[Eeglablist] Automatic ICs rejection from the EEG data in MNE Python

[Rab Nawaz]

Dear Arnaud,

I absolutely agree with you that MATLAB is still the most widely used
platform in EEG data. But, we are restricted due to the major goals of the
project that we are working on.

Thanks

*Rab Nawaz,* B.Engg., Ph.D.
Postdoctoral research associate

[image: Mailtrack]
<https://urldefense.proofpoint.com/v2/url?u=https-3A__mailtrack.io-3Futm-5Fsource-3Dgmail-26utm-5Fmedium-3Dsignature-26utm-5Fcampaign-3Dsignaturevirality11-26&d=DwIFaQ&c=-35OiAkTchMrZOngvJPOeA&r=kB5f6DjXkuOQpM1bq5OFA9kKiQyNm1p6x6e36h3EglE&m=_vhZ3SwZ4tlbaAMNjG489hKFvMDgE1n1sdRe-CCwy-ilCFJWM5XK4XZ1X_yx0a72&s=tw0Kf155lmfsozqOOjt_S_WJQyQuLXkz30mGsJagkks&e= >
Sender
notified by
Mailtrack
<https://urldefense.proofpoint.com/v2/url?u=https-3A__mailtrack.io-3Futm-5Fsource-3Dgmail-26utm-5Fmedium-3Dsignature-26utm-5Fcampaign-3Dsignaturevirality11-26&d=DwIFaQ&c=-35OiAkTchMrZOngvJPOeA&r=kB5f6DjXkuOQpM1bq5OFA9kKiQyNm1p6x6e36h3EglE&m=_vhZ3SwZ4tlbaAMNjG489hKFvMDgE1n1sdRe-CCwy-ilCFJWM5XK4XZ1X_yx0a72&s=tw0Kf155lmfsozqOOjt_S_WJQyQuLXkz30mGsJagkks&e= >
02/24/22,
01:13:46 PM

On Wed, Feb 23, 2022 at 6:58 PM Delorme, Arnaud via eeglablist <
eeglablist at sccn.ucsd.edu> wrote:

> Hi Rab,
>
> You can always program it in MATLAB and compile. 95% of EEG research is
> still under MATLAB based on publication frequency
> https://urldefense.proofpoint.com/v2/url?u=https-3A__eeglab.org_others_EEGLAB-5Fand-5Fpython.html&d=DwIFAg&c=-35OiAkTchMrZOngvJPOeA&r=kB5f6DjXkuOQpM1bq5OFA9kKiQyNm1p6x6e36h3EglE&m=NCU169VqnxdwSIOupGPKBDQgUCgBwCYoDruaT8z4mC6JFJ_Ar0tro7VvwjVlMz8w&s=UTC7RdUpsbYooUS3gVepNBPHuUKtrcf7jpeM1gVnwIg&e=
> You may also compile Python libraries in MATLAB (no MATLAB license
> necessary to deploy) if you are committed to using Python.
>
> Arno
>
> > On Feb 23, 2022, at 10:37 AM, Scott Makeig via eeglablist <
> eeglablist at sccn.ucsd.edu> wrote:
> >
> > Rab -  I would still look at ICLabel -   the application code is  not
> > elaborate and could be translated to python fairly easily I imagine.  The
> > training code is already in python.  The author is Luca Pion-Tonalchini .
> > I'll send you his email.
> >
> > Scott
> >
> > On Wed, Feb 23, 2022 at 11:06 AM Rab Nawaz <13mseerabnawaz at seecs.edu.pk>
> > wrote:
> >
> >> Scott Makeig, thanks for the prompt reply. Actually the major goal of
> the
> >> project is creating a user interface for clinical purposes and the
> >> development of the GUI is based in Python. Therefore we are trying to
> >> incorporate all the modules in the same coding environment Python from
> the
> >> beginning.
> >>
> >> *Rab Nawaz,* B.Engg., Ph.D.
> >> Postdoctoral research associate
> >>
> >>
> >> On Wed, Feb 23, 2022 at 3:57 PM Scott Makeig <smakeig at gmail.com> wrote:
> >>
> >>> Rab -
> >>>
> >>> Why not try running open source EEGLAB/Matlab tools on open source
> >>> Octave?  Arno has worked to insure this is possible ...  I would
> recommend
> >>> you try Luca Pion-Tonacdhini's ICLabel.
> >>>
> >>> Scott Makeig
> >>>
> >>> On Wed, Feb 23, 2022 at 10:55 AM Rab Nawaz via eeglablist <
> >>> eeglablist at sccn.ucsd.edu> wrote:
> >>>
> >>>> Hi EEGLABers,
> >>>>
> >>>>
> >>>>
> >>>> As in the EEGLAB we know there are multiple ICA classification methods
> >>>> available as a plugins (MARA (Winkler et al., 2011), ADJUST (Mognon et
> >>>> al.,
> >>>> 2011), SASICA, IC-MARC) for some near-automatic methods for removing
> >>>> unhealthy ICs to clean the data from artifacts.
> >>>>
> >>>>
> >>>>
> >>>> I am restricted to use an open-source tool therefore I choose Python.
> I
> >>>> am
> >>>> trying to perform data cleaning based on the ICA in MNE Python and
> >>>> looking
> >>>> for something automatic that helps in automatic ICs rejection. In MNE
> >>>> Python, there is a template matching method that uses the artifacted
> ICs
> >>>> from one person as ground and correlates it with the ICs of new EEG to
> >>>> pick
> >>>> the ICs which have strong correlation with the artifacted one. But, I
> am
> >>>> looking for something similar to the implementation of MARA or ADJUST
> in
> >>>> MNE Python. Do you know any materials that can help me in this
> regard? Or
> >>>> something else (other than template matching) that can help in
> selecting
> >>>> the artifacted ICs automatically in Python?
> >>>>
> >>>>
> >>>>
> >>>> Thanks
> >>>>
> >>>> Rab
> >>>> _______________________________________________
> >>>> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> >>>> To unsubscribe, send an empty email to
> >>>> eeglablist-unsubscribe at sccn.ucsd.edu
> >>>> For digest mode, send an email with the subject "set digest mime" to
> >>>> eeglablist-request at sccn.ucsd.edu
> >>>>
> >>>
> >>>
> >>> --
> >>> Scott Makeig, Research Scientist and Director, Swartz Center for
> >>> Computational Neuroscience, Institute for Neural Computation,
> University of
> >>> California San Diego, La Jolla CA 92093-0559,
> http://sccn.ucsd.edu/~scott
> >>>
> >>
> >
> > --
> > Scott Makeig, Research Scientist and Director, Swartz Center for
> > Computational Neuroscience, Institute for Neural Computation, University
> of
> > California San Diego, La Jolla CA 92093-0559,
> http://sccn.ucsd.edu/~scott
> > _______________________________________________
> > Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> > To unsubscribe, send an empty email to
> eeglablist-unsubscribe at sccn.ucsd.edu
> > For digest mode, send an email with the subject "set digest mime" to
> eeglablist-request at sccn.ucsd.edu
>
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to
> eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to
> eeglablist-request at sccn.ucsd.edu
>