Tumor Lesion Segmentation from 3D PET Using a Machine Learning Driven Active Surface

  • Payam AhmadvandEmail author
  • Nóirín Duggan
  • François Bénard
  • Ghassan Hamarneh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10019)


One of the key challenges facing wider adoption of positron emission tomography (PET) as an imaging biomarker of disease is the development of reproducible quantitative image interpretation tools. Quantifying changes in tumor tissue, due to disease progression or treatment regimen, often requires accurate and reproducible delineation of lesions. Lesion segmentation is necessary for measuring tumor proliferation/shrinkage and radiotracer-uptake to quantify tumor metabolism. In this paper, we develop a fully automatic method for lesion delineation, which does not require user-initialization or parameter-tweaking, to segment novel PET images. To achieve this, we train a machine learning system on anatomically and physiologically meaningful imaging cues, to distinguish normal organ activity from tumorous lesion activity. The inferred lesion likelihoods are then used to guide a convex segmentation model, guaranteeing reproducible results. We evaluate our approach on datasets from The Cancer Imaging Archive trained on data from the Quantitative Imaging Network challenge that were delineated by multiple users. Our method not only produces more accurate segmentation than state-of-the art segmentation results, but does so without any user interaction.


The Cancer Imaging Archive (TCIA) Lesion Delineation Target Tumor Lesions Quantitative Imaging Network (QIN) Convex Segmentation 
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.



Funding provided by the Canadian Institutes of Health Research (OQI-137993).


  1. 1.
    Abdoli, M., et al.: Contourlet-based active contour model for PET image segmentation. Med. Phys. 40(8), 082507: 1–082507: 12 (2013)CrossRefGoogle Scholar
  2. 2.
    Bagci, U., et al.: Joint segmentation of anatomical and functional images: applications in quantification of lesions from PET, PET-CT, MRI-PET, and MRI-PET-CT images. Med. Image Anal. 17(8), 929–945 (2013)CrossRefGoogle Scholar
  3. 3.
    Bi, L., Kim, J., Feng, D., Fulham, M.: Multi-stage thresholded region classification for whole-body PET-CT lymphoma studies. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 569–576. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10404-1_71 Google Scholar
  4. 4.
    Bresson, X., et al.: Fast global minimization of the active contour/snake model. J. Math. Imaging Vis. 28(2), 151–167 (2007)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Clark, K., et al.: The cancer imaging archive (TCIA): maintaining and operating a public information repository. J. Digit. Imaging 26(6), 1045–1057 (2013)CrossRefGoogle Scholar
  6. 6.
    Clausi, D.A.: An analysis of co-occurrence texture statistics as a function of grey level quantization. Can. J. Remote Sens. 28(1), 45–62 (2002)CrossRefGoogle Scholar
  7. 7.
    Cui, H., et al.: Primary lung tumor segmentation from PET-CT volumes with spatial-topological constraint. Int. J. Comput. Assist. Radiol. Surg. 11(1), 19–29 (2015)CrossRefGoogle Scholar
  8. 8.
    Dewalle-Vignion, A., et al.: A new method for volume segmentation of PET images, based on possibility theory. IEEE Trans. Med. Imag. 30(2), 409–423 (2011)CrossRefGoogle Scholar
  9. 9.
    Fedorov, A., et al.: DICOM for quantitative imaging biomarker development: a standards based approach to sharing clinical data and structured PET/CT analysis results in head and neck cancer research. PeerJ 4, e2057 (2016)CrossRefGoogle Scholar
  10. 10.
    Foster, B., et al.: Segmentation of PET images for computer-aided functional quantification of tuberculosis in small animal models. IEEE Trans. Biomed. Eng. 61(3), 711–724 (2014)CrossRefGoogle Scholar
  11. 11.
    Foster, B., et al.: A review on segmentation of positron emission tomography images. Comput. Biol. Med. 50, 76–96 (2014)CrossRefGoogle Scholar
  12. 12.
    Haralick, R.M., et al.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 6, 610–621 (1973)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Hatt, M., et al.: Accurate automatic delineation of heterogeneous functional volumes in positron emission tomography for oncology applications. Int. J. Radiat. Oncol. Biol. Phys. 77(1), 301–308 (2010)CrossRefGoogle Scholar
  14. 14.
    Ju, W., et al.: Random walk and graph cut for co-segmentation of lung tumor on PET-CT images. IEEE Trans. Image Process. 24(12), 5854–5867 (2015)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Kumar, A., et al.: A graph-based approach for the retrieval of multi-modality medical images. Med. Image Anal. 18(2), 330–342 (2014)CrossRefGoogle Scholar
  16. 16.
    Lapuyade-Lahorgue, J., et al.: Speqtacle: an automated generalized fuzzy c-means algorithm for tumor delineation in PET. Med. Phys. 42(10), 5720–5734 (2015)CrossRefGoogle Scholar
  17. 17.
    Layer, T., et al.: PET image segmentation using a Gaussian mixture model and Markov random fields. EJNMMI Phys. 2(1), 1–15 (2015)CrossRefGoogle Scholar
  18. 18.
    Lelandais, B., Gardin, I., Mouchard, L., Vera, P., Ruan, S.: Segmentation of biological target volumes on multi-tracer PET images based on information fusion for achieving dose painting in radiotherapy. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012. LNCS, vol. 7510, pp. 545–552. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33415-3_67 CrossRefGoogle Scholar
  19. 19.
    Liaw, A., et al.: Classification and regression by randomForest. R News 2(3), 18–22 (2002)MathSciNetGoogle Scholar
  20. 20.
    Nestle, U., et al.: 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)Google Scholar
  21. 21.
    Soh, L.K., et al.: Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans. Geosci. Remote Sens. 37(2), 780–795 (1999)CrossRefGoogle Scholar
  22. 22.
    Song, Q., et al.: Optimal co-segmentation of tumor in PET-CT images with context information. IEEE Trans. Med. Imag. 32(9), 1685–1697 (2013)CrossRefGoogle Scholar
  23. 23.
    Yu, H., et al.: Automated radiation targeting in head-and-neck cancer using region-based texture analysis of PET and CT images. Int. J. Radiat. Oncol. Biol. Phys. 75(2), 618–625 (2009)CrossRefGoogle Scholar
  24. 24.
    Zeng, Z., et al.: Unsupervised tumour segmentation in PET using local and global intensity-fitting active surface and alpha matting. Comput. Biol. Med. 43(10), 1530–1544 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Payam Ahmadvand
    • 1
    Email author
  • Nóirín Duggan
    • 1
  • François Bénard
    • 2
    • 3
  • Ghassan Hamarneh
    • 1
  1. 1.Medical Image Analysis LabSimon Fraser UniversityBurnabyCanada
  2. 2.BC Cancer AgencyVancouverCanada
  3. 3.Department of RadiologyUniversity of British ColumbiaVancouverCanada

Personalised recommendations