RISE Tutorials is a collaborative, open-source educational platform developed by the RISE-MICCAI initiative. Our mission is to democratize access to high-quality tutorials in medical image analysis and AI.
Explore the live book 👉 RISE Tutorials Website
This repository hosts the source code and content for the RISE Tutorials Book, a continuously evolving resource built with Jupyter Book.
It’s designed to be:
- 🔁 Modular – Each tutorial is independent and easy to expand
- 💻 Interactive – Code, markdown, figures, and widgets in one place
- 🌍 Community-driven – Contributions from researchers, students, and professionals worldwide
Our tutorials span a wide range of foundational and advanced topics, such as:
- 🏥 Handling medical datasets (DICOM, NIfTI, etc.)
- 📑 Cleaning, labeling, and preprocessing data
⚠️ Avoiding pitfalls like data leakage and overfitting- 📊 Using evaluation metrics (AUROC, sensitivity, specificity)
- ⚖️ Dealing with class imbalance and rare disease data
- 🧠 Building and validating classification/segmentation models
- 🔍 Applying model explainability tools (e.g., saliency maps, Grad-CAM)
- 🧪 Ensuring reproducibility and robust validation
…and more to come!
Follow these steps to build and run the book locally:
# 1. Clone the repository
git clone https://github.com/YouvenZ/rise_tutorials.git
cd rise_tutorials
# 2. Install required dependencies (use a virtual environment if possible)
pip install -r requirements.txt
# 3. (Optional) Edit content in the `rise_tutorials/` directory
# 4. Clean previous builds
jupyter-book clean rise_tutorials/
# 5. Build the HTML book
jupyter-book build rise_tutorials/📁 The rendered site will appear in: rise_tutorials/_build/html/
You can publish the book using:
- GitHub Pages (default)
- GitLab Pages
- Netlify
For GitHub CI/CD deployment, we use cookiecutter-jupyter-book, which includes GitHub Actions workflows to auto-deploy on push.
Refer to Jupyter Book’s official deployment guide for full instructions.
Here’s a preview of our current and planned tutorials:
| Tutorial | Description | Status |
|---|---|---|
| Medical image classification | What are the best practices, a beginner guide | ✅ Completed |
| Data Preprocessing 101 | Cleaning, normalizing, and splitting | 🚧 In progress |
| Evaluation Metrics in Medical AI | AUROC, sensitivity, etc. | 🚧 In progress |
| Explainability with Grad-CAM | Model interpretation | 🔜 Planned |
| Handling Class Imbalance | SMOTE, weighting, and tricks | 🔜 Planned |
🗂️ Want to suggest a topic? Submit here »
We’d love to have your contributions — whether you’re a student, researcher, or industry expert!
- Add a new tutorial (e.g., segmentation, image registration)
- Improve content clarity, fix typos, or correct code
- Translate existing content to other languages
- Submit feedback, bug reports, or feature ideas
📝 Contributor Sign-Up Form
👥 View our Contributors
Stay connected and grow with us:
- 💬 Discussion forum (coming soon!)
- 💡 Join our Slack/Discord (planned – DM us to get early access)
- 📅 Events & workshops at MICCAI
- 🗣️ Feedback and mentorship welcome!
All content is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
You are free to share and adapt the material, with proper attribution.
For code, please refer to individual notebooks/scripts for license specifics.
If you use RISE Tutorials in your research or teaching, please cite us:
@misc{rise_tutorials,
author = {MICCAI-RISE Community},
title = {RISE Tutorials: Open Educational Resources for Medical Imaging AI},
year = {2025},
howpublished = {\url{https://rise-miccai.github.io/rise-tutorials-website/}},
note = {Version 1.0}
}We are committed to fostering a welcoming and respectful community.
Please review our Code of Conduct before participating.
RISE Tutorials is made possible by:
- 🛠️ Jupyter Book
- 💡 Executable Books Project
- 🤖 Contributions from the global MICCAI & RISE community
We aim to:
- Publish a comprehensive tutorial book for MICCAI attendees and researchers
- Support community learning through hybrid events
- Foster collaborative authorship in scientific education
Be part of something bigger. Let’s build the future of medical AI education — together.