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

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.

[1]  Lawrence O. Hall,et al.  Automatic segmentation of non-enhancing brain tumors in magnetic resonance images , 2001, Artif. Intell. Medicine.

[2]  Sabine Van Huffel,et al.  Hierarchical non‐negative matrix factorization to characterize brain tumor heterogeneity using multi‐parametric MRI , 2015, NMR in biomedicine.

[3]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[4]  Christos Davatzikos,et al.  Combining Generative Models for Multifocal Glioma Segmentation and Registration , 2014, MICCAI.

[5]  Kathleen M Schmainda,et al.  Computer‐aided detection of brain tumor invasion using multiparametric MRI , 2009, Journal of magnetic resonance imaging : JMRI.

[6]  Chi-Hoon Lee,et al.  Segmenting Brain Tumors Using Pseudo-Conditional Random Fields , 2008, MICCAI.

[7]  Paul S Mischel,et al.  Quantitative volumetric analysis of conventional MRI response in recurrent glioblastoma treated with bevacizumab. , 2011, Neuro-oncology.

[8]  Brian B. Avants,et al.  N4ITK: Improved N3 Bias Correction , 2010, IEEE Transactions on Medical Imaging.

[9]  Raymond Sawaya,et al.  Prognostic significance of preoperative MRI scans in glioblastoma multiforme , 2004, Journal of Neuro-Oncology.

[10]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[11]  J. Barnholtz-Sloan,et al.  CBTRUS statistical report: primary brain and central nervous system tumors diagnosed in the United States in 2007-2011. , 2012, Neuro-oncology.

[12]  Nelly Gordillo,et al.  State of the art survey on MRI brain tumor segmentation. , 2013, Magnetic resonance imaging.

[13]  J. Uhm.  Updated Response Assessment Criteria for High-Grade Gliomas: Response Assessment in Neuro-Oncology Working Group , 2010 .

[14]  M. C. U. Araújo,et al.  The successive projections algorithm for variable selection in spectroscopic multicomponent analysis , 2001 .

[15]  R. Velthuizen,et al.  Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation. , 2004, International journal of radiation oncology, biology, physics.

[16]  José V. Manjón,et al.  Automated Glioblastoma Segmentation Based on a Multiparametric Structured Unsupervised Classification , 2015, PloS one.

[17]  Stephen T. C. Wong,et al.  Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov Random Field , 2009, Comput. Medical Imaging Graph..