Advertisement

Improving the Classification Accuracy of the Classic RF Method by Intelligent Feature Selection and Weighted Voting of Trees with Application to Medical Image Segmentation

  • Mohammad Yaqub
  • M. Kassim Javaid
  • Cyrus Cooper
  • J. Alison Noble
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7009)

Abstract

Enhancement of the Random Forests to segment 3D objects in different 3D medical imaging modalities. More accurate voxel classification is achieved by intelligently selecting "good" features and neglecting irrelevant ones; this also leads to a faster training. Moreover, weighting each tree in the forest is proposed to provide an unbiased and more accurate probabilistic decision during the testing stage. Validation is performed on adult brain MRI and 3D fetal femoral ultrasound datasets. Comparisons between the classic Random Forests and the proposed new one show significant improvement on segmentation accuracy. We also compare our work with other techniques to show its applicability.

Keywords

Random forests machine learning feature selection brain MRI segmentation 3D fetal ultrasound segmentation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Criminisi, A., Shotton, J., Robertson, D., Konukoglu, E.: Regression forests for efficient anatomy detection and localization in CT studies. In: Menze, B., Langs, G., Tu, Z., Criminisi, A., et al. (eds.) MICCAI 2010. LNCS, vol. 6533, pp. 106–117. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  2. 2.
    Lempitsky, V., Verhoek, M., Noble, J.A., Blake, A.: Random forest classification for automatic delineation of myocardium in real-time 3D echocardiography. In: Ayache, N., Delingette, H., Sermesant, M., et al. (eds.) FIMH 2009. LNCS, vol. 5528, pp. 447–456. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  3. 3.
    Yi, Z., Criminisi, A., Shotton, J., Blake, A.: Discriminative, semantic segmentation of brain tissue in MR images. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C., et al. (eds.) MICCAI 2009. LNCS, vol. 5762, pp. 558–565. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  4. 4.
    Geremia, E., Menze, B.H., Clatz, O., Konukoglu, E., Criminisi, A., Ayache, N.: Spatial Decision Forests for MS Lesion Segmentation in Multi-Channel MR Images. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 111–118. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Yaqub, M., et al.: Weighted Voting in 3D Random Forest Segmentation. In: MIUA (2010)Google Scholar
  6. 6.
    Criminisi, A., et al.: Decision Forests with Long-Range Spatial Context for Organ Localization in CT Volumes. MICCAI-PMMIA (2009)Google Scholar
  7. 7.
    Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)zbMATHGoogle Scholar
  8. 8.
    Breiman, L.: Random Forests. Machine Learning 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  9. 9.
    Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. PAMI 28(9), 1465–1479 (2006)CrossRefGoogle Scholar
  10. 10.
    Shotton, J., et al.: Semantic Texton Forests for Image Categorization and Segmentation. In: CVPR (2008)Google Scholar
  11. 11.
    Oren, M., et al.: Pedestrian detection using wavelet templates. In: CVPR, pp. 193–199 (1997)Google Scholar
  12. 12.
    Geurts, P., et al.: Extremely randomized trees. Mach. Learn. 63(1), 3–42 (2006)CrossRefzbMATHGoogle Scholar
  13. 13.
    Mahon, P.A., et al.: The use of 3D ultrasound to investigate fetal bone development. Norsk Epidemiologi. 19(1) (2009)Google Scholar
  14. 14.
    Gale, C., et al.: Maternal vitamin D status during pregnancy and child outcomes. EJCN 62, 68–77 (2008)Google Scholar
  15. 15.
    Tustison, N.J., et al.: N4ITK: Improved N3 Bias Correction. IEEE TMI 29(6), 1310–1320 (2010)Google Scholar
  16. 16.
    Thomas, J., Jouve, P.-E., Nicoloyannis, N.: Optimisation and evaluation of random forests for imbalanced datasets. In: Esposito, F., Raś, Z.W., Malerba, D., Semeraro, G., et al. (eds.) ISMIS 2006. LNCS (LNAI), vol. 4203, pp. 622–631. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  17. 17.
    Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  18. 18.
    Rajpoot, K., et al.: Local-phase based 3D boundary detection using monogenic signal and its application to real-time 3-D echocardiography images. In: ISBI (2009)Google Scholar
  19. 19.
    Tu, Z., et al.: Brain Anatomical Structure Segmentation by Hybrid Discriminative/Generative Models. IEEE TMI, 495–508 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mohammad Yaqub
    • 1
    • 2
  • M. Kassim Javaid
    • 2
  • Cyrus Cooper
    • 2
  • J. Alison Noble
    • 1
  1. 1.Institute of Biomedical Engineering, Dept. of Engineering ScienceUniversity of OxfordUK
  2. 2.Nuffield Dept. of Orthopaedics, Rheumatology & Musculoskeletal SciencesUniversity of OxfordUK

Personalised recommendations