The code for the work SwinPA-Net: Swin Transformer-Based Multiscale Feature Pyramid Aggregation Network for Medical Image Segmentation
Please prepare an virtual environment with Python 3.6, and then use the command "pip install -r requirements.txt" for the dependencies.
Polyp datasets - we adopted the division method in PraNet
ISIC 2018 dataset
The Pretrained models on ImageNet-1K (Swin-T-IN1K, Swin-S-IN1K, Swin-B-IN1K) and ImageNet-22K (Swin-B-IN22K, Swin-L-IN22K) are provided by Swin Transformer.
python3 Train.py
python3 Test.py
H. Du, J. Wang, M. Liu, Y. Wang and E. Meijering, "SwinPA-Net: Swin Transformer-Based Multiscale Feature Pyramid Aggregation Network for Medical Image Segmentation," in IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 4, pp. 5355-5366, April 2024, doi: 10.1109/TNNLS.2022.3204090.
@ARTICLE{9895210,
author={Du, Hao and Wang, Jiazheng and Liu, Min and Wang, Yaonan and Meijering, Erik},
journal={IEEE Transactions on Neural Networks and Learning Systems},
title={SwinPA-Net: Swin Transformer-Based Multiscale Feature Pyramid Aggregation Network for Medical Image Segmentation},
year={2024},
volume={35},
number={4},
pages={5355-5366},
keywords={Image segmentation;Transformers;Lesions;Task analysis;Monte Carlo methods;Semantics;Medical diagnostic imaging;Dense multiplicative connection (DMC) module;local pyramid attention (LPA) module;medical image segmentation},
doi={10.1109/TNNLS.2022.3204090}}