UTR: Unsupervised Learning of Thickness-Insensitive Representations for Electron Microscope Image

Abstract

Registration of serial section electron microscopy (ssEM) images is essential for neural circuit reconstruction. Morphologies of neurite structure in adjacent sections are different. Thus, it is challenging to extract valid features in ssEM image registration. Convolutional neural networks (CNN) have made unprecedented progress in feature extraction of natural images. However, morphological differences need not be considered in the registration of natural images. Directly applying these methods will result in matching failure or over-registration. This paper proposes an unsupervised learning-based representation taking the morphological differences of ssEM images into account. CNN architecture was used to extract the feature. To train the network, the focused ion beam scanning electron microscope (FIB-SEM) images are used. The FIB-SEM images are in situ, so they are naturally registered. Sampling those images with a certain thickness can teach CNN to learn changes in neurite structure. The learned feature can be directly applied to existing ssEM image registration methods and reduce the negative effect of section thickness on registration accuracy. The experimental results show that the proposed feature outperforms the state-of-the-art method in matching accuracy and significantly improves the registration outcome when used in ssEM images.