基于改进U2-Net网络的多裂肌MRI图像分割算法研究
作者:
作者单位:

1.桂林电子科技大学 计算机与信息安全学院;2.柳州市人民医院

中图分类号:

TP391.4

基金项目:

国家自然科学(61866009,42164002);广西重点研发计划项目 AB21220037;广西科技计划项目(基地和人才专项)(桂科AD20325004);桂林市科学研究与技术开发项目(20210227-2)


Research on MRI image segmentation algorithm for multifidus muscle based on improved U2-Net network
Author:
Affiliation:

1.School of Computer Science and Engineering,Guilin University of Electronic Technology;2.Department of Spinal Surgery,Liuzhou People'3.'4.s Hospital

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对腰间盘突出患者MRI图像多裂肌病变部位分割精度较低的问题,提出了一种改进的U2-Net网络的新模型,目标是编码和解码的子网络通过一个系列嵌套的跳跃路径来相互连接,这种重新设计的跳跃连接主要是用来降低编码解码子网络中特征图的语义缺失。基于此目的重新设计U2-Net模型中RSU-7,RSU-6,RSU-5,RSU-4中间的跳跃连接,RSU-4F部分不变。此外,为了提取到高质量的多裂肌特征,还加入了通道注意力模块,通过学习每个通道的权重,使网络能够更好地关注对任务有贡献的通道,从而提升模型的性能。为验证模型的有效性,在多裂肌MRI图像数据集上进行实验,发现相较于U-Net、U2-Net、U-Net++网络结构,MIOU、DICE、HD均有提升。实验结果表明,本文提出的算法对于多裂肌的MRI图像分割有较好的效果,能够辅助医生对病情做出判断。

    Abstract:

    To address the problem of low segmentation accuracy of multifracture muscle lesion sites in MRI images of patients with lumbar disc herniation, this paper proposes a new model to improve the U2net network with the goal that the encoding and decoding subnetworks are interconnected by a series of nested jump paths, and this redesigned jump connection is mainly used to reduce the semantic missing of feature maps in the encoding and decoding subnetworks. For this purpose, the jump connections in the middle of RSU-7, RSU-6,RSU-5,RSU-4 in the U2Net model are redesigned, and the RSU-4F part remains unchanged. In addition, the channel attention module was added to extract high quality multifractal muscle features, which effectively helps information flow in the network by using an attention mechanism to increase expressiveness, focus on important features and suppress unnecessary features. To verify the effectiveness of the model, experiments are conducted on the multi-cleft muscle MRI image dataset, and it is found that MIOU, DICE, and HD are improved compared with U-Net, U2-Net, and U-Net++ network structures. The experimental results show that the algorithm proposed in this paper has a good effect on MRI image segmentation of multifidus muscle, which can assist doctors to make judgments on the condition.

