Skip to content

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.

Sign up for GitHub

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

Merged
neuronflow merged 7 commits into from
Nov 10, 2025
Merged

Document data requirements for PeTu preprocessing #23

Changes from 5 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
ceb22ae
Initial plan
Copilot Nov 8, 2025
2ba9702
Add Data Requirements section to README
Copilot Nov 8, 2025
eee7cfc
Clarify preprocessing: co-register to T1c then atlas space
Copilot Nov 8, 2025
d823d99
Use markdown syntax for hyperlinks
Copilot Nov 8, 2025
f516ee4
Use GitHub alert syntax for important note
Copilot Nov 8, 2025
f1eba3a
Update README to remove preprocessing package install
neuronflow Nov 8, 2025
05ec702
Update README.md
neuronflow Nov 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,22 @@ PeTu is a fully automated pipeline for segmenting pediatric brain tumors. It use
## Features


## Data Requirements

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 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.
Copy link
Contributor

@MarcelRosier MarcelRosier Nov 9, 2025

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?


We recommend using the [preprocessing package](https://github.com/BrainLesion/preprocessing), part of the [BrainLesion Suite](https://github.com/BrainLesion), to design custom preprocessing pipelines tailored to your specific needs.
You can install the package with:

```bash
pip install brainles-preprocessing
```

## Installation

With a Python 3.10+ environment, you can install `petu` directly from [PyPI](https://pypi.org/project/petu/):
Expand Down