Skip to main content

Advertisement

SpringerLink
Log in

Brain tumor classification on intraoperative contrast-enhanced ultrasound

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

Contrast-enhanced ultrasound (CEUS) imaging of tissue perfusion is based on microbubble echo detection. CEUS can visualize tumors based on local perfusion variations. The acquired video data are qualitatively interpreted by subjective visualization in clinical practice. An automated CEUS classifier was developed for intraoperative identification of tumor tissue and especially tumor borders.

Methods

Support vector machines (SVM) were trained using CEU data sets to differentiate tumor and non-tumor tissue in glioblastoma patients. The classification was based on features derived from model functions approximated to time courses for each pixel in the video data. Classification performance was evaluated with single and cross- patient training data sets.

Results

The minimum mean classification error (14.6 %) with single patient data set training was achieved by SVM training using a sigmoid combination of model function parameter sets. A comparison of different model functions showed that the minimum average classification error (17.4 %) in a cross-validation study with 13 patients was achieved with the sigmoid model using an automatic relevance detection kernel.

Conclusion

CEUS-based classification map images derived from approximated model functions can be generated with moderate accuracy and have significant potential to support intraoperative decisions concerning glioblastoma tumor borders.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Albrecht T, Oldenburg A, Homann J, Skrok J, Hoffmann C, Schettler S, Wolf K (2003) Imaging of liver metastases with contrast-specific low-MI real-time ultrasound and SonoVue. Eur Radiol 13(3):79–86

    Article  Google Scholar 

  2. Boser BE, Guyon IM, Vapnik V (1992). A training algorithm for optimal margin classifiers. In: Proceedings of workshop on computational learning theory (COLT), pp 144–152

  3. Claudon M, Cosgrove D, Albrecht T, Bolondi L, Bosio M (2008) Guidlines and good clinical practice recommendations for contrast enhanced ultrasound (CEUS). Eur J Ultrasound 29:28–44

    CAS  Google Scholar 

  4. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297

    Google Scholar 

  5. Engelhardt M, Hansen C, Eyding J, Wilkening W, Brenke C, Krogias C, Scholz M, Harders A, Ermert H, Schmieder K (2005) Intraoperative contrast enhanced perfusion imaging of cerebral tumors. In: IEEE ultrasonics symposium, pp 743–746. IEEE

  6. Engelhardt M, Hansen C, Eyding J, Wilkening W, Brenke C, Krogias C, Scholz M, Harders A, Ermert H, Schmieder K (2007) Feasibility of contrast-enhanced sonography during resection of cerebral tumours: initial results of a prospective study. Ultrasound Med Biol 33(4):571–575

    Article  PubMed  Google Scholar 

  7. Eyding J, Hölscher T, Postert T (2007) Transkranielle Neurosonologie beim akuten Schlaganfall. Deutsches Ärtzteblatt 6:340–346

    Google Scholar 

  8. Guo Y, Hastie T, Tibishirani R (2007) Regularized linear discriminant analysis and its application in microarrays. Biostatistics 8:86–100

    Article  PubMed  Google Scholar 

  9. Hamilton WF, Moore JW, Kinsman JM, Spurling RG (1928) Simultaneous determination of the pulmonary and systemic circulation times in man and of a figure related to cardiac output. Am J Physiol 84:338–344

    CAS  Google Scholar 

  10. Hansen C (2009) Kontrastmittelspezifische Ultraschall-Computertomographie. Dissertation, Ruhr-Universität Bochum, Bochum, Deutschland

  11. Hardesty D, Snai N (2012) The value of glioma extent of resection in the modern neurosurgical era. Front Neurol 3:140

    PubMed Central  PubMed  Google Scholar 

  12. Hashizume H, Baluk P, Morikawa S (2000) Openings between defective endothelial cells explain tumor vessel leakiness. Am J Pathol 156:1363–1380

    Article  PubMed Central  CAS  PubMed  Google Scholar 

  13. He W, Jiang X, Wang S, Liu H et al (2008) Intraoperative contrast-enhanced ultrasound for brain tumors. Clin Imaging 32:419–424

