Medical Image Segmentation Mask Review Tool

This project provides an automated tool for reviewing and verifying segmentation masks used for AI training in medical imaging. It checks for data consistency, mask presence, and volume information. The tool updates a reference Excel file and generates detailed comparison reports.

Installation

OS X & Linux:

pip install -r requirements.txt

Windows:

pip install -r requirements.txt

Dependencies are listed in the requirements.txt file, including:

et_xmlfile==2.0.0
nibabel==5.3.2
numpy==2.2.1
openpyxl==3.1.5
packaging==24.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.17.0
typing_extensions==4.12.2
tzdata==2024.2

Ensure you have Python 3.8 or newer installed.

Usage Example

1. Place your .nii.gz medical image files in the img folder.
2. Place segmentation masks in the mask folder, each inside a subfolder named by the corresponding case ID.
3. Ensure a reference Excel file data.xlsx is present.
4. Run the script:

python AI_data_checker.py

This will process the data, update data.xlsx, and generate volume_analysis_results.xlsx with detailed reports.

More examples and usage details are available in the Wiki.

Development Setup

Install all development dependencies and run tests:

make install
npm test

Release History

• 1.0.0
  • Initial release with core features for mask verification and volume analysis

Meta

Soyoung Lim – [email protected]

Distributed under the MIT license. See LICENSE for more information.

https://github.com/imsso-bmed/AI_mask_checker

Contributing

1. Fork the repository (https://github.com/imsso-bmed/AI_mask_checker/fork).
2. Create a new branch (git checkout -b feature/fooBar).
3. Commit your changes (git commit -am 'Add some fooBar').
4. Push to the branch (git push origin feature/fooBar).
5. Create a new Pull Request.