Abstract
Magnetic resonance spectral images provide information on metabolic processes and can thus be used for in vivo tumor diagnosis. However, each single spectrum has to be checked manually for tumorous changes by an expert, which is only possible for very few spectra in clinical routine. We propose a semi-supervised procedure which requires only very few labeled spectra as input and can hence adapt to patient and acquisition specific variations. The method employs a discriminative random field with highly flexible single-side and parameter-free pair potentials to model spatial correlation of spectra. Classification is performed according to the label set that minimizes the energy of this random field. An iterative procedure alternates a parameter update of the random field using a kernel density estimation with a classification by means of the GraphCut algorithm. The method is compared to a single spectrum approach on simulated and clinical data.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hagberg, G.: From magnetic resonance spectroscopy to classification of tumors. a review of pattern recognition methods. NMR in Biomedicine 11(45), 148–156 (1998)
Devos, A., Lukas, L., Suykens, J., Vanhamme, L., Tate, A., Howe, F., Majós, C., Moreno-Torres, A., van der Graaf, M., Arús, C., Van Huffel, S.: Classification of brain tumours using short echo time 1H MR spectra. Journal of Magnetic Resonance 170(1), 164–175 (2004)
Menze, B.H., Lichy, M.P., Bachert, P., Kelm, B.M., Schlemmer, H.P., Hamprecht, F.A.: Optimal classification of long echo in vivo magnetic resonance spectra in the detection of recurrent brain tumors. NMR in Biomedicine 19(5), 599–609 (2006)
Kelm, B.M., Menze, B.H., Zechmann, C.M., Baudendistel, K.T., Hamprecht, F.A.: Automated estimation of tumor probability in prostate MRSI: Pattern recognition vs. quantification. Magnetic Resonance in Medicine 57, 150–159 (2007)
Lukas, L., Devos, A., Suykens, J., Vanhamme, L., Howe, F., Majós, C., Moreno-Torres, A., van der Graaf, M., Tate, A., Arús, C., Van Huffel, S.: Brain tumor classification based on long echo proton MRS signals. Artificial Intelligence in Medicine 31(1), 73–89 (2004)
Tate, A., Majós, C., Moreno, A., Howe, F., Griffiths, J., Arús, C.: Automated classification of short echo time in in vivo 1H brain tumor spectra: A multicenter study. Magnetic Resonance in Medicine 49(1), 29–36 (2003)
Silverman, B., Silverman, B.: Density Estimation for Statistics and Data Analysis. Chapman and Hall, New York (1986)
Besag, J.: Spatial interaction and the statistical analysis of lattice systems. Journal of the Royal Statistical Society 36, 192–236 (1974)
Ng, A., Jordan, M.: On discriminative vs. generative classifiers: A comparison of logistic regression and naïve Bayes. In: Proceedings of the 14th Conference on Advances in Neural Information Processing, vol. 14 (2001)
Kumar, S., Hebert, M.: Discriminative random fields. International Journal of Computer Vision 68(2), 179–201 (2006)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. 18th International Conf. on Machine Learning, pp. 282–289. Morgan Kaufmann, San Francisco, CA (2001)
Li, S.Z.: Markov random field modeling in computer vision. Springer, London, UK (1995)
Perona, P., Malik, J.: Scale-Space and edge detection using anistropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(7), 629–639 (1990)
Boykov, Y., Funka-Lea, G.: Graph Cuts and Efficient N-D Image Segmentation. International Journal of Computer Vision 70(2), 109–131 (2006)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(11), 1222–1239 (2001)
Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(2), 147–159 (2004)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(9), 1124–1137 (2004)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likehood from incomplete data via the EM-algorithm. Journal of the Royal Statistical Society, Series B 39(1), 1–22 (1977)
Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence 6(6), 721–741 (1984)
Robert, C., Casella, G.: Monte Carlo Statistical Methods, 2nd edn. Springer, Secaucus, NJ, USA (2004)
Kelm, B.M., Hamprecht, F.A.: Trading resolution against noise in NMR spectroscopic imaging using conditional random fields. Technical report, IWR, University of Heidelberg (2007)
Menze, B.H., Kelm, B.M., Weber, M.A., Bachert, P., Hamprecht, F.A.: Mimicking the human expert: a pattern recognition approach to score the data quality in MRSI. Technical report, Interdisciplinary Center for Scientific Computing, University of Heidelberg (2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Görlitz, L., Menze, B.H., Weber, M.A., Kelm, B.M., Hamprecht, F.A. (2007). Semi-supervised Tumor Detection in Magnetic Resonance Spectroscopic Images Using Discriminative Random Fields. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds) Pattern Recognition. DAGM 2007. Lecture Notes in Computer Science, vol 4713. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74936-3_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-74936-3_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74933-2
Online ISBN: 978-3-540-74936-3
eBook Packages: Computer ScienceComputer Science (R0)