期刊文献+

肺结节图像的自动分割与识别 预览

Automated segmentation and identification of pulmonary nodule images
在线阅读 下载PDF
收藏 分享 导出
摘要 为实现肺结节自动分析与识别,研究基于模糊建模思想和迭代相对模糊连接度(IRFC)算法的自动解剖识别(AAR)方法。该方法包括5个步骤:收集图像数据,用于模型构建和测试AAR;叙述胸腔中每个器官的精确定义,根据定义提取肺部轮廓;建立分层模糊解剖模型;利用分层模型识别和定位肺部;根据层级结构提取肺部轮廓。将分割好的肺部图片作为输入送入卷积神经网络进行肺部结节检测,通过使用VGG-16网络模型,在天池医疗AI大赛的数据集上实现了92.72%的目标检测准确率。 To realize automatic analysis and recognition of pulmonary nodules,an automatic anatomy recognition(AAR)metho-dology based on fuzzy modeling ideas and an iterative relative fuzzy connectedness(IRFC)delineation algorithm was studied.The methodology consisted of five main steps including gathering image date for both building models and testing the AAR algorithms,formulating precise definitions of each organ in the thorax and delineating lungs following these definitions,building hie-rarchical fuzzy anatomy models,recognizing and locating lungs with the hierarchical models,and delineating the lungs following the hierarchy.The segmented lung images were taken as input into the convolutional neural network for pulmonary nodule detection.By the use of the VGG-16 network model,a target detection accuracy of 92.72%is achieved on the data set of the Tianchi Medical AI Contest.
作者 郭桐 谢世朋 GUO Tong;XIE Shi-peng(College of Telecommunication and Information Engineering,Nanjing University of Posts and Telecommunication,Nanjing 210003,China)
出处 《计算机工程与设计》 北大核心 2019年第2期467-472,共6页 Computer Engineering and Design
基金 国家自然科学基金项目(11547155) 教育部-中国移动科研基金项目(MCM20150504) 江苏省科技重点研发计划-产业前瞻与共性关键技术基金项目(BE2016001-4) 南京邮电大学科研基金项目(NY214026、NY217035) 江苏省高校自然科学基金项目(17KJB510038).
关键词 模糊模型 层级结构 迭代相对模糊连接度 肺部分割 卷积神经网络 fuzzy models hierarchy iterative relative fuzzy connectedness lung segmentation convolution neural network
作者简介 郭桐(1993-),男,江苏扬州人,硕士研究生,研究方向为图像处理与图像通信。E-mail:guotlucky@163.com;谢世朋(1982-),男,安徽界首人,副教授,硕士生导师,研究方向为医学图像处理.
  • 相关文献

参考文献3

二级参考文献24

  • 1MANSOOR A, BAGCI U, XU Z, et al. A generic approach to pathological lung segmentation[J]. IEEE Transactions on Medical Imaging, 2014, 33(12): 2293-2310. doi: 10.1109/TMI. 2014.2384693. 被引量:1
  • 2WANG Nana and CHEN Shuyue. Research progress of lung parenchyma segmentation techniques based on CT images [J] Electronic Test. 2012(4): 38-43. doi: 10.3969/j.issm1000-8519.2012.04.009. 被引量:1
  • 3CHEN Qi, XIONG Boli, LU Jun, et al. Improved two- dimensional Otsu image segmentation method and faust recursive realization[J]. Journal of Electronics & Information Techuology, 2010, 32(5): 1100-1104. doi: 10.3724/SP.J.11.16. 2009.00627. 被引量:1
  • 4JIA Tong, MENG Lu, ZHAO Dazhe, et al. Automatic lung parenchyma segmentation on CT image[J]. Journal of Northeastern University (Natural Science), 2008, 29(7): 965-968. doi: 10.3321/j. issn:1005-3026.2008.07.014. 被引量:1
  • 5YANG Jianfeng, ZHAO Juanjuan, QIANG Yan, et al. Lung CT Image segmentation combined multi-scale watershed method and region growing method[J]. Computer Engineering and Design, 2014, 35(1): 213-217. doi: 10.3969/ j.issn. 1000-7024.2014.01.040. 被引量:1
  • 6QIAN Y and WEI G. Lung nodule segmentation using EM algorithmiC]. Sixth International Conference on Intelligent Human-Machine Systems and Cybernetics, Hangzhou, 2014: 20-23. 被引量:1
  • 7LIU Jia and WANG Hongqi. A graph cuts based interactive image segmentation method[J]. Journal of Electronics Information Technology, 2008, 30(8): 1973-1976. 被引量:1
  • 8DAI S, LU K, DONG J, et al. A novel approach of lung segmentation on chest CT images using graph cuts[J]. Neitrocomputing, 2015, 168: 799-807. doi: 10.1016/j.neucom. 2015.05.044. 被引量:1
  • 9BIAN Xiaoyue and WU Yam A method of careful lung segmentation based on CT images[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2010, 22(5): 665-668. doi: 10.3979/j.issn. 1673-825X.2010.05.028. 被引量:1
  • 10SUDHA V and JAYASHREE P. Lung nodule detection in CT images using thresholding and morphological operations[J]. International Journal of EmeTying Science and Engineering (IJESE), 2012, 1(2): 17-21. 被引量:1

共引文献13

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