The codes for the work "U-MLLA: A Cognitive-Inspired Enhancement of Linear Attention for Medical Image Segmentation".

Ref: [MLLA Official Implementation]

• AMOS 22
• FLARE 22
• ATLAS
• WORD
• BTCV
• ACDC

Ref: nnUNet Detailed procedure: link

Please follow the above procedure from the scratch, you are not recommended use the preprocessed data from the other work directly, otherwise it would get the worse results.

• Please prepare an environment with python=3.9 and then use the command pip install -r requirements.txt for the dependencies.

• Run the train script on synapse dataset. The batch size we used is 48. If you do not have enough GPU memory, the bacth size can be reduced to 12 or 6 to save memory.

• Train

sh train.sh

• Test

sh test.sh

• SwinUnet
• MLLA