Segmentation of Gliomas in Pre-operative and Post-operative Multimodal Magnetic Resonance Imaging Volumes Based on a Hybrid Generative-Discriminative Framework

We present an approach for segmenting both low- and high-grade gliomas in multimodal magnetic resonance imaging volumes. The proposed framework is an extension of our previous work [6,7], with an additional component for segmenting post-operative scans. The proposed approach is based on a hybrid generative-discriminative model. Firstly, a generative model based on a joint segmentation-registration framework is used to segment the brain scans into cancerous and healthy tissues. Secondly, a gradient boosting classification scheme is used to refine tumor segmentation based on information from multiple patients. We evaluated our approach in 218 cases during the training phase of the BRAin Tumor Segmentation (BRATS) 2016 challenge and report promising results. During the testing phase, the proposed approach was ranked among the top performing methods, after being additionally evaluated in 191 unseen cases.

[1]  Christos Davatzikos,et al.  Deformable Registration of Glioma Images Using EM Algorithm and Diffusion Reaction Modeling , 2011, IEEE Transactions on Medical Imaging.

[2]  Christos Davatzikos,et al.  An image-driven parameter estimation problem for a reaction–diffusion glioma growth model with mass effects , 2008, Journal of mathematical biology.

[3]  J A Sethian,et al.  A fast marching level set method for monotonically advancing fronts. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Guido Gerig,et al.  A brain tumor segmentation framework based on outlier detection , 2004, Medical Image Anal..

[5]  Luke Macyszyn,et al.  Pattern analysis of dynamic susceptibility contrast-enhanced MR imaging demonstrates peritumoral tissue heterogeneity. , 2014, Radiology.

[6]  Nahla Ben Amor,et al.  Brain Tumor Segmentation Using Support Vector Machines , 2009, ECSQARU.

[7]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[8]  Konstantinos Kamnitsas,et al.  DeepMedic for Brain Tumor Segmentation , 2016, BrainLes@MICCAI.

[9]  David N Louis,et al.  Molecular pathology of malignant gliomas. , 2006, Annual review of pathology.

[10]  Dimitrios Makris,et al.  Fast Segmentation of Focal Liver Lesions in Contrast-Enhanced Ultrasound Data , 2014, MIUA.

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

[12]  Christos Davatzikos,et al.  PORTR: Pre-Operative and Post-Recurrence Brain Tumor Registration , 2014, IEEE Transactions on Medical Imaging.

[13]  Guido Gerig,et al.  Model-based brain and tumor segmentation , 2002, Object recognition supported by user interaction for service robots.

[14]  Jayaram K. Udupa,et al.  New variants of a method of MRI scale standardization , 2000, IEEE Transactions on Medical Imaging.

[15]  Michael Kistler,et al.  The Virtual Skeleton Database: An Open Access Repository for Biomedical Research and Collaboration , 2013, Journal of medical Internet research.

[16]  Christos Davatzikos,et al.  GLISTR: Glioma Image Segmentation and Registration , 2012, IEEE Transactions on Medical Imaging.

[17]  R. Kikinis,et al.  Recognizing Deviations from Normalcy for Brain Tumor Segmentation , 2002, MICCAI.

[18]  Bilwaj Gaonkar,et al.  GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation , 2015, Brainles@MICCAI.

[19]  J. Friedman.  Stochastic gradient boosting , 2002 .

[20]  Nikos Paragios,et al.  Joint Tumor Segmentation and Dense Deformable Registration of Brain MR Images , 2012, MICCAI.

[21]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[22]  Laurent D. Cohen,et al.  Fast extraction of minimal paths in 3D images and applications to virtual endoscopy , 2001, Medical Image Anal..

[23]  Christos Davatzikos,et al.  Estimating Patient Specific Templates for Pre-operative and Follow-Up Brain Tumor Registration , 2015, MICCAI.

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

[25]  Dimitrios Makris,et al.  Fast semi-automatic segmentation of focal liver lesions in contrast-enhanced ultrasound, based on a probabilistic model , 2017, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[26]  Bilwaj Gaonkar,et al.  Automated tumor volumetry using computer-aided image segmentation. , 2015, Academic radiology.

[27]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

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

[29]  Koenraad Van Leemput,et al.  Brain Tumor Segmentation Using a Generative Model with an RBM Prior on Tumor Shape , 2015, Brainles@MICCAI.

[30]  Santosh Kesari,et al.  Malignant gliomas in adults. , 2008, The New England journal of medicine.

[31]  Ben Glocker,et al.  Decision Forests for Tissue-Specific Segmentation of High-Grade Gliomas in Multi-channel MR , 2012, MICCAI.

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

[33]  Christos Davatzikos,et al.  Joint Segmentation and Deformable Registration of Brain Scans Guided by a Tumor Growth Model , 2011, MICCAI.

[34]  Victor Alves,et al.  Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images , 2016, IEEE Transactions on Medical Imaging.

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

[36]  M A Deeley,et al.  Comparison of manual and automatic segmentation methods for brain structures in the presence of space-occupying lesions: a multi-expert study , 2011, Physics in medicine and biology.