SCoRS—A Method Based on Stability for Feature Selection and Mapping in Neuroimaging
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Feature selection (FS) methods play two important roles in the context of neuroimaging based classification: potentially increase classification accuracy by eliminating irrelevant features from the model and facilitate interpretation by identifying sets of meaningful features that best discriminate the classes. Although the development of FS techniques specifically tuned for neuroimaging data is an active area of research, up to date most of the studies have focused on finding a subset of features that maximizes accuracy. However, maximizing accuracy does not guarantee reliable interpretation as similar accuracies can be obtained from distinct sets of features. In the current paper we propose a new approach for selecting features: SCoRS (survival count on random subsamples) based on a recently proposed Stability Selection theory. SCoRS relies on the idea of choosing relevant features that are stable under data perturbation. Data are perturbed by iteratively sub-sampling both features (subspaces) and examples. We demonstrate the potential of the proposed method in a clinical application to classify depressed patients versus healthy individuals based on functional magnetic resonance imaging data acquired during visualization of happy faces.
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.
Integrity signals
Registry
Cites
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.
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
Machine learning classifiers and fMRI: A tutorial overview
Pereira, F., Mitchell, T., & Botvinick, M. (2009) · NeuroImage · doi:10.1016/j.neuroimage.2008.11.007 · Cited by 1,624 · cited 1×
“Some authors have also referred to the searchlight technique as a FS method ([11], [17], [18]).”
MethodFrontocingulate Dysfunction in Depression: Toward Biomarkers of Treatment Response
Pizzagalli, D. A. (2011) · Neuropsychopharmacology · doi:10.1038/npp.2010.166 · Cited by 945
A meta‐analytic study of changes in brain activation in depression
Fitzgerald, P. B., Laird, A. R., Maller, J., & Daskalakis, Z. J. (2008) · Human Brain Mapping · doi:10.1002/hbm.20426 · Cited by 903
Koolschijn, P. C. M. P., van Haren, N. E. M., Lensvelt‐Mulders, G. J. L. M., Hulshoff Pol, H. E., & Kahn, R. S. (2009) · Human Brain Mapping · doi:10.1002/hbm.20801 · Cited by 902
Bora, E., Fornito, A., Pantelis, C., & Yücel, M. (2012) · Journal of Affective Disorders · doi:10.1016/j.jad.2011.03.049 · Cited by 763 · cited 1×
“Specifically, we found Orbitofrontal cortex (BA 11), Middle Frontal Gyrus (BA 10), Visual Cortex (BA 19), Posterior Cingulate and Cerebellum, which are brain regions associated with these psychiatry diseases (see [38]; [39]; [40]; [41]; [42]; [43]; [44]; [45]).”
BackgroundGroenewold, N. A., Opmeer, E. M., de Jonge, P., Aleman, A., & Costafreda, S. G. (2013) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2012.11.015 · Cited by 417
Diagnostic neuroimaging across diseases
Klöppel, S., Abdulkadir, A., Jack, C. R., Koutsouleris, N., Mourão-Miranda, J., & Vemuri, P. (2012) · NeuroImage · doi:10.1016/j.neuroimage.2011.11.002 · Cited by 279
Self-citationVoxelwise meta-analysis of gray matter reduction in major depressive disorder
Du, M.-Y., Wu, Q.-Z., Yue, Q., Li, J., Liao, Y., Kuang, W.-H., Huang, X.-Q., Chan, R. C. K., Mechelli, A., & Gong, Q.-Y. (2012) · Progress in Neuro-Psychopharmacology and Biological Psychiatry · doi:10.1016/j.pnpbp.2011.09.014 · Cited by 237 · cited 1×
“Specifically, we found Orbitofrontal cortex (BA 11), Middle Frontal Gyrus (BA 10), Visual Cortex (BA 19), Posterior Cingulate and Cerebellum, which are brain regions associated with these psychiatry diseases (see [38]; [39]; [40]; [41]; [42]; [43]; [44]; [45]).”
BackgroundModel-based feature construction for multivariate decoding
Brodersen, K. H., Haiss, F., Ong, C. S., Jung, F., Tittgemeyer, M., Buhmann, J. M., Weber, B., & Stephan, K. E. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2010.04.036 · Cited by 36 · cited 1×
“Some authors have also referred to the searchlight technique as a FS method ([11], [17], [18]).”
