您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (3): 25-33.doi: 10.6040/j.issn.1672-3961.0.2022.024

• • 上一篇    

基于改进双路径网络的上肢肌肉骨骼异常检测

黄彩云1,陈德武2,何吉福1,胡艺1,王楠1,陈沛1   

  1. 1.甘肃中医药大学体育健康学院, 甘肃 兰州 730000;2.中国石油勘探开发研究院西北分院地球物理研究所, 甘肃 兰州 730020
  • 发布日期:2022-06-23
  • 作者简介:黄彩云(1986— ),女,甘肃白银人,讲师,硕士,主要研究方向为运动损伤与康复. E-mail:644380378@qq.com
  • 基金资助:
    甘肃省自然科学基金资助项目(1606RJZA197);甘肃省教育科学“十四五”规划2021年度“双减”专项课题(GS[2021]GHBZX269);甘肃中医药大学科技创新项目(30740301)

Detection of upper limb musculoskeletal abnormality based on improved dual path network

HUANG Caiyun1, CHEN Dewu2, HE Jifu1, HU Yi1, WANG Nan1, CHEN Pei1   

  1. 1. School of Physical Education and Health, Gansu University of Traditional Chinese Medicine, Lanzhou 730000, Gansu, China;
    2. Institute of Geophysics, Research Institute of Petroleum Exploration &
    Development-Northwest, Lanzhou 730020, Gansu, China
  • Published:2022-06-23

摘要: 针对传统的基于专家知识经验医学图像病变检测算法存在稳定性较差、计算复杂度较高、无法适应新出现病例等问题,提出一种基于改进双路径网络(dual path networks with skip connections, SkipConn_DPN)的上肢肌肉骨骼X射线照片异常检测方法。借助深度学习卷积神经网络在图像处理领域的优异性能,整合改进的深度残差网络在图像特征重用和密集连接卷积网络可以不断挖掘新图像特征的优点,并引入可以实现不同尺度图像特征融合的多条跳跃连接。在不增加计算资源消耗的前提下,该方法训练的8个SkipConn_DPN-92网络模型对MURA验证集中不同上肢研究类型的准确率均高于相同参数设置下训练的DPN-92、ResNet-101、ResNeXt-101(32×4d)和DenseNet-169网络模型,分别高约1.64%、2.21%、1.87%和3.22%,并且在临床上可以实现上肢肌肉骨骼异常的实时检测。提出的方法易于实现软件模块,可以作为放射科医生初步诊断的可视化辅助工具,具有良好的应用前景。

关键词: 医学图像病变检测, 上肢肌肉骨骼异常, 双路径网络, 深度残差网络, 密集连接卷积网络

中图分类号: 

