计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 220900059-7.doi: 10.11896/jsjkx.220900059

• 交叉&应用 • 上一篇    下一篇

基于边缘引导的多尺度医学影像分割方法

姜灏天1, 王琦智1, 黄扬林1, 章雅琴2, 胡凯1   

  1. 1 湘潭大学计算机学院·网络空间安全学院 湖南 湘潭 411105
    2 中南大学湘雅三医院放射科 长沙 410013
  • 发布日期:2023-11-09
  • 通讯作者: 胡凯(kaihu@xtu.edu.cn)
  • 基金资助:
    国家自然科学基金(61802328);中国大学生创新创业项目(S202110530024)

Medical Image Segmentation Based on Multi-scale Edge Guidance

JIANG Haotian1, WANG Qizhi1, HUANG Yanglin1, ZHANG Yaqin2 andHU Kai1   

  1. 1 School of Computer Science & School of Cyberspace Science,Xiangtan University,Xiangtan,Hunan 411105,China
    2 Department of Radiology,The Third Xiangya Hospital,Central South University,Changsha 410013,China
  • Published:2023-11-09
  • About author:JIANG Haotian,born in 2001,undergraduate.His main research interests include deep learning and medical image processing.
    HU Kai,born in 1984,Ph.D,associate professor,is a member of China Computer Federation.His main research intserests include machine learning,pattern recognition,bioinformatics,and medical image processing.
  • Supported by:
    National Natural Science Foundation of China(61802328) and College Students’ Innovation and Entrepreneurship Project in China(S202110530024).

PDF (PC)

180

摘要： 医学影像的灰阶变化小,分割目标与背景不易区分,因此,进行影像分割是充满挑战性的问题。现有网络模型大多将高频的分割边缘与低频的主体部分统一学习,忽视了高频与低频信息的差异性和两者在图像中占比不同的差别。针对这一问题,提出了基于边缘引导的多尺度卷积神经网络Edge Guided V-Shape Network(EGV-Net),从低频分割主体和高频分割边缘两个特征角度进行针对性学习。其中,低频特征通过编码-解码方式进行特征传递,学习分割目标的主体部分;高频特征则通过边缘提取方法,首先将高频语义信息从分割图谱中提取出来,再将分割边缘过滤分离。高频边缘通过边缘引导模块指导模型对低频特征做出精准的分割,并恢复边缘细节精度。在肝脏影像与ISIC2016数据集上进行的实验结果表明,所提算法对整体分割的把控能力更强,在边缘细节处有更好的分割效果,优于其他模型。

关键词: 深度学习, 医学影像分割, 多尺度特征, 边缘提取, 边缘引导

Abstract: Medical images have small gray-scale changes,and segmentation targets and backgrounds are not easy to distinguish,thus image segmentation is full of challenging problems.Most of the existing models unify the segmented high-frequency edges with the low-frequency subjects for learning,ignoring the difference between high-frequency information and low-frequency information and the difference in the proportion of both in the image.To address this problem,edge guided V-shape network(EGV-Net),a multi-scale convolutional neural network based on edge guidance,is proposed to perform targeted learning from two feature perspectives:low-frequency segmented subjects and high-frequency segmented edges.Among them,the low-frequency features are passed through the feature transfer by the encoder-decoder connection method to learn the main part of the segmentation target.The high-frequency features are firstly extracted from the segmentation mapping by edge extraction method,and then the segmentation edges are filtered and separated from it.The segmented edges of high frequency are guided by edge guidance module to make accurate segmentation of low frequency segmented edges and recover edge detail accuracy.Experimental results in liver images and ISIC2016 show that the proposed algorithm has better control over the overall segmentation and better segmentation effect at the edge details than other models.

Key words: Deep learning, Medical image segmentation, Multi-scale features, Edge extraction, Edge guidance

中图分类号: 

  • TP391
[1]ZHENG G Y,LIU X B,HAN G H.A review of computer-aided detection and diagnosis systems for medical imaging[J].Journal of Software,2018,29(5):1471-1514.
[2]LIN Y,TIAN J.A review of medical image segmentation me-thods[J].Pattern Recognition and Artificial Intelligence,2002,15(2):192-204.
[3]CHIEN Y.Pattern classification and scene analysis[J].IEEETransactions on Automatic Control,1974,19(4):462-463.
[4]PREWITT J M S.Object enhancement and extraction[J].Picture Processing and Psychopictorics,1970,10(1):15-19.
[5]CANNY J.A computational approach to edge detection[J].IEEE Transactionson Pattern Analysis and Machine Intelligence,1986(6):679-698.
[6]SIVAKUMAR V,MURUGESH V.A brief study of image seg-mentation using thresholding technique on a noisy image[C]//International Conference on Information Communication and Embedded Systems(ICICES2014).IEEE,2014:1-6.
[7]OTSU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems,Man,and Cyberne-tics,1979,9(1):62-66.
[8]LEVINE B F,BETHEA C G,THURMOND C D,et al.An organic crystal with an exceptionally large optical second-harmonic coefficient:2-methyl-4-nitroaniline[J].Journal of Applied Phy-sics,1979,50(4):2523-2527.
[9]PITMAN J.Poisson-Dirichlet and GEM invariant distributionsfor split-and-merge transformations of an interval partition[J].Combinatorics,Probability and Compu-ting,2002,11(5):501-514.
[10]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3431-3440.
[11]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Compu-ter-assisted Intervention.Cham:Springer,2015:234-241.
[12]ZHOU Z,RAHMAN SIDDIQUEE M M,TAJBAKHSH N,et al.Unet++:A nested u-net architecture for medical image segmentation[M]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Cham:Springer,2018:3-11.
[13]HUANG H,LIN L,TONG R,et al.Unet 3+:A full-scale connected unet for medical image segmentation[C]//ICASSP 2020-2020 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2020:1055-1059.
[14]ZHANG Z,FU H,DAI H,et al.Et-net:A generic edge-attention guidance network for medical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham:Springer,2019:442-450.
[15]SUN J M,GE Q Q,LI X M,et al.A medical image segmentation network with edge enhancement feature[J].Journal of Electro-nics & Information Technology,2022,44:1-10.
[16]VALANARASU J M J,SINDAGI V A,HACIHALILOGLU I,et al.Kiu-net:Overcomplete convolutional architectures for biomedical image and volumetric segmentation[J].IEEE Transactions on Medical Imaging,2021,41(4):965-976.
[17]MILLETARI F,NAVAB N,AHMADI S A.V-net:Fully convolutional neural networks for volumetric medical image segmentation[C]//2016 fourth international conference on 3D vision(3DV).IEEE,2016:565-571.
[18]LIN T Y,GOYAL P,GIRHICK R,et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2980-2988.
[19]HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep cosssssnvolutional networks for visual recognition[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(9):1904-1916.
[20]GUTMAN D,CODELLA N,CELEBI E,et al.Skin lesion analysis toward melanoma detection:A challenge at the international symposium on biomedical imaging (ISBI) 2016[C]//Hosted by the International Skin Imaging Collaboration (ISIC).2016.
[21]XIAO X,LIAN S,LUO Z,et al.Weighted res-unet for high-quality retina vessel segmentation[C]//2018 9th International Conference on Information Technology in Medicine and Education(ITME).IEEE,2018:327-331.
[22]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7132-7141.
[23]TAKIKAWA T,ACUNA D,JAMPANI V,et al.Gated-scnn:Gated shape cnns for semantic segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:5229-5238.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发