Image-Guided Radiotherapy with Machine Learning

  • Yaozong Gao
  • Yanrong Guo
  • Yinghuan Shi
  • Shu Liao
  • Jun Lian
  • Dinggang Shen
Chapter

Abstract

In the past decades, many machine learning techniques have been successfully developed and applied to the field of image-guided radiotherapy (IGRT). In this chapter, we will present some latest developments in the application of machine learning techniques to this field. In particular, we focus on the recently developed machine learning methods for delineating male pelvic structures for the treatment of prostate cancer. In the first few sections, we will present and discuss automatic and semiautomatic methods for CT prostate segmentation in the IGRT workflow. In the last section, we will present our extension of some recently developed machine learning approaches to segment the prostate in MR images.

Keywords

Support Vector Regression Sparse Representation Sparse Code Dictionary Learning Dice Similarity Coefficient 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

References

  1. 1.
    Weiss E, Hess CF. The impact of gross tumor volume (GTV) and clinical target volume (CTV) definition on the total accuracy in radiotherapy theoretical aspects and practical experiences. Strahlenther Onkol. 2003;179(1):21–30.PubMedCrossRefGoogle Scholar
  2. 2.
    Brouwer CL, et al. 3D Variation in delineation of head and neck organs at risk. Radiat Oncol. 2012;7:32.PubMedCentralPubMedCrossRefGoogle Scholar
  3. 3.
    Sharp G, et al. Vision 20/20: perspectives on automated image segmentation for radiotherapy. Med Phys. 2014;41(5):050902.PubMedCentralPubMedCrossRefGoogle Scholar
  4. 4.
    Rohlfing T, et al. Quo vadis, atlas-based segmentation? In: Handbook of biomedical image analysis. USA: Springer; 2005. p. 435–86.Google Scholar
  5. 5.
    Heimann T, Meinzer HP. Statistical shape models for 3D medical image segmentation: a review. Med Image Anal. 2009;13(4):543–63.PubMedCrossRefGoogle Scholar
  6. 6.
    Geremia E, et al. Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images. Neuroimage. 2011;57(2):378–90.PubMedCrossRefGoogle Scholar
  7. 7.
    Li W, et al. Learning image context for segmentation of the prostate in CT-guided radiotherapy. Phys Med Biol. 2012;57(5):1283–308.PubMedCentralPubMedCrossRefGoogle Scholar
  8. 8.
    Criminisi A, Shotton J, Konukoglu E. Decision forests: a unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Found Trends Comput Graph Vis. 2012;7(2–3):81–227.Google Scholar
  9. 9.
    Shukla-Dave A, Hricak H. Role of MRI in prostate cancer detection. NMR Biomed. 2014;27(1):16–24.PubMedCrossRefGoogle Scholar
  10. 10.
    Freedman D, et al. Model-based segmentation of medical imagery by matching distributions. IEEE Trans Med Imaging. 2005;24(3):281–92.PubMedCrossRefGoogle Scholar
  11. 11.
    Costa MJ, et al. Automatic segmentation of bladder and prostate using coupled 3D deformable models. Med Image Comput Comput Assist Interv. 2007;10(Pt 1):252–60.PubMedGoogle Scholar
  12. 12.
    Foskey M, et al. Large deformation three-dimensional image registration in image-guided radiation therapy. Phys Med Biol. 2005;50(24):5869.PubMedCrossRefGoogle Scholar
  13. 13.
    Chen S, Lovelock DM, Radke RJ. Segmenting the prostate and rectum in CT imagery using anatomical constraints. Med Image Anal. 2011;15(1):1–11.PubMedCrossRefGoogle Scholar
  14. 14.
    Haas B, et al. Automatic segmentation of thoracic and pelvic CT images for radiotherapy planning using implicit anatomic knowledge and organ-specific segmentation strategies. Phys Med Biol. 2008;53(6):1751.PubMedCrossRefGoogle Scholar
  15. 15.
    Ghosh P, Mitchell M. Segmentation of medical images using a genetic algorithm. In: Proceedings of the 8th annual conference on Genetic and evolutionary computation. Seattle:ACM; 2006. p. 1171–8.Google Scholar
  16. 16.
    Viola P, Jones MJ. Robust real-time face detection. Int J Comput Vis. 2004;57(2):137–54.CrossRefGoogle Scholar
  17. 17.
