[Eeglablist] simple question: logic of using ICLABEL to reject components

[Scott Makeig]

David -

The ICA 'experts' viewed IC properties windows like this one:
https://labeling.ucsd.edu/labelfeedback
in entering their 'expert' opinions to give ICLabel training a coherent
beginning.

Follow the ICLabel tutorial on making property-guided IC-classifying
decisions here:  https://labeling.ucsd.edu/tutorial/overview

Scott

Scott

On Thu, Feb 23, 2023 at 5:03 PM Gilbert, David G <dgilbert at siu.edu> wrote:

> A related question I have concerns the fact that ICA uses percent
> probability of being EEG, heart, EMG, other, etc. Can you refer me to how
> these percentages were calculated. I believe that there were a number of
> experts, but were they looking at epoch-by-epoch portions of the data just
> what..
> Thanks in advance,
> David Gilbert
> ------------------------------
> *From:* eeglablist <eeglablist-bounces at sccn.ucsd.edu> on behalf of Scott
> Makeig <smakeig at gmail.com>
> *Sent:* Thursday, February 23, 2023 2:01 PM
> *To:* Michael Wenger <Michael.J.Wenger at ou.edu>
> *Cc:* eeglablist at sccn.ucsd.edu <eeglablist at sccn.ucsd.edu>
> *Subject:* Re: [Eeglablist] simple question: logic of using ICLABEL to
> reject components
>
> [EXTERNAL EMAIL ALERT]: Verify sender before opening links or attachments.
>
> ICLABEL compares component properties in your data (e.g., component scalp
> projection maps, power spectra) with datasets in its large training data
> (mainly datasets from our 20-yr history of applying ICA decomposition to
> EEG data at SCCN). ICA decomposition can be negatively affected by several
> factors:  too little data, abundant non-brain noise in the data, etc. - and
> by the conditions under which it was recorded (e.g., Were participants
> moving? Were the electrodes securely placed? etc.).
>
> So the first thing I would suggest you look at is whether your data
> preprocessing and data rejection process was adequate for the data.
> Next, I would suggest you see how much of the data is accounted for by the
> labeled Brain components plus the non-brain components of known origin
> (e.g., Eye Movement components).
> Many times components rated as 'Other' by ICLabel account for quite little
> of the data (e.g., single-channel ICs) - the *de facto* decomposition noise
> subspace.
> If you perform PCA decomposition on your dataset and look at the values of
> the resulting eigenvalue spectrum, you will typically find that a large
> proportion of EEG data 'lives' in relatively few dimensions - ICA
> decompositions finds a basis for this subspace such that each basis element
> (Independent Component) is as temporally distinct from the others as
> possible -- and is thereby typically *functionally* distinct from others,
> And *spatially* distinct from others.
>
> Scott
>
> On Thu, Feb 23, 2023 at 12:56 PM Michael Wenger <Michael.J.Wenger at ou.edu>
> wrote:
>
> > All -- we've recently begun adding the use of ICLABEL to our
> pre-processing
> > pipeline. What we've found is that it labels only a minority of
> components
> > as brain activity, with the majority being labeled as "other." If we
> reject
> > the components labeled as non-brain activity, we end up rejecting the
> > majority of the components, and this seems wrong. Can anyone who has been
> > using ICLABEL comment on how to select components for removal? Thanks in
> > advance,
> >
> > -Michael
> > _______________________________________________
> > Eeglablist page:
> https://urldefense.com/v3/__https://nam11.safelinks.protection.outlook.com/?url=http*3A*2F*2Fsccn.ucsd.edu*2Feeglab*2Feeglabmail.html&data=05*7C01*7Cdgilbert*40siu.edu*7Cdc7810d99a1449af03ce08db15d8f8de*7Cd57a98e7744d43f9bc9108de1ff3710d*7C0*7C0*7C638127793852617383*7CUnknown*7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0*3D*7C3000*7C*7C*7C&sdata=oud8Lp9DDdUoqKRYRWZXTLzMyl*2FvPubAPqGv4oMK0fw*3D&reserved=0__;JSUlJSUlJSUlJSUlJSUlJSUlJSUlJQ!!Mih3wA!E3hjqLVUoSZo22tPY2jQjiUEuKeJqafNJ3EUqPPaCnahhutsEAbmnQ9EWTmtbOi8BgK2vEJgaxrAWLDsAPC7$ 
> > 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,
> https://urldefense.com/v3/__https://nam11.safelinks.protection.outlook.com/?url=http*3A*2F*2Fsccn.ucsd.edu*2F*scott&data=05*7C01*7Cdgilbert*40siu.edu*7Cdc7810d99a1449af03ce08db15d8f8de*7Cd57a98e7744d43f9bc9108de1ff3710d*7C0*7C0*7C638127793852617383*7CUnknown*7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0*3D*7C3000*7C*7C*7C&sdata=nqxK94tbS4myAbBMDd0eKnmzf8VV0QZiC2jKatgITZY*3D&reserved=0__;JSUlJX4lJSUlJSUlJSUlJSUlJSUl!!Mih3wA!E3hjqLVUoSZo22tPY2jQjiUEuKeJqafNJ3EUqPPaCnahhutsEAbmnQ9EWTmtbOi8BgK2vEJgaxrAWBbsVRUW$ 
> _______________________________________________
> Eeglablist page:
> https://urldefense.com/v3/__https://nam11.safelinks.protection.outlook.com/?url=http*3A*2F*2Fsccn.ucsd.edu*2Feeglab*2Feeglabmail.html&data=05*7C01*7Cdgilbert*40siu.edu*7Cdc7810d99a1449af03ce08db15d8f8de*7Cd57a98e7744d43f9bc9108de1ff3710d*7C0*7C0*7C638127793852617383*7CUnknown*7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0*3D*7C3000*7C*7C*7C&sdata=oud8Lp9DDdUoqKRYRWZXTLzMyl*2FvPubAPqGv4oMK0fw*3D&reserved=0__;JSUlJSUlJSUlJSUlJSUlJSUlJSUlJQ!!Mih3wA!E3hjqLVUoSZo22tPY2jQjiUEuKeJqafNJ3EUqPPaCnahhutsEAbmnQ9EWTmtbOi8BgK2vEJgaxrAWLDsAPC7$ 
> 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