[1]师文博,杨环,西永明,等.基于自注意力的双通路全脊柱 X 光图像分割模型[J].中国医学物理学杂志,2022,39(11):1385-1392.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.011]
　SHI Wenbo,YANG Huan,XI Yongming,et al.Self-attention based dual pathway network for spine segmentation in X-ray image[J].Chinese Journal of Medical Physics,2022,39(11):1385-1392.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.011]
点击复制

基于自注意力的双通路全脊柱 X 光图像分割模型()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
39卷
期数:
2022年第11期
页码:
1385-1392
栏目:
医学影像物理
出版日期:
2022-11-25

文章信息/Info

Title:
Self-attention based dual pathway network for spine segmentation in X-ray image
文章编号:
1005-202X（2022）11-1385-08
作者:
师文博1; 杨环1; 西永明2; 段文玉1; 徐同帅2; 杜钰堃2
1.青岛大学计算机科学技术学院， 山东 青岛 266071； 2.青岛大学附属医院崂山院区脊柱外科， 山东 青岛 266000
Author(s):
SHI Wenbo1;  YANG Huan1;  XI Yongming2;  DUAN Wenyu1;  XU Tongshuai2;  DU Yukun2
1. College of Computer Science and Technology, Qingdao University, Qingdao 266071, China 2. Department of Spinal Surgery, Laoshan Branch, the Affiliated Hospital of Qingdao University, Qingdao 266000, China
关键词:
脊柱图像分割; U-Net; 语义分割; 双通道网络; 自注意力机制
Keywords:
Keywords: spine image segmentation U-Net semantic segmentation dual pathway network self-attention mechanism
分类号:
R318；R816.8
DOI:
DOI:10.3969/j.issn.1005-202X.2022.11.011
文献标志码:
A
摘要:
全脊柱X光图像（包含脊柱、骶骨及髂骨）分割是目前脊椎疾病智能诊断中首要关键的环节。针对U-Net语义分割算法在全脊柱X光图像多区域分割精度较差的问题，提出一种双通道语义分割算法DAU-Net，通过空间通道与语义通道分别学习空间信息特征与图像语义特征，并在解码器端对两类特征进行融合，获取脊柱X光图像中更精准的分割边界。在空间通道中，使用空洞卷积及残差模块扩大视野域并保留更多远端特征信息。此外，将自注意力机制引入语义通道，并设计不同的自注意力编码与自注意力解码模块构建全局关联信息，实现对多个目标骨骼区域语义分割。实验结果表明，DAU-Net能够有效提高脊柱X光图像上的分割精度，相比U-Net、ResU-Net、Attention U-Net、U-Net++，Dice系数分别提高4.00%、1.90%、4.60%、1.19%。
Abstract:
The segmentation of X-ray images of the entire spine including the spine, sacrum and iliac bone is the essential step for the intelligent diagnosis of spine diseases. A semantic segmentation network named dual pathway with self-attention for refined U-Net (DAU-Net) is proposed to solve the problem of poor accuracy of U-Net semantic segmentation algorithm in multi-region segmentation in full-spine X-ray image. DAU-Net adopted spatial pathway and semantic pathway to learn spatial information and semantic information separately, and then combines these two types of features at the decoder, thereby obtaining more accurate segmentation boundaries in full-spine X-ray images. In the spatial pathway, dilated convolutions and residual blocks are used to expand the receptive field and capture the long-range dependency feature information. Furthermore, the self-attention mechanism is applied in the semantic pathway, and different self-attention encoders and self-attention decoders are designed to construct global association to achieve the semantic segmentation of multiple target bone regions. The experimental results show that DAU-Net can effectively improve the segmentation accuracy in full-spine X-ray images, and its Dice coeffcience is 4.00%, 1.90%, 4.60% and 1.19% higher than those of U-Net, ResU-Net, Attention U-Net and U-Net++, respectively.

