VISUALIZATION OF NONLINEAR CLASSIFICATION MODELS IN NEUROIMAGING - Signed Sensitivity Maps

Peter M. Rasmussen, Tanya Schmah, Kristoffer H. Madsen, Torben E. Lund, Grigori Yourganov, Stephen C. Strother, Lars K. Hansen

Abstract

Classification models are becoming increasing popular tools in the analysis of neuroimaging data sets. Besides obtaining good prediction accuracy, a competing goal is to interpret how the classifier works. From a neuroscientific perspective, we are interested in the brain pattern reflecting the underlying neural encoding of an experiment defining multiple brain states. In this relation there is a great desire for the researcher to generate brain maps, that highlight brain locations of importance to the classifiers decisions. Based on sensitivity analysis, we develop further procedures for model visualization. Specifically we focus on the generation of summary maps of a nonlinear classifier, that reveal how the classifier works in different parts of the input domain. Each of the maps includes sign information, unlike earlier related methods. The sign information allows the researcher to assess in which direction the individual locations influence the classification. We illustrate the visualization procedure on a real data from a simple functional magnetic resonance imaging experiment.

References

  1. Baehrens, D., Schroeter, T., Harmeling, S., Kawanab, M., Hansen, K., and Müller, K.-R. (2010). How to explain individual classification decisions. Journal of Machine Learning Research, 11:1803-1831.
  2. Cox, D. D. and Savoy, R. L. (2003). Functional magnetic resonance imaging (fMRI) ”brain reading”: detecting and classifying distributed patterns of fMRI activity in human visual cortex. NeuroImage 19, pages 261-270.
  3. Davatzikos, C., Ruparel, K., Fan, Y., Shen, D., Acharyya, M., Loughead, J., Gur, R., and Langleben, D. (2005). Classifying spatial patterns of brain activity with machine learning methods: application to lie detection. NeuroImage, 28(3):663-668.
  4. Friedman, J. H. (1989). Regularized discriminant analysis. J. Am. Statistical Assoc., 84:165 - 175.
  5. Golland, P., Grimson, W. E. L., Shenton, M. E., and Kikinis, R. (2005). Detection and analysis of statistical differences in anatomical shape. Medical Image Analysis, 9:69-86.
  6. Haynes, J. D. and Rees, G. (2006). Decoding mental states from brain activity in humans. Nature Reviews Neuroscience, 7(7):523-534.
  7. Kjems, U., Hansen, L. K., Anderson, J., Frutiger, S., Muley, S., Sidtis, J., Rottenberg, D., and Strother, S. C. (2002). The quantitative evaluation of functional neuroimaging experiments: mutual information learning curves. NeuroImage, 15(4):772-786.
  8. LaConte, S., Strother, S., Cherkassky, V., Anderson, J., and Hu, X. (2005). Support vector machines for temporal classification of block design fMRI data. NeuroImage, 26:317-329.
  9. Lautrup, B., Hansen, L., Law, I., Mørch, N., Svarer, C., and Strother, S. (1994). Massive weight sharing: A cure for extremely ill-posed problems. Proceedings of the Workshop on Supercomputing in Brain Research: From Tomography to Neural Networks. World Scientific, Ulich, Germany, pages 137-148.
  10. Mika, S., Rätsch, G., Schölkopf, B., Smola, A., Weston, J., and M üller, K.-R. (1999). Invariant feature extraction and classification in kernel spaces. Advances in Neural Information Processing Systems, 12:526-532.
  11. Misaki, M., Kim, Y., Bandettini, P., and Kriegeskorte, N. (2010). Comparison of multivariate classifiers and response normalizations for pattern-information fMRI. NeuroImage, 53(1):103-118.
  12. O'Toole, A. J., Jiang, F., Abdi, H., P Nard, N., Dunlop, J. P., and Parent, M. A. (2007). Theoretical, statistical, and practical perspectives on pattern-based classification approaches to the analysis of functional neuroimaging data. Journal of Cognitive Neuroscience, 19:1735- 1752.
  13. Pereira, F., Mitchell, T., and Botvinick, M. (2009). Machine learning classifiers and fMRI: a tutorial overview. NeuroImage, 45(1):S199-S209.
  14. Rasmussen, P. M., Madsen, K. H., Lund, T. E., and Hansen, L. K. (2011). Visualization of nonlinear kernel models in neuroimaging by sensitivity maps. NeuroImage, 55(3):1120 - 1131.
  15. Schmah, T., Yourganov, G., Zemel, R., Hinton, G., Small, S., and Strother, S. (2010). A Comparison of Classification Methods for Longitudinal fMRI Studies. Neural Computation, 22:2729-2762.
  16. Shawe-Taylor, J. and Cristianini, N. (2004). Kernel methods for pattern analysis. Cambridge.
  17. Sigurdsson, S., Philipsen, P., Hansen, L., Larsen, J., Gniadecka, M., and Wulf, H. (2004). Detection of skin cancer by classification of Raman spectra. IEEE Transactions on Biomedical Engineering, 51(10):1784-1793.
  18. Strother, S., Anderson, J., Hansen, L., Kjems, U., Kustra, R., Sidtis, J., Frutiger, S., Muley, S., LaConte, S., and Rottenberg, D. (2002). The quantitative evaluation of functional neuroimaging experiments: The NPAIRS data analysis framework. NeuroImage, 15(4):747- 771.
  19. Yourganov, G., Schmah, T., Small, S., PM, R., and Strother, S. (2010). Functional connectivity metrics during stroke recovery. Arch Ital Biol., 148(3):259-270.
  20. Zhang, J., Anderson, J. R., Liang, L., Pulapura, S. K., Gatewood, L., Rottenberg, D. A., and Strother, S. C. (2009a). Evaluation and optimization of fMRI single-subject processing pipelines with NPAIRS and second-level CVA. Magn Reson Imaging, 27:264- 278.
  21. Zhang, Z., Dai, G., and Jordan, M. I. (2009b). A flexible and efficient algorithm for regularized fisher discriminant analysis. In ECML PKDD 7809: Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, pages 632-647, Berlin, Heidelberg. Springer-Verlag.
  22. Zurada, J., Malinowski, A., and Cloete, I. (1994). Sensitivity analysis for minimization of input data dimension forfeedforward neural network. 1994 IEEE International Symposium on Circuits and Systems, 1994. ISCAS'94., 6:447-450.
  23. Zurada, J., Malinowski, A., and Usui, S. (1997). Perturbation method for deleting redundant inputs of perceptron networks. Neurocomputing, 14(2):177-193.
Download


