This paper proposes a novel U-Net variant using stacked dilated convolutions for medical image segmentation (SDU-Net). SDU-Net adopts the architecture of vanilla U-Net with modifications in the encoder and decoder operations (an operation indicates all the processing for feature maps of the same resolution). Unlike vanilla U-Net which incorporates two standard convolutions in each encoder/decoder operation, SDU-Net uses one standard convolution followed by multiple dilated convolutions and concatenates all dilated convolution outputs as input to the next operation. Experiments showed that SDU-Net outperformed vanilla U-Net, attention U-Net (AttU-Net), and recurrent residual U-Net (R2U-Net) in all four tested segmentation tasks while using parameters around 40% of vanilla U-Net's, 17% of AttU-Net's, and 15% of R2U-Net's.
@article{arxiv.2004.03466,
title = {U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation},
author = {Shuhang Wang and Szu-Yeu Hu and Eugene Cheah and Xiaohong Wang and Jingchao Wang and Lei Chen and Masoud Baikpour and Arinc Ozturk and Qian Li and Shinn-Huey Chou and Constance D. Lehman and Viksit Kumar and Anthony Samir},
journal= {arXiv preprint arXiv:2004.03466},
year = {2020}
}