Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Special Issue Paper
  • 176 Downloads

Abstract

Technical innovations in radiology, such as advanced cross-sectional imaging methods, have opened up new vistas for the exploration of structure and function of the human body enabling both high spatial and temporal resolution. However, these techniques have led to vast amounts of data whose precise and reliable visual analysis by radiologists requires a considerable amount of human intervention and expertise, thus resulting in a cost factor of substantial economic relevance. Hence, the computer-assisted analysis of biomedical image data has moved into the focus of interest as an issue of high priority research efforts. In this context, innovative approaches to exploratory analysis of huge complex spatio-temporal patterns play a key role to improve computer-assisted signal and image processing in radiology. Examples of such approaches are various unsupervised vector quantization methods or supervised function approximation techniques, such as Generalized Radial-Basis-Functions- (GRBF-) neural networks. Recent developments motivated by concepts of computational intelligence are the ‘Deformable Feature Map’ (DM) as an algorithm for self-organized model adaptation, the ‘Mutual Connectivity Analysis’ (MCA) as an instrument for the analysis of large time-series ensembles and the ‘Exploratory Observation Machine’ (XOM) as a novel general framework for learning by self-organization—three methods that the author has invented and applied to biomedical real-world applications. This contribution covers both conceptual foundations and applications of such methods for pattern recognition and analysis to a wide scope of radiological data sets, such as structural and functional segmentation in Magnetic Resonance Imaging (MRI), ranging from functional MRI for human brain mapping to the monitoring of disease progression in multiple sclerosis by automatic lesion segmentation, as well as novel approaches to image time-series analysis in MRI mammography for breast cancer diagnosis. Current projects related to the modeling of speech production and to genome-wide expression analysis of microarray data in bioinformatics confirm the broad applicability of the presented methods.

Keywords

Computer-assisted radiology Computational intelligence Pattern recognition Medical image computing Multidimensional imaging Neural networks Biomedical imaging 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Wismüller A, Dersch DR (eds) (1996) Symposion über biologische Informationsverarbeitung und Neuronale Netze—SINN’95, Konferenzband. Mit Beiträgen von C von der Malsburg, G Palm, H Reitböck und B Sakmann. Hanns-Seidel-Stiftung, München Google Scholar
  2. 2.
    Wismüller A, Dersch DR (1997) Neural network computation in biomedical research: chances for conceptual cross-fertilization. Theory Biosci, 116(3) Google Scholar
  3. 3.
    Handels H, Ehrhardt J (2009) Medical image computing for computer supported diagnostics and therapy—advances and perspectives. Methods Inf Med 48:11–17 Google Scholar
  4. 4.
    Lehmann TM, Aach T, Witte H (2006) Sensor, signal and image informatics—state of the art and current topics. Methods Inf Med 47(Suppl 1):S57–S67 Google Scholar
  5. 5.
    Ifeachor EC, Sperduti A, Starita A (1998) Neural networks and expert systems in medicine and healthcare. Singapore, World Scientific Google Scholar
  6. 6.
    Malmgren H, Borga M, Niklasson L (2000) Artificial neural networks in medicine and biology. Springer, London Google Scholar
  7. 7.
    Linde Y, Buzo A, Gray RM (1980) An algorithm for vector quantizer design. IEEE Trans Commun 28:84–95 CrossRefGoogle Scholar
  8. 8.
    Anderberg MR (ed) (1973) Cluster analysis for applications. Academic Press, New York MATHGoogle Scholar
  9. 9.
    Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New York MATHGoogle Scholar
  10. 10.
    Forgy EW (1965) Cluster analysis of multivariate data: efficiency vs interpretability of classifications. Biometrics 21:768 Google Scholar
  11. 11.
    Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480 CrossRefGoogle Scholar
  12. 12.
    Rose K, Gurewitz E, Fox GC (1992) Vector quantization by deterministic annealing. IEEE Trans Inf Theory 38(4):1249–1257 MATHCrossRefGoogle Scholar
  13. 13.
    Dersch DR, Tavan P (1994) Load balanced vector quantization. In: Proceedings of the international conference on artificial neural networks ICANN. Springer, Berlin, pp 1067–1070 Google Scholar
  14. 14.
    Dersch DR, Tavan P (1994) Control of annealing in minimal free energy vector quantization. In: Proceedings of the IEEE international conference on neural networks (ICNN’94), Orlando, Florida, pp 698–703 Google Scholar
  15. 15.
