Assessing Ground Truth of Glandular Tissue

  • Christina Olsén
  • Fredrik Georgsson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4046)


In medical image analysis a ground truth to compare results against is of vital importance. This ground truth is often obtained from human experts. The aim of this paper is to discuss the problem related to the use of markings made by an expert panel. As a partial solution, we propose a method to relate markings to each other in order to establish levels of agreement. By using this method we can assess the performance of, for instance, segmentation algorithms.


Ground Truth Segmentation Algorithm Domain Expert Human Expert Glandular Tissue 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Borgefors, G.: Distance transformations in digital images. Comput. Vision, Graphics, Image Processing 34, 344–371 (1986)CrossRefGoogle Scholar
  2. 2.
    Brink, A.D., Pendock, N.E.: Minimum Cross-Entropy Threshold Selection. Pattern Recognition 29(1), 179–188 (1996)CrossRefGoogle Scholar
  3. 3.
    Bromiley, P.A., Courtney, P., Thacker, N.A.: A case study in the use of ROC curves for algorithm design. In: The British Machine Vision Conference (BMVC) (2001)Google Scholar
  4. 4.
    Gual-Arnau, X., Ibáñez-Gual, M.V., Lliso, F., Roldán, S.: Organ contouring for prostate cancer: Interobserver and internal organ motion variability. Computerized Medical Imaging and Graphics 29, 639–647 (2005)CrossRefGoogle Scholar
  5. 5.
    Li, C.H., Lee, C.K.: Minimum Cross-Entropy Thresholding. Pattern Recognition 26(4), 617–625 (1993)CrossRefGoogle Scholar
  6. 6.
    Masek, M.: Hierarchical Segmentation Of Mammograms Based On Pixel Intensity. PhD thesis, Centre for Intelligent Processing Systems, School of Electrical, Electronic, and Computer Engineering, The University of Western Australia (February 2004)Google Scholar
  7. 7.
    Mukhdoomi, A.: On the problem of segementing fibro-glandular tissue in mammograms. Master’s thesis, UMNAD 619/06 Umeå University, Department of Computing Science (2006)Google Scholar
  8. 8.
    Olsén, C.: Automatic breast border extraction. In: Fitzpatrick, J.M., Reinhardt, J.M. (eds.) Image Processing, vol. 5747 (2005); Proceedings of the International Society for Optical Engineering (SPIE) Medical Imaging (2005) (to appear)Google Scholar
  9. 9.
    Olsén, C., Georgsson, F.: Problems related to automatic nipple extraction. In: Kalviainen, H., Parkkinen, J., Kaarna, A. (eds.) SCIA 2005. LNCS, vol. 3540, pp. 470–480. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Olsén, O.: Automatic Assessment of Mammogram Adequacy. Licentitate Thesis, Umeå University, Department of Computing Science (2005)Google Scholar
  11. 11.
    Smyth, P.: Bounds on the mean classification error rate of multiple experts. Pattern Recognition Letters 17, 1253–1257 (1996)CrossRefGoogle Scholar
  12. 12.
    Warfield, S.K., Zou, K.H., Wells, W.M.: Validation of image segmentation and expert quality with an expectation-maximization algorithm. In: Dohi, T., Kikinis, R. (eds.) MICCAI 2002. LNCS, vol. 2488, pp. 298–306. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  13. 13.
    Zou, K.H., Wells, W.M., Kikinis, R., Warfield, S.K.: Three validation metrics for automated probablistic image segmentation of brain tumours. Statistics in Medicine 23, 1259–1282 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Christina Olsén
    • 1
  • Fredrik Georgsson
    • 1
  1. 1.Department of Computing ScienceUmeå UniversityUmeåSweden

Personalised recommendations