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

  • Eleonora Bilotta
  • Antonio Cerasa
  • Pietro Pantano
  • Aldo Quattrone
  • Andrea Staino
  • Francesca Stramandinoli


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.


Multiple Sclerosis Expand Disability Status Scale Automate Segmentation Multiple Sclerosis Lesion Cellular Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lanzarini, L., De Giusti, A.: Pattern recognition in medical images using neural networks,
  2. 2.
    Wismuller, A., Vietze, F., Dersch, D.R.: Segmentation with Neural Networks. In: Handbook of Medical Image Processing and Analysis. ch. 7, pp. 113–143. Elsevier, Johns Hopkins University, USA, Baltimore (2008)Google Scholar
  3. 3.
    Suri, J.S., Wilson, D.L., Laxminarayan, S.: Segmentation Models, Part B. In: Handbook of Biomedical Image Analysis. ch. 7, vol. 2, pp. 315–368. Kluwer Academic, Plenum Publishers, New York (2005)Google Scholar
  4. 4.
    Wismuller, A., Meyer-Bease, A., Lange, O., Auer, D., Reiser, M.F., Sumners, D.: Model-free functional MRI analysis based on unsupervised clustering. Journal of Biomedical Informatics 37, 10–18 (2004)CrossRefGoogle Scholar
  5. 5.
    Leinsinger, G.L., Wismuller, A., Joechel, P., Lange, O., Heiss, D.T., Hahn, K.: Evaluation of the motor cortex using fMRI and image processing with self-organized cluster analysis by deterministic annealing. Radiology, 221–487 (2001)Google Scholar
  6. 6.
    Wismüller, A., Dersch, D.R., Lipinski, B., Hahn, K., Auer, D.: Hierarchical Clustering of Functional MRI Time-Series by Deterministic Annealing. In: Brause, R., Hanisch, E. (eds.) ISMDA 2000. LNCS, vol. 1933, pp. 49–54. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  7. 7.
    Döhler, F., Mormann, F., Weber, B., Elger, C.E., Lehnertz, K.: A cellular neural network based method for classification of magnetic resonance images: Towards an automated detection of hippocampal sclerosis. Journal of Neuroscience Methods 170(2), 324–331 (2008)CrossRefGoogle Scholar
  8. 8.
    Chua, L.O., Yang, L.: Cellular Neural Networks: Theory. IEEE Transactions on Circuits and Systems 35(10), 1257–1272 (1988)MathSciNetzbMATHCrossRefGoogle Scholar
  9. 9.
    Chua, L.O.: CNN: A paradigm for Complexity. World Scientific Series on Nonlinear Science (1996)Google Scholar
  10. 10.
    Chua, L.O., Roska, T.: Cellular Neural Networks and Visual Computing: Foundations and Applications. Cambridge University Press, Cambridge (2004)Google Scholar
  11. 11.
    Niederhoefer, C., Gollas, F., Tetzlaff, R.: EEG analysis by multi layer Cellular Nonlinear Networks (CNN). In: Biomedical Circuits and Systems Conference, November 29–December 1. IEEE, Los Alamitos (2006)Google Scholar
  12. 12.
    Schwarz, T., Heimann, T., Tetzlaf, R., Rau, A.M., Wolf, I., Meinzer, H.P.: Interactive Surface Correction for 3D Shape Based Segmentation. Medical Imaging (2008)Google Scholar
  13. 13.
    Bilotta, E., Cerasa, A., Pantano, P., Quattrone, A., Staino, A., Stramandinoli, F.: A CNN Based Algorithm for the Automated Segmentation of Multiple Sclerosis Lesions. In: EvoStar 2010 Conference (2010)Google Scholar
  14. 14.
    Chua, L.O.: A Nonlinear Dynamics Perspective of Wolfram’s New Kind of Science. World Scientific Publishing Co., Singapore (2007)zbMATHGoogle Scholar
  15. 15.
    Roska, T., Chua, L.O., Wolf, D., Kozek, T., Tetzlaff, R.: Simulating Nonlinear Waves and Partial Differential Equations via CNN. IEEE Transactions on Circuits and Systems 42(10) (October 1995); Part I: Basic TechniquesGoogle Scholar
  16. 16.