    Dersch DR (1996) Eigenschaften neuronaler Vektorquantisierer und ihre Anwendung in der Sprachverarbeitung. Reihe Physik, Bd 54, Verlag Harri Deutsch/Thun, Frankfurt am Main. ISBN 3-8171-1492-3 Google Scholar
  16. 16.
    Martinetz TM, Schulten K (1991) A ‘neural gas’ network learns topologies. In: Proceedings of the international conference on artificial neural networks (ICANN). Elsevier, Amsterdam, pp 397–402 Google Scholar
  17. 17.
    Willshaw DJ, von der Malsburg C (1976) How patterned neural connections can be set up by self-organization. Proc R Soc Lond, B 194:431–445 CrossRefGoogle Scholar
  18. 18.
    Becker S (1996) Mutual information maximization: models of cortical self-organization. Network 7:7–31 MATHCrossRefGoogle Scholar
  19. 19.
    Rose K, Gurewitz E, Fox G (1990) A deterministic annealing approach to clustering. Pattern Recogn Lett 11(11):589–594 MATHCrossRefGoogle Scholar
  20. 20.
    Kohonen T (1989) Self-organization and associative memory. Springer, Berlin Google Scholar
  21. 21.
    Ritter H (1991) Asymptotic level density for a class of vector quantization processes. IEEE Trans Neural Netw 1(2):173–175 CrossRefGoogle Scholar
  22. 22.
    Erwin W, Obermayer K, Schulten K (1992) Self-organizing maps: stationary states, metastability, and convergence rate. Biol Cybern 61:35–45 CrossRefGoogle Scholar
  23. 23.
    Erwin W, Obermayer K, Schulten K (1992) Self-organizing maps: ordering, convergence properties, and energy functions. Biol Cybern 61:47–55 CrossRefGoogle Scholar
  24. 24.
    Dersch DR, Tavan P (1995) Asymptotic level density in topological feature maps. IEEE Trans Neural Netw 6(1):230–236 CrossRefGoogle Scholar
  25. 25.
    Martinetz TM, Schulten K (1994) Topology representing networks. Neural Netw 7:507–522 CrossRefGoogle Scholar
  26. 26.
    Pessi T, Kangas J, Simula O (1995) Patient grouping using self-organizing map. In: Proceedings of the international conference on artificial neural networks, industrial conference, medicine Google Scholar
  27. 27.
    New York Heart Assiociation: Criteria Committee (1964) Diseases of the heart and blood vessels; nomenclature and criteria for diagnosis, 6th edn. Little/Brown, Boston Google Scholar
  28. 28.
    Lown B, Graboys TB (1977) Management in the patient with malignant ventricular arrhythmias. Am J Cardiol 39:910 CrossRefGoogle Scholar
  29. 29.
    Fritz A, Percy C, Jack A, Shanmugaratnam K, Sobin L, Parkin DM, Whelan S (eds) (2000) WHO international classification of diseases for oncology ICD-O. WHO, Geneva Google Scholar
  30. 30.
    Villmann T, Der R, Herrmann M, Martinetz T (1997) Topology preservation in self-organizing feature maps: exact definition and measurement. IEEE Trans Neural Netw 8(2):256–266 CrossRefGoogle Scholar
  31. 31.
    Bauer H-U, Pawelzik KR (1992) Quantifying the neighborhood preservation of self-organizing feature maps. IEEE Trans Neural Netw 3(4):570–579 CrossRefGoogle Scholar
  32. 32.
    Bauer HU, Der R, Herrmann M (1996) Controlling the magnification factor of self-organizing feature maps. Neural Comput 8(4):757–771 CrossRefGoogle Scholar
  33. 33.
    Sinkkonen J, Kaski S (2002) Clustering based on conditional distributions in an auxiliary space. Neural Comput 14:217–239 MATHCrossRefGoogle Scholar
  34. 34.
    Lampinen J, Kostiainen T (2001) Generative probability density model in the self-organizing map. In: Seiffert U, Jain LC (eds) Self-organizing neural networks, studies in fuzziness and soft computing. Physica-Verlag, Heidelberg/New York, pp 75–92 Google Scholar
  35. 35.
    Van Hulle M (2000) Faithful representations and topographic maps. Wiley series and adaptive learning systems for signal processing, communications, and control. Wiley, New York Google Scholar
  36. 36.
