% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Varikuti:840630,
      author       = {Varikuti, Deepthi and GENON, Sarah and Sotiras, Aristeidis
                      and Schwender, Holger and Hoffstaedter, Felix and Jockwitz,
                      Christiane and Caspers, Svenja and Moebus, Susanne and
                      Amunts, Katrin and Davatzikos, Christos and Eickhoff, Simon},
      title        = {{E}valuation of {N}on-negative matrix {F}actorization of
                      grey matter in age prediction},
      reportid     = {FZJ-2017-08134},
      year         = {2017},
      abstract     = {It has been shown that machine-learning methods applied to
                      voxel-based morphometry (VBM) data allows the prediction of
                      brain age [1]. Dimensionality reduction is a critical aspect
                      of such brain-based prediction of phenotypical
                      characteristics to counter the curse of dimensionality
                      associated with voxel-wise analysis. While previous
                      age-predictions have employed PCA based compression,
                      non-negative matrix factorization (NNMF) has recently been
                      suggested as a plausible factorization of high-dimensional
                      VBM data [4]. Non-negativity and sparsity of the components
                      obtained from NNMF facilitate relatively more optimal
                      solution than the PCA based compression [4]. Here, we
                      evaluate, i) whether NNMF compression allows predictions of
                      biological age that reproduce those from previously reported
                      analyses [2], ii) the impact of the NNMF’s granularity on
                      the prediction accuracy, iii) the possible effect of the
                      factorizations derived from different datasets on the
                      prediction, and iv) whether explicit adjustment can address
                      the model bias inherent to many brain-based
                      predictions.Methods:VBM8 preprocessing (using only
                      non-linear modulation and 8 mm FWHM smoothing [3]) was used
                      to compute voxel-wise GM volumes for two datasets, 1) 693
                      healthy older adults (age: 55-75 years) scanned at a single
                      site (“1000BRAINS) [1], 2) 1084 healthy adults (age: 18-81
                      years), scanned at multiple sites (“Mixed”) (Fig 1A).
                      NNMF solutions for both groups were derived at different
                      levels of granularity. Age prediction was performed by
                      fitting LASSO regression models either on the coefficient
                      matrix from the respective NNMF or by those that were
                      derived from projecting a group’s data on the respective
                      other groups components. Model generalization was evaluated
                      by 10-fold cross-validation replicated 25 times. To address
                      the known bias towards the mean, i.e., overestimation of
                      young and underestimation of older subjects, we additionally
                      tested models that explicitly fitted the regression-slope
                      between the real and predicted training set and used this to
                      adjust the expected slope of the test set to 45
                      degrees.Results:In both datasets, NNMF components resembled
                      neurobiologically reasonable patterning of the brain (Fig
                      1B). Prediction accuracy based on the projection of data on
                      the components from either group was virtually identical
                      (Fig 2A). For both datasets, mean absolute errors (MAE)
                      declined with higher granularity of the components and
                      reached values well comparable to previous approaches even
                      when using components derived from an independent sample
                      (MAE: 3.6 years for 1000BRAINS; 6.4 years for Mixed).
                      Plotting the prediction error relative to the biological age
                      of the subjects revealed the bias towards the mean across
                      both datasets (Fig 2B). Adjusting for the slope estimated in
                      the training set allows removing this bias, though it needs
                      to be noted that this comes at the cost of reduced
                      precision, i.e., unbiased estimates yield a slightly higher
                      MAE.Conclusion:NNMF allows the definition of co-variation
                      patterns in VBM data. Due to the non- negativity and
                      sparseness, NNMF enable substantially easier and higher
                      biological interpretation than other methods for data
                      compression such as PCA [4]. We showed that NNMF compression
                      of VBM data over the lifespan allows predicting previously
                      unseen subjects’ age with a precision that is comparable
                      to earlier reports using PCA for data compression [2], while
                      offering the potential for neurobiological interpretation.
                      Importantly, accuracy seems to be independent of whether the
                      components were derived from the same dataset or from a
                      dataset that is not only independent but also different in
                      age distribution. We note that accuracies tend to
                      continuously decrease with higher granularity, although
                      performance tends to plateau at about 300 components.
                      Finally, adjusting the inherent bias of sparse regression
                      models yields unbiased out-of-sample predictions but comes
                      at the expense of slightly higher mean errors.},
      month         = {Jun},
      date          = {2017-06-25},
      organization  = {Annual Meeting of the Organization for
                       Human Brain Mapping (OHBM), Vancouver
                       (Canada), 25 Jun 2017 - 29 Jun 2017},
      subtyp        = {Other},
      cin          = {INM-7},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {571 - Connectivity and Activity (POF3-571) / SMHB -
                      Supercomputing and Modelling for the Human Brain
                      (HGF-SMHB-2013-2017) / HBP SGA1 - Human Brain Project
                      Specific Grant Agreement 1 (720270)},
      pid          = {G:(DE-HGF)POF3-571 / G:(DE-Juel1)HGF-SMHB-2013-2017 /
                      G:(EU-Grant)720270},
      typ          = {PUB:(DE-HGF)24},
      url          = {https://juser.fz-juelich.de/record/840630},
}