Deep Neural Networks to Register and Annotate the Cells of the C. elegans Nervous System

Aligning and annotating the heterogeneous cell types that make up complex cellular tissues remains a major challenge in the analysis of biomedical imaging data. Here, we present a series of deep neural networks that allow for automatic non-rigid registration and cell identification in the context of the nervous system of freely-moving C. elegans . A semi-supervised learning approach was used to train a C. elegans registration network (BrainAlignNet) that aligns pairs of images of the bending C. elegans head with single pixel-level accuracy. When incorporated into an image analysis pipeline, this network can link neuronal identities over time with 99.6% accuracy. A separate network (AutoCellLabeler) was trained to annotate >100 neuronal cell types in the C. elegans head based on multi-spectral fluorescence of genetic markers. This network labels >100 different cell types per animal with 98% accuracy, exceeding individual human labeler performance by aggregating knowledge across manually labeled datasets. Finally, we trained a third network (CellDiscoveryNet) to perform unsupervised discovery and labeling of >100 cell types in the C. elegans nervous system by analyzing unlabeled multi-spectral imaging data from many animals. The performance of CellDiscoveryNet matched that of trained human labelers. These tools will be useful for a wide range of applications in C. elegans research and should be straightforward to generalize to many other applications requiring alignment and annotation of dense heterogeneous cell types in complex tissues.