相似文献/References:

[1]秦楠楠,薛旭东,吴爱林,等.基于U-net卷积神经网络的宫颈癌临床靶区和危及器官自动勾画的研究[J].中国医学物理学杂志,2020,37(4):524.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.023]
　QIN Nannan,XUE Xudong,WU Ailin,et al.Automatic segmentation of clinical target volumes and organs-at-risk in radiotherapy for cervical cancer using U-net convolutional neural network[J].Chinese Journal of Medical Physics,2020,37(11):524.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.023]
[2]常艳奎,彭昭,周解平,等.基于U-net的心脏自动勾画模型的临床应用及改进[J].中国医学物理学杂志,2020,37(10):1218.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.002]
　CHANG Yankui,PENG Zhao,ZHOU Jieping,et al.Clinical application and improvement of U-net-based model for automatic segmentation of the heart[J].Chinese Journal of Medical Physics,2020,37(11):1218.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.002]
[3]董国亚,宋立明,李雅芬,等.基于深度学习的跨模态医学图像转换[J].中国医学物理学杂志,2020,37(10):1335.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.021]
　DONG Guoya,SONG Liming,et al.Cross-modality medical image synthesis based on deep learning[J].Chinese Journal of Medical Physics,2020,37(11):1335.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.021]
[4]董宇波,王蕊,赵慧娟,等.革兰氏染色细菌显微图像深度学习分类与计数[J].中国医学物理学杂志,2021,38(1):127.[doi:DOI:10.3969/j.issn.1005-202X.2021.01.020]
　DONG Yubo,WANG Rui,ZHAO Huijuan,et al.Classification and counting of Gram-stained bacteria by deeply learning in micro-image[J].Chinese Journal of Medical Physics,2021,38(11):127.[doi:DOI:10.3969/j.issn.1005-202X.2021.01.020]
[5]莫春梅,周金治,李雪,等.基于改进U-Net的肝脏分割方法[J].中国医学物理学杂志,2021,38(5):571.[doi:DOI:10.3969/j.issn.1005-202X.2021.05.009]
　MO Chunmei,ZHOU Jinzhi,et al.Liver segmentation method based on improved U-Net[J].Chinese Journal of Medical Physics,2021,38(11):571.[doi:DOI:10.3969/j.issn.1005-202X.2021.05.009]
[6]李雪,周金治,莫春梅,等.基于特征融合的U-Net肺自动分割方法[J].中国医学物理学杂志,2021,38(6):704.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.009]
　LI Xue,ZHOU Jinzhi,et al.U-Net automatic lung segmentation based on feature fusion[J].Chinese Journal of Medical Physics,2021,38(11):704.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.009]
[7]顾国浩,龙英文,吉明明.U-Net改进及其在新冠肺炎图像分割的应用[J].中国医学物理学杂志,2022,39(8):1041.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.022]
　GU Guohao,LONG Yingwen,JI Mingming.Improved U-Net and its application in COVID-19 image segmentation[J].Chinese Journal of Medical Physics,2022,39(11):1041.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.022]
[8]陈菁菁,李小霞,吕念祖.结合通道权重更新与密集残差金字塔空间注意力的皮肤病变分割方法[J].中国医学物理学杂志,2023,40(1):39.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.007]
　CHEN Jingjing,LI Xiaoxia,L?Nianzu,et al.Skin lesion segmentation method combining channel weight update and dense residual pyramid spatial attention[J].Chinese Journal of Medical Physics,2023,40(11):39.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.007]
[9]吴传锋,金鑫妍,白司悦,等.基于U-Net结合改进算法对放疗危及器官自动勾画研究[J].中国医学物理学杂志,2023,40(3):303.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.008]
　WU Chuanfeng,JIN Xinyan,BAI Siyue,et al.Auto-segmentation of organs-at-risk for radiotherapy using U-Net combined with improved algorithms[J].Chinese Journal of Medical Physics,2023,40(11):303.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.008]
[10]夏文静,周腊珍,陈红池,等.基于空洞空间金字塔池化的U-Net网络在肺部图像分割上的应用[J].中国医学物理学杂志,2023,40(3):336.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.012]
　XIA Wenjing,ZHOU Lazhen,CHEN Hongchi,et al.Lung field segmentation using U-Net based on atrous spatial pyramid pooling[J].Chinese Journal of Medical Physics,2023,40(11):336.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.012]

备注/Memo

备注/Memo:
【收稿日期】2022-07-11 【基金项目】山东省重点研发计划（2019GGX101021）；山东省泰山学者项目（ts20190985） 【作者简介】师文博，硕士研究生，研究方向：计算机视觉、医疗图像处理，E-mail: shi_wenbo@outlook.com 【通信作者】杨环，博士，副教授，研究方向：计算机视觉、深度学习，E-mail: cathy_huanyang@hotmail.com
更新日期/Last Update: 2022-11-25