Automatic whole cell organelle segmentation in volumetric electron microscopy

Larissa Heinrich, Davis Bennett, David Ackerman, Woohyun Park, John Bogovic, View ORCID ProfileNils Eckstein, Alyson Petruncio, Jody Clements, C. Shan Xu, Jan Funke, Wyatt Korff, Harald F. Hess, Jennifer Lippincott-Schwartz, Stephan Saalfeld, Aubrey V. Weigel, COSEM Project Team - Janelia Research Campus, Howard Hughes Medical Institute, Ashburn, VA 20147, USA

Cells contain hundreds of different organelle and macromolecular assemblies intricately organized relative to each other to meet any cellular demands. Obtaining a complete understanding of their organization is challenging and requires nanometer-level, three-dimensional reconstruction of whole cells. Even then, the immense size of datasets and large number of structures to be characterized requires generalizable, automatic methods.

To meet this challenge, we developed an analysis pipeline for comprehensively reconstructing and analyzing the cellular organelles in entire cells imaged by focused ion beam scanning electron microscopy (FIB-SEM) at a near-isotropic size of 4 or 8 nm per voxel. The pipeline involved deep learning architectures trained on diverse samples for automatic reconstruction of 35 different cellular organelle classes – ranging from endoplasmic reticulum to microtubules to ribosomes – from multiple cell types.

Automatic reconstructions were used to directly quantify various previously inaccessible metrics about these structures, including their spatial interactions. We show that automatic organelle reconstructions can also be used to automatically register light and electron microscopy images for correlative studies. We created an open data and open source web repository, OpenOrganelle, to share the data, computer code, and trained models, enabling scientists everywhere to query and further reconstruct the datasets.

How Amira-Avizo Software is used

We manually segmented blocks at 2 nm resolution from datasets of HeLa, Jurkat, Macrophage and SUM159 cells acquired at 4 nm resolution using Amira-Avizo (ThermoFisher) and BigCat. The expert annotators used various image processing filters to enhance raw data, miscellaneous selection tools for label assignment and preliminary 3D rendering as a contextual guide. After final cross-annotator quality checks each block was stored as a N5 dataset in preparation for model training. For more details on the manual segmentation process and a complete list of organelles and sub-organelle compartments, see Supplementary Methods: Training Data and Supplementary Methods: Organelle Classification, respectively.