Classification of Body Regions Based on MRI Log Files

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 578)


Every Siemens Magnetic Resonance Imaging (MRI) system consistently writes events into log files while the system is running. The log files and their contents are constantly refined by software developers. This results in different information contents depending on the software version. One information that is missing in some log files is the examined body region. As the body region is crucial for usage analysis, we used pattern recognition methods to estimate the examined body region for software versions not logging it automatically. We learned the examined body region from a set of used MRI acquisition parameters such as grid and voxel size and could classify body region information with a classification rate up to \(94.7\%\). We compared Bayesian Network augmented Naïve Bayes, Decision Trees, and Neural Networks, and found Neural Networks resulting in the best classification rate.


Classification Data mining Pattern recognition Log file analysis System usage 


  1. 1.
    Asaro, P., Ries, J.: Data mining in medical record access logs. In: Proceedings of the AMIA Symposium, Washington, DC, p. 855 (2001)Google Scholar
  2. 2.
    Gallagher, R., Sengupta, S., Hripcsak, G., Barrows, R., Clayton, P.: An Audit Server for Monitoring Usage of Clinical Information Systems (1997)Google Scholar
  3. 3.
    Witten, I., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, San Francisco (2005)MATHGoogle Scholar
  4. 4.
    Hart, P., Stork, D., Duda, R.: Pattern Classification. Willey, New York (2001)MATHGoogle Scholar
  5. 5.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice Hall PTR, Upper Saddle River (1998)MATHGoogle Scholar
  6. 6.
    Patil, M., Patil, R., Krishnamoorthy, P., John, J.: A machine learning framework for auto classification of imaging system exams in hospital setting for utilization optimization. In: 2016 IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), Orlando, pp. 2423–2426 (2016)Google Scholar
  7. 7.
    Chen, E., Cimino, J.: Automated discovery of patient-specific clinician information needs using clinical information system log files. In: AMIA Annual Symposium Proceedings, Washington, DC, pp. 145–149 (2003)Google Scholar
  8. 8.
    Domingos, P., Pazzani, M.: On the optimality of the simple Bayesian classifier under zero-one loss. Mach. Learn. 29, 103–130 (1997)CrossRefMATHGoogle Scholar
  9. 9.
    McCallum, A., Nigam, K.: A comparison of event models for Naive Bayes text classification. In: AAAI-98 Workshop on Learning for Text Categorization, vol. 752, pp. 41–48 (1998)Google Scholar
  10. 10.
    Hampel, F.: The influence curve and its role in robust estimation. J. Am. Stat. Assoc. 69, 383–393 (1974)MathSciNetCrossRefMATHGoogle Scholar
  11. 11.
    Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29, 131–163 (1997)CrossRefMATHGoogle Scholar
  12. 12.
    Keogh, M., Pazzani, M.: Learning Augmented Bayesian Classifiers: A Comparison of Distribution-based and Classification-based Approaches (1999)Google Scholar
  13. 13.
    SAS Institute Inc: SAS®Enterprise Miner™14.1 Reference Help (2015)Google Scholar
  14. 14.
    Ville, B., Neville, P.: Decision Trees for Analytics Using SAS Enterprise Miner (2013)Google Scholar
  15. 15.
    Han, J., Kamber, M.: Data Mining: Concepts and Techniques, 2nd edn. Morgan Kaufmann Publishers, San Francisco (2006)MATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Pattern Recognition LabFAU Erlangen NurembergErlangenGermany
  2. 2.Siemens Healthcare GmbHErlangenGermany

Personalised recommendations