Clustintime: a toolbox for spatio-temporal clustering of fMRI data

Title

Clustintime: a toolbox for spatio-temporal clustering of fMRI data

Leaders

Cris Tobías (@cristobias)

Collaborators

No response

Brainhack Global 2023 Event

Brainhack Donostia

Project Description

• What are you doing, for whom, and why? This project is a toolbox that allows researchers in neuroimage to apply clustering methods to fMRI data on the spatiotemporal domain. Conventional methods of clustering in fMRI allow to see spatial patterns but cannot describe the temporal dynamics of functional activity.

• What makes your project special and exciting? Providing a tool for researchers interested in analyzing brain patterns in uncontrolled fmri experiments or clinical settings is a necessity that has not been covered yet and that could be done through clustintime.

• How to get started? Clustintime has been under development for a few years and has been already tried on data from individual epileptic patients, the skeletton of the project is already done, now there is need to transform it into a proper toolbox to release the first version of the software.

• Where to find key resources? The project already has its repository on GitHub (https://github.com/Cristina-Tobias/clustintime ) and a public fMRI data will be used for testing.

Link to project repository/sources

https://github.com/Cristina-Tobias/clustintime

Goals for Brainhack Global

Create integration testing suite/framework Create CI/CD pipeline Populate CI/CD pipeline with checks

Release version 0.1.0

Create documentation Improve user experience of adding input Structure output messages

Release version 0.2.0

Introduce new features

• group analysis
• consensus clustering

Release version 1.0.0

Good first issues

Issue 1: Create integration testing suite/framework

• Find usable data
• Execute each algorithm in a reproducible way (fix seed)
• Integrate into CI/CD pipeline

Issue 2: Create CI/CD pipeline

• Find free tier provider
• e.g., github actions, circleci

Issue 3: Populate CI/CD pipeline with checks

• Pylint, flake8, black, isort, …

Communication channels

https://mattermost.brainhack.org/brainhack/channels/clustintime

Skills

• Git: intermediate
• Python: advanced (only for those that want to develop new methods)
• Markdown: intermediate
• Bash: begginer

Onboarding documentation

No response

What will participants learn?

• Experience on collaborating with git
• Experience on how to design and build an open-source library
• Different methods of fMRI visualization
• Unsupervised machine learning methods for fMRI

Data to use

No response

Number of collaborators

more

Credit to collaborators

Project contributors will be acknowledged as contributors in GitHub, credit will also be given in future publications (if any) to those who make a major contribution to the toolbox.

Image

Leave this text if you don’t have an image yet.

Type

coding_methods, documentation, method_development, pipeline_development

Development status

1_basic structure

Topic

data_visualisation, machine_learning

Tools

other

Programming language

Python

Modalities

fMRI

Git skills

2_branches_PRs

Anything else?

No response

Things to do after the project is submitted and ready to review.

• Add a comment below the main post of your issue saying: Hi @brainhackorg/project-monitors my project is ready!
• Twitter-sized summary of your project pitch.