Advertisement

Deep Learning in Diagnosis of Brain Disorders

  • Heung-Il SukEmail author
  • Dinggang Shen
  • Alzheimer’s Disease Neuroimaging Initiative
Part of the Trends in Augmentation of Human Performance book series (TAHP, volume 5)

Abstract

In this chapter, we introduce our recent work on neuroimaging-based AD diagnosis with machine learning techniques, especially deep learning. Specifically, we focus on the problems of feature representation and complementary information fusion from different modalities, e.g., MRI and PET. In our experimental results on the publicly available ADNI dataset, we could validate the effectiveness of the deep learning-based feature representation and its superiority to the competing methods. We also present the importance of collaborating communities of machine learning and clinical neuroscience for clinical interpretation of the learned feature representations.

Keywords

Alzheimer’s disease (AD) Mild cognitive impairment (MCI) Deep learning Stacked auto-encoder Deep Boltzmann machine 

Notes

Acknowledgements

This chapter follows closely the prior published papers [30, 31] by the authors. This work was supported in part by NIH grants EB006733, EB008374, EB009634, AG041721, MH100217, and AG042599, and partial supported by ICT R&D program of MSIP/IITP [B0101-15-0307, Basic Software Research in Human-level Lifelong Machine Learning (Machine Learning Center)].

