Long Xi, Cleveland W Louis, Yao Y Lawrence
Mechanical Engineering Department, Columbia University, 500 West 120th Street, 220 Mudd. MC 4703, New York, NY 10027, USA.
Comput Biol Med. 2006 Apr;36(4):339-62. doi: 10.1016/j.compbiomed.2004.12.002.
Detection of unstained viable cells in bright field images is an inherently difficult task due to the immense variability of cell appearance. Traditionally, it has required human observers. However, in high-throughput robotic systems, an automatic procedure is essential. In this paper, we formulate viable cell detection as a supervised, binary pattern recognition problem and show that a support vector machine (SVM) with an improved training algorithm provides highly effective cell identification. In the case of cell detection, the binary classification problem generates two classes, one of which is much larger than the other. In addition, the total number of samples is extremely large. This combination represents a difficult problem for SVMs. We solved this problem with an iterative training procedure ("Compensatory Iterative Sample Selection", CISS). This procedure, which was systematically studied under various class size ratios and overlap conditions, was found to outperform several commonly used methods, primarily owing to its ability to choose the most representative samples for the decision boundary. Its speed and accuracy are sufficient for use in a practical system.
由于细胞外观的巨大变异性，在明场图像中检测未染色的活细胞是一项固有的困难任务。传统上，这需要人工观察者。然而，在高通量机器人系统中，自动程序至关重要。在本文中，我们将活细胞检测表述为一个有监督的二值模式识别问题，并表明具有改进训练算法的支持向量机（SVM）能提供高效的细胞识别。在细胞检测的情况下，二分类问题产生两类，其中一类比另一类大得多。此外，样本总数极大。这种组合对支持向量机来说是个难题。我们用一种迭代训练程序（“补偿性迭代样本选择”，CISS）解决了这个问题。该程序在各种类大小比率和重叠条件下进行了系统研究，结果发现它优于几种常用方法，主要是因为它能够为决策边界选择最具代表性的样本。其速度和准确性足以用于实际系统。
