《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (12): 3891-3899.DOI: 10.11772/j.issn.1001-9081.2021101737
收稿日期:
2021-10-09
修回日期:
2022-01-04
接受日期:
2022-01-24
发布日期:
2022-04-08
出版日期:
2022-12-10
通讯作者:
邹俊颖
作者简介:
李鸿(1995—),男,四川眉山人,硕士研究生,主要研究方向:机器学习、医学图像分割基金资助:
Hong LI, Junying ZOU(), Xicheng TAN, Guiyang LI
Received:
2021-10-09
Revised:
2022-01-04
Accepted:
2022-01-24
Online:
2022-04-08
Published:
2022-12-10
Contact:
Junying ZOU
About author:
LI Hong, born in 1995, M. S. candidate. His research interests include machine learning, medical image segmentation.Supported by:
摘要:
在深度医学图像分割领域中,TransUNet是当前先进的分割模型之一。但其编码器未考虑相邻分块之间的局部联系,在解码器上采样过程中缺乏通道间信息的交互。针对以上问题,提出一种多注意力融合网络(MFUNet)模型。首先,在编码器部分引入特征融合模块(FFM)来增强模型对Transformer中相邻分块间的局部联系并且保持图片本身的空间位置关系;其次,在解码器部分引入双通道注意力(DCA)模块来融合多级特征的通道信息,以增强模型对通道间关键信息的敏感度;最后,通过结合交叉熵损失和Dice损失来加强模型对分割结果的约束。在Synapse和ACDC公共数据集上进行实验,可以看出,MFUNet的Dice相似系数(DSC)分别达到了81.06%和90.91%;在Synapse数据集上的Hausdorff距离(HD)与基线模型TransUNet相比减小了11.5%;在ACDC数据集中右心室和心肌两部分的分割精度与基线模型TransUNet相比分别提升了1.43个百分点和3.48个百分点。实验结果表明,MFUNet在医学图像的内部填充和边缘预测方面均能实现更好的分割效果,有助于提升医生在临床实践中的诊断效率。
中图分类号:
李鸿, 邹俊颖, 谭茜成, 李贵洋. 面向医学图像分割的多注意力融合网络[J]. 计算机应用, 2022, 42(12): 3891-3899.
Hong LI, Junying ZOU, Xicheng TAN, Guiyang LI. Multi-attention fusion network for medical image segmentation[J]. Journal of Computer Applications, 2022, 42(12): 3891-3899.
模型 | DSC↑ | HD↓ | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | |||
V-Net[ | 68.81 | — | 75.34 | 51.87 | 77.10 | 80.75 | 87.84 | 40.05 | 80.56 | 56.98 |
DARR[ | 69.77 | — | 74.74 | 53.77 | 72.31 | 73.24 | 94.08 | 54.18 | 89.90 | 45.96 |
R50 UNet[ | 74.68 | 36.87 | 84.18 | 62.84 | 80.60 | 79.19 | 93.74 | 56.90 | 85.87 | 74.16 |
UNet[ | 76.60 | 35.02 | 87.80 | 67.25 | 80.47 | 73.31 | 93.36 | 53.78 | 84.87 | 71.93 |
R50 Att-UNet[ | 75.57 | 36.97 | 85.92 | 63.91 | 79.20 | 72.71 | 93.56 | 49.37 | 87.19 | 74.95 |
Att-UNet[ | 77.75 | 32.59 | 88.05 | 67.73 | 82.23 | 75.59 | 93.38 | 55.69 | 85.56 | 73.81 |
R50 Vit[ | 71.29 | 32.87 | 73.73 | 55.13 | 75.80 | 72.20 | 91.51 | 45.99 | 81.99 | 73.95 |
TransUNet[ | 77.48 | 31.69 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 |
MFUNetfffm | 79.45 | 29.35 | 87.61 | 63.58 | 83.23 | 80.65 | 94.41 | 61.36 | 87.86 | 76.89 |
MFUNetdca | 78.05 | 29.75 | 87.37 | 63.59 | 81.83 | 78.35 | 93.43 | 56.77 | 85.98 | 77.10 |
MFUNet | 81.06 | 28.05 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
表1 不同模型在Synapse多器官分割数据集上的分割精度 (%)
Tab.1 Segmentation accuracies of different models on Synapse multi-organ segmentation dataset
模型 | DSC↑ | HD↓ | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | |||
V-Net[ | 68.81 | — | 75.34 | 51.87 | 77.10 | 80.75 | 87.84 | 40.05 | 80.56 | 56.98 |
DARR[ | 69.77 | — | 74.74 | 53.77 | 72.31 | 73.24 | 94.08 | 54.18 | 89.90 | 45.96 |
R50 UNet[ | 74.68 | 36.87 | 84.18 | 62.84 | 80.60 | 79.19 | 93.74 | 56.90 | 85.87 | 74.16 |
UNet[ | 76.60 | 35.02 | 87.80 | 67.25 | 80.47 | 73.31 | 93.36 | 53.78 | 84.87 | 71.93 |
R50 Att-UNet[ | 75.57 | 36.97 | 85.92 | 63.91 | 79.20 | 72.71 | 93.56 | 49.37 | 87.19 | 74.95 |
Att-UNet[ | 77.75 | 32.59 | 88.05 | 67.73 | 82.23 | 75.59 | 93.38 | 55.69 | 85.56 | 73.81 |
R50 Vit[ | 71.29 | 32.87 | 73.73 | 55.13 | 75.80 | 72.20 | 91.51 | 45.99 | 81.99 | 73.95 |
TransUNet[ | 77.48 | 31.69 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 |
MFUNetfffm | 79.45 | 29.35 | 87.61 | 63.58 | 83.23 | 80.65 | 94.41 | 61.36 | 87.86 | 76.89 |
MFUNetdca | 78.05 | 29.75 | 87.37 | 63.59 | 81.83 | 78.35 | 93.43 | 56.77 | 85.98 | 77.10 |