    Ilsanker A (2001) Neuronale Netze in der biomedizinischen Bildfogenanalyse. Diplomarbeit, Technische Universität München, München. Supervised by A Wismüller and G Hauske (In German) Google Scholar
  37. 37.
    Vesanto J, Alhoniemi E (2000) Clustering of the self-organizing map. IEEE Trans Neural Netw 11(3):586–600 CrossRefGoogle Scholar
  38. 38.
    Su M, Chang H (2001) A new model of self-organizing neural networks and its application in data projection. IEEE Trans Neural Netw 12(1):153–158 CrossRefGoogle Scholar
  39. 39.
    Wang D, Ressom H, Musavi MT, Dommisoru C (2002) Double self-organizing maps to cluster gene expression data. In: Verleysen M (ed) Proc of European symposium on artificial neural networks (ESANN’2002). D facto publications Brussels, pp 45–50 Google Scholar
  40. 40.
    Kaski S, Sinkkonen J, Nikkilä J (2001) Clustering gene expression data by mutual information with gene function. In: Dorffner G, Bischof H, Hornik K (eds) Artificial neural networks—ICANN 2001. Springer, Berlin, pp 81–86 CrossRefGoogle Scholar
  41. 41.
    Girosi F, Poggio T (1990) Networks and the best approximation property. Biol Cybern 63:169–176 MATHMathSciNetCrossRefGoogle Scholar
  42. 42.
    Moody J, Darken C (1989) Fast learning in networks of locally-tuned processing units. Neural Comput 1:281–294 CrossRefGoogle Scholar
  43. 43.
    Wismüller A, Lange O, Auer DP, Leinsinger G (2010) Model-free functional MRI analysis for detecting low-frequency functional connectivity in the human brain. In: Proceedings of SPIE, medical imaging 7624-56, 76241M. doi: 10.1117/12.843014
  44. 44.
    Warntjes JB, Dahlqvist O, Lundberg P (2007) Novel method for rapid, simultaneous T1, T2, and proton density quantification. Magn Reson Med 57:528–537 CrossRefGoogle Scholar
  45. 45.
    Deoni SC, Rutt BK, Peters TM (2003) Rapid combined T1 and T2 mapping using gradient recalled acquisition in the steady state. Magn Reson Med 49:515–526 CrossRefGoogle Scholar
  46. 46.
    Wismüller A, Vietze F, Dersch DR (2000) Segmentation with neural networks. In: Bankman I, Rangayyan R, Evans A, Woods R, Fishman E, Huang H (eds) Handbook of medical imaging. Johns Hopkins University/Academic Press, Baltimore/San Diego. ISBN 0120777908 Google Scholar
  47. 47.
    Wismüller A, Vietze F, Dersch DR, Ritter H, Leinsinger GL, Heiss DT, Pfluger T, Hahn K (1999) Vollautomatische Segmentierung multispektraler MRT-Datensätze des menschlichen Gehirns durch elastische Verzerrung deformierbarer Merkmalskarten. Fortschr Röntgenstr, Suppl 1, 170:37 Google Scholar
  48. 48.
    Wismüller A, Vietze F, Dersch DR, Leinsinger G, Heiss DT, Pfluger T, Hahn K (1998) Automatic segmentation and volumetry of multispectral MRI data sets of the human brain by self-organizing neural networks. Radiol Suppl 209:399 Google Scholar
  49. 49.
    Wismüller A, Behrends J, Lange O, Jukic M, Hahn K, Reiser MF, Auer D (2003) High-precision computer-assisted segmentation of multispectral MRI data sets in patients with multiple sclerosis by a flexible machine learning image analysis approach. In: Wittenberg T et al. (eds) Bildverarbeitung für die Medizin 2003, Reihe Informatik aktuell. Springer, Berlin/Heidelberg/New York, pp 403–407 Google Scholar
  50. 50.
    Wismüller A, Behrends J, Lange O, Jukic M, Hahn K, Auer D (2001) Flexible machine learning image analysis for high-precision computer-assisted segmentation of multispectral MRI data sets in patients with multiple sclerosis. Radiol Suppl 209:460 Google Scholar
  51. 51.
    Filippi M, Horsfield M, Tofts P, Barkhof F, Thompson A, Miller D (1995) Quantitative assessment of MRI lesion load in monitoring the evolution of multiple sclerosis. Brain 118:1601–1612 CrossRefGoogle Scholar
  52. 52.
