Principal Component Regression Predicts Functional Responses across Individuals

详细信息    查看全文

• 作者：Bertrand Thirion (20) (21)
  Ga毛l Varoquaux (20) (21)
  Olivier Grisel (20) (21)
  Cyril Poupon (20) (21)
  Philippe Pinel (20) (21)
  
• 关键词：fMRI ; principal components regression ; random effects
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8674
• 期：1
• 页码：741-748
• 全文大小：764 KB
• 参考文献：1. Lashkari, D., Sridharan, R., Vul, E., Hsieh, P.-J., Kanwisher, N., Golland, P.: Search for patterns of functional specificity in the brain: a nonparametric hierarchical bayesian model for group fMRI data. Neuroimage聽59(2), 1348鈥?368 (2012) CrossRef
  2. Worsley, K.J., Liao, C.H., Aston, J., Petre, V., Duncan, G.H., Morales, F., Evans, A.C.: A general statistical analysis for fMRI data. Neuroimage聽15(1), 1鈥?5 (2002) CrossRef
  3. Thirion, B., Pinel, P.: Analysis of a large fMRI cohort: Statistical and methodological issues for group analyses. Neuroimage聽35(1), 105鈥?20 (2007) CrossRef
  4. Saygin, Z.M., Osher, D.E., Koldewyn, K., Reynolds, G., Gabrieli, J.D.E., Saxe, R.R.: Anatomical connectivity patterns predict face selectivity in the fusiform gyrus. Nat. Neurosci.聽15(2), 321鈥?27 (2012) CrossRef
  5. Ng, B., Abugharbieh, R., Varoquaux, G., Poline, J.B., Thirion, B.: Connectivity-informed fMRI activation detection. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part II. LNCS, vol.聽6892, pp. 285鈥?92. Springer, Heidelberg (2011) CrossRef
  6. Ye, D.H., Zikic, D., Glocker, B., Criminisi, A., Konukoglu, E.: Modality propagation: Coherent synthesis of subject-specific scans with data-driven regularization. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part I. LNCS, vol.聽8149, pp. 606鈥?13. Springer, Heidelberg (2013) CrossRef
  7. Dhillon, P.S., Foster, D.P., Kakade, S.M., Ungar, L.H.: A risk comparison of ordinary least squares vs ridge regression. Journal of Machine Learning Research聽14, 1505鈥?511 (2013)
  8. Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Machine Learning聽63(1), 3鈥?2 (2006) CrossRef
  9. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: Machine learning in Python. Journal of Machine Learning Research聽12, 2825鈥?830 (2011)
  10. Plaze, M., Paill猫re-Martinot, M.-L.: 鈥渨here do auditory hallucinations come from?鈥濃€揳 brain morphometry study of schizophrenia patients with inner or outer space hallucinations. Schizophr. Bull.聽37(1), 212鈥?21 (2011) CrossRef
  11. Van Essen, D.C., Glasser, M.F., Dierker, D.L., Harwell, J., Coalson, T.: Parcellations and hemispheric asymmetries of human cerebral cortex analyzed on surface-based atlases. Cereb. Cortex聽22(10), 2241鈥?262 (2012) CrossRef
  12. Mesmoudi, S., Perlbarg, V., Rudrauf, D., Messe, A., Pinsard, B., Hasboun, D., Cioli, C., Marrelec, G., Toro, R., Benali, H., Burnod, Y.: Resting state networks鈥?corticotopy: the dual intertwined rings architecture. PLoS One聽8(7), e67444 (2013)
  
• 作者单位：Bertrand Thirion (20) (21)
  Ga毛l Varoquaux (20) (21)
  Olivier Grisel (20) (21)
  Cyril Poupon (20) (21)
  Philippe Pinel (20) (21)
  
  20. Parietal team, INRIA Saclay-le-de-France, 91128, Palaiseau, France
  21. Neurospin, CEA, DSV, I2BM, 91191, Gif sur Yvette, France
  
• ISSN：1611-3349

文摘

Inter-subject variability is a major hurdle for neuroimaging group-level inference, as it creates complex image patterns that are not captured by standard analysis models and jeopardizes the sensitivity of statistical procedures. A solution to this problem is to model random subjects effects by using the redundant information conveyed by multiple imaging contrasts. In this paper, we introduce a novel analysis framework, where we estimate the amount of variance that is fit by a random effects subspace learned on other images; we show that a principal component regression estimator outperforms other regression models and that it fits a significant proportion (10% to 25%) of the between-subject variability. This proves for the first time that the accumulation of contrasts in each individual can provide the basis for more sensitive neuroimaging group analyzes.