MFUNet | 81.06 | 28.05 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
模型 | DSC | 器官分割精度 | ||
---|---|---|---|---|
右心室 | 心肌 | 左心室 | ||
R50 U-Net | 87.55 | 87.10 | 80.63 | 94.92 |
R50 Att-UNet | 86.75 | 87.58 | 79.20 | 93.47 |
R50 ViT | 87.57 | 86.07 | 81.88 | 94.75 |
TransUNet | 89.71 | 88.86 | 84.53 | 95.73 |
MFUNet | 90.91 | 90.29 | 88.01 | 94.42 |
表2 不同模型在ACDC心脏分割数据集上的分割精度 (%)
Tab.2 Segmentation accuracies of different models on ACDC heart segmentation dataset
模型 | DSC | 器官分割精度 | ||
---|---|---|---|---|
右心室 | 心肌 | 左心室 | ||
R50 U-Net | 87.55 | 87.10 | 80.63 | 94.92 |
R50 Att-UNet | 86.75 | 87.58 | 79.20 | 93.47 |
R50 ViT | 87.57 | 86.07 | 81.88 | 94.75 |
TransUNet | 89.71 | 88.86 | 84.53 | 95.73 |
MFUNet | 90.91 | 90.29 | 88.01 | 94.42 |
模型 | 跳跃连接 | DSC | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | |||
TransUNet | 1 | 76.18 | 83.31 | 60.57 | 79.94 | 77.39 | 92.80 | 53.46 | 85.59 | 76.34 |
2 | 76.74 | 86.72 | 60.79 | 81.07 | 76.08 | 93.78 | 55.94 | 84.76 | 75.55 | |
3 | 77.48 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 | |
MFUNet | 1 | 77.67 | 84.54 | 62.63 | 80.41 | 77.42 | 94.23 | 59.49 | 86.78 | 80.15 |
2 | 80.05 | 88.00 | 63.90 | 83.02 | 81.66 | 94.55 | 62.67 | 87.08 | 79.52 | |
3 | 81.06 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
表3 跳跃连接数量的消融实验 (%)
Tab.3 Ablation experiment for number of skip connections
模型 | 跳跃连接 | DSC | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | |||
TransUNet | 1 | 76.18 | 83.31 | 60.57 | 79.94 | 77.39 | 92.80 | 53.46 | 85.59 | 76.34 |
2 | 76.74 | 86.72 | 60.79 | 81.07 | 76.08 | 93.78 | 55.94 | 84.76 | 75.55 | |
3 | 77.48 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 | |
MFUNet | 1 | 77.67 | 84.54 | 62.63 | 80.41 | 77.42 | 94.23 | 59.49 | 86.78 | 80.15 |
2 | 80.05 | 88.00 | 63.90 | 83.02 | 81.66 | 94.55 | 62.67 | 87.08 | 79.52 | |
3 | 81.06 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
模型 | 模型规模 | DSC | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | |||
TransUNet | base | 77.48 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 |
large | 78.52 | 87.42 | 63.92 | 82.17 | 80.19 | 94.47 | 57.64 | 87.42 | 74.90 | |
MFUNet | base | 81.06 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
large | 81.46 | 88.21 | 66.67 | 85.00 | 81.84 | 94.68 | 64.87 | 90.08 | 81.46 |
表4 模型规模大小的消融实验 (%)
Tab.4 Ablation experiment for model scale
模型 | 模型规模 | DSC | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | |||
TransUNet | base | 77.48 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 |
large | 78.52 | 87.42 | 63.92 | 82.17 | 80.19 | 94.47 | 57.64 | 87.42 | 74.90 | |
MFUNet | base | 81.06 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
large | 81.46 | 88.21 | 66.67 | 85.00 | 81.84 | 94.68 | 64.87 | 90.08 | 81.46 |
模型 | 输入分辨率 | DSC | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | |||
TransUNet | 224×224 | 77.48 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 |
384×384 | 80.51 | 88.67 | 67.62 | 82.80 | 76.25 | 94.87 | 65.57 | 87.57 | 80.69 | |
MFUNet | 224×224 | 81.06 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
384×384 | 81.73 | 89.91 | 65.80 | 81.98 | 78.99 | 95.43 | 68.15 | 91.10 | 82.48 |
表5 输入分辨率的消融实验 (%)
Tab.5 Ablation experiment for input resolution
模型 | 输入分辨率 | DSC | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | |||
TransUNet | 224×224 | 77.48 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 |
384×384 | 80.51 | 88.67 | 67.62 | 82.80 | 76.25 | 94.87 | 65.57 | 87.57 | 80.69 | |
