A Semi-Automated Segmentation Framework for MRI Based Brain Tumor Segmentation Using Regularized Nonnegative Matrix Factorization

Abstract

Segmentation plays an important role in the clinical management of brain tumors. Clinical practice would benefit from accurate and automated volumetric delineation of the tumor and its subcompartments. We present a semi-automated framework for brain tumor segmentation based on regularized nonnegative matrix factorization (NMF). L1-regularization is incorporated into the NMF objective function to promote spatial consistency and sparseness of the tissue abundance maps. The pathological sources are initialized through user-defined voxel selection. Knowledge about the spatial location of the selected voxels is combined with tissue adjacency constraints in a post-processing step to enhance segmentation quality. The method is applied to the BRATS 2013 Leaderboard dataset, consisting of publicly available multi-sequence MRI data of brain tumor patients. Our method performs well in comparison with state-of-the-art, in particular for the enhancing tumor region, for which we reach the highest Dice score among all participants.