<Machine Learning for Stroke Lesion Segmentation>

[leiliew]

Title

Machine Learning for Stroke Lesion Segmentation

Short description and the goals for the OHBM BrainHack

We'd love for people interested in machine learning for image segmentation to try out our stroke lesion segmentation challenge! It's built with the RAMP platform and meant to be a collaborative and educational way to get into new research areas. It has a starter kit for people to get familiar with some basic steps for creating a lesion segmentation algorithm, and learn about packages such as PyBIDS along the way. We just released it and hope people can find it useful to learn and work together on a complicated neuroimaging problem!

Link to the Project

https://ramp.studio/problems/stroke_lesions

Image for the OHBM brainhack website

https://drive.google.com/file/d/1TDsEzr1R2T8O49ryNMqwPVFHjoXDOhaC/view?usp=sharing

Project lead

Sook-Lei Liew, Github: leiliew, discord: sliew

Main Hub

Americas

Other Hub covered by the leaders

• Glasgow
• Asia / Pacific
• Europe / Middle East / Africa
• Americas

Skills

Familiarity with python/juptyer notebook

Recommended tutorials for new contributors

• Set up a brainhack friendly computing environment
• A introduction to Bash
• Python: Writing a script
• Python: Data analysis with Python
• Python: Visualisation
• Machine learning basics
• BIDS
• Machine learning for neuroimaging
• VCS: Using Git and Github
• VCS: Data management with Datalad
• Virtualization
• High Performance Computing: Oracle cloud resource

Good first issues

Test out the starter kit, see if you can run it and see if you can extend it to create new lesion segmentation solutions - we welcome any feedback :)

Twitter summary

A beginner-friendly intro to machine learning for stroke lesion segmentation with a tutorial/starter kit!

Short name for the Discord chat channel (~15 chars)

stroke-lesion-segmentation

Please read and follow the OHBM Code of Conduct

• I agree to follow the OHBM Code of Conduct during the hackathon

[djarecka]

Thank you for submitting the project! We have 35 projects right now, woohoo! But that means the projects pitches will have to be short. We will give you tomorrow 2 minutes to pitch your project, you can have one slide or no slides!
If you decide to use a slide, please include the link to the slide here.

And don't worry, you will still have more time to talk about your project during the BrainHack :-)

[leiliew]

Great! I won't be there since I'm virtual, but I pre-recorded a short intro to the project you can see here (it's less than 2 min!) https://drive.google.com/file/d/1LRSOeT9AicgYNWzlwD0NJoO7TW7vUF2G/view?usp=sharing. I've also included the slide with links here in case it's helpful! I'll be on discord during PST hours if there's any questions :) Cheers!
ML_for_Stroke_Lesion_Segmentation.pdf

[leiliew]

P.S. Brainhack is all about fun, collaborative learning & education, hence we wanted people to get to work together and try out our RAMP challenge! (And it might be a great one to do after the ML for neuroimaging tutorial?). BUT, if you are a more competitive type of person (and no judging if you are), you can also try out our MICCAI ISLES Challenge (http://www.isles-challenge.org/) or our Grand Challenge (https://atlas.grand-challenge.org/) with the same stroke data (http://fcon_1000.projects.nitrc.org/indi/retro/atlas.html)! Either way, happy hacking!