Skip to main content
SpringerLink
Log in

Machine Learning Methodology

  • Chapter
Machine Learning in Radiation Oncology

Abstract

There is a variety of patterns we desire to learn from radiation oncologic data. The previous chapters described how these various learning objectives can commonly be formulated in theoretical nomenclatures. This chapter introduces different machine learning algorithms that could cater to readers’ specific learning goals. We intend to provide conceptual outlines of some of the widely used algorithms with minimal mathematical conundrum and examples drawn from the radiotherapy literature. In this chapter we classify the algorithms into three types, based on the availability of information: unsupervised, supervised, and reinforcement learning. The methods illustrated in this chapter include principal component analysis and clustering (unsupervised), logistic regression, neural network, support vector machine, decision tree, Bayesian networks, and naive Bayes (supervised) in addition to reinforcement learning.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Arthur D, Vassilvitskii S. K-means++: the advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms, SODA’07. Society for Industrial and Applied Mathematics; Philadelphia:2007. p. 1027–35.

    Google Scholar 

  2. Bischof H, Leonardis A, Selb A. Minimum description length principle for robust vector quantisation. Pattern Anal Appl. 1999;2(1):59–72.

    Article  Google Scholar 

  3. Blanco AI, Chao KSC, El Naqa I, Franklin GE, Zakarian K, Vicic M, Deasy JO. Dose-volume modeling of salivary function in patients with head-and-neck cancer receiving radiotherapy. Int J Radiat Oncol Biol Phys. 2005;62(4):1055–69.

    Article  PubMed  Google Scholar 

  4. Bradley J, Deasy JO, Bentzen S, El-Naqa I. Dosimetric correlates for acute esophagitis in patients treated with radiotherapy for lung carcinoma. Int J Radiat Oncol Biol Phys. 2004;58(4):1106–13.

    Article  PubMed  Google Scholar 

  5. Bradley JD, Hope A, El Naqa I, Apte A, Lindsay PE, Bosch W, Matthews J, Sause W, Graham MV, Deasy JO. A nomogram to predict radiation pneumonitis, derived from a combined analysis of rtog 9311 and institutional data. Int J Radiat Oncol Biol Phys. 2007;69(4):985–92.

    Article  PubMed Central  PubMed  Google Scholar 

  6. Breiman L. Random forests. Mach Learn. 2001;45(1):5–32.

    Article  Google Scholar 

  7. Chen S, Zhou S, Yin F-F, Marks LB, Das SK. Investigation of the support vector machine algorithm to predict lung radiation-induced pneumonitis. Med Phys. 2007;34(10):3808–14.

    Article  PubMed Central  PubMed  Google Scholar 

  8. Chen S, Zhou S, Yin FF, Marks LB, Das SK. Using patient data similarities to predict radiation pneumonitis via a self-organizing map. Phys Med Biol. 2008;53(1):203.

    Article  PubMed Central  PubMed  Google Scholar 

  9. Chow C, Liu C. Approximating discrete probability distributions with dependence trees. IEEE Trans Inf Theor. 2006;14(3):462–7.

    Article  Google Scholar 

  10. Cooper GF, Herskovits E. A Bayesian method for the induction of probabilistic networks from data. Mach Learn. 1992;9(4):309–47.

    Google Scholar 

  11. Das SK, Zhou S, Zhang J, Yin F-F, Dewhirst MW, Marks LB. Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees. Int J Radiat Oncol Biol Phys. 2007;68(4):1212–21.

    Article  PubMed Central  PubMed  Google Scholar 

  12. Dehing-Oberije C, Yu S, Ruysscher DD, Meersschout S, Beek KV, Lievens Y, Meerbeeck JV, Neve WD, Rao B, van der Weide H, Lambin P. Development and external validation of prognostic model for 2-year survival of non small cell lung cancer patients treated with chemoradiotherapy. Int J Radiat Oncol Biol Phys. 2009;74(2):355–62.

    Article  PubMed  Google Scholar 

  13. Delaney G, Barton M, Jacob S. Estimation of an optimal radiotherapy utilization rate for melanoma. Cancer. 2004;100(6):1293–301.

    Article  PubMed  Google Scholar 

  14. El Naqa I, Bradley J, Blanco AI, Lindsay PE, Vicic M, Hope A, Deasy JO. Multivariable modeling of radiotherapy outcomes, including dose-volume and clinical factors. Int J Radiat Oncol Biol Phys. 2006;64(4):1275–86.

    Article  PubMed  Google Scholar 

  15. El Naqa I, Bradley J, Deasy J. Machine learning methods for radiobiological outcome modeling. In: Mehta M, Paliwal B, Bentzen S, editors. Physical, chemical, and biological targeting in radiation oncology. Madison: Medical Physics Pub.; 2005. p. 150–9.

