Advertisement

Brain Tumor Segmantation Using Random Forest Trained on Iteratively Selected Patients

  • Abdelrahman EllwaaEmail author
  • Ahmed Hussein
  • Essam AlNaggar
  • Mahmoud Zidan
  • Michael Zaki
  • Mohamed A. Ismail
  • Nagia M. Ghanem
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10154)

Abstract

This paper extends a previously published brain tumor segmentation methods based on Random Decision Forest (RDF). An iterative approach is used in training the RDF in each iteration some patients are added to the training data using some heuristics approach instead of randomly selected training dataset. Feature extraction and selection were applied to select the most discriminative features for training our Random Decision forest on. The post-processing phase has a morphological filter to deal with misclassification errors. Our method is capable of detecting the tumor and segmenting the different tumorous tissues of the glioma achieving competitive results.

Keywords

Brain tumor segmentation Random forests 

References

  1. 1.
    Tustison, N., Gee, J.: N4ITK: Nicks N3 ITK implementation for MRI bias field correction. Insight J. (2009)Google Scholar
  2. 2.
    Nyu, L.G., Udupa, J.K.: On standardizing the MR image intensity scale image, vol. 1081 (1999)Google Scholar
  3. 3.
    Nyu, L.G., Udupa, J.K.: New variants of a method of MRI scale standardization. IEEE Trans. Med. Imaging 19(2), 143–150 (2000)CrossRefGoogle Scholar
  4. 4.
    Dinis, H., Pinto, A., Pereira, S., Silva, C.A.: Random decision forests for automatic brain tumor segmentation in multi-modal MRI imagesGoogle Scholar
  5. 5.
    Peyrat, J.-M., Abinahed, J., Malmi, E., Parambath, S., Chawla, S.: CaBS: a cascaded brain tumor segmentation approachGoogle Scholar
  6. 6.
    Wilms, M., Maier, O., Handels, H.: Highly discriminative features for glioma segmentation in MR volumes with random forestsGoogle Scholar
  7. 7.
  8. 8.
    Bauer, S., Wiest, R., Nolte, L.P., Reyes, M.: A survey of MRI-based medical image analysis for brain tumor studies. Phys. Med. Biol. 58(13), R97 (2013)CrossRefGoogle Scholar
  9. 9.
    Menze, B., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Abdelrahman Ellwaa
    • 1
    Email author
  • Ahmed Hussein
    • 1
  • Essam AlNaggar
    • 1
  • Mahmoud Zidan
    • 1
  • Michael Zaki
    • 1
  • Mohamed A. Ismail
    • 1
  • Nagia M. Ghanem
    • 1
  1. 1.Faculty of EngineeringAlexandria UniversityAlexandriaEgypt

Personalised recommendations