北京生物医学工程

腿部磁共振图像脂肪分割方法的研究

Fat Segmentation Method on Thigh MRI

作者：姜佩杰杨春兰吴水才阮祥燕

单位：北京工业大学生命学院生物医学工程中心(北京100124)

分类号：

出版年·卷·期（页码）：2010·29·5（499-452）

摘要：

腿部磁共振图像脂肪分割对于代谢综合征和代谢功能异常诊断具有重要意义，但皮下脂肪和肌肉间脂肪存在连通区域，难以分割。本文提出水平集算法和模糊C均值算法相结合的方法，对腿部磁共振图像脂肪和其他组织进行分割提取。实验结果表明，该方法能够较好地分割出腿部的皮下脂肪组织、肌肉间脂肪组织及其他组织。

Adipose tissue segmentation of thigh magnetic resonance images(MRI) is very valuable in the diagnosis of metabolic syndrome and metabolic dysfunction, however it is more difficult to segment the subcutaneous fat from intermuscular fat because of the connected domain between them in thigh MRI. In this paper, a method combining the level-set and fuzzy C means algorithms was proposed and used for the division and extraction of subcutaneous fat from other tissues in thigh MRI. The experimental results showed that the subcutaneous fat tissue, intermuscular fat tissue and other tissues of thigh could be segmented successfully using this method.

参考文献：

［1］Fujiko Irie, Hiroyasu Iso, Hiroyuki Noda, et al. Associations Between Metabolic Syndrome and Mortality From Cardiovascular Disease in Japanese General Population, Findings on Overweight and Non-Overweight Individuals［J］. Circulation Journal, 2009, 73:1635-1642.
［2］Huang PL. eNOS metabolic syndrome and cardiovascular disease ［J］. Trends in Endocrinology and Metabolism, 2009, 20(6): 295-302.
［3］Ruan XY, Gallagher D, Harris T, et al. Estimating whole body intermuscular adipose tissue from single cross-sectional magnetic resonance images［J］.J Appl Physiol, 2007, 102:748-754.
［4］Heitmann BL,Frederiksen P. Thigh circumference and risk of heart disease and premature death: prospective cohort study［J］. British Medical Journal,2009, 339: b3292.
［5］Kang H, Pinti A,Vermeiren L, et al. Tissue classification for MRI of thigh using a modified FCM method［C］ . Source:Annual International Conference of the IEEE Engineering in Medicine and Biology-Proceedings.29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07，2007：5579-5584.
［6］Pinti A, Hedoux P, Kang H, et al. An automated pixel classification method using surface expansion: Application to MRI image sequence［C］.Beijing, China:IMACS Multiconference on “Computational Engineering in Systems Applications” (CESA),2006:1514 -1519.
［7］Monzon A, Hemler PF, Nalls M, et al. Segmentation of magnetic resonance images of the thighs for a new National Institutes of Health initiative［C］. Medical Imaging 2007: Image Processing, Pts 1-3, Proceedings of the Society of Photo-optical Instrumentation Engineers,(SPIE),2007, 6512: L5123-L5123.
［8］Positano V, Christiansen T, Santarelli MF,et al. Accurate Segmentation of Subcutaneous and Intermuscular Adipose Tissue From MR Images of the Thigh［J］. Journal of Magnetic Resonance Imaging,2009,29(3): 677-684 .
［9］Mattei JP, Fur YL, Cuge N, et al. Segmentation of fascias, fat and muscle from magnetic resonance images in humans: the DISPIMAG software［J］. Magn Reson Mater Phy，2006,19(5): 275–279.
［10］Li YL, Shen Y. An automatic fuzzy c-means algorithm for image segmentation［J］. Soft Computing,2010, 14( 2): 123-128.
［11］Yu ZD, Zou RB, Yu SM. A Modified Fuzzy C-Means Algorithm with Adaptive Spatial Information for Color Image Segmentation［C］. Nashville, TN:2009 IEEE Symposium on Computational Intelligence in Image and Signal Processing, MAR 30-APR 02,2009:48-52.
［12］李宇鑫, 邓双成, 曹莹瑜. 基于水平集方法的医学图像分割［J］.北京石油化工学院学报,2008,16(4):50-54.
［13］Chen ZB, Qiu TS, Ruan S. Fuzzy Adaptive Level Set Algorithm for Brain Tissue Segmentation［C］ . ICSP:2008 9th International Conference on Signal Processing,2008: 1047-1050.
［14］Wang XF, Min H. A Level Set Based Segmentation Method for Images with Intensity Inhomogeneity［C］.Emerging Intelligent Computing Technology and Applications: With Aspects of Artificial Intelligence,2009,5755: 670 -679.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录