This repository is an official Keras implementation of the paper "CRF-EfficientUNet: an improved UNet framework for polyp segmentation in colonoscopy images with combined asymmetric loss function and CRF-RNN layer" paper from IEEE Acess 2021.
-
Linux or OSX
-
NVIDIA GPU + CUDA CuDNN (CPU mode and CUDA without CuDNN may work with minimal modification, but untested)
-
tensorflow==1.13.1
-
numpy==1.18.5
-
Keras==2.2.4
-
opencv-python==4.3.0
If you find our work useful in your research or publication, please cite our work:
@article{thanh2021crf,
title={CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer},
author={Thanh, Nguyen Chi and Long, Tran Quoc and Hong, Le Thi Thu},
journal={IEEE Access},
volume={9},
pages={156987--157001},
year={2021},
publisher={IEEE}
}