    Ge Y, Grossman RI, Udupa JK, Wei L, Mannon LJ, Polanski M, Kolson D (2000) Brain athrophy in relapsing-remitting multiple sclerosis and secondary progressive multiple sclerosis: longitudinal quantitative analysis. Radiology 214:665–670 Google Scholar
  53. 53.
    Wismüller A, Behrends J, Lange O, Dersch DR, Leinsinger GL, Vietze F, Hahn K (2001) Automatic segmentation of cerebral contours in multispectral MRI data sets of the human brain by self-organizing neural networks. Radiol Suppl 221(P):461 Google Scholar
  54. 54.
    Kurtzke JF (1983) Rating neurologic impairment in multiple sclerosis: an expanded disability status scale EDSS. Neurology Google Scholar
  55. 55.
    Wicks D, Tofts P, Miller D, du Boulay C, Feinstein A, Sacares R (1992) Volume measurement of multiple sclerosis lesions with magnetic resonance images: a preliminary study. Neuroradiology 34:475–479 CrossRefGoogle Scholar
  56. 56.
    Grassiot B, Desgranges B, Eustache F, Defer G (2010) Quantification and clinical relevance of brain atrophy in multiple sclerosis: a review. J Neurol 256(9):1397–1412. doi:10.1007/s00415-009-5108-4 CrossRefGoogle Scholar
  57. 57.
    BSI (1987) British Standards. Precision of test methods. Part I. Guide for the determination of “reproducibility” for a standard test method by inter-laboratory tests. British Standards Institution, BS 5497 Google Scholar
  58. 58.
    Rumelhart DE, McClelland JL (1986) Learning internal representations by error propagation. In: Parallel distributed processing, vol I. MIT Press, Cambridge Google Scholar
  59. 59.
    Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20(3):273–297 MATHGoogle Scholar
  60. 60.
    Kohlmorgen J, Müller KR, Pawelzik K (1995) Improving short-term prediction with competing experts. In: Proceedings of the international conference on artificial neural networks (ICANN), vol 2, pp 215–220, Paris. EC2 & Cie Google Scholar
  61. 61.
    Wismüller A, Vietze F, Dersch DR, Hahn K, Ritter H (1998) The deformable feature map—adaptive plasticity in function approximation. In: Niklasson L, Bodèn M, Ziemke T (eds) ICANN’98—Proceedings of the 8th international conference on artificial neural networks, Skövde, Sweden. Perspectives in neural computing, vol 1. Springer, London/Berlin/New York. pp 222–227 Google Scholar
  62. 62.
    Wismüller A, Vietze F, Dersch DR, Behrends J, Hahn K, Ritter H (2002) The deformable feature map—a novel neurocomputing algorithm for adaptive plasticity in pattern analysis. Neurocomputing 48:107–139 MATHCrossRefGoogle Scholar
  63. 63.
    Kullback S, Leibler RA (1951) On information and sufficiency. Ann Math Stat 22:79–86 MATHMathSciNetCrossRefGoogle Scholar
  64. 64.
    Wismüller A, Vietze F, Behrends J, Meyer-Baese A, Reiser MF, Ritter H (2004) Fully-automated biomedical image segmentation by self-organized model adaptation. Neural Netw 17:1327–1344 CrossRefGoogle Scholar
  65. 65.
    Wismüller A, Vietze F, Dersch DR, Leinsinger G, Ritter H, Hahn K (1999) Adaptive self-organized template matching of the gray-level feature space for automatic segmentation of multispectral MRI data of the human brain. Radiol Suppl 213(P):364 Google Scholar
  66. 66.
    Wismüller A, Vietze F, Dersch DR, Hahn K, Ritter H (1999) The deformable feature map—fully-automatic multispectral MRI segmentation of the human brain by self-organized elastic matching. In: Proceedings of the 20th conference of the international society for clinical biostatistics and 44th annual conference of the German society for medical informatics, biometry, and epidemiology, ISCB-GMDS’99, Heidelberg, p 501 Google Scholar
  67. 67.
    Wismüller A, Behrends J, Dersch DR, Leinsinger GL, Vietze F, Reiser M (2002) Neural network segmentation of cerebral contours in multispectral MRI data sets of the human brain. Eur Radiol 12(Suppl 1) Google Scholar
  68. 68.
