基于U-Net的特征交互分割方法

doi:10.16451/j.cnki.issn1003-6059.202111009

摘要
图/表
参考文献(0)
相关文章 (15)

全文: PDF (2174 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

针对肝脏分割中存在误分割及小目标漏分割的问题,文中提出基于U-Net的特征交互分割方法,采用ResNet34作为主干网络.为了实现不同尺度间的非局部交互,设计基于转换器机制的特征交互金字塔模块作为网络的桥接器,获得具有丰富上下文信息的特征图.设计多尺度注意力机制替代U-Net中的跳跃连接,关注图像中的小目标,充分获取目标层的上下文信息.在公开数据集LiTS及3Dircadb和CHAOS组成的数据集上的实验证实文中方法能取得较好的分割效果.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	孙君顶
	惠朕堃
	唐朝生
	毋小省

关键词 ：肝脏分割, 转换器, 注意力机制, 特征交互

Abstract：

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.

Key words： Liver Segmentation Transformer Attention Mechanism Feature Interaction

收稿日期: 2021-06-15

ZTFLH:

TP 391.41

基金资助:

河南省科技厅科技攻关项目(No.212102310084)、河南省高等学校重点科研项目(No.22A520027)、苏州大学江苏省计算机信息处理技术重点实验室开放课题项目(No.KJS2048)资助

通讯作者: 毋小省,硕士,副教授,主要研究方向为图像处理、模式识别.E-mail:wuxs@hpu.edu.cn.

作者简介: 孙君顶,博士,教授,主要研究方向为图像处理、模式识别.E-mail: sunjd@hpu.edu.cn.
惠朕堃,硕士研究生,主要研究方向为医学图像分割.E-mail:923351352@qq.com.
唐朝生,博士,讲师,主要研究方向为医学图像处理.E-mail:tcs@hpu.edu.cn.

引用本文:

孙君顶, 惠朕堃, 唐朝生, 毋小省. 基于U-Net的特征交互分割方法[J]. 模式识别与人工智能, 2021, 34(11): 1058-1068. SUN Junding, HUI Zhenkun, TANG Chaosheng, WU Xiaosheng. U-Net Based Feature Interaction Segmentation Method. , 2021, 34(11): 1058-1068.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202111009 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2021/V34/I11/1058

[1] 姜慧研,冯锐杰.基于改进的变分水平集和区域生长的图像分割方法的研究.电子学报, 2012, 40(8): 1659-1664.
(JIANG H Y, FENG R J. Image Segmentation Method Research Based on Improved Variational Level Set and Region Growth. Acta Electronica Sinica, 2012, 40(8): 1659-1664.)
[2] 李敏,梁久祯,廖翠萃.基于聚类信息的活动轮廓图像分割模型.模式识别与人工智能, 2015, 28(7): 665-672.
(LI M, LIANG J Z, LIAO C C. Active Contour Model for Image Segmentation Based on Clustering Information. Pattern Recognition and Artificial Intelligence, 2015, 28(7): 665-672.)
[3] 张荣国,刘小君,董磊,等.物体轮廓形状超像素图割快速提取方法.模式识别与人工智能, 2015, 28(4): 344-353.
(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, 2015, 28(4): 344-353.)
[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. Berlin, Germany: Springer, 2015: 234-241.
[5] HAN X. Automatic Liver Lesion Segmentation Using a Deep Convo-lutional Neural Network Method[C/OL]. [2021-05-21]. https://arxiv.org/pdf/1704.07239.pdf.
[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, 2018, 37(12): 2663-2674.
[7] OKTAY O, SCHLEMTER J, LE FOLGOC L, et al. Attention U-Net: Learning Where to Look for the Pancreas[C/OL]. [2021-05-21]. https://arxiv.org/pdf/1804.03999v2.pdf.
[8] LONG J, SHELHAMER E, DARRELL T. Fully Convolutional Networks for Semantic Segmentation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 3431-3440.
[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. Washington, USA: IEEE, 2016: 770-778.
[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. Washington, USA: IEEE, 2016: 2261-2269.
[11] HE K M, ZHANG X Y, REN S Q, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(9): 1904-1916.
[12] SPERINGENBERG J T, DOSOVITSKIY A, BROX T, et al. Striving for Simplicity: The All Convolutional Net[C/OL]. [2021-05-21]. https://arxiv.org/pdf/1412.6806.pdf.
[13] YU F, KOLTUN V. Multi-scale Context Aggregation by Dilated Con-volutions[C/OL]. [2021-05-21]. https://arxiv.org/pdf/1511.07122v1.pdf.
[14] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature Pyramid Networks for Object Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 936-944.
[15] WANG X L, GIRSHICK R, GUPTA A, et al. Non-local Neural Networks // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 7794-7803.
[16] ZHANG D, ZHANG H W, TANG J H, et al. Feature Pyramid Transformer[C/OL]. [2021-05-21]. https://arxiv.org/pdf/2007.09451.pdf.
[17] WOO S, PARK J, Lee J Y, et al. CBAM: Convolutional Block Attention Module // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 3-19.
[18] BILIC P, CHRIST P F, VORONTSOV E, et al. The Liver Tumor Segmentation Benchmark[C/OL]. [2021-05-21]. https://arxiv.org/pdf/1901.04056.pdf.
[19] CHRIST P F, ELSHAER M E A, ETTLINGER F, et al. Automa-tic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2016: 415-423.
[20] KAVUR A E, GEZER N S, BARIS M, et al. CHAOS Challenge-Combined(CT-MR) Healthy Abdominal Organ Segmentation. Medical Image Analysis, 2021, 69. DOI: 10.1016/j.media.2020.101950.
[21] CAI K, YANG R Q, CHEN H Z, et al. A Framework Combining Window Width-Level Adjustment and Gaussian Filter-Based Multi-Resolution for Automatic Whole Heart Segmentation. Neurocompu-ting, 2017, 220: 138-150.
[22] SAHI K, JACKSON S, WIEBE E. et al. The Value of "Liver Windows" Settings in the Detection of Small Renal Cell Carcinomas on Unenhanced Computed Tomography. Canadian Association of Radiologists Journal, 2014, 65(1): 71-76.
[23] LIU Z, HAN K, WANG Z H, et al. Automatic Liver Segmentation from Abdominal CT Volumes Using Improved Convolution Neural Networks. Multimedia Systems, 2020, 27: 111-124.
[24] LI X, WANG W H, HU X L, et al. Selective Kernel Networks // Proc of the IEEE Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2019: 510-519.
[25] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-Excitation Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.
[26] ZHOU Z W, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet++: A Nested U-Net Architecture for Medical Image Segmentation // Proc of the International Workshop on Deep Learning in Medical Image Analysis. Berlin, Germany: Springer, 2018: 3-11.
[27] GU Z W, CHENG J, FU H Z, et al. CE-Net: Context Encoder Network for 2D Medical Image Segmentation. IEEE Transactions on Medical Imaging, 2019, 38(10): 2281-2292.
[28] FAN T L, WANG G L, WANG X, et al. MSN-Net: A Multi-scale Context Nested U-Net for liver Segmentation. Signal, Image and Video Processing, 2021, 15: 1089-1097