Advertisement

Breast Cancer Diagnosis Using Neural-Based Linear Fusion Strategies

  • Yunfeng Wu
  • Cong Wang
  • S. C. Ng
  • Anant Madabhushi
  • Yixin Zhong
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4234)

Abstract

Breast cancer is one of the leading causes of mortality among women, and the early diagnosis is of significant clinical importance. In this paper, we describe several linear fusion strategies, in particular the Majority Vote, Simple Average, Weighted Average, and Perceptron Average, which are used to combine a group of component multilayer perceptrons with optimal architecture for the classification of breast lesions. In our experiments, we utilize the criteria of mean squared error, absolute classification error, relative error ratio, and Receiver Operating Characteristic (ROC) curve to concretely evaluate and compare the performances of the four fusion strategies. The experimental results demonstrate that the Weighted Average and Perceptron Average strategies can achieve better diagnostic performance compared to the Majority Vote and Simple Average methods.

Keywords

Receiver Operating Characteristic Receiver Operating Characteristic Curve Breast Lesion Hide Node Breast Cancer Diagnosis 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baker, J.A., Rosen, E.L., Lo, J.Y., Gimenez, E.I., Walsh, R., Soo, M.S.: Computer-aided Detection (CAD) in Screening Mammography: Sensitivity of Commercial CAD Systems for Detecting Architectural Distortion. American J. Roentgenology 181, 1083–1088 (2003)Google Scholar
  2. 2.
    Breiman, L.: Bagging Predictors. Machine Learning 24, 123–140 (1996)MATHMathSciNetGoogle Scholar
  3. 3.
    Chen, D., Hagan, M.: Optimal Use of Regularization and Cross-Validation in Neural Network Modeling. In: Proc. the 1999 Int’l Joint Conf. on Neural Networks, pp. 1275–1280 (1999)Google Scholar
  4. 4.
    Donegan, W.L., Spratt, J.S., Orsini, A. (eds.): Cancer of the Breast, 5th edn. Elsevier, Amsterdam (2002)Google Scholar
  5. 5.
    Freund, Y., Schapire, R.E.: Experiments with a New Boosting Algorithm. In: Proc. the 15th Int’l Conf. on Machine Learning, pp. 148–156 (1996)Google Scholar
  6. 6.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice-Hall, Englewood Cliffs (1998)Google Scholar
  7. 7.
    Hinton, G.E.: Connectionist Learning Procedures. Artificial Intelligence 40, 185–234 (1989)CrossRefGoogle Scholar
  8. 8.
    Hornik, K.M., Stinchcombe, M., White, H.: Multilayer Feedforward Networks are Universal Approximators. Neural Networks 2, 359–366 (1989)CrossRefGoogle Scholar
  9. 9.
    Jemal, A., Murray, T., Ward, E., Tiwari, R.C., Ghafoor, A., Feuer, E.J., Thun, M.J.: Cancer Statistics, 2005. CA: A Cancer Journal for Clinicians 55, 10–30 (2005)CrossRefGoogle Scholar
  10. 10.
    Kuncheva, L.I.: A Theoretical Study on Six Classifier Fusion Strategies. IEEE Transactions on Pattern Analysis and Machine Learning 24, 281–286 (2002)CrossRefGoogle Scholar
  11. 11.
    Madabhushi, A., Feldman, M., Metaxas, D., Tomasezweski, J., Chute, D.: Automated Segmentation of Prostatic Adenocarcinoma from High Resolution MR by Optimally Combining 3D Texture Features. IEEE Transactions on Medical Imaging 24, 1611–1625 (2005)CrossRefGoogle Scholar
  12. 12.
    Madabhushi, A., Metaxas, D.: Combining, Low, High and Empirical Domain Knowledge for Automated Segmentation of Ultrasonic Breast Lesions. IEEE Transactions on Medical Imaging 22, 155–169 (2003)CrossRefGoogle Scholar
  13. 13.
    Mangasarian, O.L., Street, W.N., Wolberg, W.H.: Breast Cancer Diagnosis and Prognosis via Linear Programming. Operations Research 43, 570–577 (1995)CrossRefMATHMathSciNetGoogle Scholar
  14. 14.
    Roli, F., Giacinto, G.: Design of Multiple Classifier Systems. In: Bunke, H., Kandel, A. (eds.) Hybrid Methods in Pattern Recognition, World Scientific, Singapore (2002)Google Scholar
  15. 15.
    Roli, F., Fumera, G., Kittler, J.: Fixed and Trained Combiners for Fusion of Unbalanced Pattern Classifiers. In: Proc. the 5th Int’l Conf. on Information Fusion, pp. 278–284 (2002)Google Scholar
  16. 16.
    Stone, M.: Cross-validatory Choice and Assessment of Statistical Predictions. Journal of Royal Statistics Society B36, 111–133 (1974)Google Scholar
  17. 17.
    Tumer, K., Ghosh, J.: Analysis of Decision Boundaries in Linearly Combined Neural Classifiers. Pattern Recognition 29, 341–348 (1996)CrossRefGoogle Scholar
  18. 18.
    Wanas, N.M., Kamel, M.S.: Decision Fusion in Neural Network Ensembles. In: Proc. of the 2001 Int’l Jt. Conf. on Neural Networks, vol. 4, pp. 2952–2957 (2001)Google Scholar
  19. 19.
    Weigend, A.S., Rumelhart, D.E., Huberman, B.A.: Generalization by Weight-Elimination with Application to Forecasting. Advances in Neural Information Processing Systems 3, 875–882 (1991)Google Scholar
  20. 20.
    Woods, K., Bowyer, K.W.: Generating ROC Curves for Artificial Neural Networks. IEEE Transactions on Medical Imaging 16, 329–337 (1997)CrossRefGoogle Scholar
  21. 21.
    Wu, Y., He, J., Man, Y., Arribas, J.I.: Neural Network Fusion Strategies for Identifying Breast Masses. In: Proc. the 2004 Int’l Jt. Conf. on Neural Networks, vol. 3, pp. 2437–2442 (2004)Google Scholar
  22. 22.
    Wu, Y., Zhang, J., Wang, C., Ng, S.C.: Linear Decision Fusions in Multilayer Perceptrons for Breast Cancer Diagnosis. In: Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence, pp. 699–700 (2005)Google Scholar
  23. 23.
    Zhou, Z.H., Wu, J., Tang, W.: Ensembling Neural Networks: Many Could be Better Than All. Artificial Intelligence 137, 239–263 (2002)CrossRefMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yunfeng Wu
    • 1
  • Cong Wang
    • 1
  • S. C. Ng
    • 2
  • Anant Madabhushi
    • 3
  • Yixin Zhong
    • 1
  1. 1.School of Information EngineeringBeijing University of Posts and TelecommunicationsBeijingChina
  2. 2.School of Science and TechnologyThe Open University of Hong KongHong Kong
  3. 3.Department of Biomedical EngineeringRutgers UniversityPiscatawayUSA

Personalised recommendations