Fully connected CRF with data-driven prior for multi-class brain tumor segmentation

Grid conditional random fields (CRFs) are widely applied in both natural and medical image segmentation tasks. However, they only consider the label coherence in neighborhood pixels or regions, which limits their ability to model long-range connections within the image and generally results in excessive smoothing of tumor boundaries. In this paper, we present a novel method for brain tumor segmentation in MR images based on fully-connected CRF (FC-CRF) model that establishes pairwise potentials on all pairs of pixels in the images. We employ a hierarchical approach to differentiate different structures of tumor and further formulate a FC-CRF model with learned data-driven prior knowledge of tumor core. The methods were evaluated on the testing and leaderboard set of Brain Tumor Image Segmentation Benchmark (BRATS) 2013 challenge. The precision of segmented tumor boundaries is improved significantly and the results are competitive compared to the start-of-the-arts.

[1]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[2]  Brian B. Avants,et al.  Optimal Symmetric Multimodal Templates and Concatenated Random Forests for Supervised Brain Tumor Segmentation (Simplified) with ANTsR , 2014, Neuroinformatics.

[3]  Jan-Olof Eklundh,et al.  Detecting Symmetry and Symmetric Constellations of Features , 2006, ECCV.

[4]  Andrew Zisserman,et al.  A Statistical Approach to Texture Classification from Single Images , 2004, International Journal of Computer Vision.

[5]  Stefano Soatto,et al.  Class segmentation and object localization with superpixel neighborhoods , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[6]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[7]  Matthew B. Blaschko,et al.  Learning Fully-Connected CRFs for Blood Vessel Segmentation in Retinal Images , 2014, MICCAI.

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

[9]  Andrew Adams,et al.  Fast High‐Dimensional Filtering Using the Permutohedral Lattice , 2010, Comput. Graph. Forum.

[10]  M. Mohammed Thaha,et al.  Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images , 2019, Journal of Medical Systems.

[11]  Doina Precup,et al.  Iterative Multilevel MRF Leveraging Context and Voxel Information for Brain Tumour Segmentation in MRI , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[13]  Samuel Kadoury,et al.  Higher-Order CRF Tumor Segmentation with Discriminant Manifold Potentials , 2013, MICCAI.