Skip to main content

Advertisement

SpringerLink
Log in

Statistical clustering of parametric maps from dynamic contrast enhanced MRI and an associated decision tree model for non-invasive tumour grading of T1b solid clear cell renal cell carcinoma

  • Magnetic Resonance
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To apply a statistical clustering algorithm to combine information from dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) into a single tumour map to distinguish high-grade from low-grade T1b clear cell renal cell carcinoma (ccRCC).

Methods

This prospective, Institutional Review Board -approved, Health Insurance Portability and Accountability Act -compliant study included 18 patients with solid T1b ccRCC who underwent pre-surgical DCE MRI. After statistical clustering of the parametric maps of the transfer constant between the intravascular and extravascular space (K trans), rate constant (K ep ) and initial area under the concentration curve (iAUC) with a fuzzy c-means (FCM) algorithm, each tumour was segmented into three regions (low/medium/high active areas). Percentages of each region and tumour size were compared to tumour grade at histopathology. A decision-tree model was constructed to select the best parameter(s) to predict high-grade ccRCC.

Results

Seven high-grade and 11 low-grade T1b ccRCCs were included. High-grade histology was associated with higher percent high active areas (p = 0.0154) and this was the only feature selected by the decision tree model, which had a diagnostic performance of 78% accuracy, 86% sensitivity, 73% specificity, 67% positive predictive value and 89% negative predictive value.

Conclusions

The FCM integrates multiple DCE-derived parameter maps and identifies tumour regions with unique pharmacokinetic characteristics. Using this approach, a decision tree model using criteria beyond size to predict tumour grade in T1b ccRCCs is proposed.

Key Points

• Tumour size did not correlate with tumour grade in T1b ccRCC.

• Tumour heterogeneity can be analysed using statistical clustering via DCE-MRI parameters.

• High-grade ccRCC has a larger percentage of high active area than low-grade ccRCCs.

• A decision-tree model offers a simple way to differentiate high/low-grade ccRCCs.

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

Similar content being viewed by others

Abbreviations

ccRCC:

clear-cell renal cell carcinoma

K trans :

transfer constant between the intravascular and extravascular extracellular space

K ep :

rate constant

Ve :

fractional volume of the extravascular extracellular space

Vp :

fractional plasma volume

iAUC :

initial area under the concentration curve

Lengthmax :

maximum length

AreaROI :

tumour area within a region of interest drawn to outline the periphery of the renal mass

Volest :

estimated tumour volume

FCM:

fuzzy c-means

LAA:

low active area

MAA:

medium active area

HAA:

high active area

References

  1. American Cancer Society (2016) Cancer facts and figures 2016. Available at: http://www.cancer.org/research/cancerfactsstatistics/cancerfactsfigures2016/

  2. Chow WH, Devesa SS, Warren JL, Fraumeni JF Jr (1999) Rising incidence of renal cell cancer in the United States. JAMA 281:1628–1631

    Article  CAS  PubMed  Google Scholar 

  3. Cooperberg MR et al (2008) Decreasing size at diagnosis of stage 1 renal cell carcinoma: analysis from the National Cancer Data Base, 1993 to 2004. J Urol 179:2131–2135

    Article  PubMed  Google Scholar 

  4. Campbell SC et al (2009) Guideline for management of the clinical T1 renal mass. J Urol 182:1271–1279

    Article  PubMed  Google Scholar 

  5. Abel EJ et al (2010) Identifying the risk of disease progression after surgery for localized renal cell carcinoma. BJU Int 106:1277–1283

    Article  PubMed  Google Scholar 

  6. Teloken PE et al (2009) Prognostic impact of histological subtype on surgically treated localized renal cell carcinoma. J Urol 182:2132–2136

    Article  PubMed  PubMed Central  Google Scholar 

  7. Igarashi T et al (2001) The impact of a 4 cm. cutoff point for stratification of T1N0M0 renal cell carcinoma after radical nephrectomy. J Urol 165:1103–1106

    Article  CAS  PubMed  Google Scholar 

  8. Mehrazin R et al (2014) Growth kinetics and short-term outcomes of cT1b and cT2 renal masses under active surveillance. J Urol 192:659–664

    Article  PubMed  PubMed Central  Google Scholar 

  9. Dechet CB et al (2003) Prospective analysis of computerized tomography and needle biopsy with permanent sectioning to determine the nature of solid renal masses in adults. J Urol 169:71–74

    Article  PubMed  Google Scholar 

  10. Lebret T et al (2007) Percutaneous core biopsy for renal masses: indications, accuracy and results. J Urol 178:1184–1188, discussion 1188

    Article  PubMed  Google Scholar 

  11. Sun M et al (2012) Treatment management of small renal masses in the 21st century: a paradigm shift. Ann Surg Oncol 19:2380–2387

    Article  PubMed  Google Scholar 

  12. Sun MR et al (2009) Renal cell carcinoma: dynamic contrast-enhanced MR imaging for differentiation of tumor subtypes—correlation with pathologic findings. Radiology 250:793–802