    Behrends J (2001) Automatische Randkontur- und Gewebesegmentierung von Kernspintomographiedatensätzen des menschlichen Gehirns durch neuronale Netze. Diplomarbeit, Technische Informatik II, Technische Universität Hamburg-Harburg, München. Supervised by A Wismüller (In German) Google Scholar
  69. 69.
    Behrends J, Hoole P, Leinsinger GL, Tillmann HG, Hahn K, Reiser M, Wismüller A (2003) A segmentation and analysis method for MRI data of the human vocal tract. In: Wittenberg T et al. (eds) Bildverarbeitung für die Medizin 2003, Reihe Informatik aktuell. Springer, Berlin/Heidelberg/New York, pp 186–190 Google Scholar
  70. 70.
    Behrends J, Wismüller A (2001) A segmentation and analysis method for MRI data of the human vocal tract. In: Human and machine perception: research reports of the institute for phonetics and speech communication (FIPKM), vol 37. University of Munich, Munich, pp 205–239. ISSN 0342-782X Google Scholar
  71. 71.
    Hoole P, Wismüller A, Leinsinger GL, Kroos C, Geumann A, Inoue M (2000) Analysis of tongue configuration in multi-speaker, multi-volume MRI data. In: Proceedings of the 5th seminar on speech production (SPS5) & CREST workshop on models of speech production, Kloster Seeon, pp 157–160 Google Scholar
  72. 72.
    Wismüller A, Behrends J, Hoole P, Leinsinger G, Reiser M, Westesson PL (2008) Human vocal tract analysis by in vivo 3D MRI during phonation: a complete system for imaging, quantitative modeling, and speech synthesis. In: Metaxas D, Axel L, Fichtinger G, Szekely G (eds) Medical image computing and computer-assisted intervention (MICCAI 2008), proceedings, Part II. Lecture notes in computer science. Springer, Berlin/Heidelberg/New York. doi:10.1007/978-3-540-85990-1_37 Google Scholar
  73. 73.
    Rudin M (2009) Noninvasive structural, functional, and molecular imaging in drug development. Curr Opin Chem Biol 13(3):360–371 MathSciNetCrossRefGoogle Scholar
  74. 74.
    Wismüller A, Lange O, Dersch DR, Leinsinger GL, Hahn K, Pütz B, Auer D (2002) Cluster analysis of biomedical image time-series. Int J Comput Vis 46(2):103–128 MATHCrossRefGoogle Scholar
  75. 75.
    Bandettini PA, Jesmanowicz A, Wong EC, Hyde JS (1993) Processing strategies for time-course data sets in functional MRI of the human brain. Magn Reson Med 30:161–173 CrossRefGoogle Scholar
  76. 76.
    Ogawa S, Lee T, Kay AR, Tank DW (1990) Brain magnetic-resonance-imaging with contrast dependent on blood oxygenation. Proc Natl Acad Sci USA 87(24):9868–9872 CrossRefGoogle Scholar
  77. 77.
    Østergaard L, Weisskopf RM, Chesler DA, Gyldensted C, Rosen BR (1996) High resolution measurement of cerebral blood flow using intravascular tracer bolus passages. Part I. Mathematical approach and statistical analysis. Magn Res Med 36:715–725 CrossRefGoogle Scholar
  78. 78.
    Hyvärinen A (1999) Survey on independent component analysis. Neural Comput Surv 2:94–128 Google Scholar
  79. 79.
    Bell AJ, Sejnowski TJ (1995) An information-maximization approach to blind separation and blind deconvolution. Neural Comput 7:1129–1159 CrossRefGoogle Scholar
  80. 80.
    Meyer-Baese A, Wismüller A, Otto T, Auer D (2004) Comparison of two exploratory data analysis methods for fMRI: unsupervised clustering vs independent component analysis. IEEE Trans Inf Technol Biomed 8(3):387–398 CrossRefGoogle Scholar
  81. 81.
    Meyer-Baese A, Wismüller A, Martinetz T, Auer D, Sumners D (2004) Model-free functional MRI analysis using topographic independent component analysis. Int J Neural Syst 14:217–229 CrossRefGoogle Scholar
  82. 82.
    Ding X, Tkach J, Ruggieri P, Masaryk T (1994) Analysis of time-course functional MRI data with clustering method without use of reference signal. In: Proc SMR, 2nd annual meeting, San Francisco, p 630 Google Scholar
  83. 83.
