Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

K-means clustering #9

Open
wby920920 opened this issue Dec 5, 2021 · 2 comments
Open

K-means clustering #9

wby920920 opened this issue Dec 5, 2021 · 2 comments

Comments

@wby920920
Copy link

Hello, can you explain the meaning of the resting state cluster diagram, why the ratio is greater than 1? How are DMN and other networks determined? Actually, I just don’t understand Figure 3 and Figure 6

@egyptdj
Copy link
Owner

egyptdj commented Dec 7, 2021

The k-means clustering model is trained with uniformly sampled FC matrices across time, and inferred with attended FC matrices within a subject.
There are three ratios provided in the paper, which are (i) female attended over uniform sampled, (ii) male attended over uniform sampled, and the (iii) (i) over (ii). The ratio (i) represents the clusters that the model attended more than by chance for female subjects, and the ratio (ii) represents same thing for male subjects. Accordingly, the ratio (iii) represents the clusters that the model attended more for female subjects than the male subjects.
If a certain pattern of FC connectivity was attended by the model more frequently for female subjects than for male subjects, then the cluster representing the pattern can have ratio (iii) over 1.0.

@wby920920
Copy link
Author

Why are the ratios in (1) and (2) greater than 1?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants