Visualization of Decision Tree State for the Classification of Parkinson's Disease

Authors

  • David Williams Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, The Netherlands
  • Deborah Mudali Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, The Netherlands
  • Hugo Buddelmeijer Kapteyn Astronomical Institute, University of Groningen, The Netherlands
  • Parisa Noorishad Kapteyn Astronomical Institute, University of Groningen, The Netherlands and Netherlands eScience Center, Amsterdam, The Netherlands
  • Sanne Meles Neuroimaging Center, University Medical Center Groningen, The Netherlands
  • Remco Renken Neuroimaging Center, University Medical Center Groningen, The Netherlands
  • Nico Leenders Department of Neurology, University Medical Center Groningen, The Netherlands
  • Edwin Valentijn Kapteyn Astronomical Institute, University of Groningen, The Netherlands
  • Jos Roerdink Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, The Netherlands

DOI:

https://doi.org/10.14738/jbemi.33.1858

Keywords:

Decision tree, Visualization, Medical imaging, Parkinson's Disease, Computer aided diagnosis,

Abstract

Decision trees have been shown to be effective at classifying subjects with Parkinson's disease when provided with features (subject scores) derived from FDG-PET data. Such subject scores have strong discriminative power but are not intuitive to understand. We therefore augment each decision node with thumbnails of the principal component (PC) images from which the subject scores are computed, and also provide labeled scatter plots of the distribution of scores. These plots allow the progress of individual subjects to be traced through the tree and enable the user to focus on complex or unexpected classifications. In addition, we present a visual representation of a typical brain activity pattern arriving at each leaf node, and show how this can be compared to a known reference to validate the behaviour of the tree.

References

(1) J. R. Quinlan, C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1993.

(2) D. Mudali, L. K. Teune, R. J. Renken, K. L. Leenders, J. B. T. M. Roerdink, Classification of Parkinsonian syndromes from FDG-PET brain data using decision trees with SSM/PCA features, Computational and Mathematical Methods in Medicine Article ID 136921 (2015) 1–10. doi:10.1155/2015/136921.

(3) J. M. Shulman, P. L. De Jager, M. B. Feany, Parkinson’s disease: Genetics and pathogenesis, Annual Review of Pathology: Mechanisms of Disease 6 (1) (2011) 193–222. doi:10.1146/annurev-pathol-011110-130242.

(4) J. Steele, J. Richardson, J. Olszewski, Progressive supranuclear palsy: A heterogeneous degeneration involving the brain stem, basal ganglia and cerebellum with vertical gaze and pseudobulbar palsy, nuchal dystonia and dementia, Archives of Neurology 10 (4) (1964) 333–359. doi:10.1055/s-0034-1377058.

(5) L. Swan, J. Dupont, Multiple system atrophy, Physical Therapy 79 (5)(1999) 488–494. URL http://www.ncbi.nlm.nih.gov/pubmed/10331752

(6) A. J. Hughes, S. E. Daniel, Y. Ben-Shlomo, A. J. Lees, The accuracy of diagnosis of parkinsonian syndromes in a specialist movement disorder service, Brain 125 (4) (2002) 861–870. URL http://www.ncbi.nlm.nih.gov/pubmed/11912118

(7) L. K. Teune, A. L. Bartels, K. L. Leenders, FDG-PET imaging in neurodegenerative brain diseases, in: F. Signorelli (Ed.), Functional Brain Mapping and the Endeavor to Understand the Working Brain, InTech, 2013.

(8) T. Eckert, A. Barnes, V. Dhawan, S. Frucht, M. F. Gordon, A. S. Feigin, D. Eidelberg, FDG PET in the differential diagnosis of parkinsonian disorders, Neuroimage 26 (2005) 912–921. URL http://www.ncbi.nlm.nih.gov/pubmed/15955501

(9) P. G. Spetsieris, D. Eidelberg, Scaled subprofile modeling of resting state imaging data in Parkinson’s disease: Methodological issues, NeuroImage 54 (4) (2011) 2899 – 2914. doi:10.1016/j.neuroimage.2010.10.025.

