基于多特征支持向量机和弹性区域生长的膝软骨自动分割

doi:10.13229/j.cnki.jdxbgxb201605045

吉林大学学报(工学版) ›› 2016, Vol. 46 ›› Issue (5): 1688-1696.doi: 10.13229/j.cnki.jdxbgxb201605045

基于多特征支持向量机和弹性区域生长的膝软骨自动分割

王品¹, 何璇¹, 吕洋¹, 李勇明^1,2, 邱明国², 刘书君¹

1.重庆大学通信工程学院,重庆 400044;
2.第三军医大学生物医学工程学院,重庆 400038

收稿日期:2015-04-21 出版日期:2016-09-20 发布日期:2016-09-20
作者简介:王品(1979-),女,副教授,博士.研究方向:医学图像处理.E-mail:wangpin@cqu.edu.cn
基金资助:
国家自然科学基金项目(61108086,11304382); 中国博士后科学基金项目(2013M532153); 重庆市自然科学基金项目(CSTC 2012jjA40015); 重庆市科技攻关计划项目(cstc2012gg-yyjs0572); 中央高校基本科研业务费项目(CDJZR12160011, CDJZR13160008, CDJZR155507).

Automatic segmentation of articular cartilages using multi-feature SVM and elastic region growing

WANG Pin¹, HE Xuan¹, LYU Yang¹, LI Yong-ming^1,2, QIU Ming-guo², LIU Shu-jun¹

1.College of Communication Engineering,Chongqing University, Chongqing 400044,China;
2.College of Biomedical Engineering, The Third Military Medical University, Chongqing 400038,China

Received:2015-04-21 Online:2016-09-20 Published:2016-09-20

摘要/Abstract

摘要： 为了从膝关节磁共振图像(MRI)中分割出膝软骨,提出一种基于多特征支持向量机(SVM)边缘定位和弹性区域生长的自动分割算法。首先,采用自适应Canny边缘检测算法提取图像主要边缘;再对边缘提取多个图像特征,结合SVM算法对边缘进行分类,完成软骨边缘定位;然后,在软骨边缘的基础上进行种子点及软骨像素区域的选择;之后基于选择的结果采用弹性区域生长进行初步软骨分割;最后,基于先验知识和形态学获得最终膝软骨分割结果。实验结果表明:该算法能够准确、快速地自动分割出膝关节MRI中不同的膝软骨,其中股软骨、胫软骨、髌软骨的平均评价重要指标(DSC)分别可达0.8543、0.8280、0.8703,与手工分割结果具有较高的一致性。

关键词: 信息处理技术, 多特征支持向量机, 弹性区域生长, 膝软骨自动分割

Abstract: We present an algorithm that automatically and accurately segments the cartilages from Magnetic Resonance Images (MRI) of knees using multi-feature Support Vector Machine (SVM) and elastic region growing. First, adaptive canny edge detection is used to extract the main edges of the images. Second, the edge features are extracted and the edges are classified with SVM to complete the location of the cartilage edges. Then, based on the cartilage edges, the seeds and regions of the cartilage are chosen, and the preliminary segmentation of knee cartilages is achieved using the elastic region growing. Finally, the priori knowledge and morphology are used to improve the preliminary segmentation results. Experimental results show that the proposed method can accurately and rapidly segment the knee cartilages with high consistency with manual segmentation results. The proposed method obtains average DSC values of 0.8543, 0.8280 and 0.8703 for the femoral, tibial and patellar cartilages.

Key words: information processing technology, multi-feature support vector machine, elastic region growing, automatic segmentation of knee cartilages

中图分类号:

TN911.73

王品, 何璇, 吕洋, 李勇明, 邱明国, 刘书君. 基于多特征支持向量机和弹性区域生长的膝软骨自动分割[J]. 吉林大学学报(工学版), 2016, 46(5): 1688-1696.

WANG Pin, HE Xuan, LYU Yang, LI Yong-ming, QIU Ming-guo, LIU Shu-jun. Automatic segmentation of articular cartilages using multi-feature SVM and elastic region growing[J]. 吉林大学学报(工学版), 2016, 46(5): 1688-1696.

