Advertisement

Gradient Boosted Trees for Corrective Learning

  • Baris U. Oguz
  • Russell T. Shinohara
  • Paul A. Yushkevich
  • Ipek OguzEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10541)

Abstract

Random forests (RF) have long been a widely popular method in medical image analysis. Meanwhile, the closely related gradient boosted trees (GBT) have not become a mainstream tool in medical imaging despite their attractive performance, perhaps due to their computational cost. In this paper, we leverage the recent availability of an efficient open-source GBT implementation to illustrate the GBT method in a corrective learning framework, in application to the segmentation of the caudate nucleus, putamen and hippocampus. The size and shape of these structures are used to derive important biomarkers in many neurological and psychiatric conditions. However, the large variability in deep gray matter appearance makes their automated segmentation from MRI scans a challenging task. We propose using GBT to improve existing segmentation methods. We begin with an existing ‘host’ segmentation method to create an estimate surface. Based on this estimate, a surface-based sampling scheme is used to construct a set of candidate locations. GBT models are trained on features derived from the candidate locations, including spatial coordinates, image intensity, texture, and gradient magnitude. The classification probabilities from the GBT models are used to calculate a final surface estimate. The method is evaluated on a public dataset, with a 2-fold cross-validation. We use a multi-atlas approach and FreeSurfer as host segmentation methods. The mean reduction in surface distance error metric for FreeSurfer was \(0.2-0.3\) mm, whereas for multi-atlas segmentation, it was 0.1mm for each of caudate, putamen and hippocampus. Importantly, our approach outperformed an RF model trained on the same features (\(p<0.05\) on all measures). Our method is readily generalizable and can be applied to a wide range of medical image segmentation problems and allows any segmentation method to be used as input.

Keywords

Gradient boosted trees Segmentation MRI Subcortical 

Notes

Acknowledgments

This work was supported, in part, by NIH grants NINDS R01NS094456, NIBIB R01EB017255, NINDS R01NS085211 and NINDS R21NS093349.