    Kozek, T., Chua, L.O., Roska, T., Wolf, D., Tetzlaff, R., Pufferand, F., Lotz, K.: Simulating Nonlinear Waves and Partial Differential Equations via CNN. IEEE Transactions on Circuits and Systems, Part 11 42(10) (October 1995)Google Scholar
  17. 17.
    Arena, P., Basile, A., Bucolo, M., Fortuna, L.: Image processing for medical diagnosis using CNN. Nuclear Instruments and Methods A 497(1), 174–178 (2003)CrossRefGoogle Scholar
  18. 18.
    Szabo, T., Barsi, P., Szolgay, P.: Application of Analogic CNN algorithms in Telemedical Neuroradiology. Journal of Neuroscience Methods 170(7), 2063–2090 (2005)Google Scholar
  19. 19.
    Kek, L., Karacs, K., Roska, T.: Cellular Wave Computing Library (Templates, Algorithms and Programs ver.2.1), Cellular Sensory Wave Computers Laboratory, Hungarian Academy of Science (2007)Google Scholar
  20. 20.
    Trapp, B.D., Ransohoff, R., Rudich, R.: Axonal pathology in multiple sclerosis: relationship to neurologic disability. Current Opinion in Neurology 12(3), 295–302 (1999)CrossRefGoogle Scholar
  21. 21.
    Keegan, B.M., Noseworthy, J.H.: Multiple sclerosis. Annual Review of Medicine 53, 285–302 (2002)CrossRefGoogle Scholar
  22. 22.
    Lassmann, H.: Cellular damage and repair in multiple sclerosis. In: Lazzarini, R.A. (ed.) Myelin Biology and Disorders, pp. 753–762. Elsevier, Amsterdam (2004)Google Scholar
  23. 23.
    Ozturk, A., Smith, S., Gordon-Lipkin, E., Harrison, D., Shiee, N., Pham, D., Caffo, B., Calabresi, P., Reich, D.: Mri of the corpus callosum in multiple sclerosis: association with disability. Multiple Sclerosis 16(2), 166–177 (2010)CrossRefGoogle Scholar
  24. 24.
    Kurtzke, J.F.: Rating neurologic impairment in multiple sclerosis: an expanded disability status scale (edss). Neurology 33(11), 1444–1452 (1983)Google Scholar
  25. 25.
    Gronwall, D.M.: Paced auditory serial-addition task: a measure of recovery from concussion. Perceptual and Motor Skills 44, 367–373 (1977)CrossRefGoogle Scholar
  26. 26.
    Young, K., Schuff, N.: Measuring Structural Complexity in Brain Images. NeuroImage 39(4), 1721–1730 (2008)CrossRefGoogle Scholar
  27. 27.
    Giorgio, A., Palace, J., Johansen-Berg, H., Smith, S.M., Ropele, S., Fuchs, S., Wallner-Blazek, M., Enzinger, C., Fazekas, F.: Relationships of brain white matter microstructure with clinical and MR measures in relapsing-remitting multiple sclerosis. Journal of Magnetic Resonance Imaging 31(2), 309–316 (2008)CrossRefGoogle Scholar
  28. 28.
    Wonderlick, J.S., Ziegler, D.A., Hosseini-Varnamkhasti, P., Locascio, J.J., Bakkour, A., Van Der Kouwe, A., Triantafyllou, C., Corkin, S., Dickerson, B.C.: Reliability of mri-derived cortical and subcortical morphometric measures: effects of pulse sequence, voxel geometry, and parallel imaging. NeuroImage 44(4), 1324–1333 (2009)CrossRefGoogle Scholar
  29. 29.
    Wu, Y., Warfield, S.K., Tan, I., Wells, W.M., Meier, D.S., Van Schijndel, R., Barkhof, F., Guttmann, C.R.: Automated segmentation of multiple sclerosis lesion subtypes with multichannel mri. NeuroImage 32(3), 1205–1215 (2006)CrossRefGoogle Scholar
  30. 30.
    Akselrod-Ballin, A., Galun, M., Gomori, J.M., Filippi, M., Valsasina, P., Basri, R., Brandt, A.: Automatic segmentation and classification of multiple sclerosis in multichannel mri. IEEE Transactions on Biomedical Engineering 56(10) ( October 2009)Google Scholar
  31. 31.
