U-Net Based Feature Interaction Segmentation Method

被引：0
|
作者：
Sun J. [1 ,2 ]
Hui Z. [1 ]
Tang C. [1 ]
Wu X. [1 ,2 ]
机构：
[1] College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo
[2] Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou
来源：
Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2021年 / 34卷 / 11期
关键词：
Attention Mechanism; Feature Interaction; Liver Segmentation; Transformer;
D O I：
10.16451/j.cnki.issn1003-6059.202111009
中图分类号：
学科分类号：
摘要：
To address the problems of mis-segmentation and missing segmentation of small targets in liver segmentation, a U-Net based feature interaction segmentation method is proposed using ResNet34 as the backbone network. To achieve non-local interactions between different scales, a transformer-based feature interaction pyramid module is designed as the bridge of the network to obtain feature maps with richer contextual information. A multi-scale attention mechanism is designed to replace the jumping connection in U-Net, considering the small targets in the image and sufficiently acquiring the contextual information of the target layer. Experiments on the public dataset LiTS and the dataset consisting of 3Dircadb and CHAOS demonstrate that the proposed method achieves good segmentation results. © 2021, Science Press. All right reserved.
引用
收藏
页码：1058 / 1068
页数：10
相关论文
共 28 条
  • [1] JIANG H Y, FENG R J., Image Segmentation Method Research Based on Improved Variational Level Set and Region Growth, Acta Electronica Sinica, 40, 8, pp. 1659-1664, (2012)
  • [2] LI M, LIANG J Z, LIAO C C., Active Contour Model for Image Segmentation Based on Clustering Information, Pattern Recognition and Artificial Intelligence, 28, 7, pp. 665-672, (2015)
  • [3] ZHANG R G, LIU X J, DONG L, Et al., Superpixel Graph Cuts Rapid Algorithm for Extracting Object Contour Shapes, Pattern Reco-gnition and Artificial Intelligence, 28, 4, pp. 344-353, (2015)
  • [4] RONNEBERGER O, FISCHER P, BROX T., U-Net: Convolutional Networks for Biomedical Image Segmentation, Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234-241, (2015)
  • [5] HAN X., Automatic Liver Lesion Segmentation Using a Deep Convo-lutional Neural Network Method
  • [6] LI X M, CHEN H, QI X J, Et al., H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Vo-lumes, IEEE Transactions on Medical Imaging, 37, 12, pp. 2663-2674, (2018)
  • [7] OKTAY O, SCHLEMTER J, LE FOLGOC L, Et al., Attention U-Net: Learning Where to Look for the Pancreas
  • [8] LONG J, SHELHAMER E, DARRELL T., Fully Convolutional Networks for Semantic Segmentation, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440, (2015)
  • [9] HE K M, ZHANG X Y, REN S Q, Et al., Deep Residual Learning for Image Recognition, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, (2016)
  • [10] HUANG G, LIU Z, VAN DER MAATEN L, Et al., Densely Connected Convolutional Networks, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261-2269, (2016)
123