ssEMnet: Serial-section Electron Microscopy Image Registration using a Spatial Transformer Network with Learned Features
This addresses the problem of reconstructing neuronal circuits in neuroscience, representing an incremental improvement over existing methods.
The paper tackled the challenge of aligning serial-section electron microscopy images for neuroscience by introducing a deep network model combining a spatial transformer and convolutional autoencoder, resulting in improved accuracy and robustness with less user intervention.
The alignment of serial-section electron microscopy (ssEM) images is critical for efforts in neuroscience that seek to reconstruct neuronal circuits. However, each ssEM plane contains densely packed structures that vary from one section to the next, which makes matching features 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 convolutional 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.