A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation

TL;DR

This paper introduces a convolutional autoencoder method for unsupervised feature extraction and weakly supervised segmentation in cellular electron cryo-tomograms, aiding in the analysis of complex cellular structures.

Contribution

It presents a novel autoencoder-based approach for coarse feature characterization and segmentation of cellular components in cryo-tomograms, requiring minimal manual annotation.

Findings

Effective in identifying macromolecular features and membranes

Detects non-cellular features like grid edges and boundaries

Enables weakly supervised segmentation with limited annotations

Abstract

Cellular electron cryo-tomography enables the 3D visualization of cellular organization in the near-native state and at submolecular resolution. However, the contents of cellular tomograms are often complex, making it difficult to automatically isolate different in situ cellular components. In this paper, we propose a convolutional autoencoder-based unsupervised approach to provide a coarse grouping of 3D small subvolumes extracted from tomograms. We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such as membranes. In addition, the autoencoder can be used to detect non-cellular features related to sample preparation and data collection, such as carbon edges from the grid and tomogram boundaries. The autoencoder is also able to detect patterns that may indicate spatial interactions between cellular components. Furthermore, we demonstrate that our autoencoder can be used for weakly supervised semantic segmentation of cellular components, requiring a very small amount of manual annotation.

Full text

See pages - of 2017-autoencoder-cluster.pdf

See pages - of 2017-autoencoder-cluster-suppl.pdf