Note
This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the user guide for the big picture.
7.11.1. nilearn.signal.clean¶

nilearn.signal.
clean
(signals, sessions=None, detrend=True, standardize='zscore', confounds=None, low_pass=None, high_pass=None, t_r=2.5, ensure_finite=False)¶ Improve SNR on masked fMRI signals.
This function can do several things on the input signals, in the following order:
detrend
low and highpass filter
remove confounds
standardize
Lowpass filtering improves specificity.
Highpass filtering should be kept small, to keep some sensitivity.
Filtering is only meaningful on evenlysampled signals.
According to Lindquist et al. (2018), removal of confounds will be done orthogonally to temporal filters (low and/or highpass filters), if both are specified.
 Parameters
 signals: numpy.ndarray
Timeseries. Must have shape (instant number, features number). This array is not modified.
 sessionsnumpy array, optional
Add a session level to the cleaning process. Each session will be cleaned independently. Must be a 1D array of n_samples elements.
 confounds: numpy.ndarray, str or list of
Confounds timeseries. Shape must be (instant number, confound number), or just (instant number,) The number of time instants in signals and confounds must be identical (i.e. signals.shape[0] == confounds.shape[0]). If a string is provided, it is assumed to be the name of a csv file containing signals as columns, with an optional oneline header. If a list is provided, all confounds are removed from the input signal, as if all were in the same array.
 t_r: float
Repetition time, in second (sampling period). Set to None if not.
 low_pass, high_pass: float
Respectively high and low cutoff frequencies, in Hertz.
 detrend: bool
If detrending should be applied on timeseries (before confound removal)
 standardize: {‘zscore’, ‘psc’, False}, default is ‘zscore’
Strategy to standardize the signal. ‘zscore’: the signal is zscored. Timeseries are shifted to zero mean and scaled to unit variance. ‘psc’: Timeseries are shifted to zero mean value and scaled to percent signal change (as compared to original mean signal). False : Do not standardize the data.
 ensure_finite: bool
If True, the nonfinite values (NANs and infs) found in the data will be replaced by zeros.
 Returns
 cleaned_signals: numpy.ndarray
Input signals, cleaned. Same shape as signals.
Notes
Confounds removal is based on a projection on the orthogonal of the signal space. See Friston, K. J., A. P. Holmes, K. J. Worsley, J.P. Poline, C. D. Frith, et R. S. J. Frackowiak. “Statistical Parametric Maps in Functional Imaging: A General Linear Approach”. Human Brain Mapping 2, no 4 (1994): 189210.
Orthogonalization between temporal filters and confound removal is based on suggestions in Lindquist, M., Geuter, S., Wager, T., & Caffo, B. (2018). Modular preprocessing pipelines can reintroduce artifacts into fMRI data. bioRxiv, 407676.