(10) C. C. Tang, K. L. Poston, T. Eckert, A. Feigin, S. Frucht, M. Gudesblatt, V. Dhawan, M. Lesser, J.-P. Vonsattel, S. Fahn, D. Eidelberg, Differential diagnosis of parkinsonism: a metabolic imaging study using pattern analysis, The Lancet Neurology 9 (2) (2010) 149–158.

(11) L. Rokach, O. Maimon, Data Mining with Decision Trees, Vol. 69, World Scientific, 2008.

(12) L. Breiman, J. H. Friedman, R. A. Olshen, C. J. Stone, Classification and regression trees, Chapman and Hall, 1984.

(13) J. Quinlan, Induction of decision trees, Machine Learning 1 (1) (1986) 81–106. doi:10.1023/A:1022643204877.

(14) C. Shannon, A mathematical theory of communication, The Bell System Technical Journal 27 (3) (1948) 379–423. doi:10.1002/j.1538-7305.1948.tb01338.x.

(15) H. Hofmann, A. P. J. M. Siebes, A. F. X. Wilhelm, Visualizing association rules with interactive mosaic plots, in: Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’00, ACM, 2000, pp. 227–235. doi:10.1145/347090.347133.

(16) M. Ankerst, M. Ester, H.-P. Kriegel, Towards an effective cooperation of the user and the computer for classification, in: Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’00, ACM, 2000, pp. 179–188. doi:10.1145/347090.347124.

(17) J. Stasko, An evaluation of space-filling information visualizations for depicting hierarchical structures, Int. J. Hum.-Comput. Stud. 53 (5) (2000) 663–694. doi:10.1006/ijhc.2000.0420.

(18) M. de Oliveira, H. Levkowitz, From visual data exploration to visual data mining: a survey, IEEE Transactions on Visualization and Computer Graphics 9 (3) (2003) 378–394. doi:10.1109/TVCG.2003.1207445.

(19) S. van den Elzen, J. van Wijk, Baobabview: Interactive construction and analysis of decision trees, in: Visual Analytics Science and Technology (VAST), 2011 IEEE Conference on, 2011, pp. 151–160. doi:10.1109/VAST.2011.6102453.

(20) S. T. Teoh, K.-L. Ma, Paintingclass: Interactive construction, visualization and exploration of decision trees, in: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’03, ACM, 2003, pp. 667–672. doi:10.1145/956750.956837.

(21) L. K. Teune, A. L. Bartels, B. M. de Jong, A. T. Willemsen, S. A. Eshuis, J. J. de Vries, J. C. van Oostrom, K. L. Leenders, Typical cerebral metabolic patterns in neurodegenerative brain diseases, Mov Disord (2010) 2395–404. doi:10.1002/mds.23291.

(22) L. K. Teune, R. J. Renken, D. Mudali, B. M. D. Jong, R. A. Dierckx, J. B. T. M. Roerdink, K. L. Leenders, Validation of parkinsonian diseaserelated metabolic brain patterns, Movement Disorders 28 (4) (2013) 547– 551. doi:10.1002/mds.25361.

(23) J. Demar, B. Zupan, Orange: Data mining fruitful and fun - a historical perspective, Informatica 37 (1) (2013) 55–60.

(24) G. Garraux, C. Phillips, J. Schrouff, A. Kreisler, C. Lemaire, C. Degueldre, C. Delcour, R. Hustinx, A. Luxen, A. Deste, E. Salmon, Multiclass classi- fication of FDG PET scans for the distinction between parkinson’s disease and atypical parkinsonian syndromes, NeuroImage: Clinical 14 (2) (2013) 883–893. doi:10.1016/j.nicl.2013.06.004.

Downloads

Published

2016-07-24

How to Cite

Williams, D., Mudali, D., Buddelmeijer, H., Noorishad, P., Meles, S., Renken, R., Leenders, N., Valentijn, E., & Roerdink, J. (2016). Visualization of Decision Tree State for the Classification of Parkinson’s Disease. British Journal of Healthcare and Medical Research, 3(3), 25. https://doi.org/10.14738/jbemi.33.1858

Issue

Vol. 3 No. 3 (2016): Journal of Biomedical Engineering and Medical Imaging

Section

Original Articles

Most read articles by the same author(s)