Abstract：
The practice of cytopathology has been significantly refined in recent years, largely through the creation of consensus rule sets for the diagnosis of particular specimens (Bethesda, Milan, Paris, and so forth). In general, these diagnostic systems have focused on reducing intraobserver variance, removing nebulous/redundant categories, reducing the use of \"atypical\" diagnoses, and promoting the use of quantitative scoring systems while providing a uniform language to communicate these results. Computational pathology is a natural offshoot of this process in that it promises 100% reproducible diagnoses rendered by quantitative processes that are free from many of the biases of human practitioners.
摘要：
近年来，细胞病理学的实践得到了显着改善，主要通过为特定标本的诊断创建共识规则集(Bethesda，米兰,巴黎,等等)。总的来说,这些诊断系统专注于减少观察者内部的差异，删除模糊/冗余类别，减少“非典型”诊断的使用，并促进定量评分系统的使用，同时提供统一的语言来传达这些结果。计算病理学是该过程的自然分支，因为它承诺通过定量过程提供100％可重复的诊断，而没有人类从业者的许多偏见。
