CoChat

Evaluation of non-negative matrix factorization of grey matter in age prediction

Open access
Varikuti, Deepthi P., Genon, Sarah, Sotiras, Aristeidis, Schwender, Holger, Hoffstaedter, Felix, Patil, Kaustubh R., Jockwitz, Christiane, Caspers, Svenja, Moebus, Susanne, Amunts, Katrin, Davatzikos, Christos, Eickhoff, Simon B. · 2018 · NeuroImage
Cited by 109

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

Abstract

&NA; The relationship between grey matter volume (GMV) patterns and age can be captured by multivariate pattern analysis, allowing prediction of individuals' age based on structural imaging. Raw data, voxel‐wise GMV and non‐sparse factorization (with Principal Component Analysis, PCA) show good performance but do not promote relatively localized brain components for post‐hoc examinations. Here we evaluated a non‐negative matrix factorization (NNMF) approach to provide a reduced, but also interpretable representation of GMV data in age prediction frameworks in healthy and clinical populations. This examination was performed using three datasets: a multi‐site cohort of life‐span healthy adults, a single site cohort of older adults and clinical samples from the ADNI dataset with healthy subjects, participants with Mild Cognitive Impairment and patients with Alzheimer's disease (AD) subsamples. T1‐weighted images were preprocessed with VBM8 standard settings to compute GMV values after normalization, segmentation and modulation for non‐linear transformations only. Non‐negative matrix factorization was computed on the GM voxel‐wise values for a range of granularities (50–690 components) and LASSO (Least Absolute Shrinkage and Selection Operator) regression were used for age prediction. First, we compared the performance of our data compression procedure (i.e., NNMF) to various other approaches (i.e., uncompressed VBM data, PCA‐based factorization and parcellation‐based compression). We then investigated the impact of the granularity on the accuracy of age prediction, as well as the transferability of the factorization and model generalization across datasets. We finally validated our framework by examining age prediction in ADNI samples. Our results showed that our framework favorably compares with other approaches. They also demonstrated that the NNMF based factorization derived from one dataset could be efficiently applied to compress VBM data of another dataset and that granularities between 300 and 500 components give an optimal representation for age prediction. In addition to the good performance in healthy subjects our framework provided relatively localized brain regions as the features contributing to the prediction, thereby offering further insights into structural changes due to brain aging. Finally, our validation in clinical populations showed that our framework is sensitive to deviance from normal structural variations in pathological aging.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.neuroimage.2018.03.007

