Advertisement

CT-based machine learning model to predict the Fuhrman nuclear grade of clear cell renal cell carcinoma

  • Fan Lin
  • En-Ming Cui
  • Yi Lei
  • Liang-ping LuoEmail author
Kidneys, Ureters, Bladder, Retroperitoneum

Abstract

Purpose

To predict the Fuhrman grade of clear cell renal cell carcinoma (ccRCC) with a machine learning classifier based on single- or three-phase computed tomography (CT) images.

Materials and methods

Patients with pathologically proven ccRCC from February 1, 2009 to September 31, 2018 who were not treated were retrospectively collected for machine learning-based analysis. The texture features were extracted and ranked from precontrast phase (PCP), corticomedullary phase (CMP), nephrographic phase (NP) and three-phase CT images, and open-source gradient boosting from the decision tree library of CatBoost was used to establish a machine learning classifier to differentiate low- from high-grade ccRCC. The performances of machine learning classifiers based on features from single- and three-phase CT images were compared with each other.

Results

A total of 231 patients with 232 pathologically proven ccRCC lesions were retrospectively collected. 35, 36, 41, and 22 Features were extracted and ranked from PCP, CMP, NP, and three-phase CT images, respectively. The machine learning model based on three-phase CT images [area under the ROC curve (AUC) = 0.87] achieved the best diagnostic performance for differentiating low- from high-grade ccRCC, followed by single-phase NP (AUC = 0.84), CMP (AUC = 0.80), and PCP images (AUC = 0.82).

Conclusion

Machine learning classifiers can be promising noninvasive techniques to differentiate low- and high-Fuhrman nuclear grade ccRCC, and classifiers based on three-phase CT images are superior to those based on features from each single phase.

Keywords

Machine learning Texture analysis Clear cell carcinoma Fuhrman nuclear grade 

Notes

Compliance with ethical standards

Conflict of interest

The authors declare there are no conflicts of interest regarding the publication of this paper.

