Skip to main content

Classification of tumor area using combined DCE and DSC MRI in patients with glioblastoma


This study proposes an automatic method for identification and quantification of different tissue components: the non-enhanced infiltrative tumor, vasogenic edema and enhanced tumor areas, at the subject level, in patients with glioblastoma (GB) based on dynamic contrast enhancement (DCE) and dynamic susceptibility contrast (DSC) MRI. Nineteen MR data sets, obtained from 12 patients with GB, were included. Seven patients were scanned before and 8 weeks following bevacizumab initiation. Segmentation of the tumor area was performed based on the temporal data of DCE and DSC at the group-level using k-means algorithm, and further at the subject-level using support vector machines algorithm. The obtained components were associated to different tissues types based on their temporal characteristics, calculated perfusion and permeability values and MR-spectroscopy. The method enabled the segmentation of the tumor area into the enhancing permeable component; the non-enhancing hypoperfused component, associated with vasogenic edema; and the non-enhancing hyperperfused component, associated with infiltrative tumor. Good agreement was obtained between the group-level, unsupervised and subject-level, supervised classification results, with significant correlation (r = 0.93, p < 0.001) and average symmetric root-mean-square surface distance of 2.5 ± 5.1 mm. Longitudinal changes in the volumes of the three components were assessed alongside therapy. Tumor area segmentation using DCE and DSC can be used to differentiate between vasogenic edema and infiltrative tumors in patients with GB, which is of major clinical importance in therapy response assessment.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4


  1. 1.

    Wen PY, Macdonald DR, Reardon DA, Cloughesy TF, Sorensen AG, Galanis E, Degroot J, Wick W, Gilbert MR, Lassman AB, Tsien C, Mikkelsen T, Wong ET, Chamberlain MC, Stupp R, Lamborn KR, Vogelbaum MA, van den Bent MJ, Chang SM (2010) Updated response assessment criteria for high-grade gliomas: response assessment in neuro-oncology working group. J Clin Oncol 28:1963–1972. doi:10.1200/JCO.2009.26.3541

    PubMed  Article  Google Scholar 

  2. 2.

    Demir MK, Hakan T, Akinci O, Berkman Z (2005) Primary cerebellar glioblastoma multiforme. Diagn Interv Radiol 11:83–86

    PubMed  Google Scholar 

  3. 3.

    Ostergaard L, Sorensen AG, Kwong KK, Weisskoff RM, Gyldensted C, Rosen BR (1996) High resolution measurement of cerebral blood flow using intravascular tracer bolus passages. Part II: experimental comparison and preliminary results. Magn Reson Med 36:726–736

    CAS  PubMed  Article  Google Scholar 

  4. 4.

    Ostergaard L, Weisskoff RM, Chesler DA, Gyldensted C, Rosen BR (1996) High resolution measurement of cerebral blood flow using intravascular tracer bolus passages. Part I: mathematical approach and statistical analysis. Magn Reson Med 36:715–725

    CAS  PubMed  Article  Google Scholar 

  5. 5.

    Sourbron S, Ingrisch M, Siefert A, Reiser M, Herrmann K (2009) Quantification of cerebral blood flow, cerebral blood volume, and blood-brain-barrier leakage with DCE-MRI. Magn Reson Med 62:205–217. doi:10.1002/mrm.22005

    PubMed  Article  Google Scholar 

  6. 6.

    Al-Okaili RN, Krejza J, Wang S, Woo JH, Melhem ER (2006) Advanced MR imaging techniques in the diagnosis of intraaxial brain tumors in adults. Radiographics 26(Suppl 1):S173–S189. doi:10.1148/rg.26si065513

    PubMed  Article  Google Scholar 

  7. 7.

    Cha S (2006) Update on brain tumor imaging: from anatomy to physiology. AJNR Am J Neuroradiol 27:475–487

    CAS  PubMed  Google Scholar 

  8. 8.