    Article  PubMed  Google Scholar 

  13. Chandarana H et al (2012) Histogram analysis of whole-lesion enhancement in differentiating clear cell from papillary subtype of renal cell cancer. Radiology 265:790–798

    Article  PubMed  Google Scholar 

  14. Notohamiprodjo M et al (2013) Combined diffusion-weighted, blood oxygen level-dependent, and dynamic contrast-enhanced MRI for characterization and differentiation of renal cell carcinoma. Acad Radiol 20:685–693

    Article  PubMed  Google Scholar 

  15. Zhang Y et al (2016) Tumor vascularity in renal masses: correlation of arterial spin-labeled and dynamic contrast-enhanced magnetic resonance imaging assessments. Clin Genitourin Cancer 14:e25–e36

    Article  PubMed  Google Scholar 

  16. Chandarana H et al (2013) High temporal resolution 3D gadolinium-enhanced dynamic MR imaging of renal tumors with pharmacokinetic modeling: preliminary observations. J Magn Reson Imaging 38:802–808

    Article  PubMed  Google Scholar 

  17. Wu WC, Su MY, Chang CC, Tseng WY, Liu KL (2011) Renal perfusion 3-T MR imaging: a comparative study of arterial spin labeling and dynamic contrast-enhanced techniques. Radiology 261:845–853

    Article  PubMed  Google Scholar 

  18. Notohamiprodjo M et al (2010) Measuring perfusion and permeability in renal cell carcinoma with dynamic contrast-enhanced MRI: a pilot study. J Magn Reson Imaging 31:490–501

    Article  PubMed  Google Scholar 

  19. Abdel Razek AA, Mousa A, Farouk A, Nabil N (2016) Assessment of semiquantitative parameters of dynamic contrast-enhanced perfusion MR Imaging in differentiation of subtypes of renal cell carcinoma. Pol J Radiol 81:90–94

    Article  PubMed  PubMed Central  Google Scholar 

  20. Cornelis F et al (2015) Multiparametric magnetic resonance imaging for the differentiation of low and high grade clear cell renal carcinoma. Eur Radiol 25:24–31

    Article  CAS  PubMed  Google Scholar 

  21. Yang X et al (2012) Nonrigid registration and classification of the kidneys in 3D dynamic contrast enhanced (DCE) MR images. Proc SPIE Int Soc Opt Eng 8314:83140B

    PubMed  PubMed Central  Google Scholar 

  22. Chang YC et al (2012) Classification of breast mass lesions using model-based analysis of the characteristic kinetic curve derived from fuzzy c-means clustering. Magn Reson Imaging 30:312–322

    Article  PubMed  Google Scholar 

  23. Shi J et al (2009) Treatment response assessment of breast masses on dynamic contrast-enhanced magnetic resonance scans using fuzzy c-means clustering and level set segmentation. Med Phys 36(2009):5052–5063

    Article  PubMed  PubMed Central  Google Scholar 

  24. Farjam R, Tsien CI, Lawrence TS, Cao Y (2014) DCE-MRI defined subvolumes of a brain metastatic lesion by principle component analysis and fuzzy-c-means clustering for response assessment of radiation therapy. Med Phys 41, 011708. doi:10.1118/1.4842556

    Article  PubMed  Google Scholar 

  25. Fram EK et al (1987) Rapid calculation of T1 using variable flip angle gradient refocused imaging. Magn Reson Imaging 5:201–208

    Article  CAS  PubMed  Google Scholar 

  26. Periaswamy S, Farid H (2003) Elastic registration in the presence of intensity variations. IEEE Trans Med Imaging 22:865–874

    Article  PubMed  Google Scholar 

  27. Parker GJ et al (2006) Experimentally-derived functional form for a population-averaged high-temporal-resolution arterial input function for dynamic contrast-enhanced MRI. Magn Reson Med 56:993–1000

    Article  PubMed  Google Scholar 

  28. Evelhoch JL (1999) Key factors in the acquisition of contrast kinetic data for oncology. J Magn Reson Imaging 10:254–259

    Article  CAS  PubMed  Google Scholar 

  29. O'Connor JPB, Jackson A, Parker GJM, Roberts C, Jayson GC (2012) Dynamic contrast-enhanced MRI in clinical trials of antivascular therapies. Nat Rev Clin Oncol 9:167–177

    Article  PubMed  Google Scholar 

  30. Bezdek JC (2012) Pattern recognition with fuzzy objective function algorithms. Springer, New York

    Google Scholar 

  31. Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth, Belmont

    Google Scholar 

  32. Efron B (1986) Jackknife, bootstrap and other resampling methods in regression analysis. Ann Stat 14:1301–1304

    Article  Google Scholar 

  33. Stephenson AJ, Hakimi AA, Snyder ME, Russo P (2004) Complications of radical and partial nephrectomy in a large contemporary cohort. J Urol 171:130–134

    Article  PubMed  Google Scholar 

  34. Uzzo RG, Novick AC (2001) Nephron sparing surgery for renal tumors: indications, techniques and outcomes. J Urol 166:6–18