References

  1. 1.
    C. Global Burden of Disease Cancer, C. Fitzmaurice, D. Dicker, et al. The Global Burden of Cancer 2013. JAMA Oncol. 2015;1(4):505–527.Google Scholar
  2. 2.
    R. L. Siegel, K. D. Miller and A. Jemal. Cancer statistics, 2016. CA Cancer J Clin. 2016;66(1):7–30.CrossRefGoogle Scholar
  3. 3.
    J. C. Cheville, C. M. Lohse, H. Zincke, et al. Comparisons of outcome and prognostic features among histologic subtypes of renal cell carcinoma. Am J Surg Pathol. 2003;27(5):612–624.CrossRefGoogle Scholar
  4. 4.
    I. S. Gill, E. M. Remer, W. A. Hasan, et al. Renal cryoablation: outcome at 3 years. J Urol. 2005;173(6):1903–1907.CrossRefGoogle Scholar
  5. 5.
    D. Jocham, A. Richter, L. Hoffmann, et al. Adjuvant autologous renal tumour cell vaccine and risk of tumour progression in patients with renal-cell carcinoma after radical nephrectomy: phase III, randomised controlled trial. Lancet. 2004;363(9409):594–599.CrossRefGoogle Scholar
  6. 6.
    S. Y. Choi, D. J. Sung, K. S. Yang, et al. Small (< 4 cm) clear cell renal cell carcinoma: correlation between CT findings and histologic grade. Abdom Radiol (NY). 2016;41(6):1160–1169.CrossRefGoogle Scholar
  7. 7.
    C. Chen, Q. Kang, B. Xu, et al. Differentiation of low- and high-grade clear cell renal cell carcinoma: Tumor size versus CT perfusion parameters. Clin Imaging. 2017;46:14–19.CrossRefGoogle Scholar
  8. 8.
    F. Cornelis, E. Tricaud, A. S. Lasserre, et al. Multiparametric magnetic resonance imaging for the differentiation of low and high grade clear cell renal carcinoma. Eur Radiol. 2015;25(1):24–31.CrossRefGoogle Scholar
  9. 9.
    G. Wu, Z. Zhao, Q. Yao, et al. The Study of Clear Cell Renal Cell Carcinoma with MR Diffusion Kurtosis Tensor Imaging and Its Histopathologic Correlation. Acad Radiol. 2018;25(4):430–438.CrossRefGoogle Scholar
  10. 10.
    B. J. Erickson, P. Korfiatis, Z. Akkus, et al. Machine Learning for Medical Imaging. Radiographics. 2017;37(2):505–515.CrossRefGoogle Scholar
  11. 11.
    L. Zhang, J. Tan, D. Han, et al. From machine learning to deep learning: progress in machine intelligence for rational drug discovery. Drug Discov Today. 2017;22(11):1680–1685.CrossRefGoogle Scholar
  12. 12.
    R. C. Deo. Machine Learning in Medicine. Circulation. 2015;132(20):1920–1930.CrossRefGoogle Scholar
  13. 13.
    B. Kocak, A. H. Yardimci, C. T. Bektas, et al. Textural differences between renal cell carcinoma subtypes: Machine learning-based quantitative computed tomography texture analysis with independent external validation. Eur J Radiol. 2018;107:149–157.CrossRefGoogle Scholar
  14. 14.
    L. Yan, Z. Liu, G. Wang, et al. Angiomyolipoma with minimal fat: differentiation from clear cell renal cell carcinoma and papillary renal cell carcinoma by texture analysis on CT images. Acad Radiol. 2015;22(9):1115–1121.CrossRefGoogle Scholar
  15. 15.
    H. Yu, J. Scalera, M. Khalid, et al. Texture analysis as a radiomic marker for differentiating renal tumors. Abdom Radiol (NY). 2017;42(10):2470–2478.CrossRefGoogle Scholar
  16. 16.
    S. A. Fuhrman, L. C. Lasky and C. Limas. Prognostic significance of morphologic parameters in renal cell carcinoma. Am J Surg Pathol. 1982;6(7):655–663.CrossRefGoogle Scholar
  17. 17.
    P. A. Yushkevich, J. Piven, H. C. Hazlett, et al. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage. 2006;31(3):1116–1128.CrossRefGoogle Scholar
  18. 18.
    J. J. M. van Griethuysen, A. Fedorov, C. Parmar, et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017;77(21):e104–e107.CrossRefGoogle Scholar
  19. 19.
    A. Zwanenburg, S. Leger, M. Vallières, et al. Image biomarker standardisation initiative. arXiv preprint arXiv:1612.07003. 2016.
  20. 20.
    A. V. Dorogush, A. Gulin, G. Gusev, et al. Fighting biases with dynamic boosting. arXiv preprint arXiv:1706.09516. 2017.
  21. 21.
    A. V. Dorogush, V. Ershov and A. Gulin. CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363. 2018.
  22. 22.
