Bone Tumor Segmentation on Bone Scans Using Context Information and Random Forests

  • Gregory Chu
  • Pechin Lo
  • Bharath Ramakrishna
  • Hyun Kim
  • Darren Morris
  • Jonathan Goldin
  • Matthew Brown
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8673)


Bone tumor segmentation on bone scans has recently been adopted as a basis for objective tumor assessment in several phase II and III clinical drug trials. Interpretation can be difficult due to the highly sensitive but non-specific nature of bone tumor appearance on bone scans. In this paper we present a machine learning approach to segmenting tumors on bone scans, using intensity and context features aimed at addressing areas prone to false positives. We computed the context features using landmark points, identified by a modified active shape model. We trained a random forest classifier on 100 and evaluated on 73 prostate cancer subjects from a multi-center clinical trial. A reference segmentation was provided by a board certified radiologist. We evaluated our learning based method using the Jaccard index and compared against the state of the art, rule based method. Results showed an improvement from 0.50 ±0.31 to 0.57 ±0.27. We found that the context features played a significant role in the random forest classifier, helping to correctly classify regions prone to false positives.


Random Forest Bone Tumor Bone Scan Context Feature Jaccard Index 
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.


  1. 1.
    Mundy, G.: Metastasis to Bone: Causes, Consequences and Therapeutic Opportunities. Nat. Rev. Cancer. 2, 584–593 (2002)CrossRefGoogle Scholar
  2. 2.
    Coleman, R.: Clinical Features of Metastatic Bone Disease and Risk of Skeletal Morbidity. Clin. Cancer Res. 12, 6243s (2006)Google Scholar
  3. 3.
    Sonpavde, G., Pond, G., Berry, W., Wit, R., Eisenberger, M., Tannock, I., Armstrong, A.: The Association Between Radiographic Response and Overall Survival in Men with Metastatic Castration-Resistant Prostate Cancer Receiving Chemotherapy. Cancer 117, 3963–3971 (2011)CrossRefGoogle Scholar
  4. 4.
    Sadik, M., Suurkula, M., Hoglund, P., Jarund, A., Edenbrandt, L.: Quality of Planar Whole-body Bone Scan Interpretations – A Nationwide Survey. Eur. J. Nucl. Med. Mol. Im. 35(8), 1464–1472 (2008)CrossRefGoogle Scholar
  5. 5.
    Bombardieri, E., Aktolun, C., Baum, R., Maffioli, L., Moncayo, R., Mortelmans, L., Reske, S.: Bone Scintigraphy: Procedure Guidelines for Tumour Imaging. Eur. J. Nucl. Med. Mol. Im. 30, 99–106 (2003)Google Scholar
  6. 6.
    Larson, S., Nelp, W.: The Radiocolloid Bone Marrow Scan in Malignant Disease. J. Surgical Onc. 3(6), 685–697 (1971)CrossRefGoogle Scholar
  7. 7.
    Holder, L., Collier, D., Fogelman, I.: An Atlas of Planar and SPECT Bone Scans. CRC Press (2000)Google Scholar
  8. 8.
    Brown, M., Chu, G., Kim, H., Allen-Auerbach, M., Poon, C., Bridges, J., Vidovic, A., Ramakrishna, B., Ho, J., Morris, M., Larson, S., Scher, H., Goldin, J.: Computer-Aided Quantitative Bone Scan Assessment of Prostate Cancer Treatment Response. Nucl. Med. Commun. 33(4), 384–394 (2012)CrossRefGoogle Scholar
  9. 9.
    Scher, H., Smith, M., Sweeney, C., Corn, P., Logothetis, C., Vogelzang, N., Smith, D., Hussain, M., George, D., Bono, J., Higano, C., Small, E., Goldin, J., Brown, M., Aftab, D., Noursalehi, M., Weitzman, A., Basch, E.: An Exploratory Analysis of Bone Scan Lesion Area, Circulating Tumor Cell change, Pain Reduction, and Overall Survival in Patients with Castration-Resistant Prostate Cancer Treated with Cabozantinib. J. Clin. Onc. 31(15), 5026 (2013)Google Scholar
  10. 10.
    Chu, G., Lo, P., Kim, H., Auerbach, M., Goldin, J., Henkel, K., Banola, A., Morris, D., Coy, H., Brown, M.: Preliminary Results of Automated Removal of Degenerative Joint Disease in Bone Scan Lesion Segmentation. In: Proc. SPIE 8670 Medical Imaging, 867007 (2013)Google Scholar
  11. 11.
    Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active Shape Models - Their Training and Application. Comp. Vis. and Im. Und. 61(1), 38–59 (1995)CrossRefGoogle Scholar
  12. 12.
    Dalal, N., Triggs, B.: Histogram of Oriented Gradients for Human Detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  13. 13.
    Vedaldi, A., Fulkerson, B.: VLFeat: An Open and Portable Library of Computer Vision Algorithms,
  14. 14.
    Haralick, R., Shanmugam, K., Dinstein, I.: Textural Features for Image Classification. IEEE Trans. Sys. Man and Cyb. 6, 610–621 (1973)CrossRefGoogle Scholar
  15. 15.
    Lindeberg, T.: Scale-Space Theory in Computer Vision. Kluwer Academic Publishers (1994)Google Scholar
  16. 16.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Bruncher, M., Perrot, M., Duchesnay, E.: Scikit-learn: Machine learning in Python. J. of Mach. Learn. Res. 12, 2825–2830 (2011)zbMATHGoogle Scholar
  17. 17.
    Breiman, L., Friedman, J., Stone, C., Olshen, R.: Classification and Regression Trees. Chapman and Hall/CRC (1984)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Gregory Chu
    • 1
  • Pechin Lo
    • 1
  • Bharath Ramakrishna
    • 1
  • Hyun Kim
    • 1
  • Darren Morris
    • 2
  • Jonathan Goldin
    • 1
  • Matthew Brown
    • 1
  1. 1.Center for Computer Vision and Imaging BiomarkersUCLA RadiologyUSA
  2. 2.MedQIA Imaging CROUSA

Personalised recommendations