AF-Net: A Medical Image Segmentation Network Based on Attention Mechanism and Feature Fusion

被引:19
作者
Hou, Guimin [1 ]
Qin, Jiaohua [1 ]
Xiang, Xuyu [1 ]
Tan, Yun [1 ]
Xiong, Neal N. [2 ]
机构
[1] Cent South Univ Forestry & Technol, Coll Comp Sci & Informat Technol, Changsha 410004, Peoples R China
[2] Northeastern State Univ, Dept Math & Comp Sci, Tahlequah, OK 74464 USA
来源
CMC-COMPUTERS MATERIALS & CONTINUA | 2021年 / 69卷 / 02期
基金
中国国家自然科学基金;
关键词
Deep learning; medical image segmentation; feature fusion; attention mechanism;
D O I
10.32604/cmc.2021.017481
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Medical image segmentation is an important application field of computer vision in medical image processing. Due to the close location and high similarity of different organs in medical images, the current segmentation algorithms have problems with mis-segmentation and poor edge segmentation. To address these challenges, we propose a medical image segmentation network (AF-Net) based on attention mechanism and feature fusion, which can effectively capture global information while focusing the network on the object area. In this approach, we add dual attention blocks (DA-block) to the backbone network, which comprises parallel channels and spatial attention branches, to adaptively calibrate and weigh features. Secondly, the multi-scale feature fusion block (MFF-block) is proposed to obtain feature maps of different receptive domains and get multi-scale information with less computational consumption. Finally, to restore the locations and shapes of organs, we adopt the global feature fusion blocks (GFF-block) to fuse high-level and low-level information, which can obtain accurate pixel positioning. We evaluate our method on multiple datasets(the aorta and lungs dataset), and the experimental results achieve 94.0% in mIoU and 96.3% in DICE, showing that our approach performs better than U-Net and other state-of-art methods.
引用
收藏
页码:1877 / 1891
页数:15
相关论文
共 42 条
[1]  
Alom M.Z., 2018, ARXIV PREPRINT
[2]   Fusing Local and Global Features for High-Resolution Scene Classification [J].
Bian, Xiaoyong ;
Chen, Chen ;
Tian, Long ;
Du, Qian .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2017, 10 (06) :2889-2901
[3]  
Bottou L., 2012, NEURAL NETWORKS TRIC, P421, DOI [10.1007/978-3-642-35289-8_25, DOI 10.1007/978-3-642-35289-8_25]
[4]  
Chen L. C., 2017, ARXIV PREPRINT
[5]   Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [J].
Chen, Liang-Chieh ;
Zhu, Yukun ;
Papandreou, George ;
Schroff, Florian ;
Adam, Hartwig .
COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :833-851
[6]   Image super-resolution reconstruction based on feature map attention mechanism [J].
Chen, Yuantao ;
Liu, Linwu ;
Phonevilay, Volachith ;
Gu, Ke ;
Xia, Runlong ;
Xie, Jingbo ;
Zhang, Qian ;
Yang, Kai .
APPLIED INTELLIGENCE, 2021, 51 (07) :4367-4380
[7]   The improved image inpainting algorithm via encoder and similarity constraint [J].
Chen, Yuantao ;
Liu, Linwu ;
Tao, Jiajun ;
Xia, Runlong ;
Zhang, Qian ;
Yang, Kai ;
Xiong, Jie ;
Chen, Xi .
VISUAL COMPUTER, 2021, 37 (07) :1691-1705
[8]   Generalized overlap measures for evaluation and validation in medical image analysis [J].
Crum, William R. ;
Camara, Oscar ;
Hill, Derek L. G. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2006, 25 (11) :1451-1461
[9]   Point attention network for semantic segmentation of 3D point clouds [J].
Feng, Mingtao ;
Zhang, Liang ;
Lin, Xuefei ;
Gilani, Syed Zulqarnain ;
Mian, Ajmal .
PATTERN RECOGNITION, 2020, 107 (107)
[10]   Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation [J].
Fu, Huazhu ;
Cheng, Jun ;
Xu, Yanwu ;
Wong, Damon Wing Kee ;
Liu, Jiang ;
Cao, Xiaochun .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2018, 37 (07) :1597-1605