    Zhan Y, Dewan M, Harder M, Krishnan A, Zhou XS. Robust automatic knee MR slice positioning through redundant and hierarchical anatomy detection. IEEE Trans Med Imaging. 2011;30(12):2087–100.PubMedCrossRefGoogle Scholar
  18. 18.
    Zhan Y, Zhou XS, Peng Z, Krishnan A. Active Scheduling of Organ Detection and Segmentation in Whole-Body Medical Images. In: Metaxas D et al., editors. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2008. Berlin/Heidelberg: Springer; 2008. p. 313–21.CrossRefGoogle Scholar
  19. 19.
    Peng H, Fulmi L, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell. 2005;27(8):1226–38.PubMedCrossRefGoogle Scholar
  20. 20.
    Zhang S, Zhan Y, Metaxas DN. Deformable segmentation via sparse representation and dictionary learning. Med Image Anal. 2012;16(7):1385–96.PubMedCrossRefGoogle Scholar
  21. 21.
    Gao Y, Zhang Y, Shen D. Incremental learning with selective memory (ILSM): towards fast prostate localization for image guided radiotherapy. IEEE Trans Med Imaging. 2014;33(2):518–34.PubMedCentralPubMedCrossRefGoogle Scholar
  22. 22.
    Davis BC, et al. Automatic segmentation of intra-treatment CT images for adaptive radiation therapy of the prostate. Med Image Comput Comput Assist Interv. 2005;8(Pt 1):442–50.PubMedGoogle Scholar
  23. 23.
    Garrigues P, Olshausen B. Group sparse coding with a laplacian scale mixture prior. Adv Neural Inf Process Syst. 2010;23:1–9.Google Scholar
  24. 24.
    Krause A, Cevher V. Submodular dictionary selection for sparse representation. In: ICML 2010: proceedings of the 27th international conference on Machine learning. Haifa: Omnipress; 2010.Google Scholar
  25. 25.
    Aharon M, Elad M, Bruckstein A. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans Signal Process. 2006;54(11):4311–22.CrossRefGoogle Scholar
  26. 26.
    Huang J, Yang M. Fast sparse representation with prototypes. In: Computer Vision and Pattern Recognition (CVPR), 2010 IEEE conference on. San Francisco, CA; 2010.Google Scholar
  27. 27.
    Jiang Z, Lin Z, Davis LS. Learning a discriminative dictionary for sparse coding via label consistent K-SVD. In: Computer Vision and Pattern Recognition (CVPR), 2011 IEEE conference on. Providence, RI; 2011.Google Scholar
  28. 28.
    Baraniuk R, et al. Applications of sparse representation and compressive sensing. Proc IEEE. 2010;98(6):906–9.CrossRefGoogle Scholar
  29. 29.
    Wright J, et al. Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell. 2009;31(2):210–27.PubMedCrossRefGoogle Scholar
  30. 30.
    Elisseeff IGA. An introduction to variable and feature selection. J Mach Learn Res. 2003;3:1157–82.Google Scholar
  31. 31.
    Zou H, Hastie T. Regularization and variable selection via the Elastic Net. J Royal Stat Soc B. 2005;67:301–20.CrossRefGoogle Scholar
  32. 32.
    Tu Z, Bai X. Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans Pattern Anal Mach Intell. 2010;32(10):1744–57.PubMedCrossRefGoogle Scholar
  33. 33.
    Dice LR. Measures of the amount of ecologic association between species. Ecology. 1945;26(3):297–302.CrossRefGoogle Scholar
  34. 34.
    Warfield SK, Zou KH, Wells WM. Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans Med Imaging. 2004;23(7):903–21.PubMedCentralPubMedCrossRefGoogle Scholar
  35. 35.
    Coupé P, et al. Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation. Neuroimage. 2011;54(2):940–54.PubMedCrossRefGoogle Scholar
  36. 36.
    Rousseau F, Habas PA, Studholme C. A supervised patch-based approach for human brain labeling. IEEE Trans Med Imaging. 2011;30(10):1852–62.PubMedCentralPubMedCrossRefGoogle Scholar
  37. 37.
    Liao S, Shen D. A learning based hierarchical framework for automatic prostate localization in CT images. In: Madabhushi A et al., editors. Prostate cancer imaging. Image analysis and image-guided interventions. Berlin/Heidelberg: Springer; 2011. p. 1–9.CrossRefGoogle Scholar
  38. 38.
    Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell. 1989;11(7):674–93.CrossRefGoogle Scholar
  39. 39.
    Dalal N, Triggs B. Histograms of oriented gradients for human detection. 2005.CrossRefGoogle Scholar