    Article  CAS  PubMed  Google Scholar 

  35. Volpe A et al (2011) Contemporary management of small renal masses. Eur Urol 60:501–515

    Article  PubMed  Google Scholar 

  36. Mally AD, Gayed B, Averch T, Davies B (2012) The current role of percutaneous biopsy of renal masses. Can J Urol 19:6243–6249

    PubMed  Google Scholar 

  37. Phe V, Yates DR, Renard-Penna R, Cussenot O, Roupret M (2012) Is there a contemporary role for percutaneous needle biopsy in the era of small renal masses? BJU Int 109:867–872

    Article  PubMed  Google Scholar 

  38. Gerlinger M et al (2012) Intratumor heterogeneity and branched evolution revealed by multiregion sequencing. N Engl J Med 366:883–892

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  39. Pedrosa I et al (2008) MR classification of renal masses with pathologic correlation. Eur Radiol 18:365–375

    Article  PubMed  Google Scholar 

  40. Yang X, Knopp MV (2011) Quantifying tumor vascular heterogeneity with dynamic contrast-enhanced magnetic resonance imaging: a review. J Biomed Biotechnol 2011:732848

    PubMed  PubMed Central  Google Scholar 

  41. Sinha S et al (1997) Multifeature analysis of Gd-enhanced MR images of breast lesions. J Magn Reson Imaging 7:1016–1026

    Article  CAS  PubMed  Google Scholar 

  42. Chen W, Giger ML, Li H, Bick U, Newstead GM (2007) Volumetric texture analysis of breast lesions on contrast-enhanced magnetic resonance images. Magn Reson Med 58:562–571

    Article  PubMed  Google Scholar 

  43. O'Sullivan F, Roy S, Eary J (2003) A statistical measure of tissue heterogeneity with application to 3D PET sarcoma data. Biostatistics 4:433–448

    Article  PubMed  Google Scholar 

  44. O'Sullivan F, Roy S, O'Sullivan J, Vernon C, Eary J (2005) Incorporation of tumor shape into an assessment of spatial heterogeneity for human sarcomas imaged with FDG-PET. Biostatistics 6:293–301

    Article  PubMed  Google Scholar 

  45. Shin TY et al (2014) Assessing the anatomical characteristics of renal masses has a limited effect on the prediction of pathological outcomes in solid, enhancing, small renal masses: results using the PADUA classification system. BJU Int 113:754–761

    Article  PubMed  Google Scholar 

  46. Yuan Q et al (2016) Intratumor heterogeneity of perfusion and diffusion in clear-cell renal cell carcinoma: correlation with tumor cellularity. Clin Genitourin Cancer 14:e585–e594-T1b

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Radiology, UT Southwestern Medical Center, 2201 Inwood Road, Dallas, TX, 75235-9085, USA

    Yin Xi, Qing Yuan, Yue Zhang, Ananth J. Madhuranthakam, Michael Fulkerson & Ivan Pedrosa

  2. Advanced Imaging Research Center, UT Southwestern Medical Center, 2201 Inwood Road, Dallas, TX, USA

    Ananth J. Madhuranthakam & Ivan Pedrosa

  3. Department of Urology, UT Southwestern Medical Center, 2201 Inwood Road, Dallas, TX, USA

    Vitaly Margulis, Payal Kapur & Jeffrey A. Cadeddu

  4. Kidney Cancer Program, Simmons Comprehensive Cancer Center, UT Southwestern Medical Center, 2201 Inwood Road, Dallas, TX, USA

    Vitaly Margulis, James Brugarolas, Payal Kapur, Jeffrey A. Cadeddu & Ivan Pedrosa

  5. Department of Internal Medicine, UT Southwestern Medical Center, 2201 Inwood Road, Dallas, TX, USA

    James Brugarolas

  6. Department of Pathology, UT Southwestern Medical Center, 2201 Inwood Road, Dallas, Texas, USA

    Payal Kapur

Authors
  1. Yin Xi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qing Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yue Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ananth J. Madhuranthakam
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Michael Fulkerson
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Vitaly Margulis
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. James Brugarolas
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Payal Kapur
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Jeffrey A. Cadeddu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Ivan Pedrosa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ivan Pedrosa.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Ivan Pedrosa.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Funding

This study has received funding by the NIH grants no. P50CA196516 and no. 5RO1CA154475.

Statistics and biometry

One of the authors has significant statistical expertise.

Ethical approval

Institutional Review Board approval was obtained.

Informed consent

Written informed consent was obtained from all subjects (patients) in this study.

Study subjects or cohorts overlap

Some study subjects or cohorts have been previously reported by Yuan et al. [46].

Methodology

Prospective, cross-sectional study; observational. Performed at one institution.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xi, Y., Yuan, Q., Zhang, Y. et al. Statistical clustering of parametric maps from dynamic contrast enhanced MRI and an associated decision tree model for non-invasive tumour grading of T1b solid clear cell renal cell carcinoma. Eur Radiol 28, 124–132 (2018). https://doi.org/10.1007/s00330-017-4925-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-017-4925-6

Keywords

Search

Navigation