References

  1. 1.
    Alzheimer’s Association (2012) 2012 Alzheimer’s disease facts and figures. Alzheimer’s & Dement 8(2):131–168CrossRefGoogle Scholar
  2. 2.
    Baron J, Chételat G, Desgranges B, Perchey G, Landeau B, de la Sayette V, Eustache F (2001) In vivo mapping of gray matter loss with voxel-based morphometry in mild Alzheimer’s disease. NeuroImage 14(2):298–309CrossRefPubMedGoogle Scholar
  3. 3.
    Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1–127CrossRefGoogle Scholar
  4. 4.
    Bengio Y, Lamblin P, Popovici D, Larochelle H (2007) Greedy layer-wise training of deep networks. In: Schölkopf B, Platt J, Hoffman T (eds) Advances in neural information processing systems, vol 19. MIT Press, Cambridge, pp 153–160Google Scholar
  5. 5.
    Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New YorkGoogle Scholar
  6. 6.
    Davatzikos C, Bhatt P, Shaw LM, Batmanghelich KN, Trojanowski JQ (2011) Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification. Neurobiol Aging 32(12):2322.e19–2322.e27Google Scholar
  7. 7.
    Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biolog Cybern 36(4):93–202CrossRefGoogle Scholar
  8. 8.
    Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554CrossRefPubMedGoogle Scholar
  9. 9.
    Hinton G, Deng L, Yu D, rahman Mohamed A, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Dahl TSG, Kingsbury B (2012) Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process Mag 29(6):82–97Google Scholar
  10. 10.
    Ishii K, Kawachi T, Sasaki H, Kono AK, Fukuda T, Kojima Y, Mori E (2005) Voxel-based morphometric comparison between early- and late-onset mild Alzheimer’s disease and assessment of diagnostic performance of z score images. Am J Neuroradiol 26:333–340PubMedGoogle Scholar
  11. 11.
    Kim M, Wu G, Wang Q, Lee SW, Shen D (2015) Improved image registration by sparse patch-based deformation estimation. NeuroImage 105:257–268CrossRefPubMedGoogle Scholar
  12. 12.
    Kohannim O, Hua X, Hibar DP, Lee S, Chou YY, Toga AW Jr, Jack CR, Weiner MW, Thompson PM (2010) Boosting power for clinical trials using classifiers based on multiple biomarkers. Neurobiol Aging 31(8):1429–1442PubMedCentralCrossRefPubMedGoogle Scholar
  13. 13.
    LeCun Y, Bottou L, Orr G, Müller KR (1998) Efficient backprop. In: Orr G, Müller KR (eds) Neural networks: tricks of the trade. Lecture notes in computer science, vol 1524. Springer, Berlin/Heidelberg, pp 9–50CrossRefGoogle Scholar
  14. 14.
    Liao S, Gao Y, Oto A, Shen D (2013) Representation learning: a unified deep learning framework for automatic prostate MR segmentation. In: Medical image computing and computer-assisted intervention (MICCAI 2013), Nagoya. Lecture notes in computer science, vol 8150, pp 254–261Google Scholar
  15. 15.
    Liu M, Zhang D, Shen D, the Alzheimer’s Disease Neuroimaging Initiative (2013) Hierarchical fusion of features and classifier decisions for Alzheimer’s disease diagnosis. Hum Brain Mapp 35(4):1305–1319Google Scholar
  16. 16.
    Mohamed A, Dahl GE, Hinton GE (2012) Acoustic modeling using deep belief networks. IEEE Trans Audio Speech Lang Process 20(1):14–22CrossRefGoogle Scholar
  17. 17.
    Montavon G, Braun ML, Müller KR (2011) Kernel analysis of deep networks. J Mach Learn Res 12:2563–2581Google Scholar
  18. 18.
    Montavon G, Orr GB, Müller KR (eds) (2012) Neural networks: tricks of the trade. Lecture notes in computer science, vol 7700, 2nd edn. Springer, Berlin/HeidelbergGoogle Scholar
  19. 19.
    Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY (2011) Multimodal deep learning. In: Proceedings of the 28th international conference on machine learning, Bellevue, pp 689–696Google Scholar
  20. 20.
    Nordberg A, Rinne JO, Kadir A, Langstrom B (2010) The use of PET in Alzheimer disease. Nat Rev Neurol 6(2):78–87CrossRefPubMedGoogle Scholar
  21. 21.
    Salakhutdinov R, Hinton GE (2009) Deep Boltzmann machines. In: Proceedings of the international conference on artificial intelligence and statistics, Clearwater Beach, pp 448–455Google Scholar
  22. 22.
    Salakhutdinov R, Hinton G (2012) An efficient learning procedure for deep Boltzmann machines. Neural Comput 24(8):1967–2006CrossRefPubMedGoogle Scholar
  23. 23.
    Salakhutdinov R, Tenenbaum J, Torralba A (2013) Learning with hierarchical-deep models. IEEE Trans Pattern Anal Mach Intell 35(8):1958–1971CrossRefPubMedGoogle Scholar
  24. 24.
    Sanroma G, Wu G, Gao Y, Shen D (2014) Learning to rank atlases for multiple-atlas segmentation. IEEE Trans Med Imaging 33(10):1939–1953PubMedCentralCrossRefPubMedGoogle Scholar
  25. 25.
    Serre T, Wolf L, Poggio T (2005) Object recognition with features inspired by visual cortex. In: Proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition, San Diego, vol 2, pp 994–1000Google Scholar
  26. 26.
    Shin HC, Orton MR, Collins DJ, Doran SJ, Leach MO (2013) Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data. IEEE Trans Pattern Anal Mach Intell 35(8):1930–1943CrossRefPubMedGoogle Scholar
  27. 27.
    Sonnenburg S, Rätsch G, Schäfer C, Schölkopf B (2006) Large scale multiple kernel learning. J Mach Learn Res 7:1531–1565Google Scholar
  28. 28.
    Srivastava N, Salakhutdinov R (2012) Multimodal learning with deep Boltzmann machines. In: Pereira F, Burges C, Bottou L, Weinberger K (eds) Advances in neural information processing systems, vol 25, Curran Associates, Inc., pp 2231–2239Google Scholar
  29. 29.
    Suk HI, Lee SW (2013) A novel Bayesian framework for discriminative feature extraction in brain-computer interfaces. IEEE Trans Pattern Anal Mach Intell 35(2):286–299CrossRefPubMedGoogle Scholar
  30. 30.
    Suk HI, Lee SW, Shen D (2015) Latent feature representation with stacked auto-encoder for AD/MCI diagnosis. Brain Struct Funct 220(2):841–859CrossRefPubMedGoogle Scholar
  31. 31.
    Suk HI, Lee SW, Shen D (2014) Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. NeuroImage 101:569–582CrossRefPubMedGoogle Scholar
  32. 32.
    Suk HI, Lee SW, Shen D (2014) Subclass-based multi-task learning for Alzheimer’s disease diagnosis. Front Aging Neurosci 6(168):1–12Google Scholar
  33. 33.
    Yuan M, Lin Y (2006) Model selection and estimation in regression with grouped variables. J R Stat Soc Ser B 68(1):49–67CrossRefGoogle Scholar
  34. 34.
    Zhang D, Shen D (2012) Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer’s disease. NeuroImage 59(2):895–907PubMedCentralCrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2015

Authors and Affiliations

  • Heung-Il Suk
    • 1
    Email author
  • Dinggang Shen
    • 1
    • 2
  • Alzheimer’s Disease Neuroimaging Initiative
  1. 1.Department of Brain and Cognitive EngineeringKorea UniversitySeoulRepublic of Korea
  2. 2.Biomedical Research Imaging CenterUniversity of North Carolina at Chapel HillChapel HillUSA

Personalised recommendations