期刊名称：Computational and Structural Biotechnology Journal
印刷版ISSN：2001-0370
出版年度：2020
卷号：18
页码：4063-4070
DOI：10.1016/j.csbj.2020.11.040
出版社：Computational and Structural Biotechnology Journal
摘要：Abnormalities in cell nuclear morphology are a hallmark of cancer. Histological assessment of cell nuclear morphology is frequently used by pathologists to grade ductal carcinoma in situ (DCIS). Objective methods that allow standardization and reproducibility of cell nuclear morphology assessment have potential to improve the criteria needed to predict DCIS progression and recurrence. Aggressive cancers are highly heterogeneous. We asked whether cell nuclear morphology heterogeneity could be incorporated into a metric to classify DCIS. We developed a nuclear heterogeneity image index to objectively, and quantitatively grade DCIS. A whole-tissue cell nuclear morphological analysis, that classified tumors by the worst ten percent in a duct-by-duct manner, identified nuclear size ranges associated with each DCIS grade. Digital image analysis further revealed increasing heterogeneity within ducts or between ducts in tissues of worsening DCIS grade. The findings illustrate how digital image analysis comprises a supplemental tool for pathologists to objectively classify DCIS and in the future, may provide a method to predict patient outcome through analysis of nuclear heterogeneity.
关键词：Nuclear morphology ; Heterogeneity ; Image analysis ; Breast cancer ; Pathology
