This is the source code for the paper, "A Multimodal Feature Distillation with CNN-Transformer Network for Brain Tumor Segmentation with Incomplete Modalities", of which I am the first author.
The Multimodal feature distillation with CNN-Transformer hybrid network for incomplete multimodal brain tumor Segmentation (MCTSeg) model configuration (i.e., network construction) file is net.py in the directory [.\model]. To train and test by running [train.py] and [test.py].
Recommended dependencies:
Python <= 3.8
Torch <= 1.7.1
CUDA <= 11.1
Datasets Brain Tumor Segmentation (BraTS) Challenge 2018/2020 (BraTS2018/BraTS2020).
Many utility codes of our project base on the codes of PyTorch-3DUNet, mmFormer, Vision Transformer PyTorch, and Factor-Transfer-pytorch repositories.