基于局部时序特征的细胞视频动态形变度量和分类  

Cell Dynamic Morphology Characterization and Classification Based on Local Temporal Feature

作　　者：李衡[1,2] 庞枫骞 姜彬[3] 刘志文 LI Heng;PANG Feng-qian;JIANG Bin;LIU Zhi-wen(School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China;School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China;Division of IT and Info Management, China Scholarship Council, Beijing 100081, China)

机构地区：[1]北京理工大学信息与电子学院,北京100081 [2]北京理工大学光电学院,北京100081 [3]国家留学基金管理委员会信息资源部,北京100081

出　　处：《北京理工大学学报》2020年第5期570-575,共6页Transactions of Beijing Institute of Technology

摘　　要：使用植皮手术后小鼠的淋巴细胞作为研究目标,针对其动态形变提出一种局部形变特征,用于提取细胞形变过程中的时序信息和空间信息.该特征提取算法被应用在淋巴细胞形变数据集上,并与多个基于图像特征的形变度量算法进行了比较.实验结果表明,局部形变特征能根据形变特性准确分类细胞,在度量和分类细胞动态形变方面比基于图像特征的算法更加有效.Cell morphology is often used as a proxy measurement of cell status to understand cell physiology.Hence,the interpretation of cell dynamic morphology is a meaningful task in biomedical research.Mouse lymphocytes were collected to observe the dynamic morphology,and two datasets were thus set up.Local temporal feature was proposed to consider spatial heterogeneity and temporal regularity of cell dynamic morphology.The local temporal feature was applied to the video data of cell dynamic morphology,and compared with existing methods.Experiment results show that,the local temporal feature can outperform the existing methods and provide remarkable advances in the accuracy and robustness of the classification on both datasets.

关 键 词：显微视频图像 细胞动态形变 局部时序特征 

分 类 号：R319[医药卫生—基础医学]