Texture Analysis of Brain CT Scans for ICP Prediction

  • Wenan Chen
  • Rebecca Smith
  • Nooshin Nabizadeh
  • Kevin Ward
  • Charles Cockrell
  • Jonathan Ha
  • Kayvan Najarian
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6134)

Abstract

Elevated Intracranial Pressure (ICP) is a significant cause of mortality and long-term functional damage in traumatic brain injury (TBI). Current ICP monitoring methods are highly invasive, presenting additional risks to the patient. This paper describes a computerized non-invasive screening method based on texture analysis of computed tomography (CT) scans of the brain, which may assist physicians in deciding whether to begin invasive monitoring. Quantitative texture features extracted using statistical, histogram and wavelet transform methods are used to characterize brain tissue windows in individual slices, and aggregated across the scan. Support Vector Machine (SVM) is then used to predict high or normal levels of ICP using the most significant features from the aggregated set. Results are promising, providing over 80% predictive accuracy and good separation of the two ICP classes, confirming the suitability of the approach and the predictive power of texture features in screening patients for high ICP.

Keywords

Computerized tomography (CT) images Intracranial Pressure (ICP) texture analysis Grey Level Run Length Method (GLRLM) Dual Tree Complex Wavelet Transform (DTCWT) 

References

  1. 1.
    Koch, M.A., Narayan, R.K., Timmons, S.D.: Traumatic Brain Injury. In: Merck manual online, http://www.merck.com/mmpe/sec21/ch310/ch310a.html (retrieved)
  2. 2.
    Castellano, G., Bonilha, L., Li, L.M., Cendes, F.: Texture Analysis of Medical Images. Clinical Radiology 59(12), 1061–1069 (2004)CrossRefGoogle Scholar
  3. 3.
    Sucu, H.K., Gelal, F., Gokmen, M., Ozer, F.D., Tektas, S.: Can midline brain shift be used as a prognostic factor to predict postoperative restoration of consciousness in patients with chronic subdural hematoma? Surgical Neurology 66(2), 178–182 (2006)CrossRefGoogle Scholar
  4. 4.
    Chen, E.L., Chung, P., Chen, C.L., Tsa, H.M., Chang, C.I.: An automated diagnostic system for CT liver image classification. IEEE Trans. Biomed. Eng. 45(6), 783–794 (1998)CrossRefGoogle Scholar
  5. 5.
    Mir, A.H., Hanmandlu, M., Tandon, S.N.: Texture Analysis of CT Images. IEEE Eng. Med. Biology 14, 781–786 (1995)CrossRefGoogle Scholar
  6. 6.
    Mougiakakou, S., Valvanis, I., Nikita, K.S., Nikita, A., Kelekis, D.: Characterization of CT liver lesions based on texture features and a multiple neural network classification scheme. In: 25th Int. Conf. of the IEEE Engineering in Medicine and Biology Society, vol. 2, pp. 1287–1290 (2003)Google Scholar
  7. 7.
    Yu, H., Caldwell, C., Mah, K., Poon, I., Balogh, J., MacKenzie, R., Khaouam, N., Tirona, R.: Automated Radiation Targeting in Head-and-Neck Cancer Using Region-Based Texture Analysis of PET and CT Images. International Journal of Radiation Oncology*Biology*Physics 75(2), 618–625 (2009)CrossRefGoogle Scholar
  8. 8.
    Kabara, S., Gabbouj, M., Dastidar, P., Alaya-Cheikh, F., Ryymin, P., Lassonen, E.: CT Image Texture Analysis of Intracerebral Hemorrhage. In: 2003 Finnish Signal Processing Symposium (FINSIG’03), Tampere, Finland, pp. 190–194 (2003)Google Scholar
  9. 9.
    Chu, A., Sehgal, C.M., Greenleaf, J.F.: Use of gray value distribution of run lengths for texture analysis. Pattern Recognition Letters 11(6), 415–420 (1990)MATHCrossRefGoogle Scholar
  10. 10.
    Tang, X.: Texture information in run-length matrices. IEEE Trans. Image Proc. 7(11), 1602–1609 (1998)CrossRefGoogle Scholar
  11. 11.
    Manthalkar, R., Biswas, P.K., Chatterji, B.N.: Rotation and scale invariant texture features using discrete wavelet packet transform. Pattern Recognition Letters 24(14), 2455–2462 (2003)CrossRefGoogle Scholar
  12. 12.
    Kingsbury, N.: Complex Wavelets for Shift Invariant Analysis and Filtering of Signals. Applied and Computational Harmonic Analysis 10(3), 234–253 (2001)MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Robnik-Sikonja, M., Kononeko, I.: An adaptation of relief for attribute estimation in regression. In: ICML’97: 14th International Conference on Machine Learning, pp. 296–304 (1997)Google Scholar
  14. 14.
    Weka 3: Data Mining Software in Java, http://www.cs.waikato.ac.nz/ml/weka/
  15. 15.
    Altman, D.G., Bland, J.M.: Diagnostic tests. 1: Sensitivity and specificity. British Medical Journal 308 (6943), 1552 (1994)Google Scholar
  16. 16.
    Ron, K., John George, H.: Wrapper for feature subset selection. Artificial Intelligence 97(1-2), 273–324 (1997)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Wenan Chen
    • 1
  • Rebecca Smith
    • 1
  • Nooshin Nabizadeh
    • 1
  • Kevin Ward
    • 1
  • Charles Cockrell
    • 1
  • Jonathan Ha
    • 1
  • Kayvan Najarian
    • 1
  1. 1.Virginia Commonwealth UniversityRichmondUnited States

Personalised recommendations