    Fatterpekar GM, Galheigo D, Narayana A, Johnson G, Knopp E (2012) Treatment-related change versus tumor recurrence in high-grade gliomas: a diagnostic conundrum–use of dynamic susceptibility contrast-enhanced (DSC) perfusion MRI. AJR Am J Roentgenol 198:19–26. doi:10.2214/AJR.11.7417

    PubMed  Article  Google Scholar 

  9. 9.

    Sourbron SP, Buckley DL (2013) Classic models for dynamic contrast-enhanced MRI. NMR Biomed 26:1004–1027. doi:10.1002/nbm.2940

    PubMed  Article  Google Scholar 

  10. 10.

    Zhang W, Kreisl TN, Solomon J, Reynolds RC, Glen DR, Cox RW, Fine HA, Butman JA (2009) Acute Effects of Bevacizumab on Glioblastoma Vascularity Assessed with DCE-MRI and Relation to Patient Survival. The International Society for Magnetic Resonance in Medicine, Honolulu

    Google Scholar 

  11. 11.

    Sorensen AG, Batchelor TT, Zhang WT, Chen PJ, Yeo P, Wang M, Jennings D, Wen PY, Lahdenranta J, Ancukiewicz M, di Tomaso E, Duda DG, Jain RK (2009) A “vascular normalization index” as potential mechanistic biomarker to predict survival after a single dose of cediranib in recurrent glioblastoma patients. Cancer Res 69:5296–5300. doi:10.1158/0008-5472.CAN-09-0814

    CAS  PubMed Central  PubMed  Article  Google Scholar 

  12. 12.

    Huo J, Okada K, van Rikxoort EM, Kim HJ, Alger JR, Pope WB, Goldin JG, Brown MS (2013) Ensemble segmentation for GBM brain tumors on MR images using confidence-based averaging. Med Phys 40:093502. doi:10.1118/1.4817475

    PubMed  Article  Google Scholar 

  13. 13.

    Liberman G, Louzoun Y, Aizenstein O, Blumenthal DT, Bokstein F, Palmon M, Corn BW, Ben Bashat D (2013) Automatic multi-modal MR tissue classification for the assessment of response to bevacizumab in patients with glioblastoma. Eur J Radiol 82:e87–e94. doi:10.1016/j.ejrad.2012.09.001

    PubMed  Article  Google Scholar 

  14. 14.

    Wu W, Chen AY, Zhao L, Corso JJ (2013) Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features. Int J Comput Assist Radiol Surg. doi:10.1007/s11548-013-0922-7

    Google Scholar 

  15. 15.

    Zhu Y, Young GS, Xue Z, Huang RY, You H, Setayesh K, Hatabu H, Cao F, Wong ST (2012) Semi-automatic segmentation software for quantitative clinical brain glioblastoma evaluation. Acad Radiol 19:977–985. doi:10.1016/j.acra.2012.03.026

    PubMed Central  PubMed  Article  Google Scholar 

  16. 16.

    Assefa D, Keller H, Menard C, Laperriere N, Ferrari RJ, Yeung I (2010) Robust texture features for response monitoring of glioblastoma multiforme on T1-weighted and T2-FLAIR MR images: a preliminary investigation in terms of identification and segmentation. Med Phys 37:1722–1736

    PubMed  Article  Google Scholar 

  17. 17.

    Zollner FG, Emblem KE, Schad LR (2010) Support vector machines in DSC-based glioma imaging: suggestions for optimal characterization. Magn Reson Med 64:1230–1236. doi:10.1002/mrm.22495

    PubMed  Article  Google Scholar 

  18. 18.

    Emblem KE, Nedregaard B, Hald JK, Nome T, Due-Tonnessen P, Bjornerud A (2009) Automatic glioma characterization from dynamic susceptibility contrast imaging: brain tumor segmentation using knowledge-based fuzzy clustering. J Magn Reson Imaging 30:1–10. doi:10.1002/jmri.21815

    PubMed  Article  Google Scholar 

  19. 19.

