北京生物医学工程

甲皱微循环显微图像去抖动方法的研究

A Stabilizing Method for the Nail-Fold Microcirculation Images

作者：钱翔孔艺颖叶大田

单位：清华大学深圳研究生院生物医学工程研究中心（广东深圳518055）

分类号：

出版年·卷·期（页码）：2011·30·4（363-367）

摘要：

利用微循环显微图像可以长时间无创地监测和分析末端微血管参数，这有助于评估一些如高血压和糖尿病等慢性和老年性疾病对人体造成的长期影响。甲皱微循环显微图像在采集的过程中往往受到被试者指尖运动的影响，产生图像抖动。本文提出了一种利用自组织映射网络分割图像序列，并采用连续两帧的二值化图像的二维互相关消除图像偏移的去抖动方法。结果表明，这种方法可以有效地去除甲皱微循环显微图像的抖动，同时还保留了每一帧图像中的血流模式特点，为后续的参数计算打下了良好的基础。

It is suggested that noninvasively accessing the morphological parameters and flow patterns of the microcirculation system through the optical images for a long period of time can be helpful to evaluate the effect of several senile and chronic diseases such as hypertension and diabetes.The nail-fold microcirculation image sequences are usually unstable because of the motion of the subjects.In this paper, a self-organizing map was firstly applied to segment the image sequences, and the 2-dimentional correlation of the two binary images segmented from successive frames was calculated to stabilize the image sequences.The results indicated that the proposed method eliminated the motion of the image sequences effectively, and moreover the flow pattern of each frame was retained, which can be a foundation for further analysis.

参考文献：

［1］Bonacci E, Santacroce N, D′Amico N，et al.Nail-fold capillaroscopy in the study of microcirculation in elderly hypertensive patients［J］.Arch Gerontol Geriatr, 1996, 22(Suppl.1)：79-83.
［2］Chang CH, Tsai RK, Wu WC, et al.Use of dynamic capillaroscopy for studying cutaneous microcirculation in patients with diabetes mellitus［J］. Microvas Res, 1997, 53(2)：121-127.
［3］Groner W, Winkelman JW, Harris AG,et al.Orthogonal polarization spectral imaging：a new method for study of the microcirculation［J］.Nat Med, 1999, 5：1209-1212.
［4］Goedhart PT, Khalilzada M, Bezemer R, et al.S idestream dark field (SDF) imaging：a novel stroboscopic LED ring-based imaging modality for clinical assessment of the microcirculation［J］. Opt Expr, 2007, 15(23)：15101-15114.
［5］Dobbe JGG, Streekstra GJ, Atasever B,et al.The measurement of functional microcirculatory density and velocity distributions using automated image analysis［J］.Med Biol Eng Comput, 2008, 46(7)：659-670.
［6］Wu CC, Zhang G, Huang TC et al.Red blood cell velocity measurements of complete capillary in finger nail-fold using optical flow estimation［J］.Microvas Res, 2009, 78(3)：319-324.
［7］Demir S, Mirshahi N, Tiba MH,et al.Image processing and machine learning for diagnostic analysis of microcirculation［C/OL］.International Conference on Complex Medical Engineering (CME). DOI：10.1109/ICCME.2009.4906669.
［8］Dong G,Xie M.Color clustering and learning for image segmentation based on neural networks［J］.IEEE Trans on Neur Netw, 2005, 16(4)：925-936.
［9］Kohonen T.The self-organizing map［J］.Neuroco, 1998, 21：1-6.
［10］Ultsch A，Siemon HP.Kohonen’s seIf organizing feature maps for exploratory data analysis［C］.Proceedings of International Neural Networks Conference (INNC), 1990：305-308.

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