MFUNet | 224×224 | 81.06 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
384×384 | 81.73 | 89.91 | 65.80 | 81.98 | 78.99 | 95.43 | 68.15 | 91.10 | 82.48 |
卷积分组数 | DSC | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | ||
1 | 80.75 | 87.80 | 64.18 | 84.13 | 79.41 | 94.69 | 64.78 | 90.30 | 80.72 |
48 | 80.53 | 88.00 | 62.64 | 84.12 | 80.53 | 94.75 | 63.22 | 89.92 | 80.70 |
768 | 81.06 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
表6 MFUNet中卷积分组数的消融实验 (%)
Tab.6 Ablation experiment for number of convolution groups in MFUNet
卷积分组数 | DSC | 器官分割精度 | |||||||
---|---|---|---|---|---|---|---|---|---|
主动脉 | 胆囊 | 肾脏(L) | 肾脏(R) | 肝脏 | 胰腺 | 脾 | 胃 | ||
1 | 80.75 | 87.80 | 64.18 | 84.13 | 79.41 | 94.69 | 64.78 | 90.30 | 80.72 |
48 | 80.53 | 88.00 | 62.64 | 84.12 | 80.53 | 94.75 | 63.22 | 89.92 | 80.70 |
768 | 81.06 | 88.40 | 65.13 | 84.63 | 81.88 | 94.71 | 63.95 | 89.22 | 80.60 |
1 | 郑光远,刘峡壁,韩光辉. 医学影像计算机辅助检测与诊断系统综述[J]. 软件学报, 2018, 29(5):1471-1514. 10.13328/j.cnki.jos.005519 |
ZHENG G Y, LIU X B, HAN G H. Survey on medical image computer aided detection and diagnosis systems[J]. Journal of Software, 2018, 29(5):1471-1514. 10.13328/j.cnki.jos.005519 | |
2 | NEGASSI M, SUAREZ-IBARROLA R, HEIN S, et al. Application of artificial neural networks for automated analysis of cystoscopic images: a review of the current status and future prospects[J]. World Journal of Urology, 2020, 38(10): 2349-2358. 10.1007/s00345-019-03059-0 |
3 | 陈屹东,张琴,兰蓝,等. 深度卷积神经网络方法在医学图像分割应用中的综述[J]. 中国卫生信息管理杂志, 2021, 18(2):278-284. 10.3969/j.issn.1672-5166.2021.02.026 |
CHEN Y D, ZHANG Q, LAN L, et al. A review of deep convolutional neural networks in medical image segmentation[J]. Chinese Journal of Health Informatics and Management, 2021, 18(2):278-284. 10.3969/j.issn.1672-5166.2021.02.026 | |
4 | 曹玉红,徐海,刘荪傲,等. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8):2273-2287. 10.11772/j.issn.1001-9081.2020101638 |
CAO Y H, XU H, LIU S A, et al. A review of medical image segmentation based on deep learning[J]. Journal of Computer Applications, 2021, 41(8): 2273-2287. 10.11772/j.issn.1001-9081.2020101638 | |
5 | LI W, JIA F C, HU Q M. Automatic segmentation of liver tumor in CT images with deep convolutional neural networks[J]. Journal of Computer and Communications, 2015, 3(11): 146-151. 10.4236/jcc.2015.311023 |
6 | VORONTSOV E, TANG A, PAL C, et al. Liver lesion segmentation informed by joint liver segmentation[C]// Proceedings of the IEEE 15th International Symposium on Biomedical Imaging. Piscataway: IEEE, 2018: 1332-1335. 10.1109/isbi.2018.8363817 |
7 | CHERUKURI V, SSENYONGA P, WARF B C, et al. Learning based segmentation of CT brain images: application to postoperative hydrocephalic scans[J]. IEEE Transactions on Biomedical Engineering, 2018, 65(8): 1871-1884. 10.1109/tbme.2017.2783305 |
8 | LI H Y, ZHAO X Q, SU A Y, et al. Color space transformation and multi-class weighted loss for adhesive white blood cell segmentation[J]. IEEE Access, 2020, 8: 24808-24818. 10.1109/access.2020.2970485 |
9 | KHENED M, KOLLERATHU V A, KRISHNAMURTHI G. Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers[J]. Medical Image Analysis, 2019, 51: 21-45. 10.1016/j.media.2018.10.004 |
10 | LIU L L, CHENG J H, QUAN Q, et al. A survey on U-shaped networks in medical image segmentations[J]. Neurocomputing, 2020, 409: 244-258. 10.1016/j.neucom.2020.05.070 |
11 | LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 3431-3440. 10.1109/cvpr.2015.7298965 |
