A Non-parametric Approach to Detect Epileptogenic Lesions using Restricted Boltzmann Machines

Visual detection of lesional areas on a cortical surface is critical in rendering a successful surgical operation for Treatment Resistant Epilepsy (TRE) patients. Unfortunately, 45% of Focal Cortical Dysplasia (FCD, the most common kind of TRE) patients have no visual abnormalities in their brains' 3D-MRI images. We collaborate with doctors from NYU Langone's Comprehensive Epilepsy Center and apply machine learning methodologies to identify the resective zones for these {MRI-negative} FCD patients. Our task is particularly challenging because MRI images can only provide a limited number of features. Furthermore, data from different patients often exhibit inter-patient variabilities due to age, gender, left/right handedness, etc. In this paper, we introduce a new approach which combines the restricted Boltzmann machines and a Bayesian non-parametric mixture model to address these issues. We demonstrate the efficacy of our model by applying it to a retrospective dataset of MRI-negative FCD patients who are seizure free after surgery.

[1]  Maria Thom,et al.  The clinicopathologic spectrum of focal cortical dysplasias: A consensus classification proposed by an ad hoc Task Force of the ILAE Diagnostic Methods Commission 1 , 2011, Epilepsia.

[2]  A. Dale,et al.  Thinning of the cerebral cortex in aging. , 2004, Cerebral cortex.

[3]  Yee Whye Teh,et al.  Dirichlet Process , 2017, Encyclopedia of Machine Learning and Data Mining.

[4]  David Haussler,et al.  Unsupervised learning of distributions on binary vectors using two layer networks , 1991, NIPS 1991.

[5]  J. Sethuraman.  A CONSTRUCTIVE DEFINITION OF DIRICHLET PRIORS , 1991 .

[6]  Anders M. Dale,et al.  Cortical Surface-Based Analysis I. Segmentation and Surface Reconstruction , 1999, NeuroImage.

[7]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[8]  Gustavo Rey,et al.  Different features of histopathological subtypes of pediatric focal cortical dysplasia , 2008, Annals of neurology.

[9]  Neda Bernasconi,et al.  Surface-Based Texture and Morphological Analysis Detects Subtle Cortical Dysplasia , 2008, MICCAI.

[10]  N. Makris,et al.  A methodology for analyzing curvature in the developing brain from preterm to adult , 2008, Int. J. Imaging Syst. Technol..

[11]  Roded Sharan,et al.  Bayesian haplo-type inference via the dirichlet process , 2004, ICML.

[12]  Emile H. L. Aarts,et al.  Boltzmann machines , 1998 .

[13]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[14]  A. James Barkovich,et al.  Malformations of cortical development and epilepsy , 2001, Brain and Development.

[15]  W. Hauser,et al.  Epilepsy: Frequency Causes and Consequences , 1990 .

[16]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[17]  Boris C. Bernhardt,et al.  Advances in MRI for 'cryptogenic' epilepsies , 2011, Nature Reviews Neurology.

[18]  I. Melle,et al.  Cortical Volume, Surface Area, and Thickness in Schizophrenia and Bipolar Disorder , 2012, Biological Psychiatry.

[19]  Z. I. Wang,et al.  The pathology of magnetic-resonance-imaging-negative epilepsy , 2013, Modern Pathology.

[20]  J Ashburner,et al.  Computational neuroanatomy: new perspectives for neuroradiology. , 2001, Revue neurologique.

[21]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[22]  Michael I. Jordan,et al.  Variational methods for the Dirichlet process , 2004, ICML.

[23]  P. Kwan,et al.  Early identification of refractory epilepsy. , 2000, The New England journal of medicine.

[24]  Neda Bernasconi,et al.  Automated detection of cortical dysplasia type II in MRI-negative epilepsy , 2014, Neurology.

[25]  Michael I. Jordan,et al.  Variational inference for Dirichlet process mixtures , 2006 .

[26]  Chong Wang,et al.  A Nested HDP for Hierarchical Topic Models , 2013, ICLR.

[27]  D. V. van Essen,et al.  Cortical Folding Abnormalities in Autism Revealed by Surface-Based Morphometry , 2007, The Journal of Neuroscience.

[28]  A M Dale,et al.  Measuring the thickness of the human cerebral cortex from magnetic resonance images. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[29]  P. Ellen Grant,et al.  A methodology for analyzing curvature in the developing brain from preterm to adult , 2008, Int. J. Imaging Syst. Technol..

[30]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[31]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[32]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[33]  Tafsir Thiam,et al.  The Boltzmann machine , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[34]  Samuel Wiebe,et al.  Long-term seizure outcomes following epilepsy surgery: a systematic review and meta-analysis. , 2005, Brain : a journal of neurology.

[35]  A. Dale,et al.  Cortical Surface-Based Analysis II: Inflation, Flattening, and a Surface-Based Coordinate System , 1999, NeuroImage.

[36]  Itzhak Fried,et al.  Assessment and surgical outcomes for mild type I and severe type II cortical dysplasia: A critical review and the UCLA experience , 2009, Epilepsia.

[37]  Geoffrey E. Hinton,et al.  Implicit Mixtures of Restricted Boltzmann Machines , 2008, NIPS.

[38]  C. Brodley,et al.  Cortical feature analysis and machine learning improves detection of “MRI-negative” focal cortical dysplasia , 2015, Epilepsy & Behavior.

[39]  Carla E. Brodley,et al.  Class Imbalance, Redux , 2011, 2011 IEEE 11th International Conference on Data Mining.

[40]  Carla E. Brodley,et al.  Hierarchical Conditional Random Fields for Outlier Detection: An Application to Detecting Epileptogenic Cortical Malformations , 2014, ICML.

[41]  Lawrence Carin,et al.  Multi-Task Learning for Classification with Dirichlet Process Priors , 2007, J. Mach. Learn. Res..

[42]  Orrin Devinsky,et al.  Detection of Epileptogenic Cortical Malformations with Surface-Based MRI Morphometry , 2011, PloS one.

[43]  Radford M. Neal.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .