Advertisement

Brain Magnetic Resonance Spectroscopy Classifiers

  • Susana Oliveira
  • Jaime Rocha
  • Victor Alves
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 73)

Abstract

During the last decade, the Magnetic Resonance Spectroscopy modality has become an integrant part of the diagnostic routine. However, the visual interpretation of these spectra is difficult and few clinicians are trained to use the technique. In this study, sixty-eight spectra obtained from twenty-two multi-voxel spectroscopies were classified using three well-known classification algorithms: K-Nearest Neighbors (KNN), Decision Trees and Naïve Bayes. The best results were obtained using NaïveBayes that presented an average balanced accuracy rate around 75%, although K-Nearest Neighbors presented very good results in some situations. The obtained results lead us to conclude that it is possible to classify magnetic resonance spectra with data mining techniques for further integration in a Clinical Decision Support System which may help in the diagnosis of new cases.

Keywords

Feature Selection Magnetic Resonance Spectroscopy Linear Discriminant Analysis Clinical Decision Support System Data Mining Technique 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bushberg, J.T., Seibert, J.A., Leidholdt, E.M., Boone, J.M.: The Essential Physics of Medical Imaging, 2nd edn. Lippincott Williams & Wilkins, Philadelphia (2002)Google Scholar
  2. 2.
    Sibtain, N.A., Howe, F.A., Saunders, D.E.: The clinical value of proton magnetic resonance spectroscopy in adult brain tumours. Clinical Radiology 62, 109–119 (2007)CrossRefGoogle Scholar
  3. 3.
    Callot, V., et al.: 1H MR spectroscopy of human brain tumours: a practical approach. European Journal of Radiology 67, 268–274 (2008)CrossRefGoogle Scholar
  4. 4.
    Tate, A.R., et al.: Automated Classification of Short Echo Time in In Vivo 1H Brain Tumor Spectra: A Multicenter Study. Magnetic Resonance in Medicine 49, 29–36 (2003)CrossRefGoogle Scholar
  5. 5.
    Übeyli, E.D.: Comparison of different classification algorithms in clinical decision-making. Expert systems 24(1), 17–31 (2007)CrossRefGoogle Scholar
  6. 6.
    Eom, J., Kim, S., Zhang, B.: AptaCDSS-E: A classifier ensemble-based clinical decision support system for cardiovascular disease level prediction. Expert Systems with Applications 34, 2465–2479 (2008)CrossRefGoogle Scholar
  7. 7.
    Bezabeh, T., et al.: Statistical classification strategy for proton magnetic resonance spectra of soft tissue sarcoma: an exploratory study with potential clinical utility. Sarcoma 6, 97–103 (2002)CrossRefGoogle Scholar
  8. 8.
    Siddall, et al.: Magnetic Resonance Spectroscopy Detects Biochemical Changes in the Brain Associated with Chronic Low Back Pain: A Preliminary Report. Anesthesia and Analgesia 102, 1164-1168 (2006)Google Scholar
  9. 9.
    Luts, et al.: A combined MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs with class probabilities and feature selection. Artificial Intelligence in Medicine 40(2), 87–102 (2007)CrossRefGoogle Scholar
  10. 10.
    García-Gómez, et al.: Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy. Magnetic Resonance Materials in Physics 22(1), 5–18 (2009)CrossRefGoogle Scholar
  11. 11.
    Siemens, MR Spectroscopy Operator Manual: Version syngo MR 2002B. Erlangen (2002)Google Scholar
  12. 12.
    Han, J., Kamber, M.: Data Mining: Concepts and Techniques. Morgan Kaufmann, San Francisco (2000)Google Scholar
  13. 13.
    Luts, J., et al.: Effect of Feature Extraction for Brain Tumor Classification Based on Short Echo Time 1H MR Spectra. Magnetic Resonance in Medicine 60, 288–298 (2008)CrossRefGoogle Scholar
  14. 14.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley-Interscience, Hoboken (2000)Google Scholar
  15. 15.
    Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning: Data Mining, Inference and Prediction. Springer, Heidelberg (2003)Google Scholar
  16. 16.
    Berry, M.J.A., Linoff, G.S.: Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management. Wiley Computer Publishing, Indianapolis (2004)Google Scholar
  17. 17.
    Kantardzic, M.: Data Mining: Concepts, Models, Methods and Algorithms. Wiley-IEEE Press (2002)Google Scholar
  18. 18.
    An, A.: Classification Methods. In: Wang, J. (ed.) Encyclopedia of Data Warehousing and Mining, pp. 144–149. Idea Group Publishing, Hershey (2006)Google Scholar
  19. 19.
    Kertész-Farkas, A., et al.: Benchmarking protein classification algorithms via supervised cross-validation. Journal of Biochemical and Biophysical Methods 70, 1215–1223 (2008)CrossRefGoogle Scholar
  20. 20.
    Kohavi, R.: A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. In: IJCAI (International Joint Conferences on Artificial Intelligence), Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Québec, Canada, August 20-25, Morgan Kaufmann, San Francisco (1995)Google Scholar
  21. 21.
    Guillet, F., Hamilton, H.J.: Quality Measures in Data Mining. Spinger, Warsaw (2007)zbMATHCrossRefGoogle Scholar
  22. 22.
    Lukas, L., et al.: Brain tumor classification based on long echo proton MRS signals. Artificial Intelligence in Medicine 31, 73–89 (2004)CrossRefGoogle Scholar
  23. 23.
    Devos, A., et al.: Classification of brain tumours using short echo time 1H MR spectra. Journal of Magnetic Resonance 170, 164–175 (2004)CrossRefGoogle Scholar
  24. 24.
    Manocha, S., Girolami, M.A.: An empirical analysis of the probabilistic K-nearest neighbour classifier. Pattern Recognition Letters 28, 1818–1824 (2007)CrossRefGoogle Scholar
  25. 25.
    Kazmierska, J., Malicki, J.: Application of the Naïve Bayesian Classifier to optimize treatment decisions. Radiotherapy and Oncology 86, 211–216 (2008)CrossRefGoogle Scholar
  26. 26.
    Opstad, et al.: Linear discriminant analysis of brain tumour 1H MR spectra: a comparison of classification using whole spectra versus metabolite quantification. NMR in Biomedicine 20, 763–770 (2007)CrossRefGoogle Scholar
  27. 27.
    Giudici, P.: Applied Data Mining: Statistical Methods for Business and Industry. Wiley, England (2003)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Susana Oliveira
    • 1
  • Jaime Rocha
    • 2
  • Victor Alves
    • 1
  1. 1.Department of InformaticsUniversity of MinhoBragaPortugal
  2. 2.Department of NeuroradiologyHospital de BragaPortugal

Personalised recommendations