Evolving Cellular Neural Networks for the Automated Segmentation of Multiple Sclerosis Lesions

This chapter presents an innovative approach for the segmentation of brain images that contain multiple sclerosis (MS) white matter lesions. Quantitative research of Magnetic Resonance Images (MRI), aimed at detecting and studying lesion load and tissue volumes, has turned out to be very useful for the re-evaluation of patients and clinical assessment of therapy. Until now, the standard procedure for this purpose has been the manual delineation of MS lesions, which makes the analysis a time-consuming process. The application presented in this work is a genetic algorithm (GA) that evolves a Cellular Neural Network (CNN) for pattern recognition. This network is capable to automatically segment the brain areas affected by lesions in MRI and also to immediately eliminate the parts of the brain that are not directly connected to the disease (like the skull, the optic nerve, etc.) in the segmentation process. In comparison to manual segmentations, the proposed method shows a very high level of reliability. It must also be reported that the relative algorithm is more accurate and it adapts to different conditions of the stimulus. Furthermore, it can create 3D images of the brain regions affected by MS, providing new perspectives of the diagnostic analysis of this disease. The work has practical applications in the medical field. Future industrial development of this work could lead to the embodiment of the algorithm directly into the MRI equipment, because CNNs can be implemented in hardware (via discrete off-the-shelf components) or fabricated as a Very Large Scale Integrated (VLSI) chip.

[1]  Ying Wu,et al.  Automated segmentation of multiple sclerosis lesion subtypes with multichannel MRI , 2006, NeuroImage.

[2]  Christophe Collet,et al.  Lesions detection on 3D brain MRI using trimmmed likelihood estimator and probabilistic atlas , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[3]  Cristina Masoller.  Measuring structural complexity in brain images , 2009 .

[4]  H. Levine.  Medical Imaging , 2010, Annals of Biomedical Engineering.

[5]  L. Chua,et al.  Simulating nonlinear waves and partial differential equations via CNN. I. Basic techniques , 1995 .

[6]  F Makedon,et al.  Statistical Methods in Medical Research Data Mining in Brain Imaging , 2022 .

[7]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[8]  D. Paty,et al.  Interferon beta‐1b is effective in relapsing‐remitting multiple sclerosis , 1993, Neurology.

[9]  Nicholas Ayache,et al.  Revue des approches de segmentation des lésions de sclérose en plaques dans les séquences conventionnelles IRM , 2009 .

[10]  L. Chua.  Cnn: A Paradigm for Complexity , 1998 .

[11]  J. Rapoport,et al.  Mapping adolescent brain change reveals dynamic wave of accelerated gray matter loss in very early-onset schizophrenia , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[13]  Wiro J. Niessen,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI 2001 , 2001, Lecture Notes in Computer Science.

[14]  Victor Maojo,et al.  Medical Data Analysis , 2001, Lecture Notes in Computer Science.

[15]  Leon O. Chua.  A Nonlinear Dynamics Perspective Of Wolfram'S New Kind Of Science , 2013 .

[16]  D. Gronwall.  Paced Auditory Serial-Addition Task: A Measure of Recovery from Concussion , 1977, Perceptual and motor skills.

[17]  Tobias Schwarz,et al.  Interactive surface correction for 3D shape based segmentation , 2008, SPIE Medical Imaging.

[18]  Ron Kikinis,et al.  A Binary Entropy Measure to Assess Nonrigid Registration Algorithms , 2001, MICCAI.

[19]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[20]  Hans Lassmann,et al.  Cellular Damage and Repair in Multiple Sclerosis , 2004 .

[21]  Heidi Johansen-Berg,et al.  Relationships of brain white matter microstructure with clinical and MR measures in relapsing‐remitting multiple sclerosis , 2010, Journal of magnetic resonance imaging : JMRI.

[22]  Massimo Filippi,et al.  Automatic Segmentation and Classification of Multiple Sclerosis in Multichannel MRI , 2009, IEEE Transactions on Biomedical Engineering.

[23]  A. Thompson,et al.  T(1) hypointense lesions in secondary progressive multiple sclerosis: effect of interferon beta-1b treatment. , 2001, Brain : a journal of neurology.

[24]  Leon O. Chua,et al.  Cellular Neural Networks and Visual Computing: Foundations and Applications , 2002 .