Cites

24 of 24 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 24 references

Research works printed but not linked: 52

  1. Ashburner, 1985, VBM tutorial, J. Classif., 2, 193
  2. Beheshti, 2017, Classification of Alzheimer's disease and prediction of mild cognitive impairment-to-Alzheimer’s conversion from structural magnetic resource imaging using feature ranking and a genetic algorithm, Comput. Biol. Med., 83, 109, 10.1016/j.compbiomed.2017.02.011 · DOI · Paper page
  3. Bellec, 2010, Multi-level bootstrap analysis of stable clusters in resting-state fMRI, Neuroimage, 51, 1126, 10.1016/j.neuroimage.2010.02.082 · DOI · Paper page
  4. Boutsidis, 2008, SVD based initialization: a head start for nonnegative matrix factorization, Pattern Recognit., 41, 1350, 10.1016/j.patcog.2007.09.010 · DOI · Paper page
  5. Bunea, 2011, Penalized least squares regression methods and applications to neuroimaging, Neuroimage, 55, 1519, 10.1016/j.neuroimage.2010.12.028 · DOI · Paper page
  6. Burgmans, 2009, The prevalence of cortical gray matter atrophy may be overestimated in the healthy aging brain, Neuropsychology, 23, 541, 10.1037/a0016161 · DOI · Paper page
  7. Caspers, 2014, Studying variability in human brain aging in a population-based German cohort-rationale and design of 1000BRAINS, Front. Aging Neurosci., 6, 1, 10.3389/fnagi.2014.00149 · DOI
  8. Davatzikos, 2016, Computational neuroanatomy using brain deformations: from brain parcellation to multivariate pattern analysis and machine learning, Med. Image Anal., 33, 149, 10.1016/j.media.2016.06.026 · DOI
  9. Davatzikos, 2004, Why voxel-based morphometric analysis should be used with great caution when characterizing group differences, Neuroimage, 23, 17, 10.1016/j.neuroimage.2004.05.010 · DOI · Paper page
  10. Eickhoff, 2017, Topographic organization of the cerebral cortex and brain cartography, Neuroimage
  11. Franke, 2012, Longitudinal changes in individual BrainAGE in healthy aging, mild cognitive impairment, and Alzheimer's disease, GeroPsych J. Gerontopsychology Geriatr. Psychiatry, 25, 235
  12. Franke, 2014, Dementia classification based on brain age estimation, Proc. MICCAI Work Chall. Comput. Diagn. Dement. Based Struct. MRI Data, 48
  13. Franke, 2012, Brain maturation: predicting individual BrainAGE in children and adolescents using structural MRI, Neuroimage, 63, 1305, 10.1016/j.neuroimage.2012.08.001 · DOI · Paper page
  14. Franke, 2014, Gender-specific impact of personal health parameters on individual brain aging in cognitively unimpaired elderly subjects, Front. Aging Neurosci., 6, 1, 10.3389/fnagi.2014.00094 · DOI
  15. Franke, 2010, Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: exploring the influence of various parameters, Neuroimage, 50, 883, 10.1016/j.neuroimage.2010.01.005 · DOI · Paper page
  16. Gaser, 2013, BrainAGE in mild cognitive impaired patients: predicting the conversion to Alzheimer's disease, PLoS One, 10.1371/journal.pone.0067346 · DOI · Paper page
  17. Genon, 2017, The right dorsal premotor mosaic: organization, functions, and connectivity, Cereb. Cortex, 27, 2095
  18. Genon, 2016, The heterogeneity of the left dorsal premotor cortex evidenced by multimodal connectivity-based parcellation and functional characterization, Neuroimage
  19. Guyon, 2003, An introduction to variable and feature selection, J. Mach. Learn Res., 3, 1157
  20. Harada, 2013, Normal cognitive aging, Clin. Geriatr. Med., 29, 737, 10.1016/j.cger.2013.07.002 · DOI · Paper page
  21. Haufe, 2014, On the interpretation of weight vectors of linear models in multivariate neuroimaging, Neuroimage, 87, 96, 10.1016/j.neuroimage.2013.10.067 · DOI · Paper page
  22. Hua, 2009, Performance of feature-selection methods in the classification of high-dimension data, Pattern Recognit., 42, 409, 10.1016/j.patcog.2008.08.001 · DOI · Paper page
  23. Kampa, 2014, Sparse optimization in feature selection: application in neuroimaging, J. Glob. Optim., 59, 439, 10.1007/s10898-013-0134-2 · DOI
  24. Lakkaraju, 2016, Interpretable decision sets: a joint framework for description and prediction, Kdd, 2016, 1675
  25. Lee, 1999, Learning the parts of objects by non-negative matrix factorization, Nature, 401, 788, 10.1038/44565 · DOI · Paper page
  26. Liem, 2017, Predicting brain-age from multimodal imaging data captures cognitive impairment, Neuroimage, 148, 179, 10.1016/j.neuroimage.2016.11.005 · DOI · Paper page
  27. Liu, 2010, Projective nonnegative graph embedding, IEEE Trans. Image Process, 19, 1126, 10.1109/TIP.2009.2039050 · doi:10.1109/tip.2009.2039050
  28. Luders, 2016, Estimating brain age using high-resolution pattern recognition: younger brains in long-term meditation practitioners, Neuroimage, 134, 508, 10.1016/j.neuroimage.2016.04.007 · DOI · Paper page
