Cargando…

Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation

The latest medical image segmentation methods uses UNet and transformer structures with great success. Multiscale feature fusion is one of the important factors affecting the accuracy of medical image segmentation. Existing transformer-based UNet methods do not comprehensively explore multiscale fea...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Shaolong, Qiu, Changzhen, Yang, Weiping, Zhang, Zhiyong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9145221/
https://www.ncbi.nlm.nih.gov/pubmed/35632229
http://dx.doi.org/10.3390/s22103820
_version_ 1784716237645807616
author Chen, Shaolong
Qiu, Changzhen
Yang, Weiping
Zhang, Zhiyong
author_facet Chen, Shaolong
Qiu, Changzhen
Yang, Weiping
Zhang, Zhiyong
author_sort Chen, Shaolong
collection PubMed
description The latest medical image segmentation methods uses UNet and transformer structures with great success. Multiscale feature fusion is one of the important factors affecting the accuracy of medical image segmentation. Existing transformer-based UNet methods do not comprehensively explore multiscale feature fusion, and there is still much room for improvement. In this paper, we propose a novel multiresolution aggregation transformer UNet (MRA-TUNet) based on multiscale input and coordinate attention for medical image segmentation. It realizes multiresolution aggregation from the following two aspects: (1) On the input side, a multiresolution aggregation module is used to fuse the input image information of different resolutions, which enhances the input features of the network. (2) On the output side, an output feature selection module is used to fuse the output information of different scales to better extract coarse-grained information and fine-grained information. We try to introduce a coordinate attention structure for the first time to further improve the segmentation performance. We compare with state-of-the-art medical image segmentation methods on the automated cardiac diagnosis challenge and the 2018 atrial segmentation challenge. Our method achieved average dice score of 0.911 for right ventricle (RV), 0.890 for myocardium (Myo), 0.961 for left ventricle (LV), and 0.923 for left atrium (LA). The experimental results on two datasets show that our method outperforms eight state-of-the-art medical image segmentation methods in dice score, precision, and recall.
format Online
Article
Text
id pubmed-9145221
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91452212022-05-29 Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation Chen, Shaolong Qiu, Changzhen Yang, Weiping Zhang, Zhiyong Sensors (Basel) Communication The latest medical image segmentation methods uses UNet and transformer structures with great success. Multiscale feature fusion is one of the important factors affecting the accuracy of medical image segmentation. Existing transformer-based UNet methods do not comprehensively explore multiscale feature fusion, and there is still much room for improvement. In this paper, we propose a novel multiresolution aggregation transformer UNet (MRA-TUNet) based on multiscale input and coordinate attention for medical image segmentation. It realizes multiresolution aggregation from the following two aspects: (1) On the input side, a multiresolution aggregation module is used to fuse the input image information of different resolutions, which enhances the input features of the network. (2) On the output side, an output feature selection module is used to fuse the output information of different scales to better extract coarse-grained information and fine-grained information. We try to introduce a coordinate attention structure for the first time to further improve the segmentation performance. We compare with state-of-the-art medical image segmentation methods on the automated cardiac diagnosis challenge and the 2018 atrial segmentation challenge. Our method achieved average dice score of 0.911 for right ventricle (RV), 0.890 for myocardium (Myo), 0.961 for left ventricle (LV), and 0.923 for left atrium (LA). The experimental results on two datasets show that our method outperforms eight state-of-the-art medical image segmentation methods in dice score, precision, and recall. MDPI 2022-05-18 /pmc/articles/PMC9145221/ /pubmed/35632229 http://dx.doi.org/10.3390/s22103820 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Communication
Chen, Shaolong
Qiu, Changzhen
Yang, Weiping
Zhang, Zhiyong
Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation
title Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation
title_full Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation
title_fullStr Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation
title_full_unstemmed Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation
title_short Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation
title_sort multiresolution aggregation transformer unet based on multiscale input and coordinate attention for medical image segmentation
topic Communication
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9145221/
https://www.ncbi.nlm.nih.gov/pubmed/35632229
http://dx.doi.org/10.3390/s22103820
work_keys_str_mv AT chenshaolong multiresolutionaggregationtransformerunetbasedonmultiscaleinputandcoordinateattentionformedicalimagesegmentation
AT qiuchangzhen multiresolutionaggregationtransformerunetbasedonmultiscaleinputandcoordinateattentionformedicalimagesegmentation
AT yangweiping multiresolutionaggregationtransformerunetbasedonmultiscaleinputandcoordinateattentionformedicalimagesegmentation
AT zhangzhiyong multiresolutionaggregationtransformerunetbasedonmultiscaleinputandcoordinateattentionformedicalimagesegmentation