Whole-cell organelle segmentation in volume electron microscopy
Whole-cell organelle segmentation in volume electron microscopy
复制标题
DOI：
10.1038/s41586-021-03977-3
复制
发表时间：
2021-10-06
期刊：
影响因子：
64.8
通讯作者：
Weigel, Aubrey V.
中科院分区：
文献类型：
--
作者：
Heinrich, Larissa;Bennett, Davis;Weigel, Aubrey V.
聚焦离子束扫描电子显微镜（FIB-SEM）结合基于深度学习的分割技术，用于生成完整细胞和组织的三维重建，其中注释了多达35种不同的细胞器类别。细胞包含数百种细胞器和大分子组装体。要完全了解它们复杂的组织结构，需要对整个细胞进行纳米级的三维重建，这只有通过强大且可扩展的自动方法才可行。在这里，为了支持这种方法的发展，我们注释了多达35种不同的细胞器类别-从内质网到微管到核糖体-在来自多个细胞类型的不同样品体积中，使用聚焦离子束扫描电子显微镜（FIB-SEM）以每体素4 nm的近各向同性分辨率成像（1）。我们训练了深度学习架构，以每体素4 nm和8 nm的FIB-SEM体积分割这些结构，验证了它们的性能，并表明自动重建可用于直接量化以前无法获得的指标，包括细胞成分之间的空间相互作用。我们还表明，这种重建可以用来自动注册相关研究的光学和电子显微镜图像。我们已经创建了一个开放数据和开源网络存储库“OpenOrganelle”，以共享数据，计算机代码和训练模型，这将使世界各地的科学家能够查询并进一步改进这些数据集的自动重建。
Focused ion beam scanning electron microscopy (FIB-SEM) combined with deep-learning-based segmentation is used to produce three-dimensional reconstructions of complete cells and tissues, in which up to 35 different organelle classes are annotated.Cells contain hundreds of organelles and macromolecular assemblies. Obtaining a complete understanding of their intricate organization requires the nanometre-level, three-dimensional reconstruction of whole cells, which is only feasible with robust and scalable automatic methods. Here, to support the development of such methods, we annotated up to 35 different cellular organelle classes-ranging from endoplasmic reticulum to microtubules to ribosomes-in diverse sample volumes from multiple cell types imaged at a near-isotropic resolution of 4 nm per voxel with focused ion beam scanning electron microscopy (FIB-SEM)(1). We trained deep learning architectures to segment these structures in 4 nm and 8 nm per voxel FIB-SEM volumes, validated their performance and showed that automatic reconstructions can be used to directly quantify previously inaccessible metrics including spatial interactions between cellular components. We also show that such reconstructions can be used to automatically register light and electron microscopy images for correlative studies. We have created an open data and open-source web repository, 'OpenOrganelle', to share the data, computer code and trained models, which will enable scientists everywhere to query and further improve automatic reconstruction of these datasets.