Learning cellular morphology with neural networks

• Published in: Nature communications Vol. 10; no. 1; pp. 2736 - 12
• Main Authors: Schubert, Philipp J., Dorkenwald, Sven, Januszewski, Michał, Jain, Viren, Kornfeld, Joergen
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 21.06.2019; Nature Publishing Group; Nature Portfolio
• Subjects: 14/28; 631/114; 631/378; Algorithms; Animals; Annotations; Automation; Brain; Brain - cytology; Brain - diagnostic imaging; Cellular communication; Datasets as Topic; Electron microscopy; Feasibility Studies; Humanities and Social Sciences; Image Processing, Computer-Assisted - methods; Male; Microscopy, Electron; Morphology; multidisciplinary; Neural networks; Neural Networks, Computer; Neuronal-glial interactions; Neurons - cytology; Passeriformes; Reconstruction; Science; Science (multidisciplinary); Synapses
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-019-10836-3

Reconstruction and annotation of volume electron microscopy data sets of brain tissue is challenging but can reveal invaluable information about neuronal circuits. Significant progress has recently been made in automated neuron reconstruction as well as automated detection of synapses. However, methods for automating the morphological analysis of nanometer-resolution reconstructions are less established, despite the diversity of possible applications. Here, we introduce cellular morphology neural networks (CMNs), based on multi-view projections sampled from automatically reconstructed cellular fragments of arbitrary size and shape. Using unsupervised training, we infer morphology embeddings (Neuron2vec) of neuron reconstructions and train CMNs to identify glia cells in a supervised classification paradigm, which are then used to resolve neuron reconstruction errors. Finally, we demonstrate that CMNs can be used to identify subcellular compartments and the cell types of neuron reconstructions. Volume electron microscopy data of brain tissue can tell us much about neural circuits, but increasingly large data sets demand automation of analysis. Here, the authors introduce cellular morphology neural networks and successfully automate a range of morphological analysis tasks.