Machine learning for neuroimaging with scikit-learn

By Alexandre Abraham, Fabian Pedregosa, Michael Eickenberg, Philippe Gervais, Andreas Mueller, Jean Kossaifi, Alexandre Gramfort, Bertrand Thirion, Gaël Varoquaux. Front. Neuroinform., 2014

2,159 citations recorded by the source corpus.

Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g., multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g., resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain.

Subfields: Cognitive Neuroscience, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/f15367ed93c3505b1d62d802f3f4b769ae0f4ba5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Assessing and tuning brain decoders: Cross‐validation, caveats, and guidelines (2016, positive): “We use scikit-learn for all decoders [1, 43].”
Analyzing Neuroimaging Data Through Recurrent Deep Learning Models (2018, neutral): “All of our preprocessing was performed by the use of the Nilearn 0.4.1 Python library [Abraham et al., 2014].”
Brains and algorithms partially converge in natural language processing (2022, methodology): “…were detrended and de-confounded from 18 variables (the six estimated head-motion parameters ( trans x,y,z , rot x,y,z ) and the ﬁ rst six noise components calculated using anatomical CompCorr 90 and six DCT-basis regressors using nilearn ’ s clean_img pipeline and otherwise default parameters 91 .”
CoSMoMVPA: Multi-Modal Multivariate Pattern Analysis of Neuroimaging Data in Matlab/GNU Octave (2016, methodology): “…lan-guage—PyMVPA (Hanke, Halchenko, Sederberg, Hanson, et al., 2009; Hanke, Halchenko, Sederberg, Olivetti, et al., 2009), MNE-python (Gramfort et al., 2013)—and the Matlab language—PRoNTO (Schrouff et al., 2013), Search-might (Pereira & Botvinick, 2011), the RSA toolbox (Nili et al., 2014)…”
Benchmarking functional connectome‐based predictive models for resting‐state fMRI (2019, positive): “3 (Abraham et al., 2014b) to de ﬁ ne brain atlases, extract representative timeseries and timeseries confounds regression, and build connectivity measures.”
neuromaps: structural and functional interpretation of brain maps (2022, methodology): “com/netneurolab/markello_neuromaps) and directly relies on the following open-source Python packages: BrainSMASH [14], BrainSpace [82], IPython [59], Jupyter [41], Matplotlib [38], NiBabel [11], Nilearn [1], NumPy [56, 73], Pandas [50], PySurfer [86], Scikit-learn [58], SciPy [81], Seaborn [85], and”
Predicting brain-age from multimodal imaging data captures cognitive impairment (2016, neutral): “2.3, nilearn.github.io, Abraham et al., 2014).”
ProFET: Feature engineering captures high-level protein functions (2015, methodology): “The underlying principle is iterative fitting of the classifier on the data, with the weakest features being pruned at each of the iterations (Abraham et al. , 2014).”
Revealing the co-existence of written and spoken language coding neural populations in the visual word form area (2025, unknown): “10.1 ( Abraham et al., 2014).”
The human auditory cortex concurrently tracks syllabic and phonemic timescales via acoustic spectral flux (2024, unknown): “The entire procedure was implemented using the open-source Python library Scikit-learn ( 108 ).”