参考文献

[1] Hani A F M, Kumar D, Malik A S, et al. Multinuclear MR and multilevel data processing: an insight into morphologic assessment of in vivo nnee articular cartilage[J]. Academic Radiology, 2015, 22(1): 93-104.
[2] Peterfy C G, Guermazi A, Zaim S, et al. Whole-organ magnetic resonance imaging score (WORMS) of the knee in osteoarthritis[J]. Osteoarthritis & Cartilage, 2004, 12(3): 177-190.
[3] Hani A F M, Kumar D, Malik A S, et al. Non-invasive and in vivo assessment of osteoarthritic articular cartilage: a review on MRI investigations[J]. Rheumatology International, 2015, 35(1):1-16.
[4] Hani A F M. Fusion of multinuclear magnetic resonance images of knee for the assessment of articular cartilage[C]∥International Conference of the IEEE Engineering in Medicine and Biology Society,Osaka, 2013:6466-6469.
[5] Jaremko J L, Cheng R W, Lambert R G, et al. Reliability of an efficient MRI-based method for estimation of knee cartilage volume using surface registration[J]. Osteoarthritis & Cartilage, 2006, 14(9): 914-922.
[6] König L, Groher M, Keil A, et al. Semi-automatic segmentation of the patellar cartilage in MRI[J].Informatik Aktuell, 2007,25(27):404-408.
[7] Swanson M S, Prescott J W, Best T M, et al. Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees[J]. Osteoarthritis & Cartilage, 2010, 18(3): 344-353.
[8] Shim H, Chang S, Tao C, et al. Knee cartilage: efficient and reproducible segmentation on high-spatial-resolution MR images with the semiautomated graph-cut algorithm method[J]. Radiology, 2009, 251(2): 548-556.
[9] Lee J G, Gumus S, Moon C H, et al. Fully automated segmentation of cartilage from the MR images of knee using a multi-atlas and local structural analysis method[J]. Medical Physics, 2014, 41(9): 092303.
[10] González G, Escalante-Ramírez B. Knee cartilage segmentation using active shape models and local binary patterns[J]. Optics Photonics & Digital Technologies for Multimedia Applications III, 2014, 9138: 91380K.
[11] Parsoon A, Petersen K, Lgel C, et al. Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network[J]. Medical Image Computing and Computer Assisted Intervention (MICCAI), 2013, 8150: 246-253.
[12] Parsoon A, Petersen K, Lgel C, et al. Femoral cartilage segmentation in knee MRI scans using two stage voxel classification[C]∥Conf Proc IEEE Eng Med Biol Soc, Osaka, 2013: 5469-5472.
[13] 庞剑飞, 邱明国, 陈伟,等. 基于边缘检测与支持向量机的关节软骨自动分割算法研究[J]. 第三军医大学学报, 2013, 35(16): 1653-1657.
Pang Jian-fei, Qiu Ming-guo, Chen Wei, et al. Segmenting articular cartilage automatically by edge detection and support vector machine[J]. J Third Mil Med Univ, 2013, 35(16): 1653-1657.
[14] Pang J, Li P Y, Qiu M, et al. Automatic articular cartilage segmentation based on pattern recognition from knee MRI images[J]. Journal of Digital Imaging, 2015,28(6):695-703.
[15] Liu H, Jezek K C. Automated extraction of coastline from satellite imagery by integrating Canny edge detection and locally adaptive thresholding methods[J]. International Journal of Remote Sensing, 2010, 25(5): 937-958.
[16] Gonzalez R C,Woods R E. Digital Image Processing[M]. 3rd ed. US: Prentice Hall, 2009: 784-788.
[17] Theodoridis S, Koutroumbas K. Pattern Recognition[M]. 4th ed. Greece: Elsevier, 2009: 134-137.
[18] Hsu C W, Lin C J. A comparison of methods for multi-class support vector machines[J]. IEEE Transactions on Neural Networks, 2002, 13(2): 415-425.
[19] Hojjatoleslami S A, Kittler J. Region growing:a new approach[J]. IEEE Transactions on Image Processing, 1998, 7(7): 1079-1084.

相关文章 15

[1]	苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.
[2]	徐岩,孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1895-1903.
[3]	黄勇,杨德运,乔赛,慕振国. 高分辨合成孔径雷达图像的耦合传统恒虚警目标检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1904-1909.
[4]	李居朋,张祖成,李墨羽,缪德芳. 基于Kalman滤波的电容屏触控轨迹平滑算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1910-1916.
[5]	应欢,刘松华,唐博文,韩丽芳,周亮. 基于自适应释放策略的低开销确定性重放方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1917-1924.
[6]	陆智俊,钟超,吴敬玉. 星载合成孔径雷达图像小特征的准确分割方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1925-1930.
[7]	刘仲民,王阳,李战明,胡文瑾. 基于简单线性迭代聚类和快速最近邻区域合并的图像分割算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1931-1937.
[8]	单泽彪,刘小松,史红伟,王春阳,石要武. 动态压缩感知波达方向跟踪算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1938-1944.
[9]	姚海洋, 王海燕, 张之琛, 申晓红. 双Duffing振子逆向联合信号检测模型[J]. 吉林大学学报(工学版), 2018, 48(4): 1282-1290.
[10]	全薇, 郝晓明, 孙雅东, 柏葆华, 王禹亭. 基于实际眼结构的个性化投影式头盔物镜研制[J]. 吉林大学学报(工学版), 2018, 48(4): 1291-1297.
[11]	陈绵书, 苏越, 桑爱军, 李培鹏. 基于空间矢量模型的图像分类方法[J]. 吉林大学学报(工学版), 2018, 48(3): 943-951.
[12]	陈涛, 崔岳寒, 郭立民. 适用于单快拍的多重信号分类改进算法[J]. 吉林大学学报(工学版), 2018, 48(3): 952-956.
[13]	孟广伟, 李荣佳, 王欣, 周立明, 顾帅. 压电双材料界面裂纹的强度因子分析[J]. 吉林大学学报(工学版), 2018, 48(2): 500-506.
[14]	林金花, 王延杰, 孙宏海. 改进的自适应特征细分方法及其对Catmull-Clark曲面的实时绘制[J]. 吉林大学学报(工学版), 2018, 48(2): 625-632.
[15]	王柯, 刘富, 康冰, 霍彤彤, 周求湛. 基于沙蝎定位猎物的仿生震源定位方法[J]. 吉林大学学报(工学版), 2018, 48(2): 633-639.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于多特征支持向量机和弹性区域生长的膝软骨自动分割

Automatic segmentation of articular cartilages using multi-feature SVM and elastic region growing

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10