帮助 关于我们

返回检索结果

SAU-Net:基于U-Net和自注意力机制的医学图像分割方法
SAU-Net:Medical Image Segmentation Method Based on U-Net and Self-Attention

查看参考文献26篇

文摘 基于深度学习的生物医学图像分割由于其精度的提高,可以更好地辅助医生做精确的诊断.目前主流的基于U-Net的分割模型通过多层卷积进行局部特征的提取,缺失了全局信息,使分割过于局部化而产生误差.本文通过自注意力机制和分解卷积策略对U-Net模型进行改进,提出一种新的深度分割网络SAU-Net,使用自注意力模块增加全局信息,将原U-Net中的级联结构改为逐像素相加,减小维度,降低计算量;提出一种快速简洁的分解卷积方法,将传统卷积分解为两路一维卷积,并加入残差连接强化上下文信息.在BRATS和Kaggle两个脑肿瘤数据集上进行的实验结果表明,SAU-Net在参数量和Dice系数上都有更优的性能.
其他语种文摘 Biomedical image segmentation based on deep learning can better help doctors make an accurate diagnosis due to its enhanced accuracy.At present,the U-Net-based mainstream segmentation model extracts local features through multi-layer convolutions,which lacks global information and leads to over-localized results with errors.This paper improves the U-Net model through the self-attention mechanism and decomposition convolution and proposes a new deep segmentation network called SAU-Net.The model uses the self-attention module to increase global information,and changes the cascade structure in the original U-Net to pixel-by-pixel addition in order to reduce the dimension and cut down the calculation cost.A fast and concise decomposition convolution method is proposed which integrates the traditional convolution into a two-way one-dimensional convolution,and the residual connection is added to enhance the context information.The experimental results conducted on the two brain tumor datasets of BRATS and Kaggle show that SAU-Net has better performance in terms of parameters and the Dice coefficients.
来源 电子学报 ,2022,50(10):2433-2442 【核心库】
DOI 10.12263/DZXB.20200984
关键词 自注意力 ; 分解卷积 ; 医学图像分割 ; 深度学习 ; U-Net
地址

青岛科技大学信息科学技术学院, 山东, 青岛, 266061

语种 中文
文献类型 研究性论文
ISSN 0372-2112
学科 自动化技术、计算机技术
基金 山东省高等学校青创人才引育计划"人工智能与医学影像分析创新团队"建设项目
文献收藏号 CSCD:7318662

参考文献 共 26 共2页

1.  Altaf F. Going deep in medical image analysis: Concepts, methods, challenges, and future directions. IEEE Access,2019,7:99540-99572 CSCD被引 6 次    
2.  Ronneberger O. U-Net: Convolutional Networks for Biomedical Image Segmentation. Lecture Notes in Computer Science,2015:234-241 CSCD被引 600 次    
3.  Zhou Z W. UNet++: A nested U-net architecture for medical image segmentation. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support,2018,11045:3-11 CSCD被引 138 次    
4.  Kamnitsas K. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Medical Image Analysis,2017,36:61-78 CSCD被引 80 次    
5.  Ghafoorian M. Non-uniform patch sampling with deep convolutional neural networks for white matter hyperintensity segmentation. 2016 IEEE 13th International Symposium on Biomedical Imaging,2016:1414-1417 CSCD被引 1 次    
6.  Hu J. Squeeze-and-excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023 CSCD被引 770 次    
7.  Xie Y P. Spatial clockwork recurrent neural network for muscle perimysium segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention,2016:185-193 CSCD被引 1 次    
8.  Chen J X. Combining fully convolutional and recurrent neural networks for 3D biomedical image segmentation. NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems,2016:3044-3052 CSCD被引 1 次    
9.  Tseng K L. Joint sequence learning and cross-modality convolution for 3D biomedical segmentation. 2017 IEEE Conference on Computer Vision and Pattern Recognition,2017:3739-3746 CSCD被引 1 次    
10.  Vaswani A. Attention is all You need. NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems,2017:6000-6010 CSCD被引 16 次    
11.  Wang X L. Non-local neural networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2018:7794-7803 CSCD被引 76 次    
12.  Zhang H. Selfattention generative adversarial networks. Proceedings of the 36th International Conference on Machine Learning,2019:12744-12753 CSCD被引 1 次    
13.  Huang Z L. CCNet: criss-cross attention for semantic segmentation. 2019 IEEE/CVF International Conference on Computer Vision (ICCV),2019:603-612 CSCD被引 13 次    
14.  Fu J. Dual attention network for scene segmentation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR),2019:3141-3149 CSCD被引 4 次    
15.  Zhang F. ACFNet: Attentional class feature network for semantic segmentation. 2019 IEEE/CVF International Conference on Computer Vision(ICCV),2019:6797-6806 CSCD被引 1 次    
16.  Sinha A. Multi-scale self-guided attention for medical image segmentation. IEEE Journal of Biomedical and Health Informatics,2021,25(1):121-130 CSCD被引 26 次    
17.  Oktay O. Attention U-Net: Learning where to look for the pancreas. 1st Conference on Medical Imaging with Deep Learning (MIDL 2018),2018:4861068 CSCD被引 1 次    
18.  Li R R. Connection Sensitive Attention U-NET for Accurate Retinal Vessel Segmentation,2019 CSCD被引 2 次    
19.  Qi K H. X-Net: Brain stroke lesion segmentation based on depthwise separable convolution and long-range dependencies. International Conference on Medical Image Computing and Computer-Assisted Intervention,2019:247-255 CSCD被引 1 次    
20.  Zhang H. RSANet: Recurrent slice-wise attention network for multiple sclerosis lesion segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention,2019:411-419 CSCD被引 2 次    
引证文献 9 篇

1 胡婷 人工智能分割心外膜脂肪组织研究进展 中国医学影像技术,2023,39(4):606-609
CSCD被引 0 次

2 程照雪 增强边缘特征的肺结节分割模型 计算机工程与应用,2023,59(24):185-195
CSCD被引 1 次

显示所有9篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号