Automated evaluation of quality metrics for brain data using deep learning

dhritimandas commented 3 years ago

hi @ohbm/project-monitors: My project is ready!'

Project info

to automate the evaluation of quality metrics (such as snr, cnr, fwhm, etc.) for neuroimaging data using deep learning methods **Title**: **Brain-QC** **Project lead**: Dhritiman Das (@dhritimandas) @Hoda1394, @Aakanksha-Rana @satra **[Timezone](https://github.com/ohbm/hackathon2021/blob/master/.github/ISSUE_TEMPLATE/handbooks/projects.md#timezone)**: Eastern Time (UTC -04) **Description**: The goal of this project is to create an automated deep-learning based pipeline for evaluation of quality metrics for 3D brain imaging data and providing a decision on the quality and usability of the data. **Link to project**: https://github.com/neuronets/auto-qc **Mattermost handle**: @dhritiman @Hoda, @Aakanksha-Rana **Goals for the OHBM Brainhack** Create a dataset for benchmarking quality metrics: many open-access datasets are available via DataLad, OpenNeuro and https://sensein.github.io/open-data-processing/ the goal is to gather the dataset, organize them and prepare for further quality assessment. Pipeline development: develop automated, robust machine learning methods to assess image quality metrics for a given scan Develop tutorials: if a successful pipeline is developed, then create suitable tutorials for dissemination within and outside the community **Good first issues**: - the goal is to first organize a sample dataset (source: https://sensein.github.io/open-data-processing/) - once the data is finalized then create a prototype pipeline to evaluate the quality metrics (such as snr, cnr, fwhm, etc.) for a given 3D brain volume, display these metrics and provide a decision on the usability of the scans. - possible methods can include decision forests, supervised learning methods, bayesian networks, or self-supervised methods. - The goal of this project is to significantly accelerate the quality assessment of a given brain data for further analysis and processing tasks. Such a pipeline would be faster and provide an automated decision on quality as compared to existing quality tools such as mri-qc, visual-qc, qoala-t, etc. **Skills**: Python-confirmed MRI: FSL: beginner Nipype: beginner BIDS: beginner Git: 1 and most importantly, Enthusiasm: Expert Willingness to learn and collaborate: Expert **Chat channel**: https://mattermost.brainhack.org/brainhack/channels/hbmhack-brain_qc

Image for the OHBM brainhack website

Project submission

Submission checklist

Once the issue is submitted, please check items in this list as you add under 'Additional project info'

Please include the following above (all required):

[x] Link to your project: could be a code repository, a shared document, etc. See here
[x] Include your Mattermost handle (i.e. your username). If you do not have an account, please sign up here.
[x] Goals for the OHBM Brainhack: describe what you want to achieve during this brainhack. See here.
[x] Flesh out at least 2 "good first issues": those are tasks that do not require any prior knowledge about your project, could be defined as issues in a GitHub repository, or in a shared document, cf here.
[x] Skills: list skills that would be particularly suitable for your project. We ask you to include at least one non-coding skill, cf. here.
[x] Chat channel: A link to a chat channel that will be used during the OHBM Brainhack. This can be an existing channel or a new one. We recommend using the Brainhack space on mattermost, cf. here.
[x] Provide an image of your project for the OHBM brainhack website

You can also include information about (all optional):

[ ] Someone co-leading the project in the timeslot you have not selected to provide additional visibility.
[ ] Number of participants, cf. here
[ ] Twitter-size summary of your project pitch, cf. here
[ ] Set up a kanban board on your repository to better divide the work and keep track of things, cf here
[ ] Project snippet for the OHBM Brainhack website, cf. here

We would like to think about how you will credit and onboard new members to your project. We recommend reading references from this section. If you'd like to share your thoughts with future project participants, you can include information about (recommended):

[ ] Specify how will you acknowledge contributions (e.g. listing members on a contributing page).
[ ] Provide links to onboarding documents if you have some.

QMENTA has agreed to sponsor the event and provide computational resources through their platform.

[x] Get in touch with QMENTA through their Brain Innovation Hub Slack space, if you think your project would benefit from their support.

dhritimandas commented 3 years ago

project proposal for brain-qc during ohbm hackathon

tiborauer commented 3 years ago

Hi @dhritimandas, Thank you for your submission. To have it completed, you need to provide specific goals for this OHBM Brainhack and an image for the Brainhack website.

dhritimandas commented 3 years ago

revised. added goals and logo.

ohbm / hackathon2021