    Google Scholar 

  16. El Naqa I, Bradley JD, PE L, Hope AJ, Deasy JO. Predicting radiotherapy outcomes using statistical learning techniques. Phys Med Biol. 2009;54(18):S9.

    Article  PubMed Central  PubMed  Google Scholar 

  17. Freund Y, Schapire RE. A brief introduction to boosting. In: Proceedings of the sixteenth international joint conference on artificial intelligence. San Francisco: Morgan Kaufmann; 1999. p. 1401–6.

    Google Scholar 

  18. Friedman JH. On bias, variance, 0/1ñloss, and the curse-of-dimensionality. Data Min Knowl Discov. 1997;1(1):55–77.

    Article  Google Scholar 

  19. Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: data mining, inference, and prediction. New York: Springer; 2009.

    Book  Google Scholar 

  20. Haykin S. Neural networks: a comprehensive foundation. Upper Saddle River: Prentice Hall PTR; 1998.

    Google Scholar 

  21. Hope AJ, Lindsay PE, Naqa IE, Alaly JR, Vicic M, Bradley JD, Deasy JO. Modeling radiation pneumonitis risk with clinical, dosimetric, and spatial parameters. Int J Radiat Oncol Biol Phys. 2006;65(1):112–24.

    Article  PubMed  Google Scholar 

  22. Hosmer D, Lemeshow S. Applied logistic regression. New York: John Wiley; 2000.

    Book  Google Scholar 

  23. Huang EX, Bradley JD, El Naqa I, Hope AJ, Lindsay PE, Bosch WR, Matthews JW, Sause WT, Graham MV, Deasy JO. Modeling the risk of radiation-induced acute esophagitis for combined Washington University and rtog trial 93-11 lung cancer patients. Int J Radiat Oncol Biol Phys. 2012;82(5):1674–9.

    Article  PubMed Central  PubMed  Google Scholar 

  24. Huang EX, Hope AJ, Lindsay PE, Trovo M, El Naqa I, Deasy JO, Bradley JD. Heart irradiation as a risk factor for radiation pneumonitis. Acta Oncol. 2011;50(1):51–60.

    Article  PubMed Central  PubMed  Google Scholar 

  25. Jain AK, Murty MN, Flynn PJ. Data clustering: a review. ACM Comput Surv. 1999;31(3):264–323.

    Article  Google Scholar 

  26. Jayasurya K, Fung G, Yu S, Dehing-Oberije C, De Ruysscher D, Hope A, De Neve W, Lievens Y, Lambin P, Dekker ALAJ. Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy. Med Phys. 2010;37(4):1401–7.

    Article  CAS  PubMed  Google Scholar 

  27. Kazmierska J, Malicki J. Application of the nave Bayesian classifier to optimize treatment decisions. Radiother Oncol. 2008;86(2):211–6.

    Article  PubMed  Google Scholar 

  28. Kim M, Ghate A, Phillips MH. A Markov decision process approach to temporal modulation of dose fractions in radiation therapy planning. Phys Med Biol. 2009;54(14):4455.

    Article  CAS  PubMed  Google Scholar 

  29. Klement R, Allgauer M, Appold S, Dieckmann K, Ernst I, Ganswindt U, Holy R, Nestle U, Nevinny-Stickel M, Semrau S, Sterzing F, Wittig A, Andratschke N, Guckenberger M. Support vector machine-based prediction of local tumor control after stereotactic body radiation therapy for early-stage non-small cell lung cancer. Int J Radiat Oncol Biol Phys. 2014;88(3):732–8.

    Article  PubMed  Google Scholar 

  30. Kohonen T. The self-organizing map. Proc IEEE. 1990;78(9):1464–80.

    Article  Google Scholar 

  31. Koller D, Friedman N. Probabilistic graphical models: principles and techniques – adaptive computation and machine learning. Cambridge: The MIT Press; 2009.

    Google Scholar 

  32. Kulkarni P. Reinforcement and systemic machine learning for decision making. Hoboken: Wiley-IEEE Press; 2012.

    Book  Google Scholar 

  33. Madigan D, York J, Allard D. Bayesian graphical models for discrete data. Int Stat Rev. 1995;63(2):215–32.

    Article  Google Scholar 

  34. Marks LB. Dosimetric predictors of radiation-induced lung injury. Int J Radiat Oncol Biol Phys. 2002;54(2):313–6.

    Article  PubMed  Google Scholar 

  35. Mitchell TM. Machine learning. 1st ed. New York: McGraw-Hill, Inc.; 1997.

    Google Scholar 

  36. Oh JH, Craft JM, Townsend R, Deasy JO, Bradley JD, El Naqa I. A bioinformatics approach for biomarker identification in radiation-induced lung inflammation from limited proteomics data. J Proteome Res. 2011;10(3):1406–15.

