Official repository for "Classification of Multi-Parametric Body MRI Series Using Deep Learning".
You may need Conda environment. You can download Anaconda from this link. Then, please run:
conda env create –f mriclassifier_env.yml
conda activate mriclassifier
This code runs using NIFTI (.nii.gz) files. Please put your NIFTI files into ./data. For preprocessing data, please run:
python data_preprocessing.py
Then, the processed data will be saved in ./data/preprocessed.
To train our model, run the following command:
sh train.sh
The checkpoints of the model will be saved in ./checkpoint/.
To test the trained our model, run:
sh test.sh
The results of the MRI classification such as the confusion matrix will be saved in ./results.