• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Optical Investigations of Cells In Vitro and In Vivo >High-speed real-time data classification and cell sorting using discriminant functions and probabilities of misclassification for stem cell enrichment and tumor purging
【24h】

High-speed real-time data classification and cell sorting using discriminant functions and probabilities of misclassification for stem cell enrichment and tumor purging

机译：利用判别函数和干细胞富集和肿瘤清除错误分类的概率进行高速实时数据分类和细胞分类

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Abstract: Data analysis and cell sorting are both fundamentally the same except in terms of the time available to make classification decisions. In the case of cell sorting the cell classification decisions must be made in real-time (in the case of cell sorting, real-time means in about 625 microseconds on this system). This dictates an approach to classification which can be implemented at memory speeds or in pre-programmed hardware. We have been developing new high-speed lookup table transformation methods, suitable for real-time data classification or cell sorting based on statistical classifiers. Multiparameter data mixtures of human MCF-7 breast cancer cells and human bone marrow were analyzed by discriminant function analysis. Cell identification tags, implemented as additional correlated listmode parameters not used for these analyses, were used to uniquely identify each cell type and to compare classifier results. The performance of classifier systems was also assessed using ROC ('receiver operating characteristics') analysis. The effectiveness of the classification system for cell sorting can be evaluated using molecular characterizations of sorted cells, either in small numbers or at single-cell level. !10
机译：摘要：数据分析和单元格排序从根本上来说都是相同的，只是可用于做出分类决策的时间不同。在进行细胞分类的情况下，必须实时做出细胞分类决定（在细胞分类的情况下，该系统上的实时时间约为625微秒）。这规定了一种分类方法，该方法可以以存储器速度或在预编程的硬件中实现。我们一直在开发新的高速查找表转换方法，适用于基于统计分类器的实时数据分类或单元分类。通过判别函数分析来分析人MCF-7乳腺癌细胞和人骨髓的多参数数据混合物。作为这些分析未使用的其他相关列表模式参数实现的单元格标识标签用于唯一标识每种单元格类型并比较分类器结果。分类器系统的性能也使用ROC（“接收机工作特性”）分析进行了评估。可以使用少量或单细胞水平的分选细胞的分子表征来评估分类系统对细胞分选的有效性。 ！10

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号