12 | RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]// Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham: Springer,2015:234-241. |
13 | ZHOU Z W, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet++: a nested U-Net architecture for medical image segmentation[C]// Proceedings of the 2018 International Workshop on Deep Learning in Medical Image Analysis/ 2018 International Workshop on Multimodal Learning for Clinical Decision Support, LNCS 11045. Cham: Springer, 2018: 3-11. |
14 | JÉGOU S, DROZDZAL M, VAZQUEZ D, et al. The one hundred layers tiramisu: fully convolutional DenseNets for semantic segmentation[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2017: 1175-1183. 10.1109/cvprw.2017.156 |
15 | HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2261-2269. 10.1109/cvpr.2017.243 |
16 | OKTAY O, SCHLEMPER J, FOLGOC L L, et al. Attention U-Net: learning where to look for the pancreas[EB/OL]. (2018-05-20) [2021-07-08].. |
17 | CAI Y T, WANG Y. MA-Unet: an improved version of Unet based on multi-scale and attention mechanism for medical image segmentation[EB/OL]. (2020-12-20) [2021-07-08].. 10.1117/12.2628519 |
18 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2017:6000-6010. |
19 | ZHENG S X, LU J C, ZHAO H S, et al. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 6877-6886. 10.1109/cvpr46437.2021.00681 |
20 | PETIT O, THOME N, RAMBOUR C, et al. U-Net transformer: self and cross attention for medical image segmentation[C]// Proceedings of the 2021 International Workshop on Machine Learning in Medical Imaging, LNCS 12966. Cham: Springer, 2021: 267-276. |
21 | ZHANG Y D, LIU H Y, HU Q. TransFuse: fusing transformers and CNNs for medical image segmentation [C]// Proceedings of the 2021 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 12901. Cham: Springer, 2021: 14-24. |
22 | VALANARASU J M J, OZA P, HACIHALILOGLU I, et al. Medical transformer: gated axial-attention for medical image segmentation[C]// Proceedings of the 2021 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 12901. Cham: Springer, 2021: 36-46. |
23 | ZHANG Z Z, SUN B Z, ZHANG W X. Pyramid medical transformer for medical image segmentation[EB/OL]. (2021-09-13) [2021-09-28].. |
24 | JI G P, CHOU Y C, FAN D P, et al. Progressively normalized self-attention network for video polyp segmentation[C]// Proceedings of the 2021 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 12901. Cham: Springer, 2021: 142-152. |
25 | CHU X X, TIAN Z, ZHANG B, et al. Conditional positional encodings for vision transformers[EB/OL]. (2021-03-18) [2021-07-08].. |
26 | CHEN J N, LU Y Y, YU Q H, et al. TransUNet: transformers make strong encoders for medical image segmentation[EB/OL]. (2021-02-08) [2021-07-08].. |
27 | ZHANG X Y, ZHOU X Y, LIN M X, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 6848-6856. 10.1109/cvpr.2018.00716 |
28 | LI Y W, ZHANG K, CAO J Z, et al. LocalViT: bringing locality to vision transformers[EB/OL]. (2021-04-12) [2021-07-08].. |
29 | WU H P, XIAO B, CODELLA N, et al. CvT: introducing convolutions to vision Transformers[C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 22-31. 10.1109/iccv48922.2021.00009 |
30 | LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 9992-10002. 10.1109/iccv48922.2021.00986 |
31 | HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141. 10.1109/cvpr.2018.00745 |
