Competition Page and Leaderboard

Team: Just4Fun

Contact: [email protected]

Source Code: https://github.com/quqixun/BioMassters

• S1 and S2 features and AGBM labels were carefully preprocessed according to statistics of training data. See code in process.py and ./libs/process for details.
• Training data was splited into 5 folds for cross validation in split.py.
• Processed S1 and S2 features were concatenated to 3D tensor in shape [B, 15, 12, 256, 256] as input, targets were AGBM labels in shape [B, 1, 256, 256].
• We applied Swin UNETR with the attention from Swin Transformer V2 as the regression model. In ./libs/models, Swin UNETR was adapted from the implementation by MONAI project.
• In training steps, Swin UNETR was optimized by weighted MAE and SSIM. RMSE of validation data was used to select the best model.
• We trained Swin UNETR using 5 folds, and got 5 models.
• For each testing sample, the average of 5 predictions was the final result.

• Ubuntu 20.04 LTS
• CUDA 11.3 or later
• Any GPU with at least 40Gb VRAM for training
• Any GPU with at least 8Gb VRAM for predicting
• At least 16Gb RAM for training and predicting
• Minconda or Anaconda for Python environment management

# create environment
conda create --name biomassters python=3.9
conda activate biomassters

# install packages
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113
pip install -r requirements.txt

• Download metadata from DATA DOWNLOAD page, and put all files in ./data/information as following structure:

./data/information
├── biomassters-download-instructions.txt  # Instructions to download satellite images and AGBM data
├── features_metadata.csv                  # Metadata for satellite images
└── train_agbm_metadata.csv                # Metadata for training set AGBM tifs

• Download image data by running ./scripts/download.sh, data is saved in ./data/source:

./data/source
├── test
│   ├── aa5e092e
│   │   ├── S1
│   │   │   ├── aa5e092e_S1_00.tif
│   │   │   ├── ...
│   │   │   └── aa5e092e_S1_11.tif
│   │   └── S2
│   │       ├── aa5e092e_S2_00.tif
│   │       ├── ...
│   │       └── aa5e092e_S2_11.tif
|   ├── ...
│   └── fff812c0
└── train
    ├── aa018d7b
    ├── ...
    └── fff05995

• Calculate statistics for normalization and split dataset into 5 folds by running ./scripts/process.sh:

./data/source
├── plot              # plot of data distribution
├── splits.pkl        # 5 folds for cross validation
├── stats_log2.pkl    # statistics of log2 transformed dataset
├── stats_plain.pkl   # statistics of original dataset
├── test
└── train

This step takes about 80Gb RAM. You don't have to run the above script again since all outputs can be found in ./data/source.

Train model with arguments (see ./scripts/train.sh):

• data_root: root directory of training dataset
• exp_root: root directory to save checkpoints, logs and models
• config_file: file path of configurations
• process_method: processing method to calculate statistics, log2 or plain, default is plain
• folds: list of folds, separated by ,

device=0
process=plain
folds=0,1,2,3,4
data_root=./data/source
config_file=./configs/swin_unetr/exp1.yaml

CUDA_VISIBLE_DEVICES=$device \
python train.py              \
    --data_root      $data_root             \
    --exp_root       ./experiments/$process \
    --config_file    $config_file           \
    --process_method $process               \
    --folds          $folds

Models and logs will be saved in ./experiments/plain/swin_unetr/exp1.

Training on 5 folds will take about 1 week if only one GPU is available.

If you have 5 GPUs, you can run each fold training on each GPU, and it will take less than 2 days.

You can download the trained model from Baidu Disc (code:jarp).

Make predictions with almost the same arguments as training (see ./scripts/predict.sh):

• data_root: root directory of training dataset
• exp_root: root directory of checkpoints, logs and models
• output_root: root directory to save predictions
• config_file: file path of configurations
• process_method: processing method to calculate statistics, log2 or plain, default is plain
• folds: list of folds, separated by ,
• apply_tta: if apply test-time augmentation, default is False

device=0
process=plain
folds=0,1,2,3,4
apply_tta=false
data_root=./data/source
config_file=./configs/swin_unetr/exp1.yaml

CUDA_VISIBLE_DEVICES=$device \
python predict.py            \
    --data_root      $data_root             \
    --exp_root       ./experiments/$process \
    --output_root    ./predictions/$process \
    --config_file    $config_file           \
    --process_method $process               \
    --folds          $folds                 \
    --apply_tta      $apply_tta

Predictions will be saved in ./predictions/plain/swin_unetr/exp1/folds_0-1-2-3-4.

Predicting testing samples on 5 folds and calculating the average will take about 30 minutes.

You can download the submission from Baidu Disc (code:w61j).

Metrics of submitted models and predictions on validation dataset and testing dataset.

• Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images. [Paper]
• Swin Transformer V2: Scaling Up Capacity and Resolution. [Paper , Code]
• Implementation of Swin UNETR by MONAI project. [Code]
• Differentiable structure similarity metric. [Code]

• MIT License