[25]  Lakhmi C. Jain,et al.  Introduction to Pattern Recognition and Classification in Medical and Astrophysical Images , 2007, Artificial Intelligence in Recognition and Classification of Astrophysical and Medical Images.

[26]  Richard M. Leahy,et al.  Optimization of landmark selection for cortical surface registration , 2009, CVPR 2009.

[27]  F. Gollas,et al.  EEG analysis by multi layer Cellular Nonlinear Networks (CNN) , 2006, 2006 IEEE Biomedical Circuits and Systems Conference.

[28]  Anke Meyer-Bäse,et al.  Model-free functional MRI analysis based on unsupervised clustering , 2004 .

[29]  Hayit Greenspan,et al.  LESION DETECTION IN NOISY MR BRAIN IMAGES USING CONSTRAINED GMM AND ACTIVE CONTOURS , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[30]  M. Modo,et al.  Non-invasive evaluation of nigrostriatal neuropathology in a proteasome inhibitor rodent model of Parkinson's disease , 2010, BMC Neuroscience.

[31]  Luigi Fortuna,et al.  Advanced Topics on Cellular Self-Organizing Nets and Chaotic Nonlinear Dynamics to Model and Control Complex Systems , 2008 .

[32]  T. Szabo,et al.  Application of analogic CNN algorithms in telemedical neuroradiology , 2002, Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications.

[33]  Richard M. Leahy,et al.  Optimization of landmark selection for cortical surface registration , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Jarkko Ylipaavalniemi,et al.  Analyzing consistency of independent components: An fMRI illustration , 2008, NeuroImage.

[35]  Pietro Pantano,et al.  A gallery of chua attractors , 2008 .

[36]  Onur Osman,et al.  Breast MR segmentation and lesion detection with cellular neural networks and 3D template matching , 2008, Comput. Biol. Medicine.

[37]  Stephen H. Koslow,et al.  Neuroinformatics as a megascience issue , 1999, IEEE Transactions on Information Technology in Biomedicine.

[38]  H. Stern,et al.  A gesture-based tool for sterile browsing of radiology images. , 2008, Journal of the American Medical Informatics Association : JAMIA.

[39]  B D Trapp,et al.  Axonal pathology in multiple sclerosis: relationship to neurologic disability. , 1999, Current opinion in neurology.

[40]  Guido Gerig,et al.  Medical Image Computing and Computer-Assisted Intervention - MICCAI 2005, 8th International Conference, Palm Springs, CA, USA, October 26-29, 2005, Proceedings, Part II , 2005, MICCAI.

[41]  Arthur W. Toga,et al.  A Probabilistic Atlas of the Human Brain: Theory and Rationale for Its Development The International Consortium for Brain Mapping (ICBM) , 1995, NeuroImage.

[42]  Bertram Ludäscher,et al.  Towards a federated neuroscientific knowledge management system using brain atlases , 2001, Neurocomputing.

[43]  Luigi Fortuna,et al.  Image processing for medical diagnosis using CNN , 2003 .

[44]  Alexander E. MacDonald,et al.  QNH: Design and Test of a Quasi-Nonhydrostatic Model for Mesoscale Weather Prediction , 2000 .

[45]  D. Louis Collins,et al.  Bayesian MS Lesion Classification Modeling Regional and Local Spatial Information , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[46]  Michael A. Arbib,et al.  The NeuroHomology database , 2001, Neurocomputing.

[47]  Lakhmi C. Jain,et al.  Artificial Intelligence in Recognition and Classification of Astrophysical and Medical Images , 2007, Studies in Computational Intelligence.

[48]  J. Noseworthy,et al.  Multiple sclerosis. , 2002, Annual review of medicine.

[49]  Pierre Hellier,et al.  STREM: A Robust Multidimensional Parametric Method to Segment MS Lesions in MRI , 2005, MICCAI.

[50]  Isaac N. Bankman,et al.  Handbook of medical image processing and analysis , 2009 .

[51]  Eleonora Bilotta,et al.  Cellular Non-linear Networks as a New Paradigm for Evolutionary Robotics , 2008 .

[52]  Paul M. Thompson,et al.  Multivariate Tensor-based Morphometry on Surfaces: Application to Mapping Ventricular Abnormalities in Hiv/aids Mapping Methods Have Revealed the 3d Profile of Structural Brain , 2022 .

[53]  J. Kurtzke.  Rating neurologic impairment in multiple sclerosis , 1983, Neurology.

