Deep neural network automated segmentation of cellular structures in volume electron microscopy.

Volume electron microscopy is an important imaging modality in contemporary cell biology. Identification of intracellular structures is a laborious process limiting the effective use of this potentially powerful tool. We resolved this bottleneck with automated segmentation of intracellular substructures in electron microscopy (ASEM), a new pipeline to train a convolutional neural network to detect structures of a wide range in size and complexity.

Inherited nuclear pore substructures template post-mitotic pore assembly.

Nuclear envelope assembly during late mitosis includes rapid formation of several thousand complete nuclear pore complexes (NPCs). This efficient use of NPC components (nucleoporins or "NUPs") is essential for ensuring immediate nucleocytoplasmic communication in each daughter cell. We show that octameric subassemblies of outer and inner nuclear pore rings remain intact in the mitotic endoplasmic reticulum (ER) after NPC disassembly during prophase.