National Institute of Biomedical Imaging and Bioengineering, NIH, Bethesda, 20892, USA.
University of Maryland, College Park, 20740, USA.
Sci Rep. 2021 Jan 28;11(1):2561. doi: 10.1038/s41598-021-81590-0.
Biologists who use electron microscopy (EM) images to build nanoscale 3D models of whole cells and their organelles have historically been limited to small numbers of cells and cellular features due to constraints in imaging and analysis. This has been a major factor limiting insight into the complex variability of cellular environments. Modern EM can produce gigavoxel image volumes containing large numbers of cells, but accurate manual segmentation of image features is slow and limits the creation of cell models. Segmentation algorithms based on convolutional neural networks can process large volumes quickly, but achieving EM task accuracy goals often challenges current techniques. Here, we define dense cellular segmentation as a multiclass semantic segmentation task for modeling cells and large numbers of their organelles, and give an example in human blood platelets. We present an algorithm using novel hybrid 2D-3D segmentation networks to produce dense cellular segmentations with accuracy levels that outperform baseline methods and approach those of human annotators. To our knowledge, this work represents the first published approach to automating the creation of cell models with this level of structural detail.
生物学家在使用电子显微镜 (EM) 图像构建全细胞及其细胞器的纳米尺度 3D 模型时，由于成像和分析的限制，历史上一直只能处理少量的细胞和细胞特征。这是限制深入了解细胞环境复杂可变性的主要因素。现代 EM 可以生成千兆像素的图像体积，其中包含大量细胞，但图像特征的准确手动分割速度较慢，限制了细胞模型的创建。基于卷积神经网络的分割算法可以快速处理大量数据，但要达到 EM 任务的准确性目标，通常会挑战当前技术。在这里，我们将密集细胞分割定义为一种用于建模细胞及其大量细胞器的多类语义分割任务，并以人类血小板为例进行说明。我们提出了一种使用新型混合 2D-3D 分割网络的算法，可以生成具有高精度水平的密集细胞分割，其性能优于基线方法，接近人类注释者的水平。据我们所知，这项工作代表了首次发布的使用这种结构细节级别自动创建细胞模型的方法。
