🧠 BrainLesion Suite

BrainLesion Suite (BLS) is a modular and open-source framework for brain lesion image analysis in Python. Developed by an international consortium of researchers, BLS enables efficient, reproducible, and customizable pipelines for processing and analyzing multi-modal brain image data.

Whether you're a radiologist, researcher, data scientist, or clinician, BLS empowers you to build robust workflows from raw data organization to segmentation, synthesis, and evaluation.

🔬 Designed for flexibility. Built for science. Made for brains.

---

🔧 Key Features

• Modular Pipeline Design: Combine individual components to fit your task.
• Cross-Platform: Compatible with Linux, Windows, and macOS.
• Preprocessing Suite: Registration, brain extraction, defacing, normalization.
• Multi-Disease Support: Glioma, metastasis, pediatric tumors, and more.
• State-of-the-Art Models: Integrates top-performing BraTS challenge models.
• Quality Estimation & Evaluation: Evaluate performance with lesion-wise metrics using tools like DQE and Panoptica.

---

🧩 Core Modules

⚠️ Note: The list below highlights key modules but may not always reflect the latest additions. Visit the BrainLesion GitHub organization for the full and most recent overview.

Module	Description
preprocessing	Co-registration, atlas alignment, skull-stripping, defacing, intensity normalization
modsort	Interactive MRI sequence sorter with drag-and-drop interface
BraTS	Orchestrator for synthesis, inpainting, and segmentation with BraTS models
AURORA	Adaptive metastasis segmentation in standardized MRI space
GlioMODA	Modality-aware glioma segmentation using dynamic nnU-Net inference
PeTu	Pediatric tumor segmentation with 3D nnU-Net models
deep_quality_estimation	Predicts segmentation quality with DL-based human surrogate models
panoptica	Instance-level segmentation evaluation framework
tutorials	End-to-end pipelines and example notebooks for common use cases

---

💡 Submit Your Module or Project

BLS is a community-driven initiative.

We actively invite external researchers and developers to contribute their own tools, models, or processing pipelines as part of the BLS ecosystem. If you have a brain imaging tool you'd like to share, we encourage you to:

1. Open an issue on our main GitHub organization page,
2. Or contact the maintainers directly.

Together, we can build a unified infrastructure for reproducible and modular brain lesion analysis.

---

🧪 Applications

• Lesion segmentation: glioma, metastasis, pediatric tumors, stroke, MS
• Imaging biomarker extraction and radiomics
• Longitudinal MRI analysis
• Tumor growth modeling
• Generative harmonization for missing modalities
• Quality control in large-scale studies

---

📚 Documentation & Tutorials

Each module comes with its own README and documentation. For complete usage examples, visit the:

📘 BrainLesion Suite Tutorials

---

🧬 Citing BrainLesion Suite

Important

If you use any module of the BrainLesion Suite, including brainles-preprocessing, in your research, please cite the suite to support its development!

Kofler, F., Rosier, M., Astaraki, M., Möller, H., Mekki, I. I., Buchner, J. A., Schmick, A., Pfiffer, A., Oswald, E., Zimmer, L., Rosa, E. de la, Pati, S., Canisius, J., Piffer, A., Baid, U., Valizadeh, M., Linardos, A., Peeken, J. C., Shit, S., … Menze, B. (2025). BrainLesion Suite: A Flexible and User-Friendly Framework for Modular Brain Lesion Image Analysis arXiv preprint arXiv:2507.09036

@misc{kofler2025brainlesionsuiteflexibleuserfriendly,
      title={BrainLesion Suite: A Flexible and User-Friendly Framework for Modular Brain Lesion Image Analysis}, 
      author={Florian Kofler and Marcel Rosier and Mehdi Astaraki and Hendrik Möller and Ilhem Isra Mekki and Josef A. Buchner and Anton Schmick and Arianna Pfiffer and Eva Oswald and Lucas Zimmer and Ezequiel de la Rosa and Sarthak Pati and Julian Canisius and Arianna Piffer and Ujjwal Baid and Mahyar Valizadeh and Akis Linardos and Jan C. Peeken and Suprosanna Shit and Felix Steinbauer and Daniel Rueckert and Rolf Heckemann and Spyridon Bakas and Jan Kirschke and Constantin von See and Ivan Ezhov and Marie Piraud and Benedikt Wiestler and Bjoern Menze},
      year={2025},
      eprint={2507.09036},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.09036}, 
}

🤝 Contributing

We welcome contributions! Please check the contributing guidelines in each repository and feel free to open issues or pull requests.

---

🛡 License

Apache License 2.0 — Open science for open minds.

---