Journal of Digital Imaging

, Volume 31, Issue 6, pp 929–939 | Cite as

A Decision-Support Tool for Renal Mass Classification

  • Gautam KunapuliEmail author
  • Bino A. Varghese
  • Priya Ganapathy
  • Bhushan Desai
  • Steven Cen
  • Manju Aron
  • Inderbir Gill
  • Vinay Duddalwar


We investigate the viability of statistical relational machine learning algorithms for the task of identifying malignancy of renal masses using radiomics-based imaging features. Features characterizing the texture, signal intensity, and other relevant metrics of the renal mass were extracted from multiphase contrast-enhanced computed tomography images. The recently developed formalism of relational functional gradient boosting (RFGB) was used to learn human-interpretable models for classification. Experimental results demonstrate that RFGB outperforms many standard machine learning approaches as well as the current diagnostic gold standard of visual qualification by radiologists.


Renal mass Multiphase CT Radiomics Statistical relational learning Clinical decision support 


  1. 1.
    National Cancer Institute. Cancer prevalence and cost of care projections. https://, 2018. [Online; accessed 03-January-2018].
  2. 2.
    Rendon RA: Active surveillance as the preferred management option for small renal masses. Can Urol Assoc J 4:136–138, 2010CrossRefGoogle Scholar
  3. 3.
    Adam C. Mues and Jaime Landman: Small renal masses: current concepts regarding the natural history and reflections on the American Urological Association guidelines. Curr Opin Urol 20, 2010.Google Scholar
  4. 4.
    Heuer R, Gill IS, Guazzoni G, Kirkali Z, Marberger M, Richie JP, de la Rosette JJMCH: A critical analysis of the actual role of minimally invasive surgery and active surveillance for kidney cancer. Eur Urol 57(2):223–232, 2010CrossRefGoogle Scholar
  5. 5.
    Xipell JM: The incidence of benign renal nodules (a clinicopathologic study). J Urol 106(4):503–506, 1971CrossRefGoogle Scholar
  6. 6.
    Gill IS, Aron M, Gervais DA, Jewett MAS: Small renal mass. N Engl J Med 362(7):624–634, 2010CrossRefGoogle Scholar
  7. 7.
    Mindrup Steven R, Pierre Jessica S, Laila D, Konety Badrinath R: The prevalence of renal cell carcinoma diagnosed at autopsy. BJU Int 95(1):31–33, 2005CrossRefGoogle Scholar
  8. 8.
    Duddalwar V, Zhang X, Hwang D, Cen S, Yap F, Ugwueze C, Abreu A, Aron M, Desai M, Gill I: PD14-07 Differentiation between clear cell renal cell carcinomas and oncocytomas using texture analysis of CT images. J Urol 195(4):e305, 2016CrossRefGoogle Scholar
  9. 9.
    Bino Abel Varghese, Darryl Hwang, Steven Cen, Bhushan Desai, Felix Yap, and Vinay Duddalwar: Spectral Analysis of Renal Tumors: Evaluation of a CT Radiomic Technique. Radiol Soc N Am, 2016.Google Scholar
  10. 10.
    C. Reddy and C. Aggarwal: Healthcare Data Analytics. Chapman & Hall/CRC Data Mining and Knowledge Discovery Series. CRC Press, 2016.Google Scholar
  11. 11.
    Miller RA: Medical diagnostic decision support systems—past, present, and future: a threaded bibliography and brief commentary. J Am Med Inform Assoc 1(1):8–27, 1994CrossRefGoogle Scholar
  12. 12.
    Wyatt JC, Altman DG: Commentary: Prognostic models: clinically useful or quickly forgotten? Br Med J 311(7019):1539–1541, 1995CrossRefGoogle Scholar
  13. 13.
    Bates DW, Kuperman GJ, Wang S, Gandhi T, Kittler A, Volk L, Spurr C, Khorasani R, Tanasijevic M, Middleton B: Ten commandments for effective clinical decision support: making the practice of evidence-based medicine a reality. J Am Med Inform Assoc 10(6):523–530, 2003CrossRefGoogle Scholar
  14. 14.
    Purcell GP: What makes a good clinical decision support system: we have some answers, but implementing good decision support is still hard. Br Med J 330(7494):740–741, 2005CrossRefGoogle Scholar
  15. 15.
    Wears RL, Berg M: Computer technology and clinical work: still waiting for Godot. J Am Med Assoc 293(10):1261–1263, 2005CrossRefGoogle Scholar
  16. 16.