Paper Citation


in Harvard Style

M. Rasmussen P., Schmah T., H. Madsen K., E. Lund T., Yourganov G., C. Strother S. and K. Hansen L. (2012). VISUALIZATION OF NONLINEAR CLASSIFICATION MODELS IN NEUROIMAGING - Signed Sensitivity Maps . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012) ISBN 978-989-8425-89-8, pages 254-263. DOI: 10.5220/0003785602540263


in Bibtex Style

@conference{biosignals12,
author={Peter M. Rasmussen and Tanya Schmah and Kristoffer H. Madsen and Torben E. Lund and Grigori Yourganov and Stephen C. Strother and Lars K. Hansen},
title={VISUALIZATION OF NONLINEAR CLASSIFICATION MODELS IN NEUROIMAGING - Signed Sensitivity Maps},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012)},
year={2012},
pages={254-263},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003785602540263},
isbn={978-989-8425-89-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012)
TI - VISUALIZATION OF NONLINEAR CLASSIFICATION MODELS IN NEUROIMAGING - Signed Sensitivity Maps
SN - 978-989-8425-89-8
AU - M. Rasmussen P.
AU - Schmah T.
AU - H. Madsen K.
AU - E. Lund T.
AU - Yourganov G.
AU - C. Strother S.
AU - K. Hansen L.
PY - 2012
SP - 254
EP - 263
DO - 10.5220/0003785602540263