32 | ROY A G, NAVAB N, WACHINGER C. Concurrent spatial and channel ‘squeeze & excitation’ in fully convolutional networks[C]// Proceedings of the 2018 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 11070. Cham: Springer, 2018: 421-429. |
33 | WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11211. Cham: Springer, 2018: 3-19. |
34 | HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13708-13717. 10.1109/cvpr46437.2021.01350 |
35 | HAN K, WANG Y, CHEN H, et al. A survey on visual transformer [EB/OL]. (2020-12-20)[2021-07-08]. . |
36 | ZHU X Z, SU W J, LU L W, et al. Deformable DETR: deformable transformers for end-to-end object detection[EB/OL]. (2021-03-18) [2021-07-08].. 10.1609/aaai.v36i1.19893 |
37 | DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale[EB/OL]. (2021-06-03) [2021-07-08].. |
38 | WANG H Y, ZHU Y K, ADAM H, et al. MaX-DeepLab: end-to-end panoptic segmentation with mask transformers[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 5459-5470. 10.1109/cvpr46437.2021.00542 |
39 | LIU N F, GARDNER M, BELINKOV Y, et al. Linguistic knowledge and transferability of contextual representations[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Stroudsburg, PA: Association for Computational Linguistics, 2019: 1073-1094. 10.18653/v1/n18-2 |
40 | ASGARI TAGHANAKI S, ABHISHEK K, COHEN J P, et al. Deep semantic segmentation of natural and medical images: a review[J]. Artificial Intelligence Review, 2021, 54(1): 137-178. 10.1007/s10462-020-09854-1 |
41 | WANG R S, LEI T, CUI R X, et al. Medical image segmentation using deep learning: a survey[J]. IET Image Processing, 2022, 16(5): 1243-1267. 10.1049/ipr2.12419 |
42 | MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C]// Proceedings of the 2016 4th International Conference on 3D Vision. Piscataway: IEEE, 2016: 565-571. 10.1109/3dv.2016.79 |
[1] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[2] | 李顺勇, 李师毅, 胥瑞, 赵兴旺. 基于自注意力融合的不完整多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2696-2703. |
[3] | 黄云川, 江永全, 黄骏涛, 杨燕. 基于元图同构网络的分子毒性预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2964-2969. |
[4] | 秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974. |
[5] | 王熙源, 张战成, 徐少康, 张宝成, 罗晓清, 胡伏原. 面向手术导航3D/2D配准的无监督跨域迁移网络[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2911-2918. |
[6] | 李力铤, 华蓓, 贺若舟, 徐况. 基于解耦注意力机制的多变量时序预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2732-2738. |
[7] | 陈彤, 杨丰玉, 熊宇, 严荭, 邱福星. 基于多尺度频率通道注意力融合的声纹库构建方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2407-2413. |
[8] | 刘禹含, 吉根林, 张红苹. 基于骨架图与混合注意力的视频行人异常检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2551-2557. |
[9] | 顾焰杰, 张英俊, 刘晓倩, 周围, 孙威. 基于时空多图融合的交通流量预测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2618-2625. |
[10] | 杨帆, 邹窈, 朱明志, 马振伟, 程大伟, 蒋昌俊. 基于图注意力Transformer神经网络的信用卡欺诈检测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2634-2642. |
[11] | 石乾宏, 杨燕, 江永全, 欧阳小草, 范武波, 陈强, 姜涛, 李媛. 面向空气质量预测的多粒度突变拟合网络[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2643-2650. |
[12] | 赵亦群, 张志禹, 董雪. 基于密集残差物理信息神经网络的各向异性旅行时计算方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2310-2318. |
[13] | 徐松, 张文博, 王一帆. 基于时空信息的轻量视频显著性目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2192-2199. |
[14] | 孙逊, 冯睿锋, 陈彦如. 基于深度与实例分割融合的单目3D目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2208-2215. |
[15] | 唐媛, 陈艳平, 扈应, 黄瑞章, 秦永彬. 基于多尺度混合注意力卷积神经网络的关系抽取模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2011-2017. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||