    C. Hu, R. Ju, Y. Shen, P. Zhou, and Q. Li: Clinical decision support for Alzheimer’s disease based on deep learning and brain network. In 2016 IEEE International Conference on Communications (ICC), pages 1–6, 2016.Google Scholar
  17. 17.
    L. Getoor and B. Taskar. Introduction to Statistical Relational Learning. MIT Press, 2007.Google Scholar
  18. 18.
    De Raedt L, Kersting K, Natarajan S, Poole D: Statistical Relational Artificial Intelligence: Logic, Probability, and Computation, volume 32 of Synthesis Lectures on Artificial Intelligence and Machine Learning. San Rafael, CA: Morgan & Claypool, 2016Google Scholar
  19. 19.
    Sriraam Natarajan, Kristian Kersting, Tushar Khot, and Jude W. Shavlik: Boosted Statistical Relational Learners—From Benchmarks to Data-Driven Medicine. Springer Briefs in Computer Science. Springer, 2014.Google Scholar
  20. 20.
    S. Yang, T. Khot, K. Kersting, G. Kunapuli, K. Hauser, and S. Natarajan: Learning from imbalanced data in relational domains: a soft margin approach. In 2014 IEEE International Conference on Data Mining (ICDM), pages 1085–1090, 2014.Google Scholar
  21. 21.
    Weiss JC, Natarajan S, Peissig PL, McCarty CA, Page D: Machine learning for personalized medicine: predicting primary myocardial infarction from electronic health records. AI Mag 33(4):33, 2012CrossRefGoogle Scholar
  22. 22.
    D. Page, S. Natarajan, V. Santos Costa, P. Peissig, A. Barnard, and M. Caldwell: Identifying adverse drug events from multi-relational healthcare data. In Proceedings of AAAI Conference on Artificial Intelligence, pages 790–793, 2012.Google Scholar
  23. 23.
    Haley MacLeod, Shuo Yang, Kim Oakes, Kay Connelly, and Sriraam Natarajan. Identifying rare diseases from behavioural data: a machine learning approach. In Proceedings of the 2016 IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), 2016.Google Scholar
  24. 24.
    Natarajan S, Saha BN, Joshi S, Edwards A, Khot T, port EMD, Kersting K, Whitlow CT, Maldjian JA: Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain. Int J Mach Learn Cybern 5:659–669, 2014CrossRefGoogle Scholar
  25. 25.
    Chen F, Huhdanpaa H, Desai B, Hwang D, Cen S, Sherrod A, Bernhard J-C, Desai M, Gill I, Duddalwar V: Whole lesion quantitative CT evaluation of renal cell carcinoma: differentiation of clear cell from papillary renal cell carcinoma. SpringerPlus 4(1):66, 2015CrossRefGoogle Scholar
  26. 26.
    Yap F, Hwang D, Cen S, Zhang X, de Castro Abreu AL, Desai M, Aron M, Gill I, Duddalwar V: The shapely renal mass: contour evaluation of renal cell carcinoma. J Urol 195(4):e204, 2016CrossRefGoogle Scholar
  27. 27.
    Bino Abel Varghese, Frank Chen, Darryl Hwang, Steven Cen, Inderbir Gill, and Vinay Duddalwar: Differentiation of predominantly solid, enhancing lipid-poor renal cell masses using contrast-enhanced computed tomography: evaluating the role of texture in tumor sub-typing. Am J Roentgenol, accepted (to appear), 2018.Google Scholar
  28. 28.
    C. G. Ugwueze, M. Nayyar, Darryl Hwang, Steven Cen, Felix Yap, Bhushan Desai, Inderbir S. Gill, M Desai, and Vinay Duddalwar. Texture analysis as an image-based discriminator between T1 renal cell carcinoma and pT3 renal cell carcinoma. RSNA Annual Meeting, Chicago, 2016.Google Scholar
  29. 29.
    Chen F, Gulati M, Hwang D, Cen S, Yap F, Ugwueze C, Varghese B, Desai M, Aron M, Gill I, Duddalwar V: Voxel-based whole-lesion enhancement parameters: a study of its clinical value in differentiating clear cell renal cell carcinoma from renal oncocytoma. Abdom Radiol 42(2):552–560, 2017CrossRefGoogle Scholar
  30. 30.
    Francesco Giuseppe Mazzei, Maria Antonietta Mazzei, Nevada Cioffi Squitieri, et al. CT perfusion in the characterisation of renal lesions: an added value to multiphasic CT. BioMed Res Int, 2014, 2014. Article ID: 135013Google Scholar
  31. 31.
    Haralick RM, Shanmugam K, Dinstein I: Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3(6):610–621, 1973CrossRefGoogle Scholar
  32. 32.