[54]  C Becker,et al.  Quantitative assessment of MRI lesion load in multiple sclerosis. A comparison of conventional spin-echo with fast fluid-attenuated inversion recovery. , 1996, Brain : a journal of neurology.

[55]  D. Arnold,et al.  Combining Robust Expectation Maximization and Mean Shift algorithms for Multiple Sclerosis Brain Segmentation , 2008 .

[56]  Armando Eduardo De Giusti,et al.  Pattern recognition in medical images using neural networks , 2001 .

[57]  Paty Dw,et al.  Interferon beta-lb is effective in relapsing-remitting multiple sclerosis. I. Clinical results of a multicenter, randomized, double-blind, placebo-controlled trial. 1993 [classical article]. , 2001, Neurology.

[58]  Jerry L. Prince,et al.  A Geometry-Driven Optical Flow Warping for Spatial Normalization of Cortical Surfaces , 2008, IEEE Transactions on Medical Imaging.

[59]  Klaus Lehnertz,et al.  A cellular neural network based method for classification of magnetic resonance images: Towards an automated detection of hippocampal sclerosis , 2008, Journal of Neuroscience Methods.

[60]  Jasjit S. Suri,et al.  Handbook of Biomedical Image Analysis , 2005 .

[61]  Klaus-Armin Nave,et al.  Myelin Biology and Disorders , 2004 .

[62]  Axel Wismüller,et al.  Hierarchical Clustering of Functional MRI Time-Series by Deterministic Annealing , 2000, ISMDA.

[63]  D. Ramasamy,et al.  Extent of cerebellum, subcortical and cortical atrophy in patients with MS A case-control study , 2009, Journal of the Neurological Sciences.

[64]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[65]  D Brzakovic,et al.  An approach to automated detection of tumors in mammograms. , 1990, IEEE transactions on medical imaging.

[66]  Arthur W. Toga,et al.  A Framework for Brain Registration via Simultaneous Surface and Volume Flow , 2009, IPMI.

[67]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[68]  Norbert Schuff,et al.  Measuring structural complexity in brain images , 2008, NeuroImage.

[69]  G Malandain,et al.  [Approaches to segment multiple-sclerosis lesions on conventional brain MRI]. , 2009, Revue neurologique.

[70]  André J. W. van der Kouwe,et al.  Reliability of MRI-derived cortical and subcortical morphometric measures: Effects of pulse sequence, voxel geometry, and parallel imaging , 2009, NeuroImage.

[71]  Leon O. Chua,et al.  WORLD SCIENTIFIC SERIES ON NONLINEAR SCIENCE , 2009 .

[72]  P. Calabresi,et al.  MRI of the corpus callosum in multiple sclerosis: association with disability , 2010, Multiple sclerosis.

[73]  Michael A. Arbib,et al.  Computing the brain : a guide to neuroinformatics , 2001 .

[74]  Tamás Roska,et al.  Cellular wave computing library (templates, algorithms, and programs). Version 2.1 , 2007 .

[75]  Richard M. Leahy,et al.  Automated graph-based analysis and correction of cortical volume topology , 2001, IEEE Transactions on Medical Imaging.

[76]  Axel Wismüller,et al.  Segmentation with neural networks , 2000 .

[77]  Antonio Cerasa,et al.  A CNN Based Algorithm for the Automated Segmentation of Multiple Sclerosis Lesions , 2010, EvoApplications.

[78]  L. Chua,et al.  Simulating nonlinear waves and partial differential equations via CNN. II. Typical examples , 1995 .

[79]  Umberto Aguglia,et al.  TEMPORAL LOBE ABNORMALITIES ON BRAIN MRI IN HEALTHY VOLUNTEERS: A PROSPECTIVE CASE-CONTROL STUDY , 2010 .

[80]  Peter A. Calabresi,et al.  A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions , 2010, NeuroImage.

[81]  Rainer Goebel,et al.  Reduced volume of Heschl's gyrus in tinnitus , 2009, NeuroImage.

[82]  Koenraad Van Leemput,et al.  Automated segmentation of multiple sclerosis lesions by model outlier detection , 2001, IEEE Transactions on Medical Imaging.

[83]  J. Duryea,et al.  Magnetic resonance image segmentation using semi-automated software for quantification of knee articular cartilage—initial evaluation of a technique for paired scans , 2009, Skeletal Radiology.