    Zharkova, V., Jain, L.: Introduction to pattern recognition and classification in medical and astrophysical images. In: Artificial Intelligence in Recognition and Classification of Astrophysical and Medical Images. SCI, vol. 46, pp. 1–18. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  32. 32.
    Brzakovic, D., Luo, X.M., Brzakovic, P.: An Approach to Automated Detection of Tumors in Mammograms. IEEE Transactions on Medical Imaging 9(3) ( September 1990)Google Scholar
  33. 33.
    Ertas, G., Gulcur, H.O., Osman, O., Ucan, O.N., Tunaci, M., Dursun, M.: Breast MR segmentation and lesion detection with cellular neural networks and 3D template matching. Computers in Biology and Medicine 38, 116–126 (2008)CrossRefGoogle Scholar
  34. 34.
    Brem, M.H., Lang, P.K., Neumann, G., Schlechtweg, P.M., Schneider, E., Jackson, R., Yu, J., Eaton, C.B., Hennig, F.F., Yoshioka, H., Pappas, G., Duryea, J.: Magnetic resonance image segmentation using semi-automated software for quantification of knee articular cartilage-initial evaluation of a technique for paired scans. Radiology 38, 505–511 (2009)Google Scholar
  35. 35.
    Filippi, M., Yousry, T., Baratti, C., Horsfield, M.A., Mammi, S., Becker, C., Voltz, R., Spuler, S., Campi, A., Reiser, M.F., Comi, G.: Quantitative assessment of MRI lesion load in multiple sclerosis. Brain 119, 1349–1355 (1996)CrossRefGoogle Scholar
  36. 36.
    Souplet, J.C., Lebrun, C., Chanalet, S., Ayache, N., Malandain, G.: Approaches to segment multiple-sclerosis lesions on conventional brain MRI. Revue Neurologique 165(1), 7–14 (2009)CrossRefGoogle Scholar
  37. 37.
    Shiee, N., Bazin, P.L., Ozturk, A., Reich, D.S., Calabresi, P.A., Pham, D.L.: A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions. NeuroImage 49(2), 1524–1535 (2010)CrossRefGoogle Scholar
  38. 38.
    Larochelle, H., Bengio, Y., Louradour, J., Lamblin, P.: Exploring Strategies for Training Deep Neural Networks. Journal of Machine Learning Research 10, 1–40 (2009)Google Scholar
  39. 39.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)zbMATHGoogle Scholar
  40. 40.
    Bilotta, E., Pantano, P.: Cellular Non-Linear Networks as a New Paradigm for Evolutionary Robotics. In: Frontiers in Evolutionary Robotics, Hitoshi Iba, Vienna, Austria, pp. 87–108 (2008)Google Scholar
  41. 41.
    Bilotta, E., Pantano, P., Stranges, F.: A Gallery of Chua Attractors. International Journal of Bifurcation and Chaos 1, 1–60 (2007)MathSciNetCrossRefGoogle Scholar
  42. 42.
    Bilotta, E., Pantano, P., Stranges, F.: A Gallery of Chua Attractors. International Journal of Bifurcation and Chaos 2, 293–380 (2007)MathSciNetCrossRefGoogle Scholar
  43. 43.
    Bilotta, E., Pantano, P., Stranges, F.: A Gallery of Chua Attractors. International Journal of Bifurcation and Chaos 17(3), 657–734 (2007)MathSciNetzbMATHCrossRefGoogle Scholar
  44. 44.
    Bilotta, E., Pantano, P., Stranges, F.: A Gallery of Chua Attractors. International Journal of Bifurcation and Chaos 17(4), 1017–1078 (2007)MathSciNetzbMATHCrossRefGoogle Scholar
  45. 45.
    Bilotta, E., Pantano, P., Stranges, F.: A Gallery of Chua Attractors. International Journal of Bifurcation and Chaos 17(5), 1383–1511 (2007)MathSciNetzbMATHCrossRefGoogle Scholar
  46. 46.
    Bilotta, E., Pantano, P., Stranges, F.: A Gallery of Chua Attractors. International Journal of Bifurcation and Chaos 17(6), 1801–1910 (2007)MathSciNetzbMATHCrossRefGoogle Scholar
  47. 47.
    MacDonald, A.E., Lee, J.L., Sun, S.: QNH: Design and test of a quasi-nonhydrostatic model for mesoscale weather prediction. Monthly Weather Review 128, 1016–1036 (2000)CrossRefGoogle Scholar
  48. 48.