    Bino A. Varghese, Darryl H. Hwang, Steven Y. Cen, Bhushan B. Desai, Felix Yap, Inderbir Gill, Mihir Desai, Manju Aron, Gangning Liang, Michael Chang, Christopher Deng, Mike Kwon, Chidubem Ugweze, Frank Chen, and Vinay A. Duddalwar. Fast Fourier transform-based analysis of renal masses on contrast-enhanced computed tomography images for grading of tumor. In Proceedings Volume 10160, 12th International Symposium on Medical Information Processing and Analysis, 2017.Google Scholar
  33. 33.
    Guyon I, Weston J, Barnhill S, Vapnik V: Gene selection for cancer classification using support vector machines. Mach Learn 46(1):389–422, 2002CrossRefGoogle Scholar
  34. 34.
    Cortes C, Vapnik V: Support-vector networks. Mach Learn 20(3):273–297, 1995Google Scholar
  35. 35.
    Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. The MIT Press, 2012.Google Scholar
  36. 36.
    P. McCullagh and John A. Nelder. Generalized Linear Models, 2nd edition. Chapman & Hall/CRC Monographs on Statistics & Applied Probability. Chapman and Hall/CRC, 1989.Google Scholar
  37. 37.
    John Shawe-Taylor and Nello Cristianini. Kernel Methods for Pattern Analysis. Cambridge University Press, 2004.Google Scholar
  38. 38.
    Leo Breiman, Jerome H. Friedman, R. A. Olshen, and C. J. Stone. Classification and Regression Trees. Wadsworth & Brooks/Cole Advanced Books & Software, 1984.Google Scholar
  39. 39.
    Robert E. Schapire. A brief introduction to boosting. In Proceedings of the 16th International Joint Conference on Artificial IntelligenceVolume 2, pages 1401–1406, 1999.Google Scholar
  40. 40.
    Breiman L: Bagging predictors. Mach Learn 24(2):123–140, 1996Google Scholar
  41. 41.
    Breiman L: Random forests. Mach Learn 45(1):5–32, 2001CrossRefGoogle Scholar
  42. 42.
    Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press, 2016.
  43. 43.
    Druzhkov PN, Kustikova VD: A survey of deep learning methods and software tools for image classification and object detection. Pattern Recognit Image Anal 26(1):9–15, 2016CrossRefGoogle Scholar
  44. 44.
    Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Snchez CI: A survey on deep learning in medical image analysis. Med Image Anal 42:60–88, 2017CrossRefGoogle Scholar
  45. 45.
    Andrearczyk V, Whelan PF: Using filter banks in convolutional neural networks for texture classification. Pattern Recogn Lett 84:63–69, 2016CrossRefGoogle Scholar
  46. 46.
    P. Domingos and D. Lowd. Markov Logic: An Interface Layer for Artificial Intelligence. Morgan & Claypool Publishers, 2009.Google Scholar
  47. 47.
    J.H. Friedman: Greedy function approximation: a gradient boosting machine. Ann Stat 29, 2001.Google Scholar
  48. 48.
    Natarajan S, Khot T, Kersting K, Gutmann B, Shavlik J: Gradient-based boosting for statistical relational learning: the relational dependency network case. Mach Learn 86(1):25–56, 2012CrossRefGoogle Scholar
  49. 49.
    Blockeel H, De Raedt L: Top-down induction of first-order logical decision trees. Artif Intell 101:285–297, 1998CrossRefGoogle Scholar
  50. 50.
    Shin T, Duddalwar VA, Ukimura O, Matsugasumi T, Chen F, Ahmadi N, de Castro Abreu AL, Mimata H, Gill IS: Does computed tomography still have limitations to distinguish benign from malignant renal tumors for radiologists? Urol Int 99(2):229–236, 2017CrossRefGoogle Scholar
  51. 51.
    Yap FY, Hwang DH, Cen SY, Varghese BA, Desai B, Quinn BD, Gupta MN, Rajarubendra N, Desai MM, Aron M, Liang G, Aron M, Gill IS, Duddalwar VA: Quantitative contour analysis as an image-based discriminator between benign and malignant renal tumors. Urology 114:121–127, 2018CrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2018

Authors and Affiliations

  1. 1.UtopiaCompression CorporationLos AngelesUSA
  2. 2.Department of Radiology, Keck School of MedicineUniversity of Southern CaliforniaLos AngelesUSA
  3. 3.Department of Pathology, Keck School of MedicineUniversity of Southern CaliforniaLos AngelesUSA
  4. 4.Institute of Urology, Keck School of MedicineUniversity of Southern CaliforniaLos AngelesUSA

Personalised recommendations