    Article  CAS  PubMed Central  PubMed  Google Scholar 

  37. Pella A, Cambria R, Riboldi M, Jereczek-Fossa BA, Fodor C, Zerini D, Torshabi AE, Cattani F, Garibaldi C, Pedroli G, Baroni G, Orecchia R. Use of machine learning methods for prediction of acute toxicity in organs at risk following prostate radiotherapy. Med Phys. 2011;38(6):2859–67.

    Article  PubMed  Google Scholar 

  38. Pelleg D, Moore A. X-means: extending k-means with efficient estimation of the number of clusters. In: Proceedings of the 17th international conference on machine learning. San Francisco: Morgan Kaufmann; 2000. p. 727–34.

    Google Scholar 

  39. Quinlan JR. Induction of decision trees. Mach Learn. 1986;1:81–106.

    Google Scholar 

  40. Quinlan JR. Simplifying decision trees. Int J Man Mach Stud. 1987;27(3):221–34.

    Article  Google Scholar 

  41. Ripley BD. Pattern recognition and neural networks. Cambridge/New York: Cambridge University Press; 1996.

    Book  Google Scholar 

  42. Scholkopf A, Smola J, Muller KR. Kernel principal component analysis. Cambridge: MIT Press; 1999. p. 327–52.

    Google Scholar 

  43. Smith WP, Doctor J, Meyer J, Kalet IJ, Phillips MH. A decision aid for intensity-modulated radiation-therapy plan selection in prostate cancer based on a prognostic Bayesian network and a Markov model. Artif Intell Med. 2009;46(2):119–30.

    Article  PubMed Central  PubMed  Google Scholar 

  44. Specht DF. A general regression neural network. IEEE Trans Neural Netw. 1991;2(6):568–76.

    Article  CAS  PubMed  Google Scholar 

  45. Spencer SJ, Bonnin DA, Deasy JO, Bradley JD, El Naqa I. Bioinformatics methods for learning radiation-induced lung inflammation from heterogeneous retrospective and prospective data. J Biomed Biotechnol. 2009(2009), 892863. doi:10.1155/2009/892863.

  46. Su M, Miften M, Whiddon C, Sun X, Light K, Marks L. An artificial neural network for predicting the incidence of radiation pneumonitis. Med Phys. 2005;32(2):318–25.

    Article  PubMed  Google Scholar 

  47. Sutton RS, Barto AG. Introduction to reinforcement learning. Cambridge: MIT Press; 1998.

    Google Scholar 

  48. Svensson JP, Stalpers LJA, Lange REEE, Franken NAP, Haveman J, Klein B, Turesson I, Vrieling H, Giphart-Gassler M. Analysis of gene expression using gene sets discriminates cancer patients with and without late radiation toxicity. PLoS Med. 2006;3(10):e422.

    Article  PubMed Central  PubMed  Google Scholar 

  49. Tucker SL, Cheung R, Dong L, Liu HH, Thames HD, Huang EH, Kuban D, Mohan R. Dose-volume response analyses of late rectal bleeding after radiotherapy for prostate cancer. Int J Radiat Oncol Biol Phys. 2004;59(2):353–65.

    Article  PubMed  Google Scholar 

  50. Vapnik V. Statistical learning theory. New York: Wiley; 1998.

    Google Scholar 

  51. Vittinghoff E, Glidden D, Shiboski S, McCulloch C. Regression methods in biostatistics: linear, logistic, survival, and repeated measures models. New York: Springer; 2006.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Medical Physics Unit, Montreal General Hospital, McGill University, L5-211, 1650 Cedar Ave, Montreal, QC, H3G 1A4, Canada

    Sangkyu Lee

  2. Department of Oncology, McGill University, Montreal, QC, Canada

    Issam El Naqa

  3. Department of Radiation Oncology, University of Michigan, Ann Arbor, USA

    Issam El Naqa

Authors
  1. Sangkyu Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Issam El Naqa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sangkyu Lee .

Editor information

Editors and Affiliations

  1. Department of Oncology, McGill University, Montreal, Canada

    Issam El Naqa

  2. Department of Radiation Oncology, Stanford University School of Medicine, Stanford, California, USA

    Ruijiang Li

  3. Department of Radiation Oncology, Virginia Commonwealth University, Richmond, Virginia, USA

    Martin J. Murphy

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this chapter

Cite this chapter

Lee, S., El Naqa, I. (2015). Machine Learning Methodology. In: El Naqa, I., Li, R., Murphy, M. (eds) Machine Learning in Radiation Oncology. Springer, Cham. https://doi.org/10.1007/978-3-319-18305-3_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-18305-3_3

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-18304-6

  • Online ISBN: 978-3-319-18305-3

  • eBook Packages: MedicineMedicine (R0)

Publish with us

Policies and ethics

Search

Navigation