    Anand, A.J., Shattuck, D.W., Pantazis, D., Li, Q., Damasio, H., Leahy, R.M.: Optimization of landmark selection for cortical surface registration. In: CVPR 2009, pp. 699–706 (2009)Google Scholar
  49. 49.
    Joshi, A., Leahy, R., Toga, A.W., Shattuck, D.: A Framework for Brain Registration via Simultaneous Surface and Volume Flow. In: Prince, J.L., Pham, D.L., Myers, K.J. (eds.) IPMI 2009. LNCS, vol. 5636, pp. 576–588. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  50. 50.
    Schneider, P., Andermann, M., Wengenroth, M., Goebel, R., Flor, H., Rupp, A., Diesch, E.: Reduced volume of Heschl’s gyrus in tinnitus. NeuroImage 45(3), 927–939 (2009)CrossRefGoogle Scholar
  51. 51.
    Ylipaavalniemi, J., Vigrio, R.: Analyzing consistency of independent components: an fMRI illustration. NeuroImage 39(1), 169–180 (2008)CrossRefGoogle Scholar
  52. 52.
    Wachs, J.P., Stern, H.I., Edan, Y., Gillan, M., Handler, J., Feied, C., Smith, M.: A gesture-based tool for sterile browsing of radiology images. Journal of the American Medical Informatics Association 15(3), 321–324 (2008)CrossRefGoogle Scholar
  53. 53.
    Thompson, P.M., Vidal, C., Giedd, J.N., Gochman, P., Blumenthal, J., Nicolson, R., Toga, A.W., Rapoport, J.L.: Mapping adolescent brain change reveals dynamic wave of accelerated gray matter loss in very early-onset schizophrenia. The Journal of Neuroscience 21(22), 8819–8829 (2001)Google Scholar
  54. 54.
    Wang, Y., Zhang, J., Gutman, B., Chan, T.F., Becker, J.T., Aizenstein, H.J., Lopez, O.L., Tamburo, R.J., Toga, A.W., Thompson, P.M.: Multivariate tensor-based morphometry on surfaces: application to mapping ventricular abnormalities in HIV/AIDS. NeuroImage 49(3), 2141–2157 (2010)CrossRefGoogle Scholar
  55. 55.
    Tosun, D., Prince, J.L.: A geometry-driven optical flow warping for spatial normalization of cortical surfaces. IEEE Transactions of Medical Imaging 27(12), 1739–1753 (2008)CrossRefGoogle Scholar
  56. 56.
    Vernon, A.C., Johansson, S.M., Modo, M.M.: Non-invasive evaluation of nigrostriatal neuropathology in a proteasome inhibitor rodent model of Parkinson’s disease. BMC Neurosci. 11(1) (2010)Google Scholar
  57. 57.
    Labate, A., Gambardella, A., Aguglia, U., Condino, F., Ventura, P., Lanza, P.: Temporal lobe abnormalities on brain MRI in healthy volunteers: A prospective case-control study. A. Neurology 74(7), 553–557 (2010)CrossRefGoogle Scholar
  58. 58.
    Leemput, K.V., Maes, F., Vandermeulen, D., Colchester, A., Suetens, P.: Automated segmentation of multiple sclerosis lesions by model outlier detection. IEEE Transactions on Medical Imaging 20(8), 677–688 (2001)CrossRefGoogle Scholar
  59. 59.
    Freifeld, O., Greenspan, H., Goldberger, J. (eds.): Lesion detection in noisy MR brain images using constrained GMM and active contours (ISBI 2007), 4th IEEE International Symposium on Biomedical Imaging (2007)Google Scholar
  60. 60.
    Aït-Ali, L.S., Prima, S., Hellier, P., Carsin, B., Edan, G., Barillot, C.: STREM: A Robust Multidimensional Parametric Method to Segment MS Lesions in MRI. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3749, pp. 409–416. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  61. 61.
    Bricq, S., Collet, C., Armspach, J.P. (eds.): 5th IEEE International Symposium on Biomedical Imaging Lesion detection in 3D brain MRI using trimmed likelihood estimator and probabilistic atlas (ISBI 2008), (2008)Google Scholar
  62. 62.
