活体细胞图像斑点的自动提取和跟踪方法  

Automated methods for particle tracking of the intracellular transport of clathrin-coated pits and vesicles

作　　者：葛云[1] 章东[1] 

机构地区：[1]南京大学电子科学与工程系,南京210093

出　　处：《东南大学学报（自然科学版）》2009年第3期464-467,共4页Journal of Southeast University：Natural Science Edition

基　　金：江苏省教育厅产业化资助项目(JHB06-01)

摘　　要：采用基于小波分解多尺度系数乘积的方法检测图像中的斑点,同时提出了基于贪婪思想的可以自动处理目标分裂和合并的模型,综合目标信息对轨迹进行跟踪.对Adaptor和Clathrin图像分割取得了比较理想的结果,Adaptor图像中的目标识别率98.61%,Clathrin图像中目标识别率达到97.65%.新的跟踪算法在处理轨迹合并和分裂方面有明显优势,对斑点跟踪效率达到为98.05%.结果表明,新的算法能有效地识别和跟踪图像中的斑点.从生物学角度,更有效的识别有助于更好地理解质膜的通道运输机制以及因为其不正常工作引起的疾病.The problem of particle detection and tracking is addressed to understand the processes at the cellular level in live cell imaging. A new tracking approach is proposed based on a greedy algo- rithm, stable match for point tracking and ＆trous wavelet transform decomposition. It can handle track creation, occlusion and termination effectively. The detection rates are 98.61% and 97.65% for Adaptor and Clathrin in microscopy images respectively. The proposed tracking approach demonstrates an obvious advantage in solving merging and splitting issues compared with traditional methods in simulated images, and the tracking accuracy achieves 98.05 %. The preliminary results show that the proposed methods are able to identify and track most of the particles successfully, and better understanding can be provided about the Clathrin-dependent pathway of membrane vesicular traffic and the disease ramifications caused by their malfunctions from a biological point of view.

关 键 词：小波分解 显微镜图像 图像分割 目标跟踪 分裂合并 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]