    Scarth G, McIntyre M, Wowk B, Somorjai RL (1995) Detection of novelty in functional images using fuzzy clustering. In: Proc SMR, 3rd annual meeting, Nice, p 238 Google Scholar
  84. 84.
    Scarth G, Moser E, Baumgartner R, Alexander M, Somorjai RL (1996) Paradigm-free fuzzy clustering-detected activations in fMRI: a case study. In: Proc SMR, 4th annual meeting, New York, p 1784 Google Scholar
  85. 85.
    Ding X, Masaryk T, Ruggieri P, Tkach J (1996) Detection of activation patterns in dynamic functional MRI with a clustering technique. In: Proc SMR, 4th annual meeting, New York, p 1798 Google Scholar
  86. 86.
    Golay X, Kollias S, Meier D, Boesinger P (1996) Optimization of a fuzzy clustering technique and comparison with conventional post processing methods in fMRI. In: Proc SMR, 4th annual meeting, New York, p 1787 Google Scholar
  87. 87.
    Galicki M, Möller U, Witte H (1997) Neural clustering networks based on global optimisation of prototypes in metric spaces. Neural Comput Appl 5:2–13 CrossRefGoogle Scholar
  88. 88.
    Fischer H, Hennig J (1999) Neural-network based analysis of MR time series. Magn Reson Med 41(1):124–131 CrossRefGoogle Scholar
  89. 89.
    Goutte C, Toft P, Rostrup E, Nielsen FA, Hansen LK (1999) On clustering fMRI time series. Neuroimage 9:298–310 CrossRefGoogle Scholar
  90. 90.
    Chuang KH, Chiu MJ, Lin CC, Chen JH (1999) Model-free functional MRI analysis using Kohonen clustering neural network and fuzzy c-menas. IEEE Trans Med Imaging 18(12):1117–1128 CrossRefGoogle Scholar
  91. 91.
    Moser E, Teichtmeister C, Diemling M (1996) Reproducibility and postprocessing of gradient echo functional MRI to improve localization of brain activity in the human visual cortex. Magn Reson Imaging 14:567–579 CrossRefGoogle Scholar
  92. 92.
    Baumgartner R, Windischberger C, Moser E (1998) Quantification in functional magnetic resonance imaging: fuzzy clustering vs. correlation analysis. Magn Reson Imaging 16(2):115–125 CrossRefGoogle Scholar
  93. 93.
    Wismüller A, Dersch DR, Lipinski B, Hahn K, Auer D (1998) Hierarchical unsupervised clustering of fMRI data by deterministic annealing. In: Proceedings of the sixth scientific meeting of the international society of magnetic resonance in medicine 1998, Sydney, p 412 Google Scholar
  94. 94.
    Wismüller A, Dersch DR, Lipinski B, Hahn K, Auer D (1998) A neural network approach to functional MRI pattern analysis—clustering of time-series by hierarchical vector quantization. In: Niklasson L, Bodèn M, Ziemke T (eds) ICANN’98—proceedings of the 8th international conference on artificial neural networks, Skövde, Sweden. Perspectives in neural computing, vol 2. Springer, London/Berlin/New York. pp 123–128 Google Scholar
  95. 95.
    Wismüller A, Meyer-Baese A, Lange O, Auer D, Sumners D (2004) Model-free fMRI analysis based on unsupervised clustering. J Biomed Inf 37(1):10–18 CrossRefGoogle Scholar
  96. 96.
    Otto T, Meyer-Baese A, Hurdal M, Sumners D, Auer D, Wismüller A (2003) Model-free functional MRI analysis using cluster-based methods. In: Proc SPIE, vol 5103, pp 17–24 CrossRefGoogle Scholar
  97. 97.
    Leinsinger GL, Wismüller A, Joechel P, Lange O, Heiss DT, Hahn K (2001) Evaluation of the motor cortex using fMRI and image processing with self-organized cluster analysis by deterministic annealing. Radiology (Suppl) 221(P):487 Google Scholar
  98. 98.
    Wismüller A, Leinsinger GL, Lange O, Gössl C, Auer DP, Hahn K (2000) Unsupervised cluster analysis as a visualization strategy for supervised functional MRI data processing methods. Radiology (Suppl) 217(P):209 Google Scholar
  99. 99.
    Wismüller A, Dersch DR, Lipinski B, Hahn K, Auer D (1998) Hierarchical clustering of fMRI time-series by deterministic annealing. In: Toga AW, Frackowiak RSJ, Mazziotta JC (eds) 4th International conference on human brain mapping 1998, Montreal, Canada, vol 7, p 593 Google Scholar
  100. 100.
