GReD, CNRS, INSERM, Université Clermont Auvergne , Clermont-Ferrand, France58.
Department of Molecular, Cellular & Developmental Biology, Yale University , New Haven, CT, USA.
Nucleus. 2020 Dec;11(1):315-329. doi: 10.1080/19491034.2020.1845012.
NucleusJ 1.0, an ImageJ plugin, is a useful tool to analyze nuclear morphology and chromatin organization in plant and animal cells. NucleusJ 2.0 is a new release of NucleusJ, in which image processing is achieved more quickly using a command-lineuser interface. Starting with large collection of 3D nuclei, segmentation can be performed by the previously developed Otsu-modified method or by a new 3D gift-wrapping method, taking better account of nuclear indentations and unstained nucleoli. These two complementary methods are compared for their accuracy by using three types of datasets available to the community at . Finally, NucleusJ 2.0 was evaluated using original plant genetic material by assessing its efficiency on nuclei stained with DNA dyes or after 3D-DNA Fluorescence hybridization. With these improvements, NucleusJ 2.0 permits the generation of large user-curated datasets that will be useful for software benchmarking or to train convolution neural networks.
NucleusJ 1.0 是一个 ImageJ 插件,是分析植物和动物细胞核形态和染色质组织的有用工具。NucleusJ 2.0 是 NucleusJ 的新版本,它使用命令行用户界面更快地实现图像处理。从大型 3D 核集合开始,可以通过先前开发的 Otsu 改进方法或新的 3D 包装方法进行分割,更好地考虑核凹陷和未染色的核仁。通过使用社区提供的三种数据集,比较了这两种互补方法的准确性。最后,使用原始植物遗传材料评估了 NucleusJ 2.0,通过评估其对用 DNA 染料染色的核或 3D-DNA 荧光杂交后的核的效率。通过这些改进,NucleusJ 2.0 允许生成大型用户 curated 数据集,这些数据集将有助于软件基准测试或训练卷积神经网络。