期刊文献+

Snake-GVF法和Snake法计算左心室容积的比较研究 被引量:1

Comparison of Snakes with and Without Gradient Vector Flow for Quantification of Left Ventricular Volumes
下载PDF
导出
摘要 目的:针对心脏核磁共振(MR)图象,分析比较运用Snake-GVF法和Snake法确定左心室(LV)内膜边界,计算LV容积的有效性。方法:对27组临床MR图象进行LV容积的计算,包括14名成人(9男5女,平均年龄55.0±23.3岁),3名幼儿(10男3女,平均年龄2.7±2.1岁)。手工勾画法结果作为评价的金标准,将Snake-GVF法与手工勾画法以及Snake-GVF法与Snake法进行线性回归分析,获得直线回归方程与相关系数。结果:Snake-GVF法[y(mL)]与手工勾画法[x(mL)]的回归方程与相关系数为:成人时y=1.008x-0.517和0.996;幼儿时y=1.174x-2.542和0.992。Snake-GVF[x(mL)]法与Snake法[y(mL)]的回归方程与相关系数:成人时y=0.495x+2.301和0.932,幼儿时y=0.637x+1.551和0.912。结论:Snake-GVF法比Snake法更加能够有效地计算心脏MR图象的LV容积。 Objective: We compared the validation with and without gradient vector flow (Snake-GVF) of estimating left ventricular (LV) volumes by Snake for cardiac cine magnetic resonance imaging (MRI). Methods: 27 sets of clinic MRI data were used, including 14 adults(9men, 5women, 55.0±23.3years ) and 13 children(10boys, 3girls, 2.7±2. 1years). LV volumes were calculated by adding the areas surrounded by the extracted contour, and those estimated by manual tracing were considered as a gold standard. SnakeGVF with manual tracing and Snake-GVF with Snake were analyzed by linear regression method. Results: Volumes estimated by Snake-GVF [y(mL)]correlated well with those estimated by manual tracing[x(mL)7. In adult cases, the regression equation and correlation coefficient were y=1. 008x-0. 517and 0. 996, respectively. In pediatric cases, they were y=1. 174x-2. 542 and 0. 992, respectively. Volumes by Snake are considerably underestimated compared to those estimated by Snake-GVF. In adult cases, the regression equation and correlation coefficient were y=0. 495x+2. 301and 0. 932, respectively. In pediatric cases, they were y= 0. 637x+1. 551 and 0. 912, respectively. Conclusion: Snake-GVF can more efficiently calculate LV volume compared to Snake for cardiac cine MRI.
出处 《数理医药学杂志》 2008年第4期389-392,共4页 Journal of Mathematical Medicine
关键词 Snake-GVF法 Snake法 LV容积 Snake-GVF Snake LV volume
  • 相关文献

参考文献6

  • 1Kass M, Witkin A, Terzopoulos D. Snakes.- active contour models. Int J Comput Vision, 1987,1(4), 321-331.
  • 2Xu C, Prince JL. Snakes, shapes, and gradient vector flow. IEEE Trans Imag Proc. 1998,7 (3), 359-369.
  • 3Nobuyoshi Tanki, Kenya Murase, Masayuki Kumashiro, et al. Quantification of Left Ventricular Volumes from Cardiac Cine MRI Using Active Contour Model Combined with Gradient Vector Flow. Magnetic Resonance in Medical Science, 2005, 4(4) :191-196.
  • 4李天庆,张毅,刘志,胡东成.Snake模型综述[J].计算机工程,2005,31(9):1-3. 被引量:47
  • 5栾红霞,戚飞虎.一种新的用于MR脑图像分割的主动轮廓模型[J].仪器仪表学报,2004,25(z1):558-560. 被引量:7
  • 6扈琳,崔炜.左心室容积的测量方法[J].临床荟萃,2004,19(11):655-656. 被引量:2

二级参考文献22

  • 1[1]Kass M,Witkin A,Terzopouls D. Snake : active contour models. Int. J. Computer Vision, 1987,1: 321~ 331.
  • 2[2]Tim McInerney,Demtri Terzopoulos. Deformable models in medical image analysis:a survey. Medical Image Analysis, 1996,1: 91~ 108.
  • 3[3]L.D. Cohen. On active contour models and balloons. In CVGIP: Image Understanding, 1991,53 (2): 211 ~ 218.
  • 4[4]C Xu, J L Prince. Snakes, spapes, and gradient vector Flow. IEEE Transaction on Image Processing, 1998,7:359~369.
  • 5[5]Tim McInerney,Demtri Terzopoulos. T-snakes:Topology adaptive snakes. Medical Image Analysis, 2000,4:73~91.
  • 6Kass M,Witkin A,Terzopoulos D.Snakes:Active Contour Models.International Journal of Computer Vision,1987:321-331
  • 7Amini A A,Tehrani S,Weymouth T E.Using Dynamic Programming for Minimizing the Energy of Active Contours in the Presence of Hard Constraints.Proc.Second International Conference on Computer Vision,1988 : 95-99
  • 8Cohen L D.On Active Contour Models and Balloons.CVGIP(53),1991,(2):211-218
  • 9Xu C,Prince P L.Snakes,Shapes,and Gradient Vector Flow.IEEE Trans.on Image Processing,1998,7: 359-369
  • 10Terzopoulos D.Matching Deformable Models to Images.Technical Digest Series: Topical Meeting in Machine Vision,1987,12:160-163

共引文献53

同被引文献8

  • 1CORSI C, LAMBERTI C, CATAEANO O, et al. Semi - automated quantification of left ventricular volumes and mass from cardiac magnetic resonance images by level set models [ C] // Computers in Cardiology. Chicago: IEEE, 2004:149 - 152.
  • 2de PABLO M M G, MALPICA N, LEDESMA-CARBAYO M J, et al. Semi automatic estimation and visualization of left ventricle volumes in cardiac MRI [C]// Computers in Cardiology. Lyon, France: IEEE, 2005:339 -402.
  • 3KASS M, WITKIN A, TERZOPOULOS D. Snakes: Active contour models [J]. Intemational Journal of Computer Vision, 1988, 1 (4) : 321 -331.
  • 4XU C, PRINCE J L. Snakes, shapes, and gradient vector flow [ J]. IEEE Transactions on Image Processing, 1998, 7(3):359 -369.
  • 5OSMAN N F, McVEIGH E R, PRINCE J L. Imaging heart motion using harmonic phase MRI [J] IEEE Transactions on Medical Imaging, 2000, 19(3): 186 -202.
  • 6HORN B K P, SCHUNCK B G. Determining optical flow [J]. Artificial Intelligence, 1981, 17(1): 185-203.
  • 7LUCAS B D, KANADE T. An iterativc image registration technique with an application to stereo vision [C]// Proceedings of Imaging Understanding Workshop. Vancouver, BC, Canada: [ s. n. ], 1981: 674 - 679.
  • 8陈邦忠,涂建平,王秀坛,彭应宁.基于梯度的光流计算方法中梯度计算对性能的影响[J].计算机工程与应用,2003,39(2):75-76. 被引量:7

引证文献1

二级引证文献1

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