    Article  PubMed  Google Scholar 

  14. Helminger G, Yuan F, Delian M (1997) Interstitial H and pO\(_2\) gradients in solid tumors in vivo: high-resolution measurments reveal a lack of correlation. Nat Rev 3:177–182

    Google Scholar 

  15. Igel C, Hüsken M (2000) Improving the Rprop learning algorithm. In: Proceedings of the second international symposium on neural computation, pp 115–121

  16. Jain R, Munn L, Fukumara D (2002) Dissecting tumor pathophysiology using intravital microscopy. Nat Rev Cancer 2:266–276

    Article  CAS  PubMed  Google Scholar 

  17. Madsen MT (1992) A simplified formulation of the gamma variate function. Phys Med Biol 37:370–377

    Google Scholar 

  18. Nemec U, Nemec S, Novotny C, Weber M, Czerny C, Krestan CK (2012) Quantitative evaluation of contrast-enhanced ultrasound after intravenous administration of a microbubble contrast agent for differentiation of benign and malignant thyroid nodules: assessment of diagnostic accuracy. Eur Radiol 22:1357–1365

    Article  PubMed  Google Scholar 

  19. Riedmiller M (1994) Advanced supervised learning in multilayer perceptrons—from backpropagation to adaptive learning algorithms. Int J Comput Stand Interfaces 16:265–278

    Article  Google Scholar 

  20. Ritschel K, Dekomien C, Winter S (2012) Modellfunktion zur Approximation von Ultraschallkontrastmittelkonzentration zur semi-quantitativen Gewebeperfusionsbestimmung. In: Proceedings of Bildverarbeitung für die Medizin (BVM), pp 159–164

  21. Ritschel K, Pechlivanis I, Kensey I, Risse R, Winter S (2013) Perfusion model approximation in cerebral tumours: feature images and computation times. Biomed Technik 58(1):627–628

    Google Scholar 

  22. Sanai N, Berger M (2008) Glioma extent of resection and its impact on patient outcome. Neurosurgery 62:753–764

    Article  PubMed  Google Scholar 

  23. Sanai N, Polley M (2011) McDermott: an extent of resection threshold for newly diagnosed glioblastomas. J Neurosurg 115:3–8

    Article  PubMed  Google Scholar 

  24. Seidel G, Meairs S (2009) Ultrasound contrast agents in ischemic stroke. Cerebrovasc Dis 2:25–39

    Article  Google Scholar 

  25. Serra C, Stauffer A, Actor B, Bernays R et al (2012) Intraoperative high frequency ultrasound in intracerebral high-grade tumors. Eur J Ultrasound 33:306–312

    Google Scholar 

  26. Smith J, Chang E, Lamborn K, Cha S et al (2008) Role of extent of resection in the long-term outcome of low-grade hemispheric gliomas. J Clin Oncol 26:1338–1345

    Article  PubMed  Google Scholar 

  27. Vicenzini E, Delfini R, Magri F, Santoro A et al (2008) Semiquantitative human cerebral perfusion assessment with ultrasound in brain space occupying lesions: preliminary data. J Ultrasound Med 27:685–692

    PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institut für Neuroinformatik, Ruhr-Universität Bochum, Universitätsstr. 150, 44780 , Bochum, Germany

    Kai Ritschel & Susanne Winter

  2. Department of Neurosurgery, University of Witten-Herdecke at the Hospital Cologne-Merheim, Ostmerheimerstr. 200, 51109 , Cologne, Germany

    Ioannis Pechlivanis

Authors
  1. Kai Ritschel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ioannis Pechlivanis
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Susanne Winter
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kai Ritschel.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ritschel, K., Pechlivanis, I. & Winter, S. Brain tumor classification on intraoperative contrast-enhanced ultrasound. Int J CARS 10, 531–540 (2015). https://doi.org/10.1007/s11548-014-1089-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-014-1089-6

Keywords

Search

Navigation