Now we have open-sourced the pre-processing, training, inference, and metrics computation codes.
SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation
https://arxiv.org/abs/2401.13560
Our advantage in speed and memory.
If you have any questions about our project, please feel free to contact us by email at zxing565@connect.hkust-gz.edu.cn or via WeChat at 18340097191. Furthermore, the data underlying this article will be shared on reasonable request to gaof57@mail.sysu.edu.cn.
Clone this repository and navigate to the root directory of the project.
git clone https://github.com/ge-xing/SegMamba.git
cd SegMambacd causal-conv1d
python setup.py installcd mamba
python setup.py installpip install monaipython 0_inference.pyData is from https://arxiv.org/abs/2305.17033
Download from Baidu Disk https://pan.baidu.com/s/1C0FUHdDtWNaYWLtDDP9TnA?pwd=ty22提取码ty22
Download from OneDrive https://hkustgz-my.sharepoint.com/:f:/g/personal/zxing565_connect_hkust-gz_edu_cn/EqqaINbHRxREuIj0XGicY2EBv8hjwEFKgFOhF_Ub0mvENw?e=yTpE9B
In my setting, the data directory of BraTS2023 is : "./data/raw_data/BraTS2023/ASNR-MICCAI-BraTS2023-GLI-Challenge-TrainingData/"
First, we need to run the rename process.
python 1_rename_mri_data.pyThen, we need to run the pre-processing code to do resample, normalization, and crop processes.
python 2_preprocessing_mri.pyAfter pre-processing, the data structure will be in this format:
When the pre-processing process is done, we can train our model.
We mainly use the pre-processde data from last step: data_dir = "./data/fullres/train"
python 3_train.pyThe training logs and checkpoints are saved in: logdir = f"./logs/segmamba"
When we have trained our models, we can inference all the data in testing set.
python 4_predict.pyWhen this process is done, the prediction cases will be put in this path: save_path = "./prediction_results/segmamba"
We can obtain the Dice score and HD95 on each segmentation target (WT, TC, ET for BraTS2023 dataset) using this code:
python 5_compute_metrics.py --pred_name="segmamba"Many thanks for these repos for their great contribution!
https://github.com/MIC-DKFZ/nnUNet