Comparing Ensembles of Learners: Detecting Prostate Cancer from High Resolution MRI

  • Anant Madabhushi
  • Jianbo Shi
  • Michael Feldman
  • Mark Rosen
  • John Tomaszewski
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4241)


While learning ensembles have been widely used for various pattern recognition tasks, surprisingly, they have found limited application in problems related to medical image analysis and computer-aided diagnosis (CAD). In this paper we investigate the performance of several state-of-the-art machine-learning methods on a CAD method for detecting prostatic adenocarcinoma from high resolution (4 Tesla) ex vivo MRI studies. A total of 14 different feature ensemble methods from 4 different families of ensemble methods were compared: Bayesian learning, Boosting, Bagging, and the k-Nearest Neighbor (kNN) classifier. Quantitative comparison of the methods was done on a total of 33 2D sections obtained from 5 different 3D MRI prostate studies. The tumor ground truth was determined on histologic sections and the regions manually mapped onto the corresponding individual MRI slices. All methods considered were found to be robust to changes in parameter settings and showed significantly less classification variability compared to inter-observer agreement among 5 experts. The kNN classifier was the best in terms of accuracy and ease of training, thus validating the principle of Occam’s Razor. The success of a simple non-parametric classifier requiring minimal training is significant for medical image analysis applications where large amounts of training data are usually unavailable.


Receiver Operating Characteristic Curve Ensemble Method Training Instance Weighted Linear Combination Bayesian Learner 
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.
    Quilan, J.R.: Bagging, Boosting, and C4.5. In: AAAI/IAAI, vol. 1, pp. 725–730 (1996)Google Scholar
  2. 2.
    Breiman, L.: Bagging Predictors. Machine Learning 24(2), 123–140 (1996)zbMATHMathSciNetGoogle Scholar
  3. 3.
    Freund, Y., Schapire, R.: Experiments with a new Boosting Algorithm. In: National Conference on Machine Learning, pp. 148–156 (1996)Google Scholar
  4. 4.
    Madabhushi, A., Feldman, M., Metaxas, D., Tomasezweski, J., Chute, D.: Automated Detection of Prostatic Adenocarcinoma from High Resolution Ex Vivo MRI. IEEE Transactions on Medical Imaging 24(12), 1611–1625 (2005)CrossRefGoogle Scholar
  5. 5.
    Duda, R., Hart, P.: Pattern Classification and Scene Analysis. Wiley, New York (1973)zbMATHGoogle Scholar
  6. 6.
    Warfield, S.K., Zou, K.H., Wells, W.M.: Simultaneous Truth and Performance Level Estimation (STAPLE): An Algorithm for the Validation of Image Segmentation. IEEE Trans. on Med. Imag. 23(7), 903–921 (2004)CrossRefGoogle Scholar
  7. 7.
    Dietterich, T.: Ensemble Methods in Machine Learning. In: Workshop on Multiple Classifier Systems, pp. 1–15 (2000)Google Scholar
  8. 8.
    Bauer, E., Kohavi, R.: An empirical comparison of voting classification algorithms: Bagging, Boosting, and Variants. Machine Learning 36, 105–142 (1999)CrossRefGoogle Scholar
  9. 9.
    Tran, Q.-L., Toh, K.-A., Srinivasan, D., Wong, K.-L., Low, S.Q.-C.: An empirical comparison of nine pattern classifiers. IEEE Trans. on Systems, Man, and Cybernetics 35(5), 1079–1091 (2005)CrossRefGoogle Scholar
  10. 10.
    Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. on Pattern Anal. & Machine Intel. 26(5), 530–549 (2004)CrossRefGoogle Scholar
  11. 11.
    Wei, L., Yuang, Y., Nishikawa, R.M., Jiang, Y.: A study on several machine-learning methods for classification of malignant and benign clustered micro-calcifications. IEEE Trans. on Medical Imag. 24(3), 371–380 (2005)CrossRefGoogle Scholar
  12. 12.
    Bay, S.: Nearest neighbor classification from multiple feature subsets. Intelligent Data Analysis 3(3), 191–209 (1999)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Anant Madabhushi
    • 1
  • Jianbo Shi
    • 2
  • Michael Feldman
    • 2
  • Mark Rosen
    • 2
  • John Tomaszewski
    • 2
  1. 1.Rutgers The State University of New JerseyPiscataway
  2. 2.University of PennsylvaniaPhiladelphia

Personalised recommendations