CPFTransformer: transformer fusion context pyramid medical image segmentation network
IntroductionThe application of U-shaped convolutional neural network (CNN) methods in medical image segmentation tasks has yielded impressive results. However, this structure’s single-level context information extraction capability can lead to problems such as boundary blurring, so it needs to be im...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-12-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1288366/full |
_version_ | 1797401459587809280 |
---|---|
author | Jiao Li Jinyu Ye Ruixin Zhang Yue Wu Gebremedhin Samuel Berhane Hongxia Deng Hong Shi |
author_facet | Jiao Li Jinyu Ye Ruixin Zhang Yue Wu Gebremedhin Samuel Berhane Hongxia Deng Hong Shi |
author_sort | Jiao Li |
collection | DOAJ |
description | IntroductionThe application of U-shaped convolutional neural network (CNN) methods in medical image segmentation tasks has yielded impressive results. However, this structure’s single-level context information extraction capability can lead to problems such as boundary blurring, so it needs to be improved. Additionally, the convolution operation’s inherent locality restricts its ability to capture global and long-distance semantic information interactions effectively. Conversely, the transformer model excels at capturing global information.MethodsGiven these considerations, this paper presents a transformer fusion context pyramid medical image segmentation network (CPFTransformer). The CPFTransformer utilizes the Swin Transformer to integrate edge perception for segmentation edges. To effectively fuse global and multi-scale context information, we introduce an Edge-Aware module based on a context pyramid, which specifically emphasizes local features like edges and corners. Our approach employs a layered Swin Transformer with a shifted window mechanism as an encoder to extract contextual features. A decoder based on a symmetric Swin Transformer is employed for upsampling operations, thereby restoring the resolution of feature maps. The encoder and decoder are connected by an Edge-Aware module for the extraction of local features such as edges and corners.ResultsExperimental evaluations on the Synapse multi-organ segmentation task and the ACDC dataset demonstrate the effectiveness of our method, yielding a segmentation accuracy of 79.87% (DSC) and 20.83% (HD) in the Synapse multi-organ segmentation task.DiscussionThe method proposed in this paper, which combines the context pyramid mechanism and Transformer, enables fast and accurate automatic segmentation of medical images, thereby significantly enhancing the precision and reliability of medical diagnosis. Furthermore, the approach presented in this study can potentially be extended to image segmentation of other organs in the future. |
first_indexed | 2024-03-09T02:10:24Z |
format | Article |
id | doaj.art-0fdf64e33d834e67b1d714cee7ef73dd |
institution | Directory Open Access Journal |
issn | 1662-453X |
language | English |
last_indexed | 2024-03-09T02:10:24Z |
publishDate | 2023-12-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neuroscience |
spelling | doaj.art-0fdf64e33d834e67b1d714cee7ef73dd2023-12-07T11:38:55ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-12-011710.3389/fnins.2023.12883661288366CPFTransformer: transformer fusion context pyramid medical image segmentation networkJiao Li0Jinyu Ye1Ruixin Zhang2Yue Wu3Gebremedhin Samuel Berhane4Hongxia Deng5Hong Shi6College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, ChinaCollege of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, ChinaCollege of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, ChinaCollege of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, ChinaCollege of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, ChinaCollege of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, ChinaSchool of Artificial Intelligence, Shenzhen Polytechnic, Shenzhen, ChinaIntroductionThe application of U-shaped convolutional neural network (CNN) methods in medical image segmentation tasks has yielded impressive results. However, this structure’s single-level context information extraction capability can lead to problems such as boundary blurring, so it needs to be improved. Additionally, the convolution operation’s inherent locality restricts its ability to capture global and long-distance semantic information interactions effectively. Conversely, the transformer model excels at capturing global information.MethodsGiven these considerations, this paper presents a transformer fusion context pyramid medical image segmentation network (CPFTransformer). The CPFTransformer utilizes the Swin Transformer to integrate edge perception for segmentation edges. To effectively fuse global and multi-scale context information, we introduce an Edge-Aware module based on a context pyramid, which specifically emphasizes local features like edges and corners. Our approach employs a layered Swin Transformer with a shifted window mechanism as an encoder to extract contextual features. A decoder based on a symmetric Swin Transformer is employed for upsampling operations, thereby restoring the resolution of feature maps. The encoder and decoder are connected by an Edge-Aware module for the extraction of local features such as edges and corners.ResultsExperimental evaluations on the Synapse multi-organ segmentation task and the ACDC dataset demonstrate the effectiveness of our method, yielding a segmentation accuracy of 79.87% (DSC) and 20.83% (HD) in the Synapse multi-organ segmentation task.DiscussionThe method proposed in this paper, which combines the context pyramid mechanism and Transformer, enables fast and accurate automatic segmentation of medical images, thereby significantly enhancing the precision and reliability of medical diagnosis. Furthermore, the approach presented in this study can potentially be extended to image segmentation of other organs in the future.https://www.frontiersin.org/articles/10.3389/fnins.2023.1288366/fullmedical image segmentationSwin TransformerEdge-Aware modulecontext pyramid fusion networkmultiscale feature |
spellingShingle | Jiao Li Jinyu Ye Ruixin Zhang Yue Wu Gebremedhin Samuel Berhane Hongxia Deng Hong Shi CPFTransformer: transformer fusion context pyramid medical image segmentation network Frontiers in Neuroscience medical image segmentation Swin Transformer Edge-Aware module context pyramid fusion network multiscale feature |
title | CPFTransformer: transformer fusion context pyramid medical image segmentation network |
title_full | CPFTransformer: transformer fusion context pyramid medical image segmentation network |
title_fullStr | CPFTransformer: transformer fusion context pyramid medical image segmentation network |
title_full_unstemmed | CPFTransformer: transformer fusion context pyramid medical image segmentation network |
title_short | CPFTransformer: transformer fusion context pyramid medical image segmentation network |
title_sort | cpftransformer transformer fusion context pyramid medical image segmentation network |
topic | medical image segmentation Swin Transformer Edge-Aware module context pyramid fusion network multiscale feature |
url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1288366/full |
work_keys_str_mv | AT jiaoli cpftransformertransformerfusioncontextpyramidmedicalimagesegmentationnetwork AT jinyuye cpftransformertransformerfusioncontextpyramidmedicalimagesegmentationnetwork AT ruixinzhang cpftransformertransformerfusioncontextpyramidmedicalimagesegmentationnetwork AT yuewu cpftransformertransformerfusioncontextpyramidmedicalimagesegmentationnetwork AT gebremedhinsamuelberhane cpftransformertransformerfusioncontextpyramidmedicalimagesegmentationnetwork AT hongxiadeng cpftransformertransformerfusioncontextpyramidmedicalimagesegmentationnetwork AT hongshi cpftransformertransformerfusioncontextpyramidmedicalimagesegmentationnetwork |