U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation
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 res...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2020
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2004.03466 https://arxiv.org/abs/2004.03466 |
id |
ftdatacite:10.48550/arxiv.2004.03466 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2004.03466 2023-05-15T15:33:28+02:00 U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation Wang, Shuhang Hu, Szu-Yeu Cheah, Eugene Wang, Xiaohong Wang, Jingchao Chen, Lei Baikpour, Masoud Ozturk, Arinc Li, Qian Chou, Shinn-Huey Lehman, Constance D. Kumar, Viksit Samir, Anthony 2020 https://dx.doi.org/10.48550/arxiv.2004.03466 https://arxiv.org/abs/2004.03466 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Image and Video Processing eess.IV Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences Article CreativeWork article Preprint 2020 ftdatacite https://doi.org/10.48550/arxiv.2004.03466 2022-03-10T15:43:44Z 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. : 8 pages MICCAI Article in Journal/Newspaper Attu DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Image and Video Processing eess.IV Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences |
spellingShingle |
Image and Video Processing eess.IV Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences Wang, Shuhang Hu, Szu-Yeu Cheah, Eugene Wang, Xiaohong Wang, Jingchao Chen, Lei Baikpour, Masoud Ozturk, Arinc Li, Qian Chou, Shinn-Huey Lehman, Constance D. Kumar, Viksit Samir, Anthony U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation |
topic_facet |
Image and Video Processing eess.IV Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences |
description |
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. : 8 pages MICCAI |
format |
Article in Journal/Newspaper |
author |
Wang, Shuhang Hu, Szu-Yeu Cheah, Eugene Wang, Xiaohong Wang, Jingchao Chen, Lei Baikpour, Masoud Ozturk, Arinc Li, Qian Chou, Shinn-Huey Lehman, Constance D. Kumar, Viksit Samir, Anthony |
author_facet |
Wang, Shuhang Hu, Szu-Yeu Cheah, Eugene Wang, Xiaohong Wang, Jingchao Chen, Lei Baikpour, Masoud Ozturk, Arinc Li, Qian Chou, Shinn-Huey Lehman, Constance D. Kumar, Viksit Samir, Anthony |
author_sort |
Wang, Shuhang |
title |
U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation |
title_short |
U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation |
title_full |
U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation |
title_fullStr |
U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation |
title_full_unstemmed |
U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation |
title_sort |
u-net using stacked dilated convolutions for medical image segmentation |
publisher |
arXiv |
publishDate |
2020 |
url |
https://dx.doi.org/10.48550/arxiv.2004.03466 https://arxiv.org/abs/2004.03466 |
genre |
Attu |
genre_facet |
Attu |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2004.03466 |
_version_ |
1766364034244804608 |