    Singh A, Rathore R, Gupta R, Haris M, Rathore DK, Verma SK, Purwar A, Bayu G, Sarma MK, Singh JK (2007) Segmentation of Gd-DTPA Enhancing Lesion of Brain using Time to Peak of Concentration Time Curve and its Pharmacokinetic Analysis in Dynamic Contrast Enhanced (DCE) MRI. The International Society for Magnetic Resonance in Medicine, Berlin

    Google Scholar 

  20. 20.

    Vonken EP, van Osch MJ, Bakker CJ, Viergever MA (2000) Simultaneous quantitative cerebral perfusion and Gd-DTPA extravasation measurement with dual-echo dynamic susceptibility contrast MRI. Magn Reson Med 43:820–827. doi:10.1002/1522-2594(200006)43:6<820:AID-MRM7>3.0.CO;2-F

    CAS  PubMed  Article  Google Scholar 

  21. 21.

    Bagher-Ebadian H, Jain R, Nejad-Davarani SP, Mikkelsen T, Lu M, Jiang Q, Scarpace L, Arbab AS, Narang J, Soltanian-Zadeh H, Paudyal R, Ewing JR (2012) Model selection for DCE-T1 studies in glioblastoma. Magn Reson Med 68:241–251. doi:10.1002/mrm.23211

    PubMed Central  PubMed  Article  Google Scholar 

  22. 22.

    Nadav G, Liberman G, Artzi M, Kiryati N, Ben Bashat D (2014) Flow and permeability estimation from DCE data: 2-compartment exchange and Tofts models comparison. The International Society for Magnetic Resonance in Medicine, Milan

    Google Scholar 

  23. 23.

    Calamante F (2013) Arterial input function in perfusion MRI: a comprehensive review. Prog Nucl Magn Reson Spectrosc 74:1–32. doi:10.1016/j.pnmrs.2013.04.002

    CAS  PubMed  Article  Google Scholar 

  24. 24.

    Smith SM, Jenkinson M, Woolrich MW, Beckmann CF, Behrens TE, Johansen-Berg H, Bannister PR, De Luca M, Drobnjak I, Flitney DE, Niazy RK, Saunders J, Vickers J, Zhang Y, De Stefano N, Brady JM, Matthews PM (2004) Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage 23(Suppl 1):S208–S219. doi:10.1016/j.neuroimage.2004.07.051

    PubMed  Article  Google Scholar 

  25. 25.

    Artzi M, Aizenstein O, Jonas-Kimchi T, Myers V, Hallevi H, Ben Bashat D (2013) FLAIR lesion segmentation: application in patients with brain tumors and acute ischemic stroke. Eur J Radiol 82:1512–1518. doi:10.1016/j.ejrad.2013.05.029

    PubMed  Article  Google Scholar 

  26. 26.

    Artzi M, Aizenstein O, Hendler T, Ben Bashat D (2011) Unsupervised multiparametric classification of dynamic susceptibility contrast imaging: study of the healthy brain. Neuroimage 56:858–864. doi:10.1016/j.neuroimage.2011.03.027

    CAS  PubMed  Article  Google Scholar 

  27. 27.

    Tofts PS, Kermode AG (1991) Measurement of the blood-brain barrier permeability and leakage space using dynamic MR imaging. 1. Fundamental concepts. Magn Reson Med 17:357–367

    CAS  PubMed  Article  Google Scholar 

  28. 28.

    Liberman G, Louzoun Y, Colliot O, BB D (2011) T1 mapping, AIF and pharmacokinetic parameter extraction from dynamic contrast enhancement MRI data. Multimodal Brain Image Anal 7012:76–83

    Article  Google Scholar 

  29. 29.

    Gerig G, Jomier M, Chakos M (2001) Valmet: a new validation tool for assessing and improving 3D object segmentation. MICCAI, Beijing

    Google Scholar 

  30. 30.

    Hossman KA, Bloink M (1981) Blood flow and regulation of blood flow in experimental peritumoral edema. Stroke 12:211–217

    CAS  PubMed  Article  Google Scholar 

  31. 31.

