise information, the proposed algorithm does not require a complex learning from a large training set, as is the case in existing methods. Therefore, the ensuing results are independent of the choice of a training set. Quantitative evaluations and comparisons with several existing methods over publicly available data demonstrate that the proposed algorithm can yield a competitive performance.