FDB-Net:结合 CNN 和变换器的融合双分支网络,用于医学图像分割。

IF 1.7 3区 医学 Q3 INSTRUMENTS & INSTRUMENTATION
Zhongchuan Jiang, Yun Wu, Lei Huang, Maohua Gu
{"title":"FDB-Net:结合 CNN 和变换器的融合双分支网络,用于医学图像分割。","authors":"Zhongchuan Jiang, Yun Wu, Lei Huang, Maohua Gu","doi":"10.3233/XST-230413","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The rapid development of deep learning techniques has greatly improved the performance of medical image segmentation, and medical image segmentation networks based on convolutional neural networks and Transformer have been widely used in this field. However, due to the limitation of the restricted receptive field of convolutional operation and the lack of local fine information extraction ability of the self-attention mechanism in Transformer, the current neural networks with pure convolutional or Transformer structure as the backbone still perform poorly in medical image segmentation.</p><p><strong>Methods: </strong>In this paper, we propose FDB-Net (Fusion Double Branch Network, FDB-Net), a double branch medical image segmentation network combining CNN and Transformer, by using a CNN containing gnConv blocks and a Transformer containing Varied-Size Window Attention (VWA) blocks as the feature extraction backbone network, the dual-path encoder ensures that the network has a global receptive field as well as access to the target local detail features. We also propose a new feature fusion module (Deep Feature Fusion, DFF), which helps the image to simultaneously fuse features from two different structural encoders during the encoding process, ensuring the effective fusion of global and local information of the image.</p><p><strong>Conclusion: </strong>Our model achieves advanced results in all three typical tasks of medical image segmentation, which fully validates the effectiveness of FDB-Net.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":" ","pages":"931-951"},"PeriodicalIF":1.7000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FDB-Net: Fusion double branch network combining CNN and transformer for medical image segmentation.\",\"authors\":\"Zhongchuan Jiang, Yun Wu, Lei Huang, Maohua Gu\",\"doi\":\"10.3233/XST-230413\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>The rapid development of deep learning techniques has greatly improved the performance of medical image segmentation, and medical image segmentation networks based on convolutional neural networks and Transformer have been widely used in this field. However, due to the limitation of the restricted receptive field of convolutional operation and the lack of local fine information extraction ability of the self-attention mechanism in Transformer, the current neural networks with pure convolutional or Transformer structure as the backbone still perform poorly in medical image segmentation.</p><p><strong>Methods: </strong>In this paper, we propose FDB-Net (Fusion Double Branch Network, FDB-Net), a double branch medical image segmentation network combining CNN and Transformer, by using a CNN containing gnConv blocks and a Transformer containing Varied-Size Window Attention (VWA) blocks as the feature extraction backbone network, the dual-path encoder ensures that the network has a global receptive field as well as access to the target local detail features. We also propose a new feature fusion module (Deep Feature Fusion, DFF), which helps the image to simultaneously fuse features from two different structural encoders during the encoding process, ensuring the effective fusion of global and local information of the image.</p><p><strong>Conclusion: </strong>Our model achieves advanced results in all three typical tasks of medical image segmentation, which fully validates the effectiveness of FDB-Net.</p>\",\"PeriodicalId\":49948,\"journal\":{\"name\":\"Journal of X-Ray Science and Technology\",\"volume\":\" \",\"pages\":\"931-951\"},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of X-Ray Science and Technology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.3233/XST-230413\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"INSTRUMENTS & INSTRUMENTATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of X-Ray Science and Technology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3233/XST-230413","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}
引用次数: 0

摘要

背景:深度学习技术的快速发展极大地提高了医学图像分割的性能,基于卷积神经网络和Transformer的医学图像分割网络在该领域得到了广泛应用。然而,由于卷积运算的感受野受限和Transformer中自注意机制缺乏局部精细信息提取能力的限制,目前以纯卷积或Transformer结构为骨干的神经网络在医学图像分割中的表现仍然不佳:本文提出了 FDB-Net(融合双分支网络,Fusion Double Branch Network,FDB-Net),这是一种结合了 CNN 和 Transformer 的双分支医学图像分割网络,通过使用包含 gnConv 块的 CNN 和包含 Varied-Size Window Attention(VWA)块的 Transformer 作为特征提取骨干网络,双路径编码器确保了网络既有全局感受野,又能获取目标局部细节特征。我们还提出了一个新的特征融合模块(深度特征融合,DFF),帮助图像在编码过程中同时融合来自两个不同结构编码器的特征,确保图像的全局和局部信息得到有效融合:我们的模型在医学图像分割的三个典型任务中都取得了先进的结果,充分验证了 FDB-Net 的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
FDB-Net: Fusion double branch network combining CNN and transformer for medical image segmentation.

Background: The rapid development of deep learning techniques has greatly improved the performance of medical image segmentation, and medical image segmentation networks based on convolutional neural networks and Transformer have been widely used in this field. However, due to the limitation of the restricted receptive field of convolutional operation and the lack of local fine information extraction ability of the self-attention mechanism in Transformer, the current neural networks with pure convolutional or Transformer structure as the backbone still perform poorly in medical image segmentation.

Methods: In this paper, we propose FDB-Net (Fusion Double Branch Network, FDB-Net), a double branch medical image segmentation network combining CNN and Transformer, by using a CNN containing gnConv blocks and a Transformer containing Varied-Size Window Attention (VWA) blocks as the feature extraction backbone network, the dual-path encoder ensures that the network has a global receptive field as well as access to the target local detail features. We also propose a new feature fusion module (Deep Feature Fusion, DFF), which helps the image to simultaneously fuse features from two different structural encoders during the encoding process, ensuring the effective fusion of global and local information of the image.

Conclusion: Our model achieves advanced results in all three typical tasks of medical image segmentation, which fully validates the effectiveness of FDB-Net.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
4.90
自引率
23.30%
发文量
150
审稿时长
3 months
期刊介绍: Research areas within the scope of the journal include: Interaction of x-rays with matter: x-ray phenomena, biological effects of radiation, radiation safety and optical constants X-ray sources: x-rays from synchrotrons, x-ray lasers, plasmas, and other sources, conventional or unconventional Optical elements: grazing incidence optics, multilayer mirrors, zone plates, gratings, other diffraction optics Optical instruments: interferometers, spectrometers, microscopes, telescopes, microprobes
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信