Segmentation of Lung Tumours in Positron Emission Tomography Scans: A Machine Learning Approach

  • Aliaksei Kerhet
  • Cormac Small
  • Harvey Quon
  • Terence Riauka
  • Russell Greiner
  • Alexander McEwan
  • Wilson Roa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5651)

Abstract

Lung cancer represents the most deadly type of malignancy. In this work we propose a machine learning approach to segmenting lung tumours in Positron Emission Tomography (PET) scans in order to provide a radiation therapist with a “second reader” opinion about the tumour location. For each PET slice, our system extracts a set of attributes, passes them to a trained Support Vector Machine (SVM), and returns the optimal threshold value for distinguishing tumour from healthy voxels in that particular slice. We use this technique to analyse four different PET/CT 3D studies. The system produced fairly accurate segmentation, with Jaccard and Dice’s similarity coefficients between 0.82 and 0.98 (the areas outlined by the returned thresholds vs. the ones outlined by the reference thresholds). Besides the high level of geometric similarity, a significant correlation between the returned and the reference thresholds also indicates that during the training phase, the learning algorithm effectively acquired the dependency between the extracted attributes and optimal thresholds.

Keywords

Support Vector Machine (SVM) Positron Emission Tomography (PET) Radiation Treatment Lung Cancer Gross Tumour Volume (GTV) 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Canadian cancer statistics 2008. Canadian Cancer Society (2008)Google Scholar
  2. 2.
    Parkin, D.M., Bray, F., Ferlay, J., Pisani, P.: Global cancer statistics, 2002. CA Cancer J. Clin. 55(2), 74–108 (2005)CrossRefPubMedGoogle Scholar
  3. 3.
    Nestle, U., Kremp, S., Grosu, A.L.: Practical integration of [18F]-FDG-PET and PET-CT in the planning of radiotherapy for non-small cell lung cancer (NSCLC): the technical basis, ICRU-target volumes, problems, perspectives. Radiother Oncol. 81(2), 209–225 (2006)CrossRefPubMedGoogle Scholar
  4. 4.
    Drever, L.A., Roa, W., McEwan, A., Robinson, D.: Comparison of three image segmentation techniques for target volume delineation in positron emission tomography. J. Appl. Clin. Med. Phys. 8(2), 93–109 (2007)PubMedGoogle Scholar
  5. 5.
    Geets, X., Lee, J.A., Bol, A., Lonneux, M., Gregoire, V.: A gradient-based method for segmenting FDG-PET images: methodology and validation. Eur. J. Nucl. Med. Mol. Imaging 34(9), 1427–1438 (2007)CrossRefPubMedGoogle Scholar
  6. 6.
    Naqa, I.E., Yang, D., Apte, A., Khullar, D., Mutic, S., Zheng, J., Bradley, J.D., Grigsby, P., Deasy, J.O.: Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning. Med. Phys. 34(12), 4738–4749 (2007)CrossRefPubMedGoogle Scholar
  7. 7.
    Black, Q.C., Grills, I.S., Kestin, L.L., Wong, C.Y.O., Wong, J.W., Martinez, A.A., Yan, D.: Defining a radiotherapy target with positron emission tomography. Int. J. Radiat Oncol. Biol. Phys. 60(4), 1272–1282 (2004)CrossRefPubMedGoogle Scholar
  8. 8.
    Nestle, U., Kremp, S., Schaefer-Schuler, A., Sebastian-Welsch, C., Hellwig, D., Rube, C., Kirsch, C.M.: Comparison of different methods for delineation of 18F-FDG PET-positive tissue for target volume definition in radiotherapy of patients with non-Small cell lung cancer. J. Nucl. Med. 46(8), 1342–1348 (2005)PubMedGoogle Scholar
  9. 9.
    Nestle, U., Schaefer-Schuler, A., Kremp, S., Groeschel, A., Hellwig, D., Rube, C., Kirsch, C.M.: Target volume definition for 18F-FDG PET-positive lymph nodes in radiotherapy of patients with non-small cell lung cancer. Eur. J. Nucl. Med. Mol. Imaging 34(4), 453–462 (2007)CrossRefPubMedGoogle Scholar
  10. 10.
    Daisne, J.F., Sibomana, M., Bol, A., Doumont, T., Lonneux, M., Gregoire, V.: Tri-dimensional automatic segmentation of PET volumes based on measured source-to-background ratios: influence of reconstruction algorithms. Radiother. Oncol. 69(3), 247–250 (2003)CrossRefPubMedGoogle Scholar
  11. 11.
    Drever, L., Robinson, D.M., McEwan, A., Roa, W.: A local contrast based approach to threshold segmentation for PET target volume delineation. Med. Phys. 33(6), 1583–1594 (2006)CrossRefPubMedGoogle Scholar
  12. 12.
    Drever, L., Roa, W., McEwan, A., Robinson, D.: Iterative threshold segmentation for PET target volume delineation. Med. Phys. 34(4), 1253–1265 (2007)CrossRefPubMedGoogle Scholar
  13. 13.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. In: Statistics for Engineering and Information Science, 2nd edn. Springer, Heidelberg (1999)Google Scholar
  14. 14.
    Scholkopf, B., Smola, A.J.: Learning with Kernels. MIT Press, Cambridge (2002)Google Scholar
  15. 15.
    Smola, A.J., Scholkopf, B.: A tutorial on support vector regression. Neurocolt2 technical report series (October 1998)Google Scholar
  16. 16.
    Boucher, L., Rodrigue, S., Lecomte, R., Benard, F.: Respiratory gating for 3-dimensional PET of the thorax: feasibility and initial results. J. Nucl. Med. 45(2), 214–219 (2004)PubMedGoogle Scholar
  17. 17.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. In: Data Mining, Inference, and Prediction. Springer, Heidelberg (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Aliaksei Kerhet
    • 1
  • Cormac Small
    • 2
  • Harvey Quon
    • 2
  • Terence Riauka
    • 3
  • Russell Greiner
    • 4
  • Alexander McEwan
    • 1
  • Wilson Roa
    • 2
  1. 1.Department of OncologyUniversity of AlbertaEdmontonCanada
  2. 2.Department of Radiation OncologyCross Cancer InstituteEdmontonCanada
  3. 3.Department of Medical PhysicsCross Cancer InstituteEdmontonCanada
  4. 4.Alberta Ingenuity Centre for Machine Learning, Department of Computing ScienceUniversity of AlbertaEdmontonCanada

Personalised recommendations