  • TP399
[1] WALSH D. Recent progress in radiography[J]. Hospital, 1899, 27(680):5-7.
[2] JORDAN A C. Duodenal obstruction as shown by radiography[J]. British Medical Journal, 1911, 1(2629):1172-1174.
[3] WAITE S, SCOTT J, GALE B, et al. Interpretive error in radiology[J]. American Journal of Roentgenology, 2016, 208(4):1-11.
[4] ELIZABETH A K, KEVIN S B, ROBERT T C, et al. Long radiology workdays reduce detection and accom-modation accuracy[J]. Journal of the American College of Radiology Jacr, 2010, 7(9):698-704.
[5] NAKAJIMA Y, YAMADA K, IMAMURA K. et al. Radiologist supply and workload: international comparison[J]. Radiat Med, 2008(26):455-465.
[6] NGAN K H, GARCEZ A D, KNAPP K M, et al. Making densenet interpretable a case study in clinical radiology[J/OL].(2019-12-05)[2021-12-26]. https://doi.org/10.1101/19013730.
[7] RAJPURKAR P, IRVIN J, BAGUL A, et al. MURA:large dataset for abnormality detection in musculoskeletal radiographs[J/OL].(2018-05-22)[2021-12-26]. https://arxiv.org/abs/1712.06957.
[8] WOOLF A D, PFLEGER B. Burden of major muscu-loskeletal conditions[J]. Bulletin of the World Health Organisation, 2003, 81(9):646-656.
[9] SHIE C K, CHUANG C H, CHOU C N, et al. Transfer representation learning for medical image analysis[C] // 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC). Milan, Italy: IEEE, 2015: 711-714.
[10] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[11] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436.
[12] 周涛, 霍兵强, 陆惠玲,等. 残差神经网络及其在医学图像处理中的应用研究[J]. 电子学报, 2020, 48(7): 1436-1447. ZHOU Tao, HUO Bingqiang, LU Huiling, et al. Research on residual neural network and its application on medical image processing[J]. Acta Electronica Sinica, 2020, 48(7): 1436-1447.
[13] KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[14] SIMONYAN K, ZISSERMAN A. Verydeep convolutional networks for large-scale image recognition[C] //2015 3rd International Conference on Learning Repres-entations(ICLR). San Diego, USA: Conference Track Pro-ceedings, 2015: 1826-1832.
[15] SZEGEDY C, LIU W, JIA Y, et al. Goingdeeper with convolutions[C] //2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Boston, USA:IEEE, 2015: 1-9.
[16] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C] //Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition( CVPR). Las Vegas, USA: IEEE, 2016: 770-778.
[17] XIE S, GIRSHICK R,P DOLLÁR, et al. Aggregated residual transformations for deep neural networks[C] //2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Hawaii, USA: IEEE, 2017: 5987-5995.
[18] HUANG G, LIU Z, LAURENS V D M, et al. Densely connected convolutional networks[C] //2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Hawaii, USA: IEEE, 2017: 2261-2269.
[19] CHEN Y P, LI J N, XIAO H X, et al. Dual path networks[J/OL].(2017-08-01)[2021-12-26]. https://arxiv.org/abs/1707.01629v2.
[20] 李海山, 陈德武, 吴杰,等. 叠前随机噪声深度残差网络压制方法[J]. 石油地球物理勘探, 2020, 55(3): 493-503. LI Haishan, CHEN Dewu, WU Jie, et al. Pre-stack random noise suppression with deep residual network[J]. Oil Geophysical Prospecting, 2020, 55(3): 493-503.
[21] RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmen-tation[J]. Lect Notes Comput Sci, 2015(9351): 234-241.
[22] 冯毅博, 仇大伟, 曹慧, 等. 基于深度可分离稠密网络的新型冠状病毒肺炎X线图像检测方法研究[J]. 生物医学工程学杂志, 2020(4): 557-565. FENG Yibo, QIU Dawei, CAO Hui, et al. Research on coronavirus disease 2019(COVID-19)detection method based on depthwise separable DenseNet in chest X-ray images[J]. Journal of Biomedical Engineering, 2020(4): 557-565.
[23] JIA D, WEI D, SOCHER R, et al. ImageNet:a large-scale hierarchical image database[J]. Proc of IEEE Computer Vision & Pattern Recognition, 2009:248-255.
[24] KINGMA D, BA J. Adam:a method for stochastic optimization[J/OL].(2017-01-30)[2021-12-26]. https://arxiv.org/abs/1412.6980.
[25] SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020, 128(2):336-359.
[26] ZHOU B, KHOSLA A, LAPEDRIZA A, et al. Learningdeep features for discriminative localization[C] //2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas, USA: IEEE, 2016: 2921-2929.
[27] BELLO I, ZOPH B, LE Q, et al. Attentionaugmented convolutional networks[C] //2019 IEEE/CVF Interna-tional Conference on Computer Vision(ICCV). Seoul, Korea: IEEE, 2019: 3286-3295.
[1] 黄劲潮. 深度残差特征与熵能量优化运动目标跟踪算法[J]. 山东大学学报 (工学版), 2019, 49(4): 14-23.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!