References

  1. 1.
    Bakas, S., et al.: GLISTRboost: combining multimodal MRI segmentation, registration, and biophysical tumor growth modeling with gradient boosting machines for glioma segmentation. In: Crimi, A., Menze, B., Maier, O., Reyes, M., Handels, H. (eds.) BrainLes 2015. LNCS, vol. 9556, pp. 144–155. Springer, Cham (2016). doi: 10.1007/978-3-319-30858-6_13 CrossRefGoogle Scholar
  2. 2.
    Becker, C., Rigamonti, R., Lepetit, V., Fua, P.: Supervised feature learning for curvilinear structure segmentation. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8149, pp. 526–533. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-40811-3_66 CrossRefGoogle Scholar
  3. 3.
    Cao, G., Ding, J., Duan, Y., Tu, L., Xu, J., Xu, D.: Classification of tongue images based on doublet and color space dictionary. In: IEEE BIBM, pp. 1170–1175 (2016)Google Scholar
  4. 4.
    Conners, R.W., Harlow, C.A.: A theoretical comparison of texture algorithms. IEEE PAMI 2(3), 204–222 (1980)CrossRefzbMATHGoogle Scholar
  5. 5.
    Cristinacce, D., Cootes, T.F.: Boosted regression active shape models. BMVC 2, 880–889 (2007)Google Scholar
  6. 6.
    Fischl, B., Salat, D.H., Busa, E., Albert, M., Dieterich, M., Haselgrove, C., van der Kouwe, A., Killiany, R., Kennedy, D., Klaveness, S., Montillo, A., Makris, N., Rosen, B., Dale, A.M.: Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron 33(3), 341–355 (2002)CrossRefGoogle Scholar
  7. 7.
    Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29(5), 1189–1232 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Friedman, J.H.: Stochastic gradient boosting. Comput. Stat. Data Anal. 38(4), 367–378 (2002)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural Features for Image Classification. IEEE Trans. Syst. Man Cybern. B Cybern. 6, 610–621 (1973)CrossRefGoogle Scholar
  10. 10.
    Kochanek, D.H.U., Bartels, R.H., Kochanek, D.H.U., Bartels, R.H.: Interpolating splines with local tension, continuity, and bias control, vol. 18. ACM (1984)Google Scholar
  11. 11.
    Long, J.D., Paulsen, J.S., Marder, K., Zhang, Y., Kim, J.I., Mills, J.A.: Researchers of the PREDICT-HD Huntington’s study group: tracking motor impairments in the progression of Huntington’s disease. Mov. Disord. 29(3), 311–319 (2014)CrossRefGoogle Scholar
  12. 12.
    Oguz, I., Kashyap, S., Wang, H., Yushkevich, P., Sonka, M.: Globally optimal label fusion with shape priors. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 538–546. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_62 CrossRefGoogle Scholar
  13. 13.
    Patenaude, B., Smith, S.M., Kennedy, D.N., Jenkinson, M.: A Bayesian model of shape and appearance for subcortical brain segmentation. NeuroImage 56(3), 907–922 (2011)CrossRefGoogle Scholar
  14. 14.
    Shinohara, R.T., Sweeney, E.M., Goldsmith, J., Shiee, N., Mateen, F.J., Calabresi, P.A., Jarso, S., Pham, D.L., Reich, D.S., Crainiceanu, C.M.: Statistical normalization techniques for MRI. NeuroImage Clin. 6, 9–19 (2014)CrossRefGoogle Scholar
  15. 15.
    Smith, S.M.: Fast robust automated brain extraction. HBM 17(3), 143–155 (2002)CrossRefGoogle Scholar
  16. 16.
    Tristán-Vega, A., García-Pérez, V., Aja-Fernández, S., Westin, C.F.: Efficient and robust nonlocal means denoising of MR data based on salient features matching. Comput. Methods Programs Biomed. 105(2), 131–144 (2012)CrossRefGoogle Scholar
  17. 17.
    Tustison, N., Avants, B., Wang, H., Yassa, M.: Multi-atlas intensity and label fusion with supervised segmentation refinement for the parcellation of hippocampal subfields. In: The 13th International Conference on Alzheimer’s and Parkinson’s Diseases Abstract 029 (2017)Google Scholar
  18. 18.
    Tustison, N., Avants, B., Cook, P., Zheng, Y., Egan, A., Yushkevich, P., Gee, J.: N4ITK: improved N3 bias correction. IEEE TMI 29(6), 1310–1320 (2010)Google Scholar
  19. 19.
    Wang, H., Das, S.R., Suh, J.W., Altinay, M., Pluta, J., Craige, C., Avants, B., Yushkevich, P.A.: ADNI: A learning-based wrapper method to correct systematic errors in automatic image segmentation: consistently improved performance in hippocampus, cortex and brain segmentation. NeuroImage 55(3), 968–985 (2011)CrossRefGoogle Scholar
  20. 20.
    Wang, H., Suh, J.W., Das, S.R., Pluta, J., Craige, C., Yushkevich, P.A.: Multi-Atlas Segmentation with Joint Label Fusion. IEEE PAMI 35(3), 611–623 (2012)CrossRefGoogle Scholar
  21. 21.
    Yang, T., Chen, W., Cao, G.: Automated classification of neonatal amplitude-integrated EEG based on gradient boosting method. Biomed. Signal Process. Control 28, 50–57 (2016)CrossRefGoogle Scholar
  22. 22.
    Yin, Y., Zhang, X., Williams, R., Wu, X., Anderson, D.D., Sonka, M.: LOGISMOS-layered optimal graph image segmentation of multiple objects and surfaces: cartilage segmentation in the knee joint. IEEE TMI 29(12), 2023–2037 (2010)Google Scholar
  23. 23.
    Yushkevich, P.A., Pluta, J., Wang, H., Wisse, L.E., Das, S., Wolk, D.: Fast automatic segmentation of hippocampal subfields and medial temporal lobe subregions in 3 Tesla and 7 Tesla T2-weighted MRI. Alzheimer’s & Dementia. J. Alzheimer’s Assoc. 12(7), 126–127 (2016)Google Scholar
  24. 24.
    Yushkevich, P.A., Pluta, J.B., Wang, H., Xie, L., Ding, S.L., Gertje, E.C., Mancuso, L., Kliot, D., Das, S.R., Wolk, D.A.: Automated volumetry and regional thickness analysis of hippocampal subfields and medial temporal cortical structures in mild cognitive impairment. Hum. Brain Mapp. 36(1), 258–287 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Baris U. Oguz
    • 1
  • Russell T. Shinohara
    • 1
  • Paul A. Yushkevich
    • 1
  • Ipek Oguz
    • 1
    Email author
  1. 1.University PennsylvaniaPhiladelphiaUSA

Personalised recommendations