-
Notifications
You must be signed in to change notification settings - Fork 1
Document data requirements for PeTu preprocessing #23
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
Conversation
Co-authored-by: neuronflow <7048826+neuronflow@users.noreply.github.com>
neuronflow
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@copilot please adress changes
README.md
Outdated
|
|
||
| PeTu is trained on pediatric brain MRI data from the Children's Hospital Zurich (Kispi), including cases with optic glioma affecting the optic nerve. | ||
|
|
||
| The model expects co-registered multi-parametric MRI scans (T1c, T1n, T2w, T2f) that have been registered to the SRI-24 brain atlas (template). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
scans should be co-registered to T1c and then brought into atlas space.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Updated the line to clarify that scans should be co-registered to T1c and then brought into SRI-24 atlas space (eee7cfc).
Co-authored-by: neuronflow <7048826+neuronflow@users.noreply.github.com>
README.md
Outdated
|
|
||
| **Important:** Since PeTu handles optic gliomas affecting the optic nerve, input data should be **raw brain scans without defacing or skull-stripping** to preserve critical anatomical structures. However, it may be worth experimenting with skull-stripped (BET) or defaced brain scans depending on your specific use case. | ||
|
|
||
| We recommend using the <a href="https://github.com/BrainLesion/preprocessing">preprocessing package</a>, part of the <a href="https://github.com/BrainLesion">BrainLesion Suite</a>, to design custom preprocessing pipelines tailored to your specific needs. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
use markdown syntac for hyperlinks
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@copilot please adress comments
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Converted HTML <a> tags to markdown syntax [text](url) (d823d99).
Co-authored-by: neuronflow <7048826+neuronflow@users.noreply.github.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR adds a new "Data Requirements" section to the README, providing essential information about the training data, expected input formats, and preprocessing recommendations for users of the PeTu pediatric brain tumor segmentation tool.
- Added comprehensive data requirements section explaining training data source, expected MRI modalities, and preprocessing needs
- Included important guidance about using raw brain scans for optic glioma cases
- Added reference to the BrainLesion preprocessing package with installation instructions
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
neuronflow
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@copilot please implement changes based on comments
README.md
Outdated
|
|
||
| The model expects multi-parametric MRI scans (T1c, T1n, T2w, T2f) that are co-registered to T1c and then brought into SRI-24 brain atlas space. | ||
|
|
||
| **Important:** Since PeTu handles optic gliomas affecting the optic nerve, input data should be **raw brain scans without defacing or skull-stripping** to preserve critical anatomical structures. However, it may be worth experimenting with skull-stripped (BET) or defaced brain scans depending on your specific use case. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@copilot rather use this syntax
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changed to use GitHub alert syntax > [!IMPORTANT] instead of bold text (f516ee4).
Co-authored-by: neuronflow <7048826+neuronflow@users.noreply.github.com>
Removed installation instructions for the preprocessing package.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
MarcelRosier
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
one comment, otherwise LGTM
README.md
Outdated
| The model expects multi-parametric MRI scans (T1c, T1n, T2w, T2f) that are co-registered to T1c and then brought into SRI-24 brain atlas space. | ||
|
|
||
| > [!IMPORTANT] | ||
| >Since PeTu handles optic gliomas affecting the optic nerve, input data should be **raw brain scans without defacing or skull-stripping** to preserve critical anatomical structures. However, it may be worth experimenting with skull-stripped (BET) or defaced brain scans depending on your specific use case. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
raw might sound a bit misleading since we do expect registration?
Document Data Requirements
Summary
Successfully documented data requirements with clear preprocessing steps:
This addresses issue #21 and clarifies the exact preprocessing procedure for pediatric brain data.
Original prompt
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.