    Garcia-Lorenzo, D., Prima, S., Collins, D., Arnold, D., Morrissey, S., Barillot, C. (eds.): Combining robust expectation maximization and mean shift algorithms for multiple sclerosis brain segmentation (MIAMS 2008), MCCAI Workshop on Medical Image Analysis on Multiple Sclerosis (2008)Google Scholar
  63. 63.
    Harmouche, R., Collins, L., Arnold, D., Francis, S., Arbel, T. (eds.): 18th International Conference on Pattern Recognition Bayesian MS lesion classification modeling regional and local spatial information (ICPR 2006) (2006)Google Scholar
  64. 64.
    Ramasamy, D.P., Benedict, R., Cox, J.L., Fritz, D., Abdelrahman, N., Hussein, S., Minagar, A., Dwyer, M.G., Zivadinov, R.: Extent of cerebellum, subcortical and cortical atrophy in patients with ms: a case-control study. Journal of the Neurological Sciences 282(1-2), 47–54 (2001)CrossRefGoogle Scholar
  65. 65.
    Beltrame, F., Koslow, S.H.: Neuroinformatics as a megascience issue. IEEE Transactions on Information Technology in Biomedicine 3, 339–340 (1999)CrossRefGoogle Scholar
  66. 66.
    Bota, M., Arbib, M.A.: The NeuroHomology Database. In: Arbib, M.A., Grethe, J. (eds.) Computing the brain: A guide to neuroinformatics, pp. 337–351. Academic Press, New York (2001)Google Scholar
  67. 67.
    Burns, G.A.P.C., Stephan, K.E., Ludäscher, B., Gupta, A., Kötter, R.: Towards a federated neuroscientific knowledge management system using brain atlases. Neurocomputing 38(40), 1633–1641 (2001)CrossRefGoogle Scholar
  68. 68.
    Shattuck, D.W., Leahy, R.M.: Graph Based Analysis and Correction of Cortical Volume Topology. IEEE Transactions on Medical Imaging 20(11), 1167–1177 (2001)CrossRefGoogle Scholar
  69. 69.
    Megalooikonomou, V., Ford, J., Shen, L., Makedon, F., Saykin, F.: Data mining in brain imaging. Statistical Methods in Medical Research 9, 359–394 (2000)zbMATHCrossRefGoogle Scholar
  70. 70.
    Mazziotta, J.C., Toga, A.W., Evans, A.C., Fox, P., Lancaster, J.: A probabilistic atlas of the human brain: theory and rationale for its development. NeuroImage 2(2), 89–101 (1995)CrossRefGoogle Scholar
  71. 71.
    Caponetto, R., Fortuna, L., Frasca, M.: Advanced Topics on Cellular Self-Organizing Nets and Chaotic Nonlinear Dynamics to Model and Control Complex Systems. World Scientific Series on Nonlinear Science, vol. 63 (2008)Google Scholar
  72. 72.
    Holland, J.: Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor (1975)Google Scholar
  73. 73.
    Warfield, S.K., Rexilius, J., Huppi, P.S., Inder, T.E., Miller, E.G., Wells III, W.M., Zientara, G.P., Jolesz, F.A., Kikinis, R.: A binary entropy measure to assess nonrigid registration algorithms. In: Niessen, W.J., Viergever, M.A. (eds.) MICCAI 2001. LNCS, vol. 2208, pp. 266–274. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  74. 74.
    Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)CrossRefGoogle Scholar
  75. 75.
    Barkhof, F., Van Waesberghe, J.H., Filippi, M.: T(1) hypointense lesions in secondary progressive multiple sclerosis: effect of interferon beta-1b treatment. Brain 124, 1396–1402 (2001)CrossRefGoogle Scholar
  76. 76.
    Paty, D.W., Li, D.K.: Interferon beta-lb is effective in relapsing remitting multiple sclerosis: II. MRI analysis results of a multicenter, randomized, double-blind, placebo-controlled trial. Neurology 57 (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Eleonora Bilotta
    • 1
  • Antonio Cerasa
    • 2
  • Pietro Pantano
    • 1
  • Aldo Quattrone
    • 2
  • Andrea Staino
    • 1
  • Francesca Stramandinoli
    • 1
  1. 1.Evolutionary Systems GroupUniversity of CalabriaArcavacata di RendeItaly
  2. 2.Neuroimaging Research Unit, Institute of Neurological SciencesNational Research CouncilCatanzaroItaly

Personalised recommendations