  29. Moradi, 2015, Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects, Neuroimage, 104, 398, 10.1016/j.neuroimage.2014.10.002 · DOI · Paper page
  30. Mwangi, 2013, Prediction of individual subject's age across the human lifespan using diffusion tensor imaging: a machine learning approach, Neuroimage, 75, 58, 10.1016/j.neuroimage.2013.02.055 · DOI
  31. Petersen, 2010, Alzheimer's disease: progress in prediction, Lancet Neurol., 9, 4, 10.1016/S1474-4422(09)70330-8 · DOI · Paper page
  32. Raz, 2010, Trajectories of brain aging in middle-aged and older adults: regional and individual differences, Neuroimage, 51, 501, 10.1016/j.neuroimage.2010.03.020 · DOI · Paper page
  33. Schippling, 2017, Global and regional annual brain volume loss rates in physiological aging, J. Neurol., 264, 520
  34. Sotiras, 2015, Finding imaging patterns of structural covariance via Non-Negative Matrix Factorization, Neuroimage, 108, 1, 10.1016/j.neuroimage.2014.11.045 · DOI · Paper page
  35. Sotiras, 2017, Patterns of coordinated cortical remodeling during adolescence and their associations with functional specialization and evolutionary expansion, Proc. Natl. Acad. Sci., 114, 3527, 10.1073/pnas.1620928114 · DOI · Paper page
  36. Terribilli, 2011, Age-related gray matter volume changes in the brain during non-elderly adulthood, Neurobiol. Aging, 32, 354, 10.1016/j.neurobiolaging.2009.02.008 · DOI · Paper page
  37. Thirion, 2014, Which fMRI clustering gives good brain parcellations?, Front. Neurosci., 8, 1, 10.3389/fnins.2014.00167 · DOI · Paper page
  38. Tibshirani, 1996, Regression selection and shrinkage via the lasso, J. R. Stat. Soc. B, 58, 267, 10.1111/j.2517-6161.1996.tb02080.x · DOI · Paper page
  39. Tipping, 2001, Sparse bayesian learning and the relevance vector mach, J. Mach. Learn Res., 1, 211
  40. Tipping, 2003, Fast marginal likelihood maximisation for sparse bayesian models, Ninth Int. Work Aritficial Intell. Stat., 1
  41. Tisserand, 2002, Regional frontal cortical volumes decrease differentially in aging: an MRI study to compare volumetric approaches and voxel-based morphometry, Neuroimage, 17, 657, 10.1006/nimg.2002.1173 · DOI · Paper page
  42. Varoquaux, 2012, Small-sample brain mapping: sparse recovery on spatially correlated designs with randomization and clustering, Proc. 29th Int. Conf. Mach. Learn, 1375
  43. Varoquaux, 2017, Assessing and tuning brain decoders: cross-validation, caveats, and guidelines, Neuroimage, 145, 166, 10.1016/j.neuroimage.2016.10.038 · DOI · Paper page
  44. Wang, 2016, Multimodal classification of mild cognitive impairment based on partial least squares, J. Alzheimer’s Dis., 54, 359, 10.3233/JAD-160102 · DOI
  45. Yang, 2010, Linear and nonlinear projective nonnegative matrix factorization, Trans. Neur Netw., 21, 734, 10.1109/TNN.2010.2041361 · DOI · Paper page
  46. Yang, 2007, Projective Non-negative matrix factorization with application to facial image processing, Pattern Recognit., 21, 1353, 10.1142/S0218001407005983 · doi:10.1142/s0218001407005983
  47. Yuan, 2007, Projective nonnegative matrix Factorization : sparseness, orthogonality, and clustering, Technology, 1
  48. Zhang, 2008, The sparsity and bias of the lasso selection in high-dimensional linear regression, Ann. Stat., 36, 1567, 10.1214/07-AOS520 · DOI · Paper page
  49. Zhao, 2006, On model selection consistency of lasso, J. Mach. Learn Res., 7, 2541
  50. Ziegler, 2012, Brain structural trajectories over the adult lifespan, Hum. Brain Mapp., 33, 2377, 10.1002/hbm.21374 · DOI · Paper page
  51. Ziegler, 2014, Individualized Gaussian process-based prediction and detection of local and global gray matter abnormalities in elderly subjects, Neuroimage, 97, 333, 10.1016/j.neuroimage.2014.04.018 · DOI · Paper page
  52. Zou, 2005, Regularization and variable selection via the elastic-net, J. R. Stat. Soc., 67, 301, 10.1111/j.1467-9868.2005.00503.x · DOI · Paper page

Cited by

Metadata

Authors
Varikuti, D. P., Genon, S., Sotiras, A., Schwender, H., Hoffstaedter, F., Patil, K. R., Jockwitz, C., Caspers, S., Moebus, S., Amunts, K., Davatzikos, C., & Eickhoff, S. B.
Venue
NeuroImage
Publisher
Elsevier BV
Published
2018-06
Volume
173
Pages
394-410
ISSN
1053-8119 (ISSN-L)
OpenAlex
W2736045761
Cited by
109
References
24
FWCI
7.47
Type
journal article
Language
en
Open access
bronze
Licence
Funders
  • National Institute of Mental Health (R01-MH074457)
  • Deutsche Forschungsgemeinschaft (GE 2835/1-1, EI 816/4-1)
  • Helmholtz-Alberta Initiative
  • National Institutes of Health (R01-AG014971)
  • National Institute on Aging (RF1-AG054409)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.