ssEMnet: Serial-Section Electron Microscopy Image Registration Using a Spatial Transformer Network with Learned Features

Abstract

The alignment of serial-section electron microscopy (ssEM) images is critical for eorts in neuroscience that seek to reconstruct neu- ronal circuits. However, each ssEM plane contains densely packed struc-tures that vary from one section to the next, which makes matching fea-tures across images a challenge. Advances in deep learning has resulted in unprecedented performance in similar computer vision problems, but to our knowledge, they have not been successfully applied to ssEM image co-registration. In this paper, we introduce a novel deep network model that combines a spatial transformer for image deformation and a convo-lutional autoencoder for unsupervised feature learning for robust ssEM image alignment. This results in improved accuracy and robustness while requiring substantially less user intervention than conventional methods. We evaluate our method by comparing registration quality across several datasets.