RAS⁴DG:Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis

Qiang Qiao¹, Wenyu Wang¹, Meixia Qu¹, Kun Su¹, Bin Jiang¹, Qiang Guo²

¹ Shandong University, ² Shandong University of Finance and Economics

🏃‍♂️ Getting Started

Download the DATASETS for Atlases, FeTA 2021, DRIVE, IOSTAR, [LES-AV](https://figshare.com/articles/dataset/LES-AV dataset/11857698/1).

Place the DATASETS as follows:

⚒️ Installation

prerequisites: python>=3.8, CUDA>=11.3, and torch>=1.12.0.

Install with conda and pip:

conda create -n ras4dg python==3.8
conda activate ras4dg
conda install pytorch==1.12.0 torchvision==0.13.0 torchaudio==0.12.0 cudatoolkit=11.3 -c pytorch
pip install -r requirements.txt

Citation

@InProceedings{Qiao_2024_RAS4DG,
    author    = {Qiao, Qiang and Wang, Wenyu and Qu Meixia and Su Kun and Jiang Bin and Guo Qiang},
    title     = {Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis},
    booktitle = {International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)},
    year      = {2024},
}