    Joechel P (2003) Analyse der funktionellen MRT des motorischen Handareals unter Anwendung künstlicher neuronaler Netze. Dissertation, Ludwig-Maximilians-Universität, München Google Scholar
  101. 101.
    Wismüller A, Lange O, Meyer-Baese A, Reiser MF, Leinsinger GL (2006) Cluster analysis of dynamic cerebral contrast-enhanced perfusion MRI time-series. IEEE Trans Med Imaging 25(1):62–73 CrossRefGoogle Scholar
  102. 102.
    Wismüller A, Lange O, Dersch DR, Hahn K, Leinsinger GL (2001) Analysis of dynamic perfusion MRI data by neural networks. In: Verleysen M (ed) Proc ESANN’2001, Europ symp on artificial neural networks. d-Side Publishers, Bruges, pp 19–24 Google Scholar
  103. 103.
    Wismüller A, Lange O, Dersch DR, Hahn K, Leinsinger G (2001) Neural network analysis of dynamic contrast-enhanced MRI mammography. In: Dorffner G, Bischof H, Hornik K (eds) ICANN’2001—proceedings of the international conference on artificial neural networks, Vienna, Austria. Lecture Notes in Computer Science, vol 2130. Springer, Berlin/Heidelberg/New York, pp 1000–1005 Google Scholar
  104. 104.
    Wismüller A, Leinsinger GL, Dersch DR, Lange O, Scherr M, Hahn K (2000) Neural network processing in contrast-enhanced MRI mammography—unsupervised cluster analysis of signal dynamics time-series by deterministic annealing. Radiologe (Suppl) 217(P):208–209 Google Scholar
  105. 105.
    Nattkemper TW, Wismüller A (2005) Tumour classification with unsupervised machine learning. Med Image Anal 9(4):344–351 CrossRefGoogle Scholar
  106. 106.
    Scherr M (2003) Vergleich der dynamischen MR-Mammographie mit der Sestamibi-Mammaszintigraphie bei mammographisch unklaren Mammaläsionen. Dissertation, Ludwig-Maximilians-Universität, München Google Scholar
  107. 107.
    Wismüller A, Lange O, Krammer C, Schlossbauer T, Reiser M, Leinsinger G (2009) Neural network analysis of side-specific 99mTcMAG3 renal scintigraphy in children. In: Radiological society of North America scientific meeting, pp 603–604 Google Scholar
  108. 108.
    Krammer C (2004) Evaluation der seitengetrennten MAG3-Nierenszintigraphie im Kindesalter unter Anwendung eines künstlichen neuronalen Netzes. Dissertation, Ludwig-Maximilians-Universität, München Google Scholar
  109. 109.
    Eisen MB, Spellman PT, Botstein D (1998) Cluster analysis and display of genome-wide expression patterns. Proc Natl Acad Sci 95:14863–14868 CrossRefGoogle Scholar
  110. 110.
    Tamayo P, Slonim D, Mesirov J, Zhu Q, Kitareewan S, Dmitrovsky E, Lander ES, Golub TR (1999) Interpreting patterns of gene expression with self-organizing maps: Methods and application to hematopoietic differentiation. Proc Natl Acad Sci USA 96:2907–2912 CrossRefGoogle Scholar
  111. 111.
    Kaski S (2001) SOM-based exploratory analysis of gene expression data. In: Allinson N, Yin H, Allinson L, Slack J (eds) Advances in self-organizing maps. Springer, London, pp 124–131 Google Scholar
  112. 112.
    Graepel T, Burger M, Obermayer K (1998) Self-organizing maps: generalizations and new optimization techniques. Neurocomputing 21:173–190 MATHCrossRefGoogle Scholar
  113. 113.
    Wismüller A (2006) Exploratory Morphogenesis (XOM): a novel computational framework for self-organization. PhD thesis, Technical University of Munich, Department of Electrical and Computer Engineering Google Scholar
  114. 114.
    Wismüller A (2009) The exploration machine—a novel method for data visualization. In: Advances in self-organizing maps. Lecture notes in computer science, pp 344–352 CrossRefGoogle Scholar
  115. 115.
    Wismüller A (2009) A computational framework for nonlinear dimensionality reduction and clustering. In: Advances in self-organizing maps, Lecture notes in computer science, pp 334–343 CrossRefGoogle Scholar
  116. 116.
