Due to difficulties in collecting sufficient training data, recent advances in neural-network-based methods have not been fully explored in the analysis of brain Magnetic Resonance Imaging (MRI). A possible solution to the limited-data issue is to augment the training set with synthetically generated data. In this paper, we propose a data augmentation strategy based on regional feature substitution. We demonstrate the advantages of this strategy with respect to training a simple neural-network-based classifier in predicting when individual youth transition from no-to-low to medium-to-heavy alcohol drinkers solely based on their volumetric MRI measurements. Based on 20-fold cross-validation, we generate more than one million synthetic samples from less than 500 subjects for each training run. The classifier achieves an accuracy of 74.1% in correctly distinguishing non-drinkers from drinkers at baseline and a 43.2% weighted accuracy in predicting the transition over a three year period (5-group classification task). Both accuracy scores are significantly better than training the classifier on the original dataset.



This research was supported in part by NIH grants U24AA021697, AA005965, AA013521, AA026762, and National Natural Science Foundation of China grants 11501352, 61573235, 11871328.


  1. 1.
    Mueller, S., et al.: Ways toward an early diagnosis in Alzheimer’s disease: the Alzheimer’s disease neuroimaging initiative (ADNI). J. Alzheimers Dement. 1(1), 55–66 (2005)CrossRefGoogle Scholar
  2. 2.
    Frisoni, G.B., Fox, N.C., Jack, C.R., Scheltens, P., Thompson, P.M.: The clinical use of structural MRI in Alzheimer disease. Nat. Rev. Neurol. 6(2), 67–77 (2011)CrossRefGoogle Scholar
  3. 3.
    Di Martino, A., Yan, C.G., Li, Q., et al.: The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol. Psychiatry 19(6), 659–667 (2014)CrossRefGoogle Scholar
  4. 4.
    Wilkinson, L.: Statistical methods in psychology journals; guidelines and explanations. Am. Psychol. 5(8), 594–604 (1999)CrossRefGoogle Scholar
  5. 5.
    Madsen, H., Thyregod, P.: Introduction to General and Generalized Linear Models. Chapman & Hall/CRC, Boca Raton (2011)zbMATHGoogle Scholar
  6. 6.
    Wernick, M.N., Yang, Y., Brankov, J.G., Yourganov, G., Strother, S.C.: Machine learning in medical imaging. IEEE Signal Process. Mag. 27(4), 25–38 (2010)CrossRefGoogle Scholar
  7. 7.
    Shen, D., Wu, G., Suk, H.I.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248 (2017)CrossRefGoogle Scholar
  8. 8.
    Gibson, E., Li, W., Sudre, C., Fidon, L., et al.: NiftyNet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)CrossRefGoogle Scholar
  9. 9.
    Tajbakhsh, N., et al.: Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE TMI 35(5), 1299–1312 (2016)Google Scholar
  10. 10.
    Hussain, Z., Gimenez, F., Yi, D., Rubin, D.: Differential data augmentation techniques for medical imaging classification tasks. In: AMIA Annual Symposium Proceedings, pp. 979–984 (2017)Google Scholar
  11. 11.
    Wong, S.C., Gatt, A., Stamatescu, V., McDonnell, M.D.: Understanding data augmentation for classification: when to warp? CoRR abs/1609.08764 (2016)Google Scholar
  12. 12.
    Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)CrossRefGoogle Scholar
  13. 13.
    Bielza, C., Larranaga, P.: Bayesian networks in neuroscience: a survey. Front. Comput. Neurosci. 8(131), 1–23 (2014)zbMATHGoogle Scholar
  14. 14.
    Adeli, E., et al.: Chained regularization for identifying brain patterns specific to HIV infection. Neuroimage 183, 425–437 (2018)CrossRefGoogle Scholar
  15. 15.
    Brown, S., Brumback, T., Tomlinson, K., et al.: The national consortium on alcohol and neurodevelopment in adolescence (NCANDA): a multisite study of adolescent development and substance use. J. Stud. Alcohol Drugs 76(6), 895–908 (2015)CrossRefGoogle Scholar
  16. 16.
    Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), 1–46 (2015)Google Scholar
  17. 17.
    Pfefferbaum, A., Kwon, D., Brumback, T., et al.: Altered brain developmental trajectories in adolescents after initiating drinking. Am. J. Psychiatry 175(4), 370–380 (2018)CrossRefGoogle Scholar
  18. 18.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: The IEEE International Conference on Computer Vision (ICCV) (2015)Google Scholar
  19. 19.
    Pfefferbaum, A., et al.: Brain gray and white matter volume loss accelerates with aging in chronic alcoholics: a quantitative mri study. Alcohol. Clin. Exp. Res. 16(6), 1078–1089 (1992)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Tuo Leng
    • 1
    • 2
  • Qingyu Zhao
    • 2
  • Chao Yang
    • 1
  • Zhufu Lu
    • 1
  • Ehsan Adeli
    • 2
    Email author
  • Kilian M. Pohl
    • 2
    • 3
  1. 1.School of Computer Engineering and SciencesShanghai UniversityShanghaiChina
  2. 2.School of MedicineStanford UniversityStanfordUSA
  3. 3.SRI International, Center for Health SciencesMenlo ParkUSA

Personalised recommendations