https://github.com/hilab-git/csal-3d
[MICCAI 2025] Official code for CSAL-3D
https://github.com/hilab-git/csal-3d
Last synced: 8 months ago
JSON representation
[MICCAI 2025] Official code for CSAL-3D
- Host: GitHub
- URL: https://github.com/hilab-git/csal-3d
- Owner: HiLab-git
- Created: 2025-06-25T06:24:04.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-08-28T03:28:00.000Z (8 months ago)
- Last Synced: 2025-08-28T10:29:41.546Z (8 months ago)
- Language: Python
- Homepage:
- Size: 972 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# [MICCAI 2025] CSAL-3D
This repository contains the official implementation of our paper:
**CSAL-3D: Cold-start Active Learning for 3D Medical Image Segmentation via SSL-driven Uncertainty-Reinforced Diversity Sampling**, for 28th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025, Early Accept).
## 📌 Overall Framework
The overall CSAL-3D pipeline consists of:
- A **CSAL-adapted Self-Supervised Learning (SSL)** framework for both 3D-aware feature extraction and uncertainty estimation.
- An **Ensemble-based Uncertainty Estimation** strategy to generate sample-level uncertainty scores.
- A **URDS (Uncertainty-Reinforced Diversity Sampling)** method that hierarchically combines diversity and uncertainty for one-shot sample selection.
## 📁 Dataset and Dependency
We evaluate our method on three publicly available 3D medical image segmentation datasets from the **Medical Segmentation Decathlon (MSD)**:
- **Brain Tumor (Task01_BrainTumour)** [MRI, multi-modality]
- **Heart (Task02_Heart)** [MRI]
- **Spleen (Task09_Spleen)** [CT]
- Datasets can be downloaded from the official MSD website:
👉 [http://medicaldecathlon.com/](http://medicaldecathlon.com/)
### Environment Setup
Python 3.8+ with PyTorch 2.3.1 and MONAI 1.3+.
## 🙏 Acknowledgement
Our codebase is built upon the excellent COLosSAL project (https://github.com/han-liu/COLosSAL), which provides a benchmark for Cold-Start Active Learning in 3D medical image segmentation.