    参考文献
    [1] Richard A. Deyo, Sohail K. Mirza. CLINICAL PRACTICE. Herniated Lumbar Intervertebral Disk.[J], The New England Journal of Medicine, 2016, 374(18): 1763-1772.
    [2] Vialle LR, Vialle EN, Suárez Henao JE, et al.Lumbar disc herniation[J].Rev Bras Ortop, 2015,45(1):17-22.
    [3] Alexa S, Hassan R, Amanda R, Stephane F, Mathieu B, Maryse F, et al. Ultrasonography Of Lumbar Multifidus Muscle In University American Football Players[J], Medicine and Science in Sports and Exercise, 2020, 52(7): 1495-1501.
    [4] 陈齐齐,陈立平,金军,等. 多裂肌横截面积与经皮椎间孔镜治疗腰椎间盘突出症患者预后的关系[J]. 实用医学杂志,2021,37(09):1136-1140.
    [5] CHEN Qiqi,CHEN Liping,JIN Jun, et al. Relationship between cross sectional area of multifidus muscle and prognosis of patients with lumbar disc herniation treated by percutaneous intervertebral foramenoscopy[J]. Journal of practical medicine,2021,37(09):1136-1140.
    [6] [5] Samuel R W, Choll W K, Carolyn M E, Lionel J G, Akihito T, Steven R G, Richard L L, et al. Architectural Analysis And Intraoperative Measurements Demonstrate The Unique Design Of The Multifidus Muscle For Lumbar Spine Stability[J], Journal of Bone and Joint Surgery, American Volume, 2009, 91A(1): 176-185.
    [7] [6] 钭大雄, 王君瑞, 陈绍东,等. 单侧腰痛患者腰椎多裂肌萎缩相关因素研究[J]. 浙江医学, 2014(10):4.
    [8] Tou Daxiong, Wang Junrui, Chen Shaodong,et al. Study on factors related to lumbar multifidus muscle atrophy in patients with unilateral low back pain[J]. Zhejiang Medicine, 2014(10):4.
    [9] [7] Kalichman L,Hodges P,Li L,et al. Changes in paraspinal muscles and their association with low back pain and spinal degeneration:CT study[J]. Eur Spine J,2010,19(7):1136-1144.
    [10] [8] Evan Shelhamer, Jonathan Long, Trevor Darrell. Fully Convolutional Networks for Semantic Segmentation.[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, abs/1605.06211(4): 640-651.
    [11] [9] ASLAN M S,FARAG A A,ARNOLD B,et al.Segmentation of vertebrae using level sets with expectation maximization algorithm[C].Proceedings of the 8th IEEE International Symposium on Biomedical Imaging:FromNano to Macro,ISBI 2011,March 30-April 2,2011,Chicago,Illinois,USA.Chicago:IEEE,2011:2010-2013.
    [12] [10] RASOULIAN A,ROHLING R,ABOLMAESUMI P.Lumbar spine segmentation using a statistical multi-vertebrae anatomical shape+pose model[J].IEEE Transactions on Medical Imaging,2013,32(10):1890-1900.
    [13] [11] LIM P H,BAGCI U,BAI L.Introducing willmore flow into level set segmentation of spinal vertebrae[J].IEEE Transactions on Biomedical Engineering,2012,60(1):115-122.
    [14] [12] 何晓云,许江淳,陈文绪.基于改进U-Net网络的眼底血管图像分割研究[J].电子测量与仪器学报,2021,35(10):202-208.
    [15] He Xiaoyun, Xu Jiangchun, Chen Wenxu. Research on fundus vascular image segmentation based on improved U-Net network[J]. Journal of Electronic Measurement and Instrumentation, 2021,35(10):202-208.
    [16] [13] 赵其杰,周安稳,朱俊豪,等.基于PE-Vnet网络的三维骨骼图像分割方法[J].仪器仪表学报,2020,41(7):243-251.
    [17] Zhao Qijie,Zhou Anwen,Zhu Junhao, et al. A three-dimensional skeletal image segmentation method based on PE-Vnet network[J]. Journal of Instrumentation, 2020,41(7):243-251.
    [18] [14] 杨志秀,韩建宁,于本知,等.一种改进的DeepLab V3+的医学图像分割方法[J].国外电子测量技术,2021,40(9):18-23.
    [19] YANG Zhixiu, HAN Jianning, YU Benzhi, et al. An improved medical image segmentation method with DeepLab V3+[J]. Foreign Electronic Measurement Technology, 2021,40(9):18-23.
    [20] [15] ZHANG L,WANG H.A novel segmentation method for cervical vertebrae based on PointNet++and converge segmentation[J].Computer Methods and Programs in Biomedicine,2021,200(2):105798.
    [21] [16] KUOK C P,HSUE J Y,SHEN T L,et al.An effective CNN approach for vertebrae segmentation from 3D CT images[C].2018 Pacific Neighborhood Consortium Annual Conference and Joint Meetings(PNC).San Francisco:IEEE,2018:1-6.
    [22] [17] RONNEBERGER O,FISCHER P,BROX T.U-net:Convolutional networks for biomedical image segmentation[C].International Conference on Medical Image Computing and Computer-Assisted Intervention.Munich:Springer,Cham,2015:234-241.
    [23] [18] OKTAY O,SCHLEMPER J,FOLGOC L L,et al.Attention u-net:Learning where to look for the pancreas[EB/OL].(2018-04-11)[2022-03-20]
    [24] [19] ZHOU Z W,SIDIQUEE M M R,TAJBAKNSH N,et al.UNet++:A nested U-Net archifecture for medical image segmentation[C].Proceedings of lntermaional Workshop on Deep Learning in Medical Image Analysis and International Workshop on Multimodal Learning for Clinical Decision Support,Heidelberg:Springer,2018:3-11.
    [25] [20] 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),Barcelona,Spain:IEEE,2020:1055-1059.
    [26] [21] Xuebin Q, Zichen Z, Chenyang H, Masood D, Osmar R Z, Martin J, et al. U2-Net: Going deeper with nested U-structure for salient object detection[J], Pattern recognition,2020, 106
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

王子民,周悦,关挺强,郭欣,胡巍,王茂发.基于改进U2-Net网络的多裂肌MRI图像分割算法研究[J].南京信息工程大学学报,,():

复制
分享
文章指标
  • 点击次数:133
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2023-07-17
  • 最后修改日期:2023-10-22
  • 录用日期:2023-10-27

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司