Method
Research works printed but not linked: 36
- 10.1145/1961189.1961199 · DOI · Paper page
- vapnik, 1998, Statistical Learning Theory
- 10.1145/130385.130401 · DOI · Paper page
- sj�strand, 2005, Matlab implementation of LASSO LARS the elastic net and SPCA informatics and mathematical modelling
- 10.1016/j.neuroimage.2006.08.016 · DOI
- 10.1001/archgenpsychiatry.2010.178 · DOI · Paper page
- 10.1016/j.patcog.2011.09.011 · DOI
- lamparter, 2011, Stability selection for error control in high-dimensional regression
- balci, 2008, Prediction of successful memory encoding from fMRI data, Med Image Comput Comput Assist Interv, 11, 97
- 10.1111/j.1399-5618.2011.00893.x · DOI · Paper page
- 10.1016/j.neuroimage.2008.06.037 · DOI · Paper page
- 10.1109/IEMBS.2006.259260 · DOI
- 10.1109/TMI.2006.886812 · DOI · Paper page
- yamashita, 2008, Sparse estimation automatically selects voxels relevant for the decoding of fMRI activity patterns, NeuroImage, 42, 1414, 10.1016/j.neuroimage.2008.05.050 · DOI · Paper page
- 10.1162/neco.2007.09-06-340 · DOI · Paper page
- 10.1016/j.neulet.2010.10.007 · DOI
- 10.1073/pnas.0600244103 · DOI · Paper page
- 10.1111/j.1467-9868.2005.00503.x · DOI · Paper page
- 10.1016/j.compbiolchem.2004.11.001 · DOI · Paper page
- tibshirani, 1996, Regression shrinkage and selection via the LASSO, J R Stat Soc, 58, 267, 10.1111/j.2517-6161.1996.tb02080.x · DOI · Paper page
- 10.1016/j.neuroimage.2010.07.074 · DOI · Paper page
- yeung, 2003, Multiclass classification of microarray data with repeated measurements: Application to cancer, Genome Biol, 4, 10.1186/gb-2003-4-12-r83 · DOI
- 10.1007/978-3-642-34713-9_7 · DOI
- 10.1109/CSB.2003.1227396 · DOI · Paper page
- 10.1093/bioinformatics/btm344 · DOI · Paper page
- 10.1162/153244303322753616 · DOI · Paper page
- 10.1109/TMI.2012.2216543 · DOI · Paper page
- 10.1088/0031-9155/55/10/002 · DOI · Paper page
- 10.1109/TMI.2011.2114362 · DOI
- 10.1109/PRNI.2012.31 · DOI
- 10.1111/j.1467-9868.2010.00740.x · DOI · Paper page
- fan, 2005, Classification of structural images via high-dimensional image warping, robust feature extraction, and SVM, Med Image Comput Assist Interv, 8, 1
- 10.1023/A:1012487302797 · DOI · Paper page
- 10.1016/j.neuroimage.2012.04.005 · DOI · Paper page
- 10.1016/j.neuroimage.2011.08.070 · DOI
- 10.1016/j.neunet.2010.12.010 · DOI
Cited by
Stability of feature selection algorithm: A review
Khaire, U. M., & Dhanalakshmi, R. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2019.06.012 · Cited by 630
Machine learning in major depression: from classification to treatment outcome prediction
Gao, S., Calhoun, V. D., & Sui, J. (2018) · CNS Neuroscience & Therapeutics · doi:10.1111/cns.13048 · Cited by 370
Loda: Lightweight on-line detector of anomalies
Pevný, T. (2016) · Machine Learning · doi:10.1007/s10994-015-5521-0 · Cited by 357
Clinical prediction from structural brain MRI scans: A large-scale empirical study
Initiative, F. T. A. D. N., Sabuncu, M. R., & Konukoglu, E. (2015) · Neuroinformatics · doi:10.1007/s12021-014-9238-1 · Cited by 161
“…feature learning is intimately related to the recent line of research that aims to measure the statistical significance of each variable in a discriminative (predictive) model, e.g., (Gaonkar and Davatzikos 2013; Lockhart et al. 2012; Meinshausen and Buhlmann 2010; Rondina et al. 2013).”
BackgroundInfluentialRecommendations and future directions for supervised machine learning in psychiatry
Cearns, M., Hahn, T., & Baune, B. T. (2019) · Translational Psychiatry · doi:10.1038/s41398-019-0607-2 · Cited by 127
Self-citation
Metadata
- Authors
- Rondina, J. M., Hahn, T., de Oliveira, L., Marquand, A. F., Dresler, T., Leitner, T., Fallgatter, A. J., Shawe-Taylor, J., & Mourao-Miranda, J.
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2014-01
- Volume
- 33
- Issue
- 1
- Pages
- 85-98
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2022561739
- Cited by
- 64
- References
- 9
- FWCI
- 3.87
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.