    H. Coy, J. R. Young, M. L. Douek, et al. Association of qualitative and quantitative imaging features on multiphasic multidetector CT with tumor grade in clear cell renal cell carcinoma. Abdom Radiol (NY). 2018.Google Scholar
  23. 23.
    L. C. Adams, B. Ralla, P. Jurmeister, et al. Native T1 Mapping as an In Vivo Biomarker for the Identification of Higher-Grade Renal Cell Carcinoma: Correlation With Histopathological Findings. Invest Radiol. 2018.Google Scholar
  24. 24.
    L. Shen, L. Zhou, X. Liu, et al. Comparison of biexponential and monoexponential DWI in evaluation of Fuhrman grading of clear cell renal cell carcinoma. Diagn Interv Radiol. 2017;23(2):100–105.CrossRefGoogle Scholar
  25. 25.
    Y. D. Zhang, C. J. Wu, Q. Wang, et al. Comparison of Utility of Histogram Apparent Diffusion Coefficient and R2* for Differentiation of Low-Grade From High-Grade Clear Cell Renal Cell Carcinoma. AJR Am J Roentgenol. 2015;205(2):W193–201.CrossRefGoogle Scholar
  26. 26.
    A. T. Hale, D. P. Stonko, L. Wang, et al. Machine learning analyses can differentiate meningioma grade by features on magnetic resonance imaging. Neurosurg Focus. 2018;45(5):E4.CrossRefGoogle Scholar
  27. 27.
    Y. W. Park, J. Oh, S. C. You, et al. Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging. Eur Radiol. 2018.Google Scholar
  28. 28.
    Y. Li, Z. Qian, K. Xu, et al. MRI features predict p53 status in lower-grade gliomas via a machine-learning approach. Neuroimage Clin. 2018;17:306–311.CrossRefGoogle Scholar
  29. 29.
    C. T. Bektas, B. Kocak, A. H. Yardimci, et al. Clear Cell Renal Cell Carcinoma: Machine Learning-Based Quantitative Computed Tomography Texture Analysis for Prediction of Fuhrman Nuclear Grade. Eur Radiol. 2018.Google Scholar
  30. 30.
    J. Ding, Z. Xing, Z. Jiang, et al. CT-based radiomic model predicts high grade of clear cell renal cell carcinoma. Eur J Radiol. 2018;103:51–56.CrossRefGoogle Scholar
  31. 31.
    S. Oh, D. J. Sung, K. S. Yang, et al. Correlation of CT imaging features and tumor size with Fuhrman grade of clear cell renal cell carcinoma. Acta Radiol. 2017;58(3):376–384.CrossRefGoogle Scholar
  32. 32.
    J. H. Friedman and B. E. Popescu. Predictive Learning via Rule Ensembles. The Annals of Applied Statistics. 2008;2(3):916–954.CrossRefGoogle Scholar
  33. 33.
    I. Frank, M. L. Blute, J. C. Cheville, et al. An outcome prediction model for patients with clear cell renal cell carcinoma treated with radical nephrectomy based on tumor stage, size, grade and necrosis: the SSIGN score. J Urol. 2002;168(6):2395–2400.CrossRefGoogle Scholar
  34. 34.
    T. Klatte, J. J. Patard, M. de Martino, et al. Tumor size does not predict risk of metastatic disease or prognosis of small renal cell carcinomas. J Urol. 2008;179(5):1719–1726.CrossRefGoogle Scholar
  35. 35.
    L. Marconi, S. Dabestani, T. B. Lam, et al. Systematic Review and Meta-analysis of Diagnostic Accuracy of Percutaneous Renal Tumour Biopsy. Eur Urol. 2016;69(4):660–673.CrossRefGoogle Scholar
  36. 36.
    R. Guarch, J. M. Cortes, C. H. Lawrie, et al. Multi-site tumor sampling (MSTS) improves the performance of histological detection of intratumor heterogeneity in clear cell renal cell carcinoma (CCRCC). F1000Res. 2016;5:2020.Google Scholar
  37. 37.
    C. Shen, Z. Liu, M. Guan, et al. 2D and 3D CT Radiomics Features Prognostic Performance Comparison in Non-Small Cell Lung Cancer. Transl Oncol. 2017;10(6):886–894.CrossRefGoogle Scholar
  38. 38.
    J. Ker, L. Wang, J. Rao, et al. Deep learning applications in medical image analysis. IEEE Access. 2018;6:9375–9389.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Medical Imaging CenterThe First Affiliated Hospital of Jinan UniversityGuangzhouChina
  2. 2.Department of Radiology, The First Affiliated Hospital of Shenzhen University, Health Science CenterShenzhen Second People’s HospitalShenzhenChina
  3. 3.Department of Radiology, Jiangmen Central HospitalAffiliated Jiangmen Hospital of Sun YAT-SEN UniversityJiangmenChina

Personalised recommendations