    Wismüller A (2001) Exploration-organized morphogenesis (XOM)—a general framework for learning by self-organization. In: Human and machine perception. Research reports of the institute for phonetics and speech communication (FIPKM), vol 37. University of Munich, Munich, pp 205–239. ISSN 0342-782X Google Scholar
  117. 117.
    Wismüller A (2009) A computational framework for exploratory data analysis. In: Verleysen M (ed) European symposium on artificial neural networks—advances in computational intelligence and learning. 22–24 April 2009. d-Side Publishers, Bruges. ISBN 2-930307-09-9 Google Scholar
  118. 118.
    Wismüller A (2009) The exploration machine—a novel method for structure-preserving dimensionality reduction. In: Verleysen M (ed) European symposium on artificial neural networks—advances in computational intelligence and learning. 22–24 April 2009. d-Side Publishers, Bruges. ISBN 2-930307-09-9 Google Scholar
  119. 119.
    Wismüller A (2009) The exploration machine: a novel method for analyzing high-dimensional data in computer-aided diagnosis. In: Karssemeijer N, Giger M (eds) Medical imaging 2009: computer-aided diagnosis. Proceedings of SPIE, vol 7260, pp 72600G–72600G–7 Google Scholar
  120. 120.
    Bunte K, Hammer B, Wismüller A, Biehl M (2010) Adaptive local dissimilarity measures for discriminative dimension reduction of labeled data. Neurocomputing 73(7–9):1074–1092 CrossRefGoogle Scholar
  121. 121.
    Bunte K, Hammer B, Villmann T, Biehl M, Wismüller A (2010) Exploratory Observation Machine (XOM) with Kullback-Leibler divergence for dimensionality reduction and visualization. In: Proc of the 18th Europ symp on art neur netw (ESANN). d-Side Publishers, Bruges Google Scholar
  122. 122.
    Hinton G, Roweis S (2003) Stochastic neighbor embedding. In: Advances in neural information processing systems, vol 15. MIT Press, Cambridge Google Scholar
  123. 123.
    Then Bergh F, Kuempfel T, Schumann E, Held U, Gottschalk M, Blazevic M, Wismüller A, Holsboer F, Yassouridis A, Uhr M, Weber F, Daumer M, Trenkwalder C, Auer DP (2006) Monthly i.v. methylprednisolone in relapsing-remitting MS-reduction of enhancing lesions, T2 lesion volume and plasma prolactin concentrations. BMC Neurol 6(19). doi:10.1186/1471-2377-6-19
  124. 124.
    Wismüller A, Meyer-Baese A, Leinsinger GL, Lange O, Schlossbauer T, Reiser MF (2007) Neural network vector quantization improves the diagnostic quality of computer-aided diagnosis in dynamic breast MRI. Proc SPIE 6514. doi:10.1117/12.708819
  125. 125.
    Wismüller A, Meyer-Baese A, Lange O, Schlossbauer T, Kallergi M, Reiser MF, Leinsinger G (2006) Segmentation and classification of dynamic breast MR image data. J Electr Imaging 15. doi:013020
  126. 126.
    Leinsinger G, Schlossbauer T, Scherr M, Lange O, Reiser M, Wismüller A (2006) Cluster analysis of signal-intensity time course in dynamic breast MRI: does unsupervised vector quantization help to evaluate small mammographic lesions? Eur Radiol 16(5):1138–1146 CrossRefGoogle Scholar
  127. 127.
    Meyer-Baese A, Schlossbauer T, Lange O, Wismüller A (2009) Small lesions evaluation based on unsupervised cluster analysis of signal-intensity time courses in dynamic breast MRI. Int J Biomed Imaging. Article ID 326924. doi:10.1155/2009/326924
  128. 128.
    Schlossbauer T, Leinsinger G, Wismüller A, Lange O, Scherr M, Meyer-Baese A, Reiser M (2008) Classification of small contrast enhancing breast lesions in dynamic magnetic resonance imaging using a combination of morphological criteria and dynamic analysis based on unsupervised vector quantization. Invest Radiol 43(1):56–64 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  1. 1.Depts. of Radiology and Biomedical EngineeringUniversity of Rochester Medical CenterRochesterUSA
  2. 2.Dept. of RadiologyUniversity of MunichMunichGermany

Personalised recommendations