    Law M, Cha S, Knopp EA, Johnson G, Arnett J, Litt AW (2002) High-grade gliomas and solitary metastases: differentiation by using perfusion and proton spectroscopic MR imaging. Radiology 222:715–721. doi:10.1148/radiol.2223010558

    PubMed  Article  Google Scholar 

  32. 32.

    Law M, Yang S, Wang H, Babb JS, Johnson G, Cha S, Knopp EA, Zagzag D (2003) Glioma grading: sensitivity, specificity, and predictive values of perfusion MR imaging and proton MR spectroscopic imaging compared with conventional MR imaging. AJNR Am J Neuroradiol 24:1989–1998

    PubMed  Google Scholar 

  33. 33.

    Croteau D, Scarpace L, Hearshen D, Gutierrez J, Fisher JL, Rock JP, Mikkelsen T (2001) Correlation between magnetic resonance spectroscopy imaging and image-guided biopsies: semiquantitative and qualitative histopathological analyses of patients with untreated glioma. Neurosurgery 49:823–829

    CAS  PubMed  Google Scholar 

  34. 34.

    Law M, Yang S, Babb JS, Knopp EA, Golfinos JG, Zagzag D, Johnson G (2004) Comparison of cerebral blood volume and vascular permeability from dynamic susceptibility contrast-enhanced perfusion MR imaging with glioma grade. AJNR Am J Neuroradiol 25:746–755

    PubMed  Google Scholar 

  35. 35.

    Lu S, Ahn D, Johnson G, Law M, Zagzag D, Grossman RI (2004) Diffusion-tensor MR imaging of intracranial neoplasia and associated peritumoral edema: introduction of the tumor infiltration index. Radiology 232:221–228. doi:10.1148/radiol.2321030653

    PubMed  Article  Google Scholar 

  36. 36.

    Kinoshita M, Goto T, Okita Y, Kagawa N, Kishima H, Hashimoto N, Yoshimine T (2010) Diffusion tensor-based tumor infiltration index cannot discriminate vasogenic edema from tumor-infiltrated edema. J Neurooncol 96:409–415. doi:10.1007/s11060-009-9979-0

    PubMed  Article  Google Scholar 

  37. 37.

    Pope WB, Young JR, Ellingson BM (2011) Advances in MRI assessment of gliomas and response to anti-VEGF therapy. Curr Neurol Neurosci Rep 11:336–344. doi:10.1007/s11910-011-0179-x

    CAS  PubMed Central  PubMed  Article  Google Scholar 

  38. 38.

    LaViolette PS, Cohen AD, Rand SD, Mueller W, Schmainda KM (2011) Independent component analysis of dynamic susceptibility contrast MRI in brain tumor: a new biomarker for measuring tumor perfusion patterns. The International Society for Magnetic Resonance in Medicine, Montreal

    Google Scholar 

  39. 39.

    LaViolette PS, Cohen AD, Prah MA, Rand SD, Connelly J, Malkin MG, Mueller WM, Schmainda KM (2013) Vascular change measured with independent component analysis of dynamic susceptibility contrast MRI predicts bevacizumab response in high-grade glioma. Neuro Oncol 15:442–450. doi:10.1093/neuonc/nos323

    CAS  PubMed Central  PubMed  Article  Google Scholar 

Download references


To Guy Nadav for technical support and to Vicki Myers for editorial assistance. This work was performed in partial fulfillment of the requirements for a Ph.D. degree of Artzi Moran, Sackler Faculty of Medicine, Tel Aviv University, Israel.

Conflict of interest

We declare that there is no conflict of interest for any of the authors.


This work was supported by the James S. McDonnell Foundation number 220020176.

Author information



Corresponding author

Correspondence to Dafna Ben Bashat.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Artzi, M., Blumenthal, D.T., Bokstein, F. et al. Classification of tumor area using combined DCE and DSC MRI in patients with glioblastoma. J Neurooncol 121, 349–357 (2015).

Download citation


  • DCE
  • DSC
  • Tumor segmentation
  • Infiltrative tumor
  • Vasogenic edema