  40. 40.
    Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell. 2002;24(7):971–87.CrossRefGoogle Scholar
  41. 41.
    Tibshirani R. Regression shrinkage and selection via the lasso: a retrospective. J Royal Stat Soc B Stat Methodol. 2011;73(3):273–82.CrossRefGoogle Scholar
  42. 42.
    Belkin M, Niyogi P, Sindhwani V. Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res. 2006;7:2399–434.Google Scholar
  43. 43.
    Shi Y, et al. Transductive prostate segmentation for CT image guided radiotherapy. In: Wang F et al., editors. Machine learning in medical imaging. Berlin/Heidelberg: Springer; 2012. p. 1–9.CrossRefGoogle Scholar
  44. 44.
    Tibshirani R, et al. Sparsity and smoothness via the fused lasso. J Royal Stat Soc B Stat Methodol. 2005;67(1):91–108.CrossRefGoogle Scholar
  45. 45.
    Feng Q, et al. Segmenting CT prostate images using population and patient-specific statistics for radiotherapy. In: Proceedings of the sixth IEEE international conference on symposium on biomedical imaging: From Nano to Macro. Boston: IEEE Press; 2009. p. 282–5.Google Scholar
  46. 46.
    Jain A, Zongker D. Feature selection: evaluation, application, and small sample performance. IEEE Transactions Pattern Anal Mach Intell. 1997;19(2):153–8.CrossRefGoogle Scholar
  47. 47.
    Bühlmann P. Bagging, boosting and ensemble methods. In: Gentle JE, Härdle WK, Mori Y, editors. Handbook of computational statistics. Berlin/Heidelberg: Springer; 2012. p. 985–1022.CrossRefGoogle Scholar
  48. 48.
    Zhang S, et al. Towards robust and effective shape modeling: sparse shape composition. Med Image Anal. 2012;16(1):265–77.PubMedCrossRefGoogle Scholar
  49. 49.
    Shen D, Ip HHS. A Hopfield neural network for adaptive image segmentation: an active surface paradigm. Pattern Recognit Lett. 1997;18(1):37–48.CrossRefGoogle Scholar
  50. 50.
    Liao S, et al. Automatic prostate MR image segmentation with sparse label propagation and domain-specific manifold regularization. In: Gee J et al., editors. Information processing in medical imaging. Berlin/Heidelberg: Springer; 2013. p. 511–23.CrossRefGoogle Scholar
  51. 51.
    Liao S, et al. Representation learning: a unified deep learning framework for automatic prostate MR segmentation. In: Mori K et al., editors. Medical image computing and computer-assisted intervention – MICCAI 2013. Berlin/Heidelberg: Springer; 2013. p. 254–61.CrossRefGoogle Scholar
  52. 52.
    Kirschner M, Jung F, Wesarg S. Automatic prostate segmentation in MR images with a probabilistic active shape model. In: PRostate MR Image SEgmentation, PROMISE 2012. Nice: Electronic Publication; 2012. p. 28–35.Google Scholar
  53. 53.
    Maan B, van der Heijden F. Prostate MR image segmentation using 3D active appearance models. In: PRostate MR Image SEgmentation, PROMISE 2012. Nice: Electronic Publication; 2012. p. 44–51.Google Scholar
  54. 54.
    Martin S, Troccaz J, Daanen V. Automated segmentation of the prostate in 3D MR images using a probabilistic atlas and a spatially constrained deformable model. Med Phys. 2010;37(4):1579–90.PubMedCrossRefGoogle Scholar
  55. 55.
    Birkbeck N, Zhang J, Zhou SK. Region-specific hierarchical segmentation of MR prostate using discriminative learning. In: The PRostate MR Image SEgmentation, PROMISE 2012. Nice: Electronic Publication; 2012.Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Yaozong Gao
    • 1
  • Yanrong Guo
    • 1
  • Yinghuan Shi
    • 2
  • Shu Liao
    • 3
  • Jun Lian
    • 4
  • Dinggang Shen
    • 1
    • 5
  1. 1.UNC IDEA Group, Department of Radiology, Biomedical Research Imaging Center (BRIC)University of North CarolinaChapel HillUSA
  2. 2.State Key Laboratory for Novel Software Technology, Department of Computer Science and TechnologyNanjing UniversityNanjingChina
  3. 3.Syngo, Siemens Medical SolutionsMalvernUSA
  4. 4.Department of Radiation OncologyUniversity of North CarolinaChapel HillUSA
  5. 5.Department of RadiologyUniversity of North CarolinaChapel HillUSA

Personalised recommendations