Advertisement

Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain

  • Sriraam NatarajanEmail author
  • Baidya Saha
  • Saket Joshi
  • Adam Edwards
  • Tushar Khot
  • Elizabeth M. Davenport
  • Kristian Kersting
  • Christopher T. Whitlow
  • Joseph A. Maldjian
Original Article

Abstract

Magnetic resonance imaging (MRI) has emerged as an important tool to identify intermediate biomarkers of Alzheimer’s disease (AD) due to its ability to measure regional changes in the brain that are thought to reflect disease severity and progression. In this paper, we set out a novel pipeline that uses volumetric MRI data collected from different subjects as input and classifies them into one of three classes: AD, mild cognitive impairment (MCI) and cognitively normal (CN). Our pipeline consists of three stages—(1) a segmentation layer where brain MRI data is divided into clinically relevant regions; (2) a classification layer that uses relational learning algorithms to make pairwise predictions between the three classes; and (3) a combination layer that combines the results of the different classes to obtain the final classification. One of the key features of our proposed approach is that it allows for domain expert’s knowledge to guide the learning in all the layers. We evaluate our pipeline on 397 patients acquired from the Alzheimer’s Disease Neuroimaging Initiative and demonstrate that it obtains state-of-the-art performance with minimal feature engineering.

Keywords

Statistical relational learning FMRI prediction Biomedical applications Ensemble methods 

Notes

Acknowledgments

We would like to thank Ben Wagner for help with programming and creating the data set. SN acknowledges the support of Translational Science Institute of Wake Forest School of Medicine. KK was supported by the Fraunhofer ATTRACT fellowship STREAM.

References

  1. 1.
  2. 2.
    http://www.slicer.org. Accessed May 2012
  3. 3.
    Blockeel H, De Raedt L (1998) Top-down induction of first-order logical decision trees. Artif Intell 101:285–297CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Chen K, Reiman EM, Alexander GE, Bandy D, Renaut R, Crum WR, Fox NC, Rossor MN (2004) An automated algorithm for the computation of brain volume change from sequential mris using an iterative principal component analysis and its evaluation for the assessment of whole-brain atrophy rates in patients with probable Alzheimer’s disease. Neuroimage 22(1):134–143CrossRefGoogle Scholar
  5. 5.
    Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc 39:1–38zbMATHMathSciNetGoogle Scholar
  6. 6.
    Dietterich TG, Ashenfelter A, Bulatov Y (2004) Training conditional random fields via gradient tree boosting. In: ICML 2004Google Scholar
  7. 7.
    Freund Y, Schapire R (1996) Experiments with a new boosting algorithm. In: ICML 1996Google Scholar
  8. 8.
    Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232CrossRefzbMATHGoogle Scholar
  9. 9.
    Galar M, Fernández A, Barrenechea E, Bustince H, Herrera F (2011) An overview of ensemble methods for binary classifiers in multi-class problems. Experimental study on one-vs-one and one-vs-all schemes. Pattern Recogn 44:1761–1776CrossRefGoogle Scholar
  10. 10.
    Getoor L, Taskar B (2007) Introduction to statistical relational learning. MIT Press, CambridgezbMATHGoogle Scholar
  11. 11.
    Gutmann B, Kersting K (2006) TildeCRF: conditional random fields for logical sequences. In: ECML 2006Google Scholar
  12. 12.
    Hastie T, Tibshirani R (1998) Classification by pairwise coupling. In: NIPS, pp 507–513Google Scholar
  13. 13.
    Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning. Springer, New YorkCrossRefzbMATHGoogle Scholar
  14. 14.
    Huang J, Ling LCX (2005) Using auc and accuracy in evaluating learning algorithms. IEEE Trans Knowl Data Eng 17(3):299–310CrossRefGoogle Scholar
  15. 15.
    Karwath A, Kersting K, Landwehr N (2008) Boosting relational sequence alignments. In: ICDM 2008Google Scholar
  16. 16.
    Kersting K, Driessens K (2008) Non-parametric policy gradients: a unified treatment of propositional and relational domains. In: ICML 2008Google Scholar
  17. 17.
    Knerr S, Personnaz L, Dreyfus G (1990) Single-layer learning revisited: a stepwise procedure for building and training a neural network. In: Soulié F, Hérault J (eds) Neurocomputing: algorithms, architectures and applications, vol F68. Springer, Berlin, pp 41–50Google Scholar
  18. 18.
    Maldjian JA, Laurienti PJ, Kraft RA, Burdette JB (2003) An automated method for neuroanatomic and cytoarchitectonic atlas-based interrogation of fMRI data sets. NeuroImage 19(3):1233–1239CrossRefGoogle Scholar
  19. 19.
    Natarajan S, Joshi S, Tadepalli P, Kristian K, Shavlik J (2011) Imitation learning in relational domains: a functional-gradient boosting approach. In: IJCAI 2011Google Scholar
  20. 20.
    Natarajan S, Khot T, Kersting K, Guttmann B, Shavlik J (2012) Gradient-based boosting for statistical relational learning: the relational dependency network case. Mach Learn 86(1):25–56CrossRefzbMATHMathSciNetGoogle Scholar
  21. 21.
    Sun L, Patel R, Liu J, Chen K, Wu T, Li J, Reiman E, Ye J (2009) Mining brain region connectivity for Alzheimer’s disease study via sparse inverse covariance estimation. In: KDD 2009Google Scholar
  22. 22.
    Supekar K, Menon V, Rubin D, Musen M, Greicius M D (2008) Network analysis of intrinsic functional brain connectivity in Alzheimer’s disease. PLoS Comput Biol 4(6):e1000100CrossRefGoogle Scholar
  23. 23.
    Tang Y, Yan P, Yuan Y, Li X (2011) Single-image super-resolution via local learning. Int J Mach Learn Cybern 2(1):15–23CrossRefGoogle Scholar
  24. 24.
    Xu X, Liu W, Venkatesh S (2012) An innovative face image enhancement based on principle component analysis. Int J Mach Learn Cybern 3(4):259–267CrossRefGoogle Scholar
  25. 25.
    Ye J, Alexander G, Reiman E, Chen K, Wu T, Li J, Zhao Z, Patel R, Bae M, Janardan R et al (2008) Heterogeneous data fusion for alzheimer’s disease study. In: KDD p 1025Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sriraam Natarajan
    • 1
    Email author
  • Baidya Saha
    • 1
  • Saket Joshi
    • 2
  • Adam Edwards
    • 1
  • Tushar Khot
    • 3
  • Elizabeth M. Davenport
    • 1
  • Kristian Kersting
    • 4
  • Christopher T. Whitlow
    • 1
  • Joseph A. Maldjian
    • 1
  1. 1.Wake Forest School of MedicineWinston-SalemUSA
  2. 2.Oregon State UniversityCorvallisUSA
  3. 3.University of Wisconsin-MadisonMadisonUSA
  4. 4